Feature selection, reducing number of input variables to develop classification model, is an important process to reduce computational and modelling complexity and affects the performance of image process. In this paper, we have proposed new statistical approaches for feature selection based on sample selection. We have applied our new approaches to grapevine leaves data that possesses properties of shape, thickness, featheriness, and slickness are investigated in images. To analyze such kind of data by using image process, thousands of features are created and selection of features plays important role to predict the outcome properly. In our numerical study, Convolutional Neural Networks (CNNs) have been used as feature extractors and then obtained features from the last average pooling layer to detect the type of grapevine leaves from images. These features have been reduced by using our suggested four statistical methods: Simple random sampling (SRS), ranked set sampling (RSS), extreme ranked set sampling (ERSS), Moving extreme ranked set sampling (MERSS). Then selected features have been classified with Artificial Neural Network (ANN) and we have obtained the best accuracy of 97.33% with our proposed approaches. Based on our empirical analysis, it has been determined that the proposed approach exhibits efficacy in the classification of grapevine leaf types. Furthermore, it possesses the potential for integration into various computational devices.
Research Article
A Novel Feature Selection Approach Based Sampling Theory on Grapevine Images using Convolutional Neural Networks
https://doi.org/10.21203/rs.3.rs-3215586/v1
This work is licensed under a CC BY 4.0 License
Version 1
posted
You are reading this latest preprint version
Artificial Neural Network (ANN)
Deep Learning
Feature Selection
Moving extreme ranked set sampling (MERSS).
This study demonstrates how pre-trained architectures can identify different plant species from images. Therefore, automatic species identification for experts, farmers, and researchers is provided by image classification of plants. However, because of the suggested algorithm, people are not spending a lot more time identifying plant species. We can say that the created structure is capable of performing and being advanced in plant detection. We'll use the suggested feature selection techniques on a variety of datasets from various fields in our upcoming work.
The annual grapevine leaves harvest yields an additional product for the field of agriculture especially in Turkey. The classification of grapevine leaves holds significance with regards to their valuation and flavor characteristics (Koklu et al., 2022, Saglam and Saglam, 2018). Various kind of grapevine leaves exhibit distinct leaf attributes, encompassing criteria such as shape, depth, length, featheriness, and sliciness, which display considerable variation (Cangi and Yağci, 2017, Göktürk et al., 1997, Koklu et al., 2022). Due to this reason, the grapevine leaves of every variant are not utilized for culinary purposes. Consumers exhibit a lack of preference towards leaves that possess a substantial thickness, with feathers, and are sliced. The optimal choice for culinary purposes is a grapevine leaves cultivar that possesses a slender morphology, devoid of feathers, exhibiting delicate venation, sliced to the most thinness, and imparting a tangy sensation upon the tasting receptors (Koklu et al., 2022). Hence, the categorization of consumable species from non-consumable grapevine leaves species and the identification of them based on leaf and fruit images are crucial prerequisites in this domain. However, for individuals lacking specialized knowledge, discerning the type of grapevine leaves poses a considerable challenge (Koklu et al., 2022).
Deep learning algorithms have been utilized to develop prediction in classification models. Convolutional Neural Networks (CNNs) are a variant of deep learning algorithms and they are widely used for image classification or prediction in many fields (Ozaltin et al., 2023a -2023b, Ozaltin and Yeniay, 2023, Singh et al., 2022, Karadal et al., 2021). However, it is important to note that CNNs by themselves may not yield optimal levels of accuracy every time. CNNs possess the capability to perform automated feature extraction without the need for manual crafting and thus, researchers benefit from this property of CNNs (Adeel et al., 2022, Koklu et al., 2022, Nguyen et al., 2021).
In this study, we prefer to use pre-trained architectures as opposed to developing novel CNNs due to encountered challenges (Hazirbas et al., 2016). The pre-trained architectures selected including DarkNet-53(Redmon and Farhadi, 2018), GoogleNet (Szegedy et al., 2015), InceptionResNet_v2 (Szegedy et al., 2017), NASNetMobile (Zoph et al., 2018), and ResNet-18 (He et al., 2016). These choices are made due to their frequent utilization in the field. The appointed performs of these architectures involve serving as deep feature generators, wherein their final layer produces features of varying sizes. However, a subset of these features exhibits noise, and employing the entire set results in increased computational complexity. The task of determining the significance of features and performing feature reduction is a highly crucial problem. In order to achieve optimal outcomes in image detection, it is advantageous to leverage feature selection techniques and machine learning algorithms. Various feature selection methods can be employed for this purpose in the literature, including Neighborhood Component Analysis (NCA) (Goldberger et al., 2004), Principle Component Analysis (PCA) (Liu and Durlofsky, 2021), Chi-Square (Hussein and Özyurt, 2021), minimum redundancy maximum relevance (mRMR) (Toğaçar et al., 2020) and others. Nevertheless, during the application of these feature selection methods, researchers may face challenges related to computational complexity, assumptions, or time-consuming processes. In this study, we focus on overcoming these issues, particularly the challenges associated with computational complexity. The objective of this paper is to propose novel methodologies for feature selection utilizing sampling theory (SRS, RSS, ERSS, and MERSS) and analyze their impact on the performance of classification models. In order to conduct a comparative analysis between our proposed and existing method, we utilize the grapevine leaves dataset. Experimental results shows that our proposed method is superior than the others. Then, reduced features using our proposed method are classified via ANN. Therefore, our proposed approach develops a novel hybrid algorithm-based CNN, new feature selection method, and ANN.
In the pursuit of our objective, we attempt to employ based on CNNs to discern and classify grapevine leaf images, thus helping with the identification of plant species.
1.1 Novelties and Contribution of this Study
The main contributions and novelties of this study are as follows:
-
Obtained original grapevine leaves images having five classes: Ak, Ala Idris, Büzgülü, Dimnit, and Nazli from the website http://www.muratkoklu.com/datasets/Grapevine_Leaves_Image_Dataset.rar
-
Utilized 5-fold cross-validation to obtain reliable outcomes for DarkNet-53, GoogleNet, InceptionResNet_v2, NASNetMobile, and ResNet-18.
-
Compared these pre-trained architectures utilizing the SoftMax layer for the purpose of classifying grapevine leaves images.
-
Employed these architectures for extracting features from images. Extracted features were obtained specifically from the average pooling layer of the respective architecture.
-
Proposed novel feature selection methods based on sampling theory: SRS, RSS, ERSS, MERSS.
-
Identified number of features and selected important features using these methods.
-
Classified selected features through Artificial Neural Network (ANN).
-
Investigated performance of classification on the hybrid algorithms from grapevine leaf images.
-
Compared these suggested methods with NCA on the performance of classification.
-
Finally, the highest accuracy is obtained by using DarkNet53-MERSS-ANN hybrid algorithm. Figure 1 shows the pipeline of this presented study.
1.2 Literature Review
In recent years, scientific investigations have primarily concentrated on the examination of disease identification and species classification through the utilization of leaf images, as documented in current collections of literature (Lilhore et al., 2022, Koklu et al., 2022, Atila et al., 2021).
Tiwari et al. (2021) performed a deep learning-based system to detect plant diseases and classify various types. Besides, they implemented five cross validations while training the dataset, which has 27 different classes. As a result, they obtained an average cross-validation accuracy of 99.58% and an average test accuracy of 99.199%.
Ahila Priyadharshini et al. (2019) aimed to identify crop disease from maize leaf images via their proposed convolutional neural network (CNN). In fact, they modified LeNet and trained four different classes—three diseases and one health class—from the PlantVillage dataset.
Azim et al. (2021) utilized decision trees, which are one of the machine learning algorithms, to detect three different rice leaf diseases from images. They manually extracted features from images such as color, shape, and texture. Lastly, their study achieved an accuracy of 86.58%.
