Road cracks pose a significant challenge to pavement maintenance by affecting structural integrity, jeopardizing traffic safety, and reducing driving comfort. With the limitations of manual inspection methods, such as being labor intensive, time consuming, and prone to human error, automated detection techniques have emerged as efficient and scalable alternatives. This study presents a detailed comparative analysis of state-of-the-art crack detection models, i.e., YOLOv7, VGG-19, ResNet-50, Naive Bayes, and deep convolutional neural networks, evaluating their performance on diverse and complex pavement image datasets. To ensure fairness and consistency, all models were trained and tested under identical conditions. ResNet-50 demonstrated superior performance, achieving the highest accuracy, that is, 99.8% in detecting and segmenting cracks in a variety of pavement scenarios. Its ability to balance precision and robustness makes it a leading solution for automated crack detection.
Heart diseases are a major cause of death worldwide, highlighting the need for early detection. The electrocardiogram (ECG) records the heart’s electrical activity using electrodes. Our research focuses on the ECG data to diagnose heart disorders, particularly arrhythmias. We utilized the MIT-BIH arrhythmia dataset for comparative analysis of various machine learning techniques, including random forest, K-Nearest Neighbor, and Decision Tree, along with deep learning algorithms like Long short-term memory and Convolutional Neural Networks. This required employing various preprocessing methods like filtering and normalization and feature selection techniques such as chi-square and sequential feature selectors to improve the performance of heart disease prediction. Therefore, hybrid machine and deep learning models are proposed, and the results reveal that hybrid models perform better than conventional models.
Automated assessment of tomato crop maturity is vital for improving agricultural productivity and reducing food waste. Traditionally, farmers have relied on visual inspection and manual assessment to predict tomato maturity, which is prone to human error and time-consuming. Computer vision and deep learning automate this process by analysing visual characteristics, enabling data-driven harvest decisions, optimising quality, and reducing waste for sustainable and efficient agriculture. This research demonstrates deep learning models accurately classifying tomato maturity stages using computer vision techniques, utilising a novel dataset of 4,353 tomato images. The Vision Transformer (ViT) model exhibited superior performance in classifying tomatoes into three ripeness categories (immature, mature, and partially mature), achieving a remarkable testing accuracy of 98.67% and the Convolution neural network (CNN) models, including EfficientNetB1, EfficientNetB5, EfficientNetB7, InceptionV3, ResNet50, and VGG16, achieved testing accuracies of 88.52%, 89.84%, 91.16%, 90.94%, 93.15%, and 92.27%, respectively, when tested with unseen data. ViT significantly surpassed the performance of CNN models. This research highlights the potential for deploying ViT in agricultural environments to monitor tomato maturity stages and packaging facilities smartly. Transformer-based systems could substantially reduce food waste and improve producer profits and productivity by optimising fruit harvest time and sorting decisions.
Associative rule mining is a technique for discovering common patterns and correlations in data sets from different databases, including relational, transactional and other types of data repositories, such as relational databases. Different types of patterns exist in data mining such as frequent patterns, extended patterns, regular patterns etc. Many searches have focused on finding the frequent patterns and very little work has been carried out on negative or rare patterns. It has also been observed that only those items which are positively correlated(frequent) are been executed by various algorithms but very less attention is been given to negatively correlated items. Negatively correlated items also called infrequent items are the items which negate with each other. The items which do not satisfy the minimum threshold value generally are always been ignored by many researchers. Mining of Negative association helps in business such as for customer segmentation, in risk management as well as in medical field. So the main aim of writing this paper is to provide a short overview of various research issues involved in finding out positive and negative associations.
The equalization of digital channels is widely recognized as a nonlinear classification problem. In such scenarios, utilizing networks that approximate nonlinear mappings can be highly advantageous. There has also been extensive research on equalizers based on Radial Basis Function Neural Networks (RBFNNs). This study introduces a training methodology centred on the Improved Butterfly Optimization Algorithm (IBOA) for channel equalization using RBFNN. This approach aims to optimize the performance of RBFNN equalizers by leveraging the IBOA algorithm for training. Previous literature primarily approached the equalization problem as an optimization challenge. In contrast, this study addresses it as a classification problem. This training approach exhibits substantial enhancements compared to conventional metaheuristic algorithms.
