Comparative study on traditional manual checking methods and machine learning based checking methods for Pomegranate plant leaf disease

As the mileage of electrified railroads continues to expand, insulators, as a key component of the power transmission system, are crucial to the cleaning and maintenance of insulators to ensure the safety of railroad power supply. However, the dirt deposit-ed in daily use leads to the frequent occurrence of dirt flash accidents, and the traditional manual cleaning method can no longer meet the safety requirements of modern railroad operation due to its low efficiency, high operational risk and difficulty in adapting to the needs of large-scale maintenance. In view of the above problems, this paper proposes a servo control system design method based on current feedback, and designs an insulator wiping end-effector based on current feedback control. Firstly, the mechanical structure and control module design are proposed, and the three-dimensional parametric model is constructed through SolidWorks to optimize the actuator kinematic characteristics. Secondly, a high-precision servo control system is developed based on the STM32F407 master control platform, which innovatively integrates the PID regulation technology, the high-sensitivity current acquisition module and the sliding average filtering algorithm to realize the real-time dynamic and precise control of the contact pressure between the brush and insulator. Then, the model is constructed, and the actuator prototype is completed through electromechanical coupling, and simulation experiments are conducted to verify the feasibility of the project. Finally, the operation verification is carried out by building experimental platform to simulate the railway environment, and the results show that the actuator can intelligently adapt to a variety of installation postures, such as horizontal, vertical and tilted, and the accuracy of contact pressure control reaches ±0.2kg, and the efficiency of a single cleaning is improved compared with the traditional manual method. This study effectively solves the technical problem of unmanned cleaning and maintenance of railroad insulators, and provides a generalizable technical solution for the research and development of intelligent unmanned operation and maintenance equipment for contact networks.

The inconsistent parameters of different lead-acid batteries in the same battery pack will result in the reduction of battery pack capacity and life. It is difficult to fundamentally solve the inconsistent parameters problem of lead-acid batteries. Battery grouping is a simple and effective approach for solving the performance inconsistency problem by packing batteries with close characteristic parameters. The traditional manual grouping method is labor intensive and prone to errors in measurement that will result in wrong grouping. In this article, a novel lead-acid battery automatic grouping system is developed based on graph cuts. This system consists of a PC server end, a wireless router, and several portable grouping devices. Based on embedded real-time operating, the proposed system realizes battery parameters characterization, data uploading, and automatic grouping processes. Using this battery automatic grouping system, batteries with close charge and discharge characteristics will be grouped into the same battery pack. Experimental results demonstrate that the proposed approach can provide superior performance over traditional manual methods.

Application of Artificial intelligence (AI) in agriculture sector plays an important role to enhance the yields by predicting and detecting the plant diseases and improving health of the crop. The early detection of plant diseases is crucial and helpful to the farmers to minimize the crop loss and ensure healthy crop. However, the traditional manual methods, are time consuming, error-prone, and inefficient for large-scale farming. Adopting recent technologies in Artificial Intelligence (AI) and Deep Learning, particularly Convolutional Neural Networks (CNNs) in the recent years have revolutionized the automation process of plant disease detection. However, singlemodal approaches depend on only RGB images often fail to capture critical physiological and biochemical changes in plants. To overcome these limitations, we propose a Single-Stream CNN in Multi-Modal Plant Disease Detection, integrating RGB, thermal, and hyperspectral imaging into a unified model. Unlike traditional multistream architectures that increase computational complexity, our model processes multi-modal data as a single 4-channel input tensor, optimizing feature fusion while maintaining computational efficiency. The proposed architecture, based on a Modified VGG-16 CNN model, which enhances disease detection accuracy by leveraging complementary information from different imaging modalities. Experimental evaluations demonstrate significant improvements in classification accuracy compared to RGB-only models. Furthermore, our model is optimized for real-time deployment on edge computing devices, making it scalable for precision agriculture applications, including automated greenhouse monitoring, drone-based crop surveillance, and IoTintegrated farming systems. This research work highlights the transformative potential of AI-driven multi-modal plant disease detection, flagging the way for more efficient, cost-effective, and scalable agricultural solutions.

The global food security and agricultural sustainability face a major threat from plant diseases. Effective management requires both early and accurate identification of these diseases. The development of Artificial Intelligence (AI) has led Machine Learning (ML) techniques to become promising tools for automated disease detection and classification. The paper presents an extensive evaluation of current progress in employing ML methods for plant disease detection. The role of image processing combined with deep learning and traditional ML classifiers in disease identification is discussed in detail. A detailed literature survey is provided followed by a method- dataset-performance metrics comparison. The paper also discusses future research directions and challenges.