Sembiring et al. (2021) focused on detecting tomato leaf diseases, which are classified into nine different classes via CNNs architectures: Very Deep Convolutional Neural Networks (VGG), ShuffleNet, and SqueezeNet. They also used healthy leaves to distinguish themselves from the competition. In total, 10 different classes were utilized and classified with these architectures. Finally, the study obtained the highest accuracy of 97.15%.
Zhang et al. (2017) proposed a novel approach to detecting cucumber leaf disease. Firstly, they segmented disease by using K-means clustering, and then they extracted features such as shape and color from lesion information. Lastly, they classified leaf images to detect disease utilizing sparse representation (SR). At the end of the study, they obtained an accuracy of 85.7% with this approach.
Sladojevic et al. (2016) created a model using the CNNs algorithm to distinguish 13 different plant diseases from leaf images via Caffe. Finally, their study achieved an average precision of 96.3%.
Kan et al. (2017) searched for medicinal plants, which are essential in traditional Chinese medicine, via a support vector machine (SVM). Before the classification stage, image features such as shape and texture are extracted for each of the 12 different leaf types. When the features are classified via SVM, application results achieve an average accuracy of 93.3%.
Koklu et al. (2022) performed grapevine leaf image classification using MobileNetv2, which is one of the pre-trained convolutional neural network architectures. Their dataset consists of five different classes and 500 grapevine leaf images. While they classify the dataset via MobileNetv2, they do not find it sufficient and then combine it with SVM to obtain the best classification results. Prior to this merging, the feature selection method, Chi-Square, is applied, and then which kernel is successful is investigated. At the end of the study, they express that the best kernel is Cubic with 250 features selected and an accuracy of 97.60%.
Dudi and Rajesh (2022) introduced a novel deep learning hybrid algorithm to identify leaf types. Their algorithm includes enhanced CNN with optimization methods for activation functions and hidden neurons. Their proposed method is the Shark Smell-Based Whale Optimization Algorithm (SS-WOA). Besides, they tested this hybrid algorithm on untrained and collected leaf images and obtained an accuracy of 86%. In addition to these studies, Table 1 displays state-of-the-art studies belonging to leaf image classification.
| Study | Methods | Number of Images | Classes | Accuracy (%) |
|---|---|---|---|---|
| Hridoy et al. (2022) | EfficientNet-B5 | 10,662 | - | 98.84% |
| Tiwari et al. (2022) | DenseNet201 | 4503 | Multi-classes (22) | 97.69% |
| Ruth et al. (2022) | Optimal Deep Neural Network | - | Multi-classes (38) | 99.00% |
| Koklu et al. (2022) | MobileNetv2-Support Vector Machine | 500 | Multi-classes (5) | 97.60% |
| Paymode and Malode (2022) | VGG-16 | Using different datasets | Multi-classes | over 95.7% |
| Reddy et al. (2022) | Deep Neural Network | Using different datasets (augmented) | Multi-classes | over 95.9% |
| Dudi and Rajesh (2022) | Hybrid Convolutional Neural Network | Using different datasets | Multi-classes | 86% |
| Ganguly et al. (2022) | Convolutional Neural Network | Using different datasets | Multi-classes | over 92.2% |
| Chen et al. (2022) | AlexNet | 22,930 | Multi-classes | 96% |
| Arun and Viknesh (2022) | EfficientNet-B5 | - | Multi-classes | 99.75% |
| Bhujel et al. (2022) | ResNet20 based on Lightweight | 19,510 | Multi-classes (11) | 99.69% |
| Wei et al. (2022) | VGG, GoogleNet, ResNet | 34,000 | Multi-classes (34) | 98.02% |
| Saberi Anari (2022) | Deep Learning- Ensemble Learning | 90,000 | Multi-classes | 99.10% |
| Lilhore et al. (2022) | Enhanced Convolutional Neural Network | 6256 | Multi-classes | 99.3% |
The rest of this study is organized as follows: the grapevine leaves dataset and used methods are given in Section 2. Next, we present experimental results, performance metrics, fine tuning parameters, and cross validation in Section 3. Then, we have discussed advantages and disadvantaged of this study in Section 4. Eventually, we have finalized this study and express the future works, in Section 5.
2.1 Dataset of Grapevine Leaves
Plants play an important role in the world (Wang et al., 2008). In nature, there are many species of plants, and their detection is so difficult and time-consuming. Grapevine leaf is also a special plant that has different properties such as shape, thickness, featheriness, and slickness, and detecting it is quite hard.
The dataset includes grapevine leaf images with five classes: Ak, Ala Idris, Büzgülü, Dimnit, and Nazli. In total, there are 500 images, consisting of 100 images for each class. Besides, all images have RGB (red, green, and blue) format and 512x512x3 dimensions. This dataset was created by Koklu et al. (2022) and obtained from the website http://www.muratkoklu.com/datasets/Grapevine_Leaves_Image_Dataset.rar.
In this study, we did not resize the images during the preprocessing phase manually. However, each pre-trained architecture may accept different input sizes of the image. Therefore, we perform the data augmentation process automatically to resize the dimension that is accepted as the input size for each pre-trained architecture. Table 2 displays the input size of each architecture. Figure 2 displays classes of grapevine leaves.
2.2 Deep Feature Extractors
With the implosive advance in data and the fast development of algorithms such as machine learning, deep learning, etc., artificial intelligence (AI) has obtained novelties in a wide range of applications (Shi et al., 2020). Notably, researchers prefer deep learning algorithms to analyze images due to their ability to extract features (Koklu et al., 2022, Saberi Anari, 2022, Ozaltin et al., 2022, Ozaltin and Yeniay, 2022, Özaltın and Yeniay, 2021). When desiring to classify any image using a machine learning algorithm, the features of the image are extracted manually through a process known as hand-crafting. Nonetheless, this circumstance is time-consuming and requires expert consideration. To analyze images from any field, it is difficult to locate specialists; consequently, results cannot be obtained rapidly. The feature extraction problem can now be handled by CNNs (Ozaltin et al., 2022).
In this study, we automatically extract features from grapevine images using the networks DarkNet-53, GoogleNet, InceptionResNet_v2, NASNetMobile, and ResNet-18. Table 2 exhibits the number of parameters, the layers, the input size, and the years in which pre-trained architectures have been developed. Furthermore, the next sub-section will provide a concise presentation of these architectures.
|
Architecture Name |
Year |
Input Size |
Number of Layers |
Parameters (millions) |
|---|---|---|---|---|
|
DarkNet-53(Redmon and Farhadi, 2018) |
2018 |
256x256 |
106 |
62.2 |
|
GoogleNet (Szegedy et al., 2015) |
2015 |
224x224 |
144 |
7 |
|
InceptionResNet_v2 (Szegedy et al., 2017) |
2017 |
299x299 |
164 |
55.9 |
|
NASNetMobile (Zoph et al., 2018) |
2018 |
224x224 |
* |
5.3 |
|
ResNet-18 (He et al., 2016) |
2016 |
224x224 |
71 |
11.7 |
*: showing that NASNetMobile does not possess a linear sequence of modules.