In mountainous regions, landslides pose significant and frequent threats, causing extensive damage due to their destructive nature and frequency, therefore determining their likely occurrence sites and environmental factors is essential for hazard assessment. The infinite slope approach characterizes slope stability using a factor of safety (FOS) to assess the likelihood of slope failure and is frequently used to estimate the occurrence of shallow landslides on soil and regolith-covered slopes. Various methods have been used to evaluate and spread uncertainty across such models. Slope failure is a significant geological occurrence brought on by topography and weather, which result in a variety of ground movements. Engineers must plan and implement measures to mitigate hazards, safeguarding both lives and property from potential risks and dangers by using an adequate stabilizing solution. Technology and software advancements have made it simpler than ever to handle challenging issues that used to require a lot of time in every profession. Over the past decade, software utilization in civil engineering has surged. GEO 5 is a versatile program gaining prominence, aiding in the resolution of diverse geotechnical challenges. Through the installation of IoT cameras in various sand and clay areas along the bank of the Mahandi River in Odisha, we have gathered the data necessary to develop the region in this case. a select selection of which we have chosen for our research. In this study, slope stability-related modules have been carefully examined and used for the analysis of slope stability. Using the GEO5 program, the geometry of the issues was established, and the study took into account several stability optimization techniques. Additionally, the cost factor of various reinforcing techniques was calculated and contrasted.
This review discusses the integration of intelligent technologies into customer interactions in organizations and highlights the benefits of using artificial intelligence systems based on a multimodal approach. Multimodal learning in marketing is explored, focusing on understanding trends and preferences by analyzing behavior patterns expressed in different modalities. The study suggests that research in multimodality is scarce but reveals that it is as a promising field for overcoming decision-making complexity and developing innovative marketing strategies. The article introduces a methodology for accurately representing multimodal elements and discusses the theoretical foundations and practical impact of multimodal learning. It also examines the use of embeddings, fusion techniques, and explores model performance evaluation. The review acknowledges the limitations of current multimodal approaches in marketing and encourages more guidelines for future research. Overall, this work emphasizes the importance of integrating intelligent technology in marketing to personalize customer experiences and improve decision-making processes.
Mammogram image analysis is a crucial domain in the image-based diagnosis process. It is a trusted modality of non-invasive imaging for detecting tumour regions in the breast mass. However, poor contrast in the mammogram images is a key challenging issue. To address the issue, a brightness preserving gradient based joint histogram equalization (BPGJHE) method is suggested for enhancing the image quality while restoring the actual brightness and the structural information. The key contributions of the proposed method are (1) preserve the actual brightness of the mammogram images, (2) preserve the multi-scale structural details using an improved gradient filtering approach, (3) enrich the performance of the histogram equalization approach by incorporating the spatial information in the histogram. The suggested method is assessed using a series of mammogram images from standard datasets. The performance of the suggested method is validated in competence to the cutting-edge schemes. The quantitative assessment is performed using extensive validation metrics. The results indicate the efficacy of the suggested method.
Monitoring equipment wear is an important problem that requires constant attention, since this process can lead to a decrease in its efficiency, accidents or breakdown. The problem of replacing equipment is a production problem, in which it is necessary to consider many factors that influence the efficiency of the enterprise itself. This paper examines various formulations of the equipment replacement problem: in the classical formulation of dynamic programming, in the stochastic formulation and fuzzy graph representation. The idea to solve the problem using periodic fuzzy graphs is proposed. We also consider the age of equipment when determining the wear coefficient, determined by the degree of belonging to a particular class of parameters defined in the formulation of the problem. Periodic fuzzy graphs allow considering the problem of replacing equipment not for one type of equipment, but for a complex of machines, which ensures the scalability of the classical dynamic programming problem under uncertain initial data. When determining the membership function, it is possible to consider those factors that may influence the solution of the optimization production problem. Setting the problem in a fuzzy form makes it possible to forecast and plan the activities of an enterprise for future periods.
Handwritten number recognition has been extensively studied in the fields of machine literacy and computer vision, with datasets like MNIST serving as benchmarks. However, handwritten Roman numeral recognition presents unique challenges due to the diverse forms and structures of Roman numerals. In this paper, we propose a novel approach that combines Federated Learning with advanced neural network architectures to tackle this challenge effectively. Our methodology involves data acquisition and preprocessing, including the normalization of handwritten number and Roman numeral images. We design a hybrid neural network architecture that integrates Gated Convolutional Neural Networks (CNNs) for pixel-level feature extraction and Bidirectional Gated Recurrent Units (BGRUs) for sequence modeling. This architecture is essential for handling the complexity of recognizing both image and sequence data. Federated Learning is incorporated into our approach to train the model across multiple decentralized devices or servers while preserving data privacy. This ensures that sensitive handwritten data remains secure throughout the training process. By allowing model updates to be computed locally and aggregated without sharing raw data, Federated Learning maintains privacy and security in distributed learning environments. During training, each device computes gradients based on its local data and shares only the model updates with the central server. The central server aggregates these updates to update the global model, which is then sent back to the participating devices for further refinement. This iterative process continues until the model converges, while metrics such as accuracy, precision, recall, and F1-score are used to evaluate the model’s performance on a separate test dataset. Our approach demonstrates promising results in accurately recognizing both handwritten integers and Roman numerals, even in the presence of noise and variability in writing styles. By combining Federated Learning with advanced neural network architectures, our approach not only achieves state-of-the-art performance but also ensures data privacy and security in distributed learning environments.
Cholangiocarcinoma (CCA) is a type of cancer that forms in the bile duct that carry digestive fluid from the liver. CCA is the primary form of liver cancer that affects population ranging from age 60 to 69 years. CCA is difficult to diagnose at an early stage. Hyperspectral (HS) imaging is an advanced imaging technique that combines spectroscopy with conventional imaging. HS imaging is an emerging field of study which can be used for early CCA detection. HS imaging involves capturing images across various spectral bands, which forms a three-dimensional data cube often called as hyperspectral data cube. In this study, we have utilized U-Net based models, namely U-Net and DenseUNet were used to perform semantic segmentation on the HS images of CCA tissues. A band selective approach was employed to derive a subset of meaningful bands based on the spectrum plot from the HS image. The HS images are further preprocessed with Principal Component Analysis (PCA). The models were further evaluated by computing the accuracy, AUC (Area under the ROC curve), sensitivity and specificity metrics. The proposed models, namely, U-Net and DenseUNet reported an overall accuracy of 73.47% and 77.09% respectively. The DenseUNet models outperforms the U-Net model on every evaluation metric. The proposed models were also compared with other state-of-the-art (SOTA) models trained on various HS dataset. This study explores the application of HS imaging in carcinoma detection. The findings of this study could be used for further enhancement of the approach.
This study unveils an advanced convolutional-neural-network (CNN) algorithm that was meticulously engineered to examine resting-state functional magnetic resonance imaging (fMRI) for early ASD detection in pediatric cohorts. The CNN architecture amalgamates convolutional, pooling, batch-normalization, dropout, and fully connected layers, optimized for high-dimensional data interpretation. Rigorous preprocessing yielded 22,176 two-dimensional echo planar samples from 126 subjects (56 ASD, 70 controls) who were sourced from the Autism Brain Imaging Data Exchange (ABIDE I) repository. The model, trained on 17,740 samples across 50 epochs, demonstrated unparalleled diagnostic metrics – accuracy of 99.39%, recall of 98.80%, precision of 99.85%, and an F1 score of 99.32% – and thereby eclipsed extant computational methodologies. Feature map analyses substantiated the model’s hierarchical feature extraction capabilities. This research elucidates a deep learning framework for computer-assisted ASD screening via fMRI, with transformative implications for early diagnosis and intervention. And, this study addresses the critical need for early detection and intervention in autism spectrum disorder (ASD) using machine learning. Specific therapies are needed for ASD, a neurodevelopmental disease that affects social interaction and communication. To find trends in ASD, our research uses a variety of early childhood screening tests as training sets for machine learning algorithms. The methodology that has been suggested utilizes methods of machine learning to compute the ASD spectrum, considering its many expressions. By using multidisciplinary methods and sophisticated screening instruments, we want to create an accurate system for early ASD detection. Algorithmic transparency, data protection, and ethical considerations are essential. This study seeks to build precise instruments for early ASD detection by promoting collaboration between specialists in neurodevelopment, psychology, and machine learning. A robust instrument that enhances the knowledge of medical practitioners is machine learning. Results show how innovation may transform early interventions and help people on the autistic spectrum achieve enhanced results.