A review on automated plant disease detection: motivation, limitations, challenges, and recent advancements for future research

Crops play a vital role in the global food supply. Various environmental factors can cause crop diseases and insect pests, resulting in severe production losses. However, manual detection of crop diseases and insect pests is a time-consuming and error-prone process, which often fails to identify and prevent the spread of plant diseases in a timely and effective manner. To overcome these challenges, machine learning (ML) and deep learning (DL) technologies have been introduced in recent years to improve early identification and effective response to plant pests and diseases. In this article, the principles of convolutional neural network (CNN), recurrent neural network (RNN) and adversarial generative neural network (GAN) are explained, as well as the latest progress in the improvement and application of the three algorithms in plant disease detection and detection. By applying DL technology, efficient and accurate detection of pests and diseases can be achieved, thereby providing reliable support for agricultural production. It is hoped that this work will become a valuable resource for researchers studying plant pest and disease detection and provide guidance to further advance research and practice in this field. At the same time, some current challenges and issues that need to be solved are also discussed, such as data quality, target occlusion, model generalization ability, and adaptability in practical applications. Deep learning holds great promise in revolutionizing precision agriculture by providing efficient and accurate solutions for pest and disease management.

Image-based plant disease detection is among the essential activities in precision agriculture for observing incidence and measuring the severity of variability in crops. 70% to 80% of the variabilities are attributed to diseases caused by pathogens, and 60% to 70% appear on the leaves in comparison to the stem and fruits. This work provides a comparative analysis through the model implementation of the two renowned machine learning models, the support vector machine (SVM) and deep learning (DL), for plant disease detection using leaf image data. Until recently, most of these image processing techniques had been, and some still are, exploiting what some considered as "shallow" machine learning architectures. The DL network is fast becoming the benchmark for research in the field of image recognition and pattern analysis. Regardless, there is a lack of studies concerning its application in plant leaves disease detection. Thus, both models have been implemented in this research on a large plant leaf disease image dataset using standard settings and in consideration of the three crucial factors of architecture, computational power, and amount of training data to compare the duos. Results obtained indicated scenarios by which each model best performs in this context, and within a particular domain of factors suggests improvements and which model would be more preferred. It is also envisaged that this research would provide meaningful insight into the critical current and future role of machine learning in food security

Chemical heuristics have been fundamental to the advancement of chemistry and materials science. These heuristics are typically established by scientists using knowledge and creativity to extract patterns from limited datasets. Machine learning offers opportunities to perfect this approach using computers and larger datasets. Here, we discuss the relationships between traditional heuristics and machine learning approaches. We show how traditional rules can be challenged by large-scale statistical assessment and how traditional concepts commonly used as features are feeding the machine learning techniques. We stress the waste involved in relearning chemical rules and the challenges in terms of data size requirements for purely data-driven approaches. Our view is that heuristic and machine learning approaches are at their best when they work together.

There are many high dam hubs in the world, and the regular inspection of high dams is a critical task for ensuring their safe operation. Traditional manual inspection methods pose challenges related to the complexity of the on-site environment, the heavy inspection workload, and the difficulty in manually observing inspection points, which often result in low efficiency and errors related to the influence of subjective factors. Therefore, the introduction of intelligent inspection technology in this context is urgently necessary. With the development of UAVs, computer vision, artificial intelligence, and other technologies, the intelligent inspection of high dams based on visual perception has become possible, and related research has received extensive attention. This article summarizes the contents of high dam safety inspections and reviews recent studies on visual perception techniques in the context of intelligent inspections. First, this article categorizes image enhancement methods into those based on histogram equalization, Retinex, and deep learning. Representative methods and their characteristics are elaborated for each category, and the associated development trends are analyzed. Second, this article systematically enumerates the principal achievements of defect and obstacle perception methods, focusing on those based on traditional image processing and machine learning approaches, and outlines the main techniques and characteristics. Additionally, this article analyzes the principal methods for damage quantification based on visual perception. Finally, the major issues related to applying visual perception techniques for the intelligent safety inspection of high dams are summarized and future research directions are proposed.

<b><sc>Abstract.</sc></b> <b>Two-spotted spider mite (TSSM) is one of the most harmful pests for the strawberry plant. TSSM usually feeds on strawberry leaf and affect photosynthesis. Counting TSSM (larva, protonymph, deutonymph, and adult) and TSSM eggs can help growers apply the right amount of pesticide or release the right amount of predatory mite. However, the traditional manual counting method is time-consuming. For the past several years, many deep learning-based object detection models achieved state-of-the-art performance, including Faster R-CNN, YOLO, and SSD. These methods outperformed the traditional computer vision and machine learning methods. Therefore, this study adopted a deep learning-based object detection method for TSSM and TSSM eggs counting and developed an Android app for growers to use in the field. In this study, 875 images were collected using a smartphone with a macro lens. Then, YOLO was trained to detect TSSM and TSSM eggs, and the trained YOLO model was deployed in the Android App. The mean average precision of the model was 0.645, and the average precision for TSSM and TSSM eggs was 0.62 and 0.67, respectively. This study showed that a deep learning-based smartphone app could effectively detect TSSM and TSSM eggs from the image. When more images are collected, and data augmentation techniques are used in model training, the mite detection accuracy could be much improved. </b>

A comprehensive review on detection of plant disease using machine learning and deep learning approaches