2.2.1 DarkNet-53
Darknet-53, a convolutional neural network (CNN) developed by Redmon and Farhadi (2018), is the primary module for extracting features in order to identify objects within the Yolov3 network (Pathak and Raju, 2021). The architecture comprises a total of 53 deep convolutional layers, and it is denoted as DarkNet-53 due to the specific count of these layers. Indeed, there exist repetition blocks, resulting in a total number of layers amounting to 106. The specified architecture is designed to accommodate an image input with dimensions of 256x256. Table 3 presents comprehensive information regarding the architectures. Furthermore, it has been observed that DarkNet-53 exhibits superior performance in the context of classification and extraction of features within the scope of this investigation.
|
Type of layers |
Number of Filters |
Size |
Stride |
Output |
Repetition |
|---|---|---|---|---|---|
|
Convolutional |
32 |
3x3 |
256x256 |
||
|
Convolutional |
64 |
3x3 |
2 |
128x128 |
|
|
Convolutional |
32 |
1x1 |
2 |
x1 |
|
|
Convolutional |
64 |
3x3 |
|||
|
Residual |
128x128 |
||||
|
Convolutional |
128 |
3x3 |
2 |
64x64 |
|
|
Convolutional |
64 |
1x1 |
x2 |
||
|
Convolutional |
128 |
3x3 |
|||
|
Residual |
64x64 |
||||
|
Convolutional |
256 |
3x3 |
2 |
32x32 |
|
|
Convolutional |
128 |
1x1 |
x8 |
||
|
Convolutional |
256 |
3x3 |
|||
|
Residual |
32x32 |
||||
|
Convolutional |
512 |
3x3 |
2 |
16x16 |
|
|
Convolutional |
256 |
1x1 |
x8 |
||
|
Convolutional |
512 |
3x3 |
|||
|
Residual |
16x16 |
||||
|
Convolutional |
1024 |
3x3 |
2 |
8x8 |
|
|
Convolutional |
512 |
1x1 |
x4 |
||
|
Convolutional |
1024 |
3x3 |
|||
|
Residual |
8x8 |
||||
|
Average pooling |
Global |
||||
|
Connected |
1000 |
||||
|
Softmax |
2.2.2 GoogleNet
The GoogleNet architecture was proposed by Szegedy et al. (2015). The architecture exhibits a multitude of layers, including two convolutional layers, four max-pooling layers, nine inception layers, a global average pooling layer, a dropout layer, a linear layer, and a Softmax layer. GoogLeNet is composed of a total of 22 layers, which are deeper in nature. It effectively employs activation layers using the Rectified Linear Unit (ReLU) function. GoogleNet consists of a total of 7 million parameters.
2.2.3 InceptionResNet
The InceptionResNet_v2 model is a fusion of the ResNet and Inception architectures, as proposed by by Szegedy et al. (2017) (Kamble et al., 2018). The architecture executes residual connections in an efficient manner, rather than employing connection filtering to enhance performance and accelerate training time (Wang et al., 2021).
2.2.4 NasNetMobile
The NASNetMobile architecture, developed by Zoph et al. (2018), aims to explore optimal CNNs structures using reinforcement learning methods. The team from Google Brain, as presented by (Addagarla et al., 2020), has made significant advancements in the field of Neural Architecture Search (NAS). While NAS architectures exhibit variations in their sizes, it is worth noting that NasNetMobile represents a scaled-down iteration. The parameter count of NASNetMobile is approximately 4.5 million. The accepted input image size is 224x224 pixels.
2.2.5 ResNet-18
The architecture known as ResNet-18, as described by He et al. (2016), consists of a total of 72 layers, with 18 of them being deep layers. Moreover, it was developed in the year 2016. This architecture aims to efficiently provide a multitude of convolutional layers for functioning. The core principle of ResNet involves implementing skip connections, commonly referred to as shortcut connections. During this iterative process, the interconnection compresses the underlying structure, leading to accelerated learning within the network. The structure is recognized as a Directed Acyclic Graph (DAG) network due to its intricate layered configuration (Chandola et al., 2021).
These architectures have been employed for the purpose of both classification and the generation of deep features. When they are utilized as the classifiers, the Softmax layer is applied. However, in the case of utilizing deep feature generators, the implementation of the Softmax layer is absent, resulting in the acquisition of deep features widely from the last layers. For example, DarkNet-53 yields a feature vector of dimension 1024. However, it is necessary to decrease the number of features in order to attain optimal performance. In the context of this study, our objective is to design innovative techniques for selecting features.
2.3 A Novel Feature Selection Approach based on Sampling Theory
In this study, we aim to find solutions to these problems, with a special emphasis on those involving computational complexity. Therefore, we present a novel feature selection methodologies SRS, RSS, ERSS, and MERSS based on sampling theory for improving the classification performance of grapevine leaves images. In the next sub-sections, we introduce the proposed methods, and overall Algorithm process.
2.3.1. Simple Random Sampling (SRS)
Simple random sampling (SRS) is a very common sampling design used by many researchers because of practicality. To improve the precision new sampling designs are also suggested in literature. One of these designs is Ranked set sampling (RSS) was first proposed by McIntyre (1952) as an alternative the SRS. When we compare both sampling designs for the same sample size, we can say that RSS becomes more efficient than SRS as long as a more accurate and accessible ranking criterion is available for increasing grapevine leaves classification performance. For detail literature; kindly see Zamanzade and Mahdizadeh (2020), Bouza-Herrera and Al-Omari (2018), Koyuncu and Al-Omari (2021), etc. In big data literature, there are many important studies using sampling designs to reduce computational complexity, challenge imbalanced data and increase the precision (Djouzi et al., 2022, Rendon et al., 2020). In this study, following new ranked set sampling designs, we have proposed new procedure for feature selection weights.
2.3.2. Ranked Set Sampling (RSS) Procedure for Feature Selection
Following McIntyre (1952), we can define a new procedure for feature selection as:
- Order the weights descending order by an inexpensive method.
- Select “n” features of size n respectively called sets.
- Measure accurately the first ordered feature from the first set, the second ordered feature from the second set. The process continues in this way until the maximum ordered feature from the last n-th set is measured.
Note that we can select “Integer (sqrt (weight_size)” size of feature with this procedure.
2.3.3 Extreme Ranked Set Sampling (ERSS) Procedure for Feature Selection
When the set size n is large, RSS may have ranking errors. As an attempt to overcome this problem several variations of RSS have been proposed by researchers. The main idea of ERSS is that the identification of the maximum rank is much easier than the determination of the all ranks (Samawi et al., 2020). We can define a new procedure called “ERSS Procedure” for feature selection as:
- Order the weights descending order by an inexpensive method.
- Select “n” features of size n respectively called sets.
- Measure accurately the maximum ordered feature from the first set, the maximum ordered feature from the second set. The process continues in this way until the maximum ordered feature from the last n-th set is measured.
Note that we can select same feature size with RSS and unlike the classical ERSS defined by Samawi et al. (2020), in our approach we only take into account maximum values instead of minimum.
2.3.4 Moving Extreme Ranked Set Sampling (MERSS) Procedure for Feature Selection
Another modification of RSS, namely Moving Extreme Ranked Set Sampling (MERSS), was introduced by Al-Odat and Al-Saleh (2001). Following Al-Odat and Al-Saleh (2001), we have suggested following procedure to select feature weights:
- Order the weights descending order by an inexpensive method.
- Select “n” features of size 1, 2, 3, ..., n respectively called sets.
- Measure accurately the maximum ordered feature from the first set, the maximum ordered feature from the second set. The process continues in this way until the maximum ordered feature from the last n-th set is measured.
This modification of RSS, in addition of being easier to execute than both usual RSS and fixed size extreme RSS, keeps some of the balancing inherited in the usual RSS. Hence, it can be concluded that the MERSS algorithm exhibits superior efficiency compared to other methods in the task of feature selection, resulting in a significantly enhanced performance in the classification of grapevine leaves images.
According to our proposed feature selection methods, we select significant features, which are subsequently subjected to classification using an ANN with high efficiency.
2.4 Classification via Artificial Neural Network (ANN)
Artificial neural networks (ANN), as introduced by Mcculloch and Pitts (1943), emerged as a result of studying brain functionality and subsequently found application in computer programs (Ozaltin et al., 2023a). In addition, it is important to note that any ANN comprises numerous individual units, commonly referred to as neurons or processing elements (PE). These units are interconnected through weights, which facilitate the neural structure of the network. Furthermore, these interconnected units are typically organized in layers to ensure proper coordination and functioning of the ANN (Agatonovic-Kustrin and Beresford, 2000).
ANN originates from a prosperous lineage of non-linear algorithms. When utilized in the domain of machine learning, particularly in the context of supervised learning, the outcomes have exhibited considerable success in recent times. Additionally, artificial neural networks (ANN) possess a flexible architecture that can be effectively employed to accommodate a wide range of real-world datasets (Jiang, 2021). One may consider referring to the book authored by H. Jiang (2021) in order to acquire specific information.
Based on the aforementioned considerations, the implementation of an ANN is carried out in this study for the purpose of efficient classification of grapevine leaves images. This decision is based on the fundamental principles established by Ozaltin et al. (2023a) in their study. When implementing an ANN, a configuration is chosen where there are one hundred hidden layers followed by a softmax layer. Furthermore, ReLU activation layer is employed to enhance the efficiency of the algorithm. The training solver has selected the limited-memory Broyden-Fletcher-Goldfarb-Shanno quasi-Newton algorithm. Additionally, the maximum number of iterations is set to 1000, while the learning rate, minimum gradient tolerance, and loss tolerance are assigned values of 0.02, 1e-4, and 1e-5, correspondingly. By carefull choosing these parameters, we can achieve improved classification performance.
2.5 Performance Metrics
In this study, to measure of algorithms’ performance metrics, accuracy, area of under curve (AUC), F1-measure, geometric mean (G-mean), kappa value and sensitivity are used, in addition, expressed Equation (1)-(5) as follows:
where : True Positive, : False Positive, :True Negative, and : False Negative are shown (Sharifrazi et al., 2021, Singh et al., 2022, Rajinikanth et al., 2020).
The above performance metrics are widely employed to compute the performance of the classifier. In this study, not only calculated these metrics but also kappa value ( ) is acquired which algorithms performances are acceptable. If is close to 1, we can say that the results are perfect. Otherwise, if is close to 0, the results are unacceptable (Wang et al., 2019). Equation (6) and (7) are employed to evaluate as shown in Equation (8).
2.6 Cross Validation
The deep learning algorithm lacks the capability to communicate coherently using mathematical models, resulting in a lack of clarity regarding the transformation of inputs into outputs (Gao et al., 2018). Hence, the algorithm is denoted as encapsulating a black-box. The k-fold cross-validation method is commonly preferred by researchers in order to obtain reliable outcomes (Subasi, 2012, Lopez-Del Rio et al., 2019, Saber et al., 2021, Ozaltin et al., 2022). Moreover, this algorithm effectively mitigates the problem of overfitting during data analysis (Saber et al., 2021). In this algorithmic procedure, the dataset gets a process of partitioning into a set of subsets, wherein the number of subsets is randomly determined. One of these subsets is then designated as the test set, while the remaining subsets are utilized for training the structure (Koklu and Ozkan, 2020). The algorithm is iterated for k folds and evaluated using the framework proposed (Arlot and Celisse, 2010). In this study, the variable k is assigned a value of 5 to ensure reliable outcomes in the classification process.
2.7 Fine Tuning Parameters
In this study, the determination of fine-tuning parameters is crucial for attaining optimal outcomes and ensuring fair comparability with DarkNet-53, GoogleNet, NasNetMobile, InceptionResNet_v2, and ResNet-18. The identified parameters for fine-tuning are as follows: stochastic gradient descent (sgdm) is used as the optimizer, the learning rate is set to 0.0001, the maximum number of epochs is 10, the minibatch size is 8, and a constant learning rate schedule is utilized.
Following the utilization of methods and parameters, the pseudo code including the entirety of the Algorithm can be accessed below.
Algorithm
This study of procedures to detect grapevine leaves image types as follows:
- Start with input color grapevine leaf images (512x512x3)
- Resize into images according to each architecture’s accepted dimension.
- Train the images with 5-fold cross-validation using DarkNet-53- GoogleNet- InceptionResNet_v2- NasNetMobile- ResNet-18 through fine tuning parameters.
- Calculate performance metrics to compare algorithms.
- Save net.
- Split the images as 70% training and 30% testing.
- Activate the net.
- DarkNet-53- GoogleNet- InceptionResNet_v2- NasNetMobile- ResNet-18 is utilized to reduce high dimension of images and extract features from average pooling layer.
- Obtain “n” features weights via Mahalanobis distance metric.
- Apply suggested method: ERSS-MERSS-RSS-SRS, and NCA.
- Take selected features.
- Classify with ANN to detect types of grapevine leaf images.
- Calculate performance metrics.
- Save result.
- Find the best structure according to performance metrics.
- End.
1.1 Experimental Results
The investigation has been prepared using MATLAB 2021b. The primary objective of this study is to propose a new method for selecting features and to identify grapevine leaves types using hybrid algorithms that have been developed. First and foremost, the dataset is acquired from the public website, as indicated in the dataset section. The following models, namely DarkNet-53, GoogleNet, NasNetMobile, InceptionResNet_v2, and ResNet-18, are utilized as automatic feature extractors using a 5-fold cross-validation and transfer learning approach, each model being evaluated individually. In the subsequent procedure, we derive feature weights from the final layer of the relevant architecture. Subsequently, the features are chosen using recommended techniques: ERSS, MERSS, RSS, and SRS. In the meantime, we employ ANN to classify all the selected features. Table 4 demonstrates the performance of these pre-trained architectures in classifying grapevine leaf images through the utilization of 5-fold cross-validation.
| Architecture | Accuracy | Sensitivity | G-Mean | F-measure | Kappa | AUC |
|---|---|---|---|---|---|---|
| DarkNet-53 | 0.9620 | 0.9620 | 0.9761 | 0.9621 | 0.8812 | 0.9990 |
| GoogleNet | 0.8600 | 0.8600 | 0.9109 | 0.8603 | 0.5625 | 0.9788 |
| InceptionResNet_v2 | 0.8980 | 0.8980 | 0.9354 | 0.8980 | 0.6812 | 0.9858 |
| NASNetMobile | 0.8820 | 0.8820 | 0.9520 | 0.8816 | 0.6312 | 0.9762 |
| ResNet-18 | 0.9500 | 0.9500 | 0.9686 | 0.9500 | 0.8437 | 0.9974 |
Based on the data presented in Table 4, it can be observed that the utilization of pre-trained architectures has resulted in highly successful performances. The empirical findings suggest that DarkNet-53 achieves the most optimal performance, exhibiting an accuracy rate of 96.20% during this particular stage. The second model is ResNet-18, which exhibits a commendable accuracy of 95%. Following the series of performances, InceptionResNet_v2, NASNetMobile, and GoogleNet exhibit accuracies of 89.8%, 88.2%, and 86% in that order.
Despite the satisfactory nature of the performances, we employ the feature selection technique and machine learning algorithm to ascertain the credibility of the research findings. In the current phase of this study, we have partitioned the dataset into a 70% training subset and a 30% testing subset subsequent to training the dataset using the relevant architecture. Subsequently, we extract features from the last layer (which varies depending on the specific architecture) and subsequently employ our proposed methodologies, namely ERSS, MERSS, RSS, and SRS, to select the desired features. The classification stage has commenced using an ANN, and we have evaluated all hybrid structures. The outcomes of these evaluations have been documented in Table 5–9.
When extracting features from DarkNet-53, it has been observed that the global average pooling layer, commonly referred to as 'gap', proves to be beneficial. A total of 1024 features are acquired from the layer, and a subset of 36 features is selected using the ERSS, RSS, and SRS techniques. Furthermore, a total of 45 significant features have been determined using the MERSS method. The output is presented in Table 5.
| Hybrid Algorithm | Test Accuracy | Sensitivity | G-Mean | F-measure | Kappa | AUC |
|---|---|---|---|---|---|---|
| DarkNet53-ERSS-ANN | 0.9533 | 0.9533 | 0.9707 | 0.9533 | 0.8542 | 0.9956 |
| DarkNet53-RSS-ANN | 0.9333 | 0.9333 | 0.9580 | 0.9339 | 0.7917 | 0.9942 |
| DarkNet53-MERSS-ANN | 0.9733 | 0.9733 | 0.9833 | 0.9733 | 0.9167 | 0.9925 |
| DarkNet53-SRS-ANN | 0.8400 | 0.8400 | 0.8980 | 0.8391 | 0.5000 | 0.9633 |
Based on the findings presented in Table 5, the application of our proposed methodologies yields efficient results. It is worth noting that the performances obtained are in the form of test results. We are pleased to report that these results exhibit a high level of confidence in accurately identifying different types of grapevine leaf. The DarkNet53-MERSS-ANN algorithm has achieved the highest test accuracy of 97.33% along with other metrics. Additionally, the kappa value approaches 1, indicating that the algorithm can be considered highly successful. Furthermore, the performance is enhanced with the proposed methodology. In the previous iteration, the DarkNet-53 model demonstrated a classification accuracy of 96.20%. Furthermore, the algorithm employed in this study yields the utmost test accuracy when tasked with classifying grapevine leaf images. Additionally, Fig. 3 depicts the confusion matrix obtained from the DarkNet53-MERSS-ANN algorithm.
The following model in consideration is GoogleNet. If features are extracted from the GoogleNet model, the average pooling layer, specifically named 'pool5-7x7_s1', is observed to be useful. Indeed, a total of 1024 features are extracted from the layer, and subsequently, a selection process is performed using ERSS, RSS, and SRS techniques to identify the most significant 36 features. Furthermore, a total of 45 significant features have been identified using the MERSS method. The output of the computation is displayed in Table 6.
| Hybrid Algorithm | Test Accuracy | Sensitivity | G-Mean | F-measure | Kappa | AUC |
|---|---|---|---|---|---|---|
| GoogleNet-ERSS-ANN | 0.9400 | 0.9400 | 0.9622 | 0.9402 | 0.8125 | 0.9892 |
| GoogleNet -RSS-ANN | 0.9533 | 0.9533 | 0.9707 | 0.9533 | 0.8542 | 0.9946 |
| GoogleNet -MERSS-ANN | 0.9400 | 0.9400 | 0.9622 | 0.9388 | 0.8125 | 0.9897 |
| GoogleNet -SRS-ANN | 0.9067 | 0.9067 | 0.9410 | 0.9051 | 0.7083 | 0.9822 |
Table 6 indicates that the GoogleNet-RSS-ANN algorithm, with a test accuracy of 95.33%, is the most accurate of the methods we have proposed. The values for the sensitivity, G-Mean, F-measure, kappa value, and AUC are 95.33%, 97.07%, 0.9533, 0.8542, and 0.9946, respectively. In addition, the kappa value is close to 1, which indicates that the algorithm is quite successful. Moreover, the performance is enhanced by the suggested method. Previously, the accuracy of GoogleNet was 86%.
The model is referred to as NasNetMobile. If it's desired to collect features from NasNetMobile, it is possible to employ a global average pooling layer, denoted as 'global_average_pooling2d_1'. A total of 1056 features have been extracted from the layer, and a subset of 36 feature is selected using the ERSS, RSS, and SRS methods. Additionally, the MERSS method is utilized to identify a total of 45 crucial features. The outcomes are presented in Table 7.
| Hybrid Algorithm | Test Accuracy | Sensitivity | G-Mean | F-measure | Kappa | AUC |
|---|---|---|---|---|---|---|
| NasNetMobile -ERSS-ANN | 0.7333 | 0.7333 | 0.8273 | 0.7339 | 0.1667 | 0.9186 |
| NasNetMobile -RSS-ANN | 0.7733 | 0.7733 | 0.8541 | 0.7730 | 0.2917 | 0.8914 |
| NasNetMobile -MERSS-ANN | 0.7933 | 0.7933 | 0.8674 | 0.7894 | 0.3542 | 0.9375 |
| NasNetMobile -SRS-ANN | 0.7067 | 0.7067 | 0.8092 | 0.7077 | 0.0833 | 0.9099 |
Table 7 shows that the NasNetMobile-MERSS-ANN algorithm outperforms our suggested methods, with a test accuracy of 79.33%. Furthermore, its sensitivity, G-Mean, F-measure, kappa value, and AUC are 79.33%, 86.74%, 0.7894, 0.3542, and 0.9375, respectively. When the kappa value is compared to one, it indicates that the algorithm is not preferable. NasNetMobile previously had an accuracy of 88.20%.
The one after that is InceptionResNet_v2. If features are obtained from it, a global average pooling layer known as 'avg-pool' is found to be useful. Essentially, 1536 features are extracted from the layer, with significant 53 features selected using the ERSS, RSS, and SRS methods. The MERSS method also identifies 55 essential features. Table 8 displays all of the results.
| Hybrid Algorithm | Test Accuracy | Sensitivity | G-Mean | F-measure | Kappa | AUC |
|---|---|---|---|---|---|---|
| InceptionResNet -ERSS-ANN | 0.9267 | 0.9267 | 0.9538 | 0.9266 | 0.7708 | 0.9953 |
| InceptionResNet -RSS-ANN | 0.9000 | 0.9000 | 0.9367 | 0.8995 | 0.6875 | 0.9972 |
| InceptionResNet -MERSS-ANN | 0.9267 | 0.9267 | 0.9538 | 0.9267 | 0.7708 | 0.9842 |
| InceptionResNet -SRS-ANN | 0.8400 | 0.8400 | 0.8980 | 0.8418 | 0.5000 | 0.9811 |
Table 8 shows that when using our recommended techniques, two algorithms—InceptionResNet-ERSS-ANN and InceptionResNet-MERSS-ANN—perform best, with test accuracy of 92.67%. Additionally, they achieve the same ratio for their sensitivity, G-Mean, F-measure, kappa value, and AUC, which are 92.67%, 95.38%, 0.9266, 0.7708, and 0.9953, respectively. InceptionResNet previously achieved an accuracy of 89.90%.
ResNet-18 is the last. If features are taken from it, the 'pool5' average pooling layer is discovered to be useful. In essence, 512 features from the layer are collected, and the most significant 24 features are chosen using the ERSS, RSS, and SRS methods. 32 significant features are also found using the MERSS method. Table 9 displays the complete results.
| Hybrid Algorithm | Test Accuracy | Sensitivity | G-Mean | F-measure | Kappa | AUC |
|---|---|---|---|---|---|---|
| ResNet18-ERSS-ANN | 0.8000 | 0.8000 | 0.8718 | 0.7988 | 0.3750 | 0.9531 |
| ResNet18 -RSS-ANN | 0.8000 | 0.8000 | 0.8718 | 0.7999 | 0.3750 | 0.9626 |
| ResNet18 -MERSS-ANN | 0.8533 | 0.8533 | 0.9067 | 0.8531 | 0.5417 | 0.9761 |
| ResNet18 -SRS-ANN | 0.7733 | 0.7733 | 0.8541 | 0.7748 | 0.2917 | 0.9472 |
Analyzing our suggested methods, Table 9 shows that ResNet18-MERSS-ANN performs the best, with a test accuracy of 85.33%. Additionally, its sensitivity, G-Mean, F-measure, kappa value, and AUC are all achieved at respective levels of 85.33%, 90.67%, 0.8531, 0.5417, and 0.9761. Prior to this, ResNet18 has a 95% accuracy rate.
In recent years, numerous researchers have employed various feature selection methods in their studies(Chandrashekar and Sahin, 2014, Ozaltin et al., 2022, Koklu et al., 2022). However, the process of identifying the suitable feature selection is not straightforward, as certain methods may rely on underlying assumptions. This study proposes several practical methods and conducts a comparison with Neighborhood Component Analysis (NCA), a non-parametric method that operates without making any assumptions. The results of applying various combinations of NCA are presented in Table 10
| Algorithm | Accuracy | Sensitivity | G-Mean | F-measure | Kappa | AUC |
|---|---|---|---|---|---|---|
| DarkNet53-NCA-ANN | 0.9667 | 0.9667 | 0.9790 | 0.9664 | 0.8958 | 1.00 |
| GoogleNet NCA-ANN | 0.9333 | 0.9333 | 0.9580 | 0.9329 | 0.7917 | 0.9858 |
| InceptionResNet -NCA-ANN | 0.8800 | 0.8800 | 0.9239 | 0.8790 | 0.6250 | 0.9911 |
| NASNetMobile-NCA-ANN | 0.7000 | 0.7000 | 0.8047 | 0.6953 | 0.0625 | 0.8690 |
| ResNet18- NCA-ANN | 0.8133 | 0.8133 | 0.8805 | 0.8126 | 0.4167 | 0.9778 |
Based on the findings presented in Table 10, it can be observed that DarkNet53-NCA-ANN emerges as the most effective feature selection method, exhibiting a notable accuracy rate of 96.67%. In addition, the sensitivity, G-Mean, F-measure, kappa value, and AUC of the system were determined to be 96.67%, 97.90%, 0.9664, 0.8958, and 1.00, respectively. The confusion matrix of the DarkNet53-NCA-ANN model is depicted in Fig. 4.
DarkNet-53 architecture is employed as a deep feature extractor for grapevine leaf images. To enhance the performance of the feature extraction process, the most effective feature selection method, known as MERSS, is utilized. Through the application of MERSS on the extracted features, a notable accuracy rate of 97.33% is achieved. In contrast to NCA, MERSS demonstrates superior performance. Hence, it can be asserted that the feature selection method we have developed exhibits the highest level of performance.
The deep feature extractor GoogleNet is used for the purpose of extracting features from grapevine leaf images. The feature selection method that yields successful results is RSS, which is applied to the extracted features. This method achieves an accuracy of 95.33%. When comparing it to NCA, it exhibits inferior performance in comparison to RSS. Our model, GoogleNet, consistently outperforms other models, making it the optimal choice.
InceptionResNet_v2 is implemented as a deep feature extractor for grapevine leaf images. The successful feature selection methods employed are MERSS and ERSS, which operate on the features and achieve a hit accuracy of 92.67%. When comparing it to NCA, it performs worse than MERSS and ERSS. Our model, InceptionResNet_v2, is the best one to use.
NasNetMobile operates as a deep feature extractor for grapevine leaf images. The top feature selection method used is MERSS, which is applied to the extracted features. This method resulted in an accuracy of 79.33%. When comparing it to NCA, MERSS exhibits better performance. In conclusion, when utilizing NasNetMobile, our solution proves to be the most effective once again.
ResNet18 is utilized as a deep feature extractor for grapevine leaf images. The feature selection method employed was MERSS, which was applied to the extracted features. This approach resulted in an accuracy of 85.33%. When comparing it to NCA, MERSS has lower performance. Once again, when utilizing ResNet-18, we eventually have the best one. Based on the results, it can be concluded that MERSS performs well after implementing deep feature extractors. Additionally, it has been mentioned earlier that MERSS is superior to NCA.
Some advantages and disadvantages are discussed in this section of the study. The following are the primary benefits of the study:
(i) Extensive comparisons are made using pre-trained architectures such as DarkNet-53, GoogleNet, NasNetMobile, InceptionResNet_v2, and ResNet-18.
(ii) To achieve confidential results, each architecture uses 5-fold cross-validation, and all results are measured using accuracy, sensitivity, G-Mean, F1-measure, kappa value, and AUC.
(iii) To improve classification performance on grapevine leaf images, pre-trained architectures are used as automatic deep feature extractors from the final layers (pooling layers are used). This is critical because expert opinions are not required.
(iv) To reduce dimensions and select significant features, we propose novel sampling theory-based methods that ensure reliable study results.
(v) Finally, ANN is an excellent classification tool for detecting different types of grapevine leaf images. In addition, to evaluate the proposed methods, we compared them to NCA, a widely used feature selection method. Our proposed method outperforms NCA.
The following are the study's drawbacks:
(i) Grapevine leaf images are restricted and only investigated as a balanced dataset.
Deep learning implementations are getting better and better today. This reflection can be seen with the naked eye and intensifies near vegetation. With this viewpoint, we have successfully extracted features from images of grapevine leaves in order to categorize the species of these leaves using pre-trained architectures. First, using 5-fold cross-validation, DarkNet-53, GoogleNet, InceptionResNet_v2, NasNetMobile, and ResNet-18 are used to directly classify images of grapevine leaves. The accuracy of DarkNet-53 in this section of the study is 96.20%. Although the results are excellent, we look into how they can be improved and offer new feature selection techniques based on sampling theory. Pre-trained architectures are used in the following section of this study as feature extractors, and their final average pooling layer automatically incorporates features from images. All of these features, though, are not crucial details for images. We recommend SRS, RSS, ERSS, and MERSS as four feature selection methods to choose significant features. Additionally, using methodology, we determine how many features should be chosen. It allows for effective classification using a minimal set of features. Additionally, ANN is used to classify these features. In brief, the following outcomes are attained:
DarkNet-53 is used as a deep feature extractor, and the MERSS feature selection method and ANN classifier yield a maximum accuracy of 97.33%. While GoogleNet is used as a deep feature extractor, the RSS feature selection method and ANN classifier are used to achieve the highest accuracy, which is 95.33%. Better accuracy is attained as 92.67% when InceptionResNet_v2 is used as a deep feature extractor, providing the RSS and MERSS feature selection methods and ANN classifier. The accuracy increases to 79.33% when NasNetMobile is used as a deep feature extractor in combination with the MERSS feature selection method and ANN classifier. As a deep feature extractor, ResNet-18 is implemented, but using the MERSS feature selection method and ANN classifier, accuracy is improved to 85.33%. After all, a comparison with NCA has been made, and we can state that our suggested methods, specifically the MERSS method, are superior to it under comparable circumstances.As a result, the performance is effectively improved by the planned hybrid algorithms, and it can be inferred from explanatory methods that the results are reliable. Using DarkNet53-MERSS-ANN, the study's best performance is achieved with an accuracy of 97.33% when identifying different grapevine leaf types from images. Finally, we can affirm that the structure we created performs superbly.
What happens in the next study?
This study demonstrates how pre-trained architectures can identify different plant species from images. Therefore, automatic species identification for experts, farmers, and researchers is provided by image classification of plants. However, because of the suggested algorithm, people are not spending a lot more time identifying plant species. We can say that the created structure is capable of performing and being advanced in plant detection. We'll use the suggested feature selection techniques on a variety of datasets from various fields in our upcoming work.
Authors Contributions
Oznur Ozaltin: Idealization, methodology, software, analysis, writing, review and editing. Nursel Koyuncu: Idealization, methodology, software, analysis, writing, review and editing.
Funding
No funding was received for this study.
Data Availability
The data set is available from the website:
http://www.muratkoklu.com /datasets/Grapevine_Leaves_Image_Dataset.rar
Declarations Conflict of interests
Oznur Ozaltin and Nursel Koyuncu declare no competing interest. Oznur Ozaltin and Nursel Koyuncu declare that they have no known competing fnancial interests or personal relationships that could have appeared to infuence the work reported in this paper.
Compliance with ethical standards
Our manuscript is original and has not been previously published, nor currently under review at any other journal. We have complied with all ethical guidelines for conducting research and have obtained all necessary approvals for the study.
- Addagarla, S. K., Chakravarthi, G. K. & Anitha, P. 2020. Real time multi-scale facial mask detection and classification using deep transfer learning techniques. International Journal, 9, 4402-4408.
- Adeel, A., Khan, M. A., Akram, T., Sharif, A., Yasmin, M., Saba, T. & Javed, K. 2022. Entropy‐controlled deep features selection framework for grape leaf diseases recognition. Expert Systems, 39, e12569.
- Agatonovic-Kustrin, S. & Beresford, R. 2000. Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. Journal of pharmaceutical and biomedical analysis, 22, 717-727.
- Ahila Priyadharshini, R., Arivazhagan, S., Arun, M. & Mirnalini, A. 2019. Maize leaf disease classification using deep convolutional neural networks. Neural Computing and Applications, 31, 8887-8895.
- Al-Odat, M. T. & Al-Saleh, M. F. 2001. A variation of ranked set sampling. Journal of Applied Statistical Science, 10, 137-146.
- Arlot, S. & Celisse, A. 2010. A survey of cross-validation procedures for model selection. Statistics surveys, 4, 40-79.
- Arun, Y. & Viknesh, G. Leaf Classification for Plant Recognition Using EfficientNet Architecture. 2022 IEEE Fourth International Conference on Advances in Electronics, Computers and Communications (ICAECC), 2022. IEEE, 1-5.
- Atila, Ü., Uçar, M., Akyol, K. & Uçar, E. 2021. Plant leaf disease classification using EfficientNet deep learning model. Ecological Informatics, 61, 101182.
- Azim, M. A., Islam, M. K., Rahman, M. M. & Jahan, F. 2021. An effective feature extraction method for rice leaf disease classification. TELKOMNIKA (Telecommunication Computing Electronics and Control), 19, 463-470.
- Bhujel, A., Kim, N.-E., Arulmozhi, E., Basak, J. K. & Kim, H.-T. 2022. A lightweight Attention-based convolutional neural networks for tomato leaf disease classification. Agriculture, 12, 228.
- Bouza-Herrera, C. N. & Al-Omari, A. I. F. 2018. Ranked set sampling: 65 years improving the accuracy in data gathering, Academic Press.
- Cangi, R. & Yağci, A. 2017. Bağdan sofraya yemeklik asma yaprak üretimi. Nevşehir Bilim ve Teknoloji Dergisi, 6, 137-148.
- Chandola, Y., Virmani, J., Bhadauria, H. & Kumar, P. 2021. Chapter 4 -Deep Learning for Chest Radiographs: Computer-Aided Classification, Elsevier.
- Chandrashekar, G. & Sahin, F. 2014. A survey on feature selection methods. Computers & Electrical Engineering, 40, 16-28.
- Chen, H.-C., Widodo, A. M., Wisnujati, A., Rahaman, M., Lin, J. C.-W., Chen, L. & Weng, C.-E. 2022. AlexNet convolutional neural network for disease detection and classification of tomato leaf. Electronics, 11, 951.
- Djouzi, K., Beghdad-Bey, K. & Amamra, A. 2022. A new adaptive sampling algorithm for big data classification. Journal of Computational Science, 61, 101653.
- Dudi, B. & Rajesh, V. 2022. Optimized threshold-based convolutional neural network for plant leaf classification: a challenge towards untrained data. Journal of Combinatorial Optimization, 43, 312-349.
- Ganguly, S., Bhowal, P., Oliva, D. & Sarkar, R. 2022. BLeafNet: a Bonferroni mean operator based fusion of CNN models for plant identification using leaf image classification. Ecological Informatics, 69, 101585.
- Gao, J., Lanchantin, J., Soffa, M. L. & Qi, Y. Black-box generation of adversarial text sequences to evade deep learning classifiers. 2018 IEEE Security and Privacy Workshops (SPW), 2018. IEEE, 50-56.
- Goldberger, J., Hinton, G. E., Roweis, S. & Salakhutdinov, R. R. 2004. Neighbourhood components analysis. Advances in neural information processing systems, 17.
- Göktürk, N., Artik, N., Yavaş, İ. & Fidan, Y. 1997. Bazı üzüm çeşitleri ve asma anacı yapraklarının yaprak konservesi olarak değerlendirilme olanakları üzerinde bir araştırma. Gıda, 22.
- Hazirbas, C., Ma, L., Domokos, C. & Cremers, D. Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture. Asian conference on computer vision, 2016. Springer, 213-228.
- He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016. 770-778.
- Hridoy, R. H., Habib, T., Rahman, S. & Uddin, M. S. 2022. Deep Neural Networks-Based Recognition of Betel Plant Diseases by Leaf Image Classification. Evolutionary Computing and Mobile Sustainable Networks. Springer.
- Hussein, M. & Özyurt, F. 2021. A new technique for sentiment analysis system based on deep learning using Chi-Square feature selection methods. Balkan Journal of Electrical and Computer Engineering, 9, 320-326.
- Jiang, H. 2021. Machine Learning Fundamentals: A Concise Introduction, Cambridge University Press.
- Kamble, R. M., Chan, G. C., Perdomo, O., Kokare, M., Gonzalez, F. A., Müller, H. & Mériaudeau, F. Automated diabetic macular edema (DME) analysis using fine tuning with inception-resnet-v2 on OCT images. 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), 2018. IEEE, 442-446.
- Kan, H., Jin, L. & Zhou, F. 2017. Classification of medicinal plant leaf image based on multi-feature extraction. Pattern recognition and image analysis, 27, 581-587.
- Karadal, C. H., Kaya, M. C., Tuncer, T., Dogan, S. & Acharya, U. R. 2021. Automated classification of remote sensing images using multileveled MobileNetV2 and DWT techniques. Expert Systems with Applications, 185, 115659.
- Koklu, M. & Ozkan, I. A. 2020. Multiclass classification of dry beans using computer vision and machine learning techniques. Computers and Electronics in Agriculture, 174, 105507.
- Koklu, M., Unlersen, M. F., Ozkan, I. A., Aslan, M. F. & Sabanci, K. 2022. A CNN-SVM study based on selected deep features for grapevine leaves classification. Measurement, 188, 110425.
- Koyuncu, N. & Al-Omari, A. I. 2021. Generalized robust-regression-type estimators under different ranked set sampling. Mathematical Sciences, 15, 29-40.
- Lilhore, U. K., Imoize, A. L., Lee, C.-C., Simaiya, S., Pani, S. K., Goyal, N., Kumar, A. & Li, C.-T. 2022. Enhanced convolutional neural network model for cassava leaf disease identification and classification. Mathematics, 10, 580.
- Liu, Y. & Durlofsky, L. J. 2021. 3D CNN-PCA: A deep-learning-based parameterization for complex geomodels. Computers & Geosciences, 148, 104676.
- Lopez-Del Rio, A., Nonell-Canals, A., Vidal, D. & Perera-Lluna, A. 2019. Evaluation of cross-validation strategies in sequence-based binding prediction using deep learning. Journal of chemical information and modeling, 59, 1645-1657.
- Mcculloch, W. S. & Pitts, W. 1943. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5, 115-133.
- Mcintyre, G. 1952. A method for unbiased selective sampling, using ranked sets. Australian journal of agricultural research, 3, 385-390.
- Nguyen, C., Sagan, V., Maimaitiyiming, M., Maimaitijiang, M., Bhadra, S. & Kwasniewski, M. T. 2021. Early detection of plant viral disease using hyperspectral imaging and deep learning. Sensors, 21, 742.
- Ozaltin, O., Coskun, O., Yeniay , O. & Subasi , A. 2022. Classification of brain hemorrhage computed tomography images using OzNet hybrid algorithm. Int J Imaging SystTechnol., 1‐23. .
- Ozaltin, O., Coskun, O., Yeniay, O. & Subasi, A. 2023a. Classification of brain hemorrhage computed tomography images using OzNet hybrid algorithm. International Journal of Imaging Systems and Technology, 33, 69-91.
- Ozaltin, O. & Yeniay, O. 2022. A Novel Proposed CNN-SVM Architecture for ECG Scalograms Classification. Available at Research Square Platform LLC [Online].
- Ozaltin, O. & Yeniay, O. 2023. Detection of monkeypox disease from skin lesion images using Mobilenetv2 architecture. Communications Faculty of Sciences University of Ankara Series A1 Mathematics and Statistics, 72, 482-499.
- Ozaltin, O., Yeniay, O. & Subasi, A. 2023b. Artificial intelligence-based brain hemorrhage detection. Accelerating Strategic Changes for Digital Transformation in the Healthcare Industry. Elsevier.
- Özaltın, Ö. & Yeniay, Ö. Ecg classification performing feature extraction automatically using a hybrid cnn-svm algorithm. 2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), 2021. IEEE, 1-5.
- Pathak, D. & Raju, U. 2021. Content-based image retrieval using feature-fusion of GroupNormalized-Inception-Darknet-53 features and handcraft features. Optik, 246, 167754.
- Paymode, A. S. & Malode, V. B. 2022. Transfer Learning for Multi-Crop Leaf Disease Image Classification using Convolutional Neural Network VGG. Artificial Intelligence in Agriculture, 6, 23-33.
- Rajinikanth, V., Joseph Raj, A. N., Thanaraj, K. P. & Naik, G. R. 2020. A customized VGG19 network with concatenation of deep and handcrafted features for brain tumor detection. Applied Sciences, 10, 3429.
- Reddy, S. R., Varma, G. & Davuluri, R. L. 2022. Deep Neural Network (DNN) Mechanism for Identification of Diseased and Healthy Plant Leaf Images Using Computer Vision. Annals of Data Science, 1-30.
- Redmon, J. & Farhadi, A. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.
- Rendon, E., Alejo, R., Castorena, C., Isidro-Ortega, F. J. & Granda-Gutierrez, E. E. 2020. Data sampling methods to deal with the big data multi-class imbalance problem. Applied Sciences, 10, 1276.
- Ruth, J. A., Uma, R., Meenakshi, A. & Ramkumar, P. 2022. Meta-Heuristic Based Deep Learning Model for Leaf Diseases Detection. Neural Processing Letters, 1-17.
- Saber, A., Sakr, M., Abo-Seida, O. M., Keshk, A. & Chen, H. 2021. A novel deep-learning model for automatic detection and classification of breast cancer using the transfer-learning technique. IEEE Access, 9, 71194-71209.
- Saberi Anari, M. 2022. A Hybrid Model for Leaf Diseases Classification Based on the Modified Deep Transfer Learning and Ensemble Approach for Agricultural AIoT-Based Monitoring. Computational Intelligence and Neuroscience, 2022.
- Saglam, H. & Saglam, Ö. C. 2018. A historical review on Turkish viticulture; the importance of viticulture genetic resources. Selcuk Journal of Agriculture and Food Sciences, 32, 601-606.
- Samawi, H. M., Yu, L., Rochani, H. & Vogel, R. 2020. Reducing sample size needed for cox-proportional hazards model analysis using more efficient sampling method. Communications in Statistics-Theory and Methods, 49, 1281-1298.
- Sembiring, A., Away, Y., Arnia, F. & Muharar, R. Development of concise convolutional neural network for tomato plant disease classification based on leaf images. Journal of Physics: Conference Series, 2021. IOP Publishing, 012009.
- Sharifrazi, D., Alizadehsani, R., Roshanzamir, M., Joloudari, J. H., Shoeibi, A., Jafari, M., Hussain, S., Sani, Z. A., Hasanzadeh, F. & Khozeimeh, F. 2021. Fusion of convolution neural network, support vector machine and Sobel filter for accurate detection of COVID-19 patients using X-ray images. Biomedical Signal Processing and Control, 68, 102622.
- Shi, Y., Yang, K., Jiang, T., Zhang, J. & Letaief, K. B. 2020. Communication-efficient edge AI: Algorithms and systems. IEEE Communications Surveys & Tutorials, 22, 2167-2191.
- Singh, D., Taspinar, Y. S., Kursun, R., Cinar, I., Koklu, M., Ozkan, I. A. & Lee, H.-N. 2022. Classification and Analysis of Pistachio Species with Pre-Trained Deep Learning Models. Electronics, 11, 981.
- Sladojevic, S., Arsenovic, M., Anderla, A., Culibrk, D. & Stefanovic, D. 2016. Deep neural networks based recognition of plant diseases by leaf image classification. Computational intelligence and neuroscience, 2016.
- Subasi, A. 2012. Medical decision support system for diagnosis of neuromuscular disorders using DWT and fuzzy support vector machines. Computers in Biology and Medicine, 42, 806-815.
- Szegedy, C., Ioffe, S., Vanhoucke, V. & Alemi, A. A. Inception-v4, inception-resnet and the impact of residual connections on learning. Thirty-first AAAI conference on artificial intelligence, 2017.
- Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V. & Rabinovich, A. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition, 2015. 1-9.
- Tiwari, V., Joshi, R. C. & Dutta, M. K. 2021. Dense convolutional neural networks based multiclass plant disease detection and classification using leaf images. Ecological Informatics, 63, 101289.
- Tiwari, V., Joshi, R. C. & Dutta, M. K. 2022. Deep neural network for multi‐class classification of medicinal plant leaves. Expert Systems, e13041.
- Toğaçar, M., Ergen, B., Cömert, Z. & Özyurt, F. 2020. A deep feature learning model for pneumonia detection applying a combination of mRMR feature selection and machine learning models. Irbm, 41, 212-222.
- Wang, J., He, X., Faming, S., Lu, G., Cong, H. & Jiang, Q. 2021. A Real-Time Bridge Crack Detection Method Based on an Improved Inception-Resnet-v2 Structure. IEEE Access, 9, 93209-93223.
- Wang, J., Yang, Y. & Xia, B. 2019. A simplified Cohen’s Kappa for use in binary classification data annotation tasks. IEEE Access, 7, 164386-164397.
- Wang, X.-F., Huang, D.-S., Du, J.-X., Xu, H. & Heutte, L. 2008. Classification of plant leaf images with complicated background. Applied mathematics and computation, 205, 916-926.
- Wei, K., Chen, B., Zhang, J., Fan, S., Wu, K., Liu, G. & Chen, D. 2022. Explainable Deep Learning Study for Leaf Disease Classification. Agronomy, 12, 1035.
- Zamanzade, E. & Mahdizadeh, M. 2020. Using ranked set sampling with extreme ranks in estimating the population proportion. Statistical methods in medical research, 29, 165-177.
- Zhang, S., Wu, X., You, Z. & Zhang, L. 2017. Leaf image based cucumber disease recognition using sparse representation classification. Computers and electronics in agriculture, 134, 135-141.
- Zoph, B., Vasudevan, V., Shlens, J. & Le, Q. V. Learning transferable architectures for scalable image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, 2018. 8697-8710.
No competing interests reported.