The identification and severity assessment of plant leaf diseases is crucial to food security and sustainable agriculture. This study shows an innovative way to improve plant leaf disease detection. The recommended method uses Optuna for parameter optimization and the Genetic Algorithm for feature selection to improve plant leaf disease identification. We do this to improve diagnosis accuracy. This method improves classification accuracy and is called ECPLDD-OGA. Modern hyper parameter optimization framework Optuna is employed. This allows classification model parameters to be fine-tuned. A systematic feature selection method is the Genetic Algorithm. It finds the most useful characteristics in the input dataset. By applying the algorithm on the data. By facilitation, the iterative process helps create a simplified and meaningful subset of features. Contrary to parameter tinkering and feature selection, empirical data suggests that utilizing Optuna and the Genetic Algorithm simultaneously improves disease identification. The updated model recognizes sick plants more accurately and generalizes better. Optimization enabled both gains. The usage of this technology can improve agricultural operations and reduce crop losses by increasing productivity. The present ECPLDD-OGA technique helps integrate hyper parameter tweaking and feature selection into machine learning-based agricultural applications.
There are many reasons associated with stress, long term stress induces neurological and psychosomatic disorders like hypertension, hypothyroidism, diabetes, anxiety and depression which affect the lifestyle of human beings. Consequently, behavioural activity and action gradually change in their surrounding environment and also perceived by others. In general, stressful respiration is relatively different from normal. To release stress and control all the neuropsychological hormones, multiple activities like playing games, watching a movie, listening to songs and music, etc. or intake of medicine/drugs such as (Allopathic /Homeopathic/Ayurvedic) are used. Medicines can provide easy stress evasion, but relief is only temporary. Thus, yoga and Sudarshan kriya (SK) meditation is a unique and alternate therapy identified by Gurudev Sri Sri Ravi Shankar by Art of living. It would be a healthy way to get rid of stress in peoples’ lives. Study of long-term effects of (SKY) Sudarshan kriya Yoga before and after and response of the brain regions in experienced (10–15 yrs) practitioners, mediocre (3–5 yrs) and novice(non-practitioners) is the main objective of this work. This study is planned in three phases, the first phase is an experiment on SKY practitioners for more than 10–15 years, in which their (EEG) Electroencephalogram is recorded just after a session of meditation and the common portion of excitation amongst the three subjects is mined and analysed, to draw inferences. This inference would help us draw a conclusion about (BLOC) base level of consciousness considered as benchmark. In the second phase, comparison of benchmark data with the Mediocre (3–5 yrs) measurement and in third phase, benchmark versus Novice data, is done. Next is the phase of interpretation of the response in the form of EEG spectral waves as Type I- 10 to 15 years SKY Practitioners (Superconscious), Type II- SKY practitioners 3 to 5 years (mediocre/semiconscious) and Type. III- Non-practitioner subjects (Novice/Un-conscious). The unconsciousness here means a state of complete unawareness of the self, though conscious of the external, physical world. Thus, power spectrum analysis (PSA) is carried out and frequency of each electrode is computed through segment analysis, Power Spectrum Density (PSD), Correlation coefficient, Mean and Standard Deviation, for finding the level of consciousness. The spectral waveform of these recordings is analysed programmatically using machine learning techniques (used Python Language run on the Jupyter notebook, Spyder, Google colab environment).Frequency analysis results are obtained by placing 21 electrodes in human brain in different lobes that is (Fz, C2, P2, FP1, FP2, F3, F4, C3, C4, P3, P4, O1, O2, F7, F8, T3, T4, T5, BP4, E.G, T6) those are frequency measuring electrodes/channels placed on the frontal lobe, temporal lobe, parietal lobe and occipital lobe over skull and brainwaves alpha (α)[8–12 Hz], beta (β)[12–16 Hz], delta (δ)[0.5–4 Hz], theta (Θ)[4–8 Hz], gamma (γ)[16–32 Hz] are synthesized. The interpretation of these analyses suggests alternative therapeutic techniques, to improve both mentally and psychologically and thus become socially acceptable.
The genetic algorithm with aggressive mutations GAAM, is a specialised algorithm for feature selection. This algorithm is dedicated to the selection of a small number of features and allows the user to specify the maximum number of features desired. A major obstacle to the use of this algorithm is its high computational cost, which increases significantly with the number of dimensions to be retained. To solve this problem, we introduce a surrogate model based on machine learning, which reduces the number of evaluations of the fitness function by an average of 48% on the datasets tested, using the standard parameters specified in the original paper. Additionally, we experimentally demonstrate that eliminating the crossover step in the original algorithm does not result in any visible changes in the algorithm’s results. We also demonstrate that the original algorithm uses an artificially complex mutation method that could be replaced by a simpler method without loss of efficiency. The sum of the improvements resulted in an average reduction of 53% in the number of evaluations of the fitness functions. Finally, we have shown that these outcomes apply to parameters beyond those utilized in the initial article, while still achieving a comparable decrease in the count of evaluation function calls. Tests were conducted on 9 datasets of varying dimensions, using two different classifiers.
In the battle against the COVID-19 pneumonia outbreak, which is brought on by the coronavirus strain SARS-Cov-2, radiological chest exams, such as chest X-rays, are crucial. In order to understand the unique radiographic characteristics of COVID-19, this research looks into classification models to distinguish chest X-ray images based on Radiomics features. This study is performed with datasets composed of 136 segmented chest X-rays, which were used to train and test the categorization algorithms. First and second-order statistical texture characteristics were extracted from the right (R), left (L), superior, middle, and bottom lung zones for each lung side using the Pyradiomics collection. Data was divided into training (80%) and test (20%) groups for feature selection. After assessing the respective feature significance and confirmation accuracy, the most pertinent Radiomics features were chosen. A model of lung segmentation based grey level pixels was used to evaluate support vector machines (SVM) as possible classifiers (AUC = 83.7%). Our research reveals a preference for the upper lung zone and a preponderance of Radiomics feature selection in the right lung. Our future research will concentrate on COVID-19 categorization and segmentation for more precise forecast using a hybrid method based on SVM and Radiogenomics features.
The optimal functioning of the power system is crucially dependent upon the sound protection of its major stakeholder, i.e., the transmission line, as it is prone to fault. To maintain the integrity of the power system and protect costly power system equipment, protective relaying is necessary to provide a steady and affordable supply of electricity. Relays recognize, classify, and identify transmission line faults using input signals of voltage and current. Many artificial intelligent methods based on Expert Systems, Artificial Neural Networks, Fuzzy Logic, Support Vector Machines, Wavelet-based systems, and deep learning techniques are being investigated to improve modern digital relays’ consistency, speed, and accuracy. This paper is a comprehensive and all-inclusive survey that reviews and incorporates Phasor Measurement Unit (PMU) and Global Positioning System (GPS) approaches together with all of these intelligent transmission line safety strategies and concepts. Initial investigators will benefit from this study by being able to examine, evaluate, and analyze a variety of approaches with references for all relevant contributions.
The adoption of automated methods for the identification and assessment of tomato-related disorders is highly sought-after in the agriculture sector. Using this technology is crucial for reducing wasteful spending, increasing the efficiency of treatments, and ultimately growing more resilient crops by reducing losses in agricultural output and maximising the effectiveness of these processes. An automated method has been suggested for accurately identifying and classifying diseases using a single photograph. The described method for disease detection in tomato plants makes use of a computer vision-based technique. Image processing, ML, and deep learning are just a few of the methods that this strategy uses. The goal of this approach is to prevent tomato crops from being damaged by various illnesses by reducing the need of conventional procedures. Bacterial spot, early blight, late blight, leaf mould, spider mites, target spot, spotted spider mite, mosaic virus, and yellow leaf curl are all examples of these illnesses. The following ten diseases frequently strike tomato crops in India. By utilising picture segmentation in combination with the Enhanced OPTICS algorithm (EOPTICSA), the affected area of the tomato plant may be precisely detected and defined after image pre-processing procedures have been used. It may be necessary to look for certain visual signs in order to diagnose the previously mentioned illnesses. The primary goal of this study was to evaluate the efficacy of the EOPTICSA method for detecting diseases in plant leaves. To eliminate the geometric features associated with colour, texture, and leaf arrangement in the provided plant pictures, image segmentation and edge detection methods are employed. Using these methods allows us to achieve our goal. Various efficacy measures are used to assess and provide a technique recommendation. This research shows that when performance metrics are used to implement these strategies, the suggested strategy outperforms the current methods in terms of accuracy, precision, and F1-score. The process of detecting sickness involves several consecutive steps. Capturing images, segmenting them, detecting edges, and determining the infection’s severity are all steps in this process. To accomplish the goal of recognising and categorising different types of diseases that might impact tomato plants, the method of transfer learning is employed. As soon as the problem is identified, it is recommended to take proactive measures to help individuals and organisations involved in agriculture address the effects of these disorders using appropriate measures.
In the last decade, the world has witnessed remarkable technological development, especially in artificial intelligence, which helps researchers find solutions to problems of concern to the individual and society, mainly, the huge propagation of hate speech with the increased use of social media platforms. In this study, we aim to enhance the detection of Arabic hate speech on social media by addressing challenges related to imbalanced datasets through data augmentation techniques. Several machine learning algorithms and the DziriBert, a pre-trained transformer model, are implemented on the Tunisian Hate Speech and Abusive Dataset (T-HSAB). The proposed approach achieves good results, improving the detection of hateful comments on Arabic social media using the Synthetic Minority Over-sampling Technique (SMOTE). Notably, the DziriBert model exhibits remarkable proficiency in detecting hate speech, achieving an accuracy of 82%. Random Forest (RF) and Linear SVC outperform the state of the art approaches, achieving the best result.
Visual Speech Recognition (VSR) is a popular area in computer vision research, attracting interest for its ability to precisely analyze lip motion and seamlessly convert them into textual representation. VSR systems leverage visual features to augment the understanding of automated speech and predict text. VSR finds various applications, including enhancing speech recognition in scenarios with degraded acoustic signals, aiding individuals with hearing impairments, bolstering security by reducing reliance on text based passwords, facilitating biometric authentication for liveness detection, and enabling underwater communications. Despite the various techniques proposed for improving the resilience and precision of automatic speech recognition, VSR still has challenges like homophones of words, gradient descent issues with varying sequence lengths, and lip reading demands accounting for short and long range correlations between consecutive video frames. We have proposed a hybrid network (HNet) with multilayered three dimensional dilated convolution neural network (3D-CNN). The spatio-temporal feature extraction process will be facilitated by dilated 3D-CNN. HNet integrates two bidirectional recurrent neural networks (BiGRU and BiLSTM) to process the feature sequences bidirectionally to establish the temporal relationship. The fusion of BiGRU-BiLSTM capabilities allows the model to process feature sequences more comprehensively and effectively. The proposed work focuses on face based biometric authentication for liveness detection using the VSR model to boost security against face spoofing. The existing face based biometric systems are widely used