<title>Abstract</title> In recent years, psychological anxiety has emerged as a pervasive mental health issue impacting socioeconomic development and individual well-being, making scientific assessment of anxiety cru- cial. While traditional manual evaluation methods and machine learning-based automated assessment approaches each possess unique advantages, they often struggle to simultaneously address efficiency, reliability, and feature generalization capabilities, lacking systematic comparative validation with standard clinical tools. To tackle this challenge, this study first proposes an anxiety risk assess- ment model based on interactive large language models (LLMs). The model is fine-tuned using multi-round psychological counseling dialogue datasets to provide high-quality psychological support.Subsequently, we introduce a dual-channel BERT framework for anxiety risk assessment, compris- ing a main channel and a high-risk channel. The framework strictly maps symptom dimensions and score ranges from the GAD-7 and HAMA clinical scales. This design enables accurate anxiety risk assessment while promoting psychological intervention through interactive dialogue. Experimental results demonstrate that the proposed model achieves high accuracy (88.86%) and robustness in gen- eral case evaluations, maintains 88.20% accuracy in cross-dataset validation, and exhibits superior performance in identifying high-risk cases (99.34% high-risk recall rate), significantly outperforming advanced baseline models like MentalBERT.

Growth in system complexity increases the need for automated techniques dedicated to different log analysis tasks such as Log-based Anomaly Detection (LAD). The latter has been widely addressed in the literature, mostly by means of a variety of deep learning techniques. However, despite their many advantages, that focus on deep learning techniques is somewhat arbitrary as traditional Machine Learning (ML) techniques may perform well in many cases, depending on the context and datasets. In the same vein, semi-supervised techniques deserve the same attention as supervised techniques since the former have clear practical advantages. Further, current evaluations mostly rely on the assessment of detection accuracy. However, this is not enough to decide whether or not a specific ML technique is suitable to address the LAD problem in a given context. Other aspects to consider include training and prediction times as well as the sensitivity to hyperparameter tuning, which in practice matters to engineers. In this paper, we present a comprehensive empirical study, in which we evaluate a wide array of supervised and semi-supervised, traditional and deep ML techniques w.r.t. four evaluation criteria: detection accuracy, time performance, sensitivity of detection accuracy and time performance to hyperparameter tuning. Our goal is to provide much stronger and comprehensive evidence regarding the relative advantages and drawbacks of alternative techniques for LAD. The experimental results show that supervised traditional and deep ML techniques fare similarly in terms of their detection accuracy and prediction time on most of the benchmark datasets considered in our study. Moreover, overall, sensitivity analysis to hyperparameter tuning with respect to detection accuracy shows that supervised traditional ML techniques are less sensitive than deep learning techniques. Further, semi-supervised techniques yield significantly worse detection accuracy than supervised techniques.

Machine learning (ML) and Deep learning (DL) have transformed agriculture by addressing challenges such as soil fertility assessment, crop recommendation, yield prediction, and plant disease detection. These technologies enable farmers to make informed decisions, enhancing productivity and sustainability. Notable advancements include Random Forest achieving 84% accuracy in soil fertility prediction and CNN- based soil classification reaching 95.21% accuracy, both integrated into accessible web platforms. Yield prediction models, such as Random Forest and LSTM, have delivered up to 98.96% accuracy, while innovations in disease detection in plants using CenterNet with DenseNet-77 achieved a mean Average Precision (mAP) of 99%. These tools empower farmers by streamlining processes, optimizing resource utilization, and reducing losses due to uncertainties. Collectively, the integration of ML and DL is shaping a more resilient and efficient agricultural sector. Keywords— Machine learning, deep learning, soil fertility, crop recommendation, yield prediction, plant disease detection, precision agriculture.

The Turkish Music Emotion Dataset in the CL database is a dataset for music emotion classification, which contains many music samples and their corresponding emotion labels. This paper presents a comparative analysis of the performance of the traditional random forest machine learning model and the XGBoost model on the given dataset. The findings indicate that the traditional random forest machine learning model outperforms the XGBoost model in terms of accuracy, accuracy, and recall rate. The traditional random forest machine learning model achieves an accuracy of 80.8%, whereas the XGBoost model achieves an accuracy of 75%. The recall rate of the traditional random forest machine learning model is 80.8%, whereas the recall rate of the XGBoost model is 77.2%. The traditional random forest machine learning model achieved an F1 score of 80.5%, whereas the XGBoost model attained an F1 score of 75.3%. The comprehensive evaluation of the XGBoost model outperforms the traditional random forest machine learning model. Generally, the traditional random forest machine learning model demonstrates strong performance in the domain of music emotion classification. It exhibits favorable qualities such as robustness and interpretability, and possesses the ability to effectively handle noise and missing data. The XGBoost model, on the other hand, can be trained and predicted quickly, with high accuracy and generalization ability. Therefore, in practical application, it is necessary to select the appropriate model according to the specific situation, and optimize and adjust it to obtain the best classification effect.