Tea cultivation holds significant economic and agricultural value across many regions, particularly in developing countries, where it supports millions of livelihoods. However, the productivity and quality of tea leaves are severely threatened by a wide range of foliar diseases, which, if undetected or misdiagnosed, can lead to substantial crop losses. Existing manual and traditional image-based detection methods are time-consuming and often lack the precision required for early-stage identification across multiple disease types. To address these limitations, this study proposes TeaLeafNet-GWO, an intelligent deep learning framework that integrates a hybrid CNN–Transformer architecture with Gray Wolf Optimization (GWO) for automated tea leaf disease classification. The model combines the spatial feature extraction power of CNNs with the global contextual awareness of Transformer blocks (MobileViT), enhanced by channel-wise recalibration using a squeeze-and-excitation network (SENet). GWO is employed to fine-tune critical hyperparameters, ensuring optimal performance and generalization. The dataset comprises 999 high-resolution images representing eight distinct tea leaf conditions, including both healthy and diseased classes. Preprocessing techniques such as contrast-limited adaptive histogram equalization (CLAHE) and median filtering were applied to enhance image quality and suppress noise. The model was trained and evaluated using a stratified split (70% training, 30% testing). TeaLeafNet-GWO achieved an average accuracy of 97.72%, F1-score of 86.66%, and Matthews correlation coefficient (MCC) of 84.44% in the training phase, with similarly high performance in testing, outperforming several state-of-the-art hybrid models in comparative analysis. These results demonstrate TeaLeafNet-GWO’s effectiveness as a lightweight, scalable, and accurate solution for real-time disease monitoring, offering tangible benefits to precision agriculture and smart farming systems.
38Using a multi-convolutional neural network to automatically identify small-sample tea leaf diseases
Using a multi-convolutional neural network to automatically identify small-sample tea leaf diseases
190Tea leaf disease detection and identification based on YOLOv7 (YOLO-T)
A reliable and accurate diagnosis and identification system is required to prevent and manage tea leaf diseases. Tea leaf diseases are detected manually, increasing time and affecting yield quality and productivity. This study aims to present an artificial intelligence-based solution to the problem of tea leaf disease detection by training the fastest single-stage object detection model, YOLOv7, on the diseased tea leaf dataset collected from four prominent tea gardens in Bangladesh. 4000 digital images of five types of leaf diseases are collected from these tea gardens, generating a manually annotated, data-augmented leaf disease image dataset. This study incorporates data augmentation approaches to solve the issue of insufficient sample sizes. The detection and identification results for the YOLOv7 approach are validated by prominent statistical metrics like detection accuracy, precision, recall, mAP value, and F1-score, which resulted in 97.3%, 96.7%, 96.4%, 98.2%, and 0.965, respectively. Experimental results demonstrate that YOLOv7 for tea leaf diseases in natural scene images is superior to existing target detection and identification networks, including CNN, Deep CNN, DNN, AX-Retina Net, improved DCNN, YOLOv5, and Multi-objective image segmentation. Hence, this study is expected to minimize the workload of entomologists and aid in the rapid identification and detection of tea leaf diseases, thus minimizing economic losses.
Read moreHDMFRTDB: Design of a High-Efficiency Deep Learning Classification Model for Fruit Ripeness-Type Differentiation Via Bioinspired Optimization
Fruits often alter their outward appearance in accordance with their inside makeup. As a result, immature fruits seem different from ripe fruits, and fruits that have a disease look different from fruits that are healthy. Today, artificial fruit ripening is expanding quite quickly in order to produce fruits more quickly in order to meet the needs of the rising population. However, these fruits are unhealthy and regularly consumed individuals experience a broad range of physical and mental health problems. In order to let daily customers verify their fruits before purchasing or regularly eating them, high-efficiency identification of these fruits based on their visual appearance is required. Researchers have suggested a broad range of clinical approaches to carry out this duty, but the most of them either have poor accuracy or can’t be applied to many fruit varieties. The contribution of this research is the building of a unique, very effective deep learning classification model for fruit ripeness-type separation using bioinspired optimization, which is suggested in this text to get beyond these restrictions. To properly categorize fruits, the suggested model first combines a Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement technique with a CNN model based on LAB color space. A bioinspired model based on Grey Wolf Optimization (GWO) and Particle Swarm Optimization (PSO) is used to identify classes of fruit ripeness based on this categorization. Using a cloud-based subscription model, these categories—which include naturally ripened, artificially ripened, and unripe categories—will help regular consumers identify fruit classifications. The inclusion of pre-trained VGGNet-19, You Look Only Once (YoLo V2), and Mobile V Net2 models, which aid in high-efficiency classification, gives the proposed model a high processing speed. These models were chosen because they performed more accurately over a variety of dataset settings. The suggested model was evaluated using data from the ILSVRC2014 dataset, Fresh Fruit Database, and Fruits 360 databases. This examination led to the conclusion that the suggested model outperformed current techniques in terms of accuracy, delay, precision, and recall by 15.4%, 8.3%, 9.5%, and 6.2%. Additionally, it was discovered that the suggested model had a 94.5% accuracy rate when predicting the maturity type of five distinct fruit varieties. The model was also installed on the cloud for general testing and assessment, and it was shown to be capable of high-speed deployments since it could analyze fruit photos in less than 500 ms. The suggested approach is helpful for a broad range of clinical and real-time use cases because of its excellent performance.
Read more9Liver Tumor Classification Using Optimal Opposition-Based Grey Wolf Optimization
Image processing plays a significant role in various fields like military, business, healthcare and science. Ultrasound (US), Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are the various image tests used in the treatment of the cancer. Detecting the liver tumor by these tests is a complex process. Hence, in this research work, a novel approach utilizing a deep learning model is used. That is Deep Belief Network (DBN) with Opposition-Based Learning (OBL)-Grey Wolf Optimization (GWO) is used for the classification of liver cancer. This process undergoes five major processes. Initially, in pre-processing the color contrast is improved by Contrast Limited Adaptive Histogram Equalization (CLAHE) and the noise is removed by Wiener Filtering (WF). The liver is segmented by adaptive thresholding following pre-processing. Following that, the kernelizedFuzzy C Means (FCM) method is used to segment the tumor area. The form, color, and texture features are then extracted during the feature extraction process. Finally, these traits are categorized using DBN, and OBL-GWO is employed to enhance system performance. The entire evaluation is done on Liver Tumor Segmentation (LiTS) benchmark dataset. Finally, the performance of the proposed DBN-OBL-GWO is compared to other models and their achievements are proved. The proposed DBN-OBL-GWO achieves a better accuracy of 0.995, precision of 0.948 and false positive rate (FPR) of 0.116, respectively.
Read moreTL-GWO: Fine-tuned transfer learning with grey wolf optimizer for accurate fundus image-based eye disease classification.
TL-GWO: Fine-tuned transfer learning with grey wolf optimizer for accurate fundus image-based eye disease classification.
Read moreNovel IDS Framework: Integrating GWO Feature Selection with KAN Classification
The past few decades have seen significant lifestyle improvements through cutting-edge innovations like AI and fog computing enabled by the World Wide Web, which are crucial for practical applications involving both symmetrical and asymmetrical information distributions. However, these advancements also come with the risk off requent and dangerous cyber-attacks. To mitigate these unwanted malwares, researchers must develop and implement novel intrusion detection systems (IDSs). Challenges such as inadequate accuracy scores due to numerous unnecessary and ineffective features, poor identification of attacks through specific deep learning classification methods, the costly and inefficient use of labeled training databases, and the excessive time required for system development and evaluation hinder there liability and efficiency of IDSs.This paper proposes a hybrid approach that combines the Grey Wolf Optimizer (GWO) for feature selection and the Kolmogorov-Arnold Network(KAN) algorithm for classification to address these challenges.The GWO is utilized to extract important features through meta-heuristic methods, demonstrating its effectiveness in feature selection. The proposed model achieves a high accuracy score, precision, recall, and F1-score of 92.09%, indicating its capability to accurately identify both normal and intrusive activities. The Matthews Correlation Coefficient (MCC) of 0.9019 further validates the model's robustness.
Read moreA Robust Grey Wolf-based Deep Learning for Brain Tumour Detection in MR Images
In recent times, the detection of brain tumour is a common fatality in the field of the health community. Generally, the brain tumor is an abnormal mass of tissue where the cells grow up and increase uncontrollably, apparently unregulated by mechanisms that control cells. A number of techniques have been developed so far; however, the time consumption in detecting brain tumor is still a challenge in the field of image processing. This paper intends to propose a new detection model even accurately. The model includes certain processes like Preprocessing, Segmentation, Feature Extraction and Classification. Particularly, two extreme processes like contrast enhancement and skull stripping are processed under initial phase, in the segmentation process, this paper uses Fuzzy Means Clustering (FCM) algorithm. Both Gray Level Co-occurrence Matrix (GLCM) as well as Gray-Level Run-Length Matrix (GRLM) features are extracted in feature extraction phase. Moreover, this paper uses Deep Belief Network (DBN) for classification. The DBN is integrated with the optimization approach, and hence this paper introduces the optimized DBN, for which Grey Wolf Optimization (GWO) is used here. The proposed model is termed as GW-DBN model. The proposed model compares its performance over other conventional methods in terms of Accuracy, Specificity, Sensitivity, Precision, Negative Predictive Value (NPV), F 1 Score and Matthews Correlation Coefficient (MCC), False negative rate (FNR), False positive rate (FPR) and False Discovery Rate (FDR), and proven the superiority of proposed work.
Read moreA Hybrid Deep Learning Multi-Class Classification Model for Alzheimer’s Disease Using Enhanced MRI Images
Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder that significantly affects cognitive function, making early and accurate diagnosis essential. Traditional Deep Learning (DL)-based approaches often struggle with low-contrast MRI images, class imbalance, and suboptimal feature extraction. This paper develops a Hybrid DL system that unites MobileNetV2 with adaptive classification methods to boost Alzheimer’s diagnosis by processing MRI scans. Image enhancement is done using Contrast-Limited Adaptive Histogram Equalization (CLAHE) and Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN). A classification robustness enhancement system integrates class weighting techniques and a Matthews Correlation Coefficient (MCC)-based evaluation method into the design. The trained and validated model gives a 98.88% accuracy rate and 0.9614 MCC score. We also performed a 10-fold cross-validation experiment with an average accuracy of 96.52% (), a loss of 0.1671, and an MCC score of 0.9429 across folds. The proposed framework outperforms the state-of-the-art models with a 98% weighted F1-score while decreasing misdiagnosis results for every AD stage. The model demonstrates apparent separation abilities between AD progression stages according to the results of the confusion matrix analysis. These results validate the effectiveness of hybrid DL models with adaptive preprocessing for early and reliable Alzheimer’s diagnosis, contributing to improved computer-aided diagnosis (CAD) systems in clinical practice.
Read more267Predicting TBM penetration rate in hard rock condition: A comparative study among six XGB-based metaheuristic techniques
Predicting TBM penetration rate in hard rock condition: A comparative study among six XGB-based metaheuristic techniques
21Performance of different kernel functions for LS‐SVM‐GWO to estimate flashover voltage of polluted insulators
This work attempts to clarify the potentials of hybrid model based on least‐squares support vector machine (LS‐SVM) and a novel meta‐heuristic algorithm called Grey Wolf optimiser (GWO) in high‐voltage applications, considering several kernel functions. The selection of the suitable kernel function and its parameters play an important role in the performance of LS‐SVM. For this purpose, GWO is proposed in this study as an efficient optimisation approach to adjust the parameters of various kernel functions such as linear kernel (Lin), radial basis function kernel, polynomial kernel (poly) and multi‐layer perceptron kernel. Afterwards, the LS‐SVM with the most appropriate kernel function is designed to model flashover voltage of polluted high‐voltage insulators. The performance of the developed model is compared with the previous works. The results confirm high capabilities of the proposed hybrid model for the prediction of the flashover voltage of polluted insulators.
Read more97Novel forecasting models for immediate-short-term to long-term influent flow prediction by combining ANFIS and grey wolf optimization
Novel forecasting models for immediate-short-term to long-term influent flow prediction by combining ANFIS and grey wolf optimization
Read more3GLCM-based detection and classification of microaneurysm in diabetic retinopathy fundus images
Diabetic retinopathy is a major cause of blindness and it includes the lesions like microaneurysms, haemorrhages, and exudates. Microaneurysms are the first clinical sign of diabetic retinopathy and it is a small red dot on the retinopathy fundus images. The number of micro aneurysms is used to indicate the severity of the disease. The proposed algorithm detects and classifies the micro aneurysm from diabetic retinopathy fundus images in low resolution images also. Initially the image is processed by a median filter and enhanced by contrast limited adaptive histogram equalisation (CLAHE). Micro aneurysms are detected by extended minima method for candidate extraction. The statistical features are extracted by grey level coocurrence matrix (GLCM) and are given to the classifier to classify microaneurysms accurately. These detected MA are validated by comparing with expert ophthalmologists' hand-drawn ground-truth images. The simulation results show the performance of the proposed algorithm.
Read more95A thresholding based technique to extract retinal blood vessels from fundus images
A thresholding based technique to extract retinal blood vessels from fundus images
3Improved Methods for Mammogram Breast Cancer Using by Denoising Filtering
In diagnosing breast cancer, digital mammograms have shown their effectiveness as an appropriate and simple instrument in the early detection of tumor. Mammograms offer helpful cancer symptoms information, including microcalcifications and masses, which are not easy to distinguish because there are some flaws with the mammography images, including low contrast, high noise, fuzzy and blur. Additionally, there is a major problem with mammography because of a high density of the breast which conceals As a result of the mammographic image, it is more difficult to distinguish between the tissues with normal dense and the tissues that are cancerous. Therefore, mammography images need to be improved in order to accurately identify and diagnose breast cancer. The most typical goals of images enhancement are to remove noise and improve image details. With the aid of mammography image processing techniques, a special data including distinctive characteristics of tumors can be differentiated, this could help distinguish between malignant and benign cancers. This work focuses on removing noise of pepper & salt, improving image to increase the quality of mammography and enhance early detection of breast cancer. A specific approach is employed to do this, including of two phases of image denoising base filtration and one phase to improve contrast. The stages of filtering contain the using of wiener and median filters. The contrast enhancement stage utilizes (CLAHE) which is an abbreviation for contrast limited adaptive histogram equalization. Evaluating the performance is done via contrast histogram for the CLAHE and MSE & PSNF for the filters. The results demonstrate that the work technique is doing better when put to comparison with other approaches in term of low MSE (1.1645) and high PSNR (47.4750). The technique will be assessed with additional kinds of noise for future work.
Read more6Multimodal Technique for Human Authentication Using Fusion of Palm and Dorsal Hand Veins
Multimodal biometric systems have been widely used to achieve high recognition accuracy. This paper presents a new multimodal biometric system using an intelligent technique to authenticate human by fusion of palm and dorsal hand veins pattern. We developed an image analysis technique to extract region of interest (ROI) from palm and dorsal hand veins image. After extracting ROI we design a sequence of preprocessing steps to improve palm and dorsal hand veins images using Homomorphic, Median filter, Wiener filter and Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance vein image. Our smart technique is based on the following intelligent algorithms, namely; principal component analysis (PCA) algorithm for feature extraction and k-Nearest Neighbors (K-NN) classifier for matching operation. The database chosen was the CASIA Multi-Spectral Palmprint Image Database V1.0 and Bosphorus Hand Vein Database. The achieved result for the fusion of both biometric traits was Correct Recognition Rate (CRR) is 97.6% with FAlse Reject Rate (FRR) 2.4%.KeywordsBiometric systemsPattern recognitionIntelligent computingImage processingMachine learning
Read more
Copyright 2026 Cactus Communications. All rights reserved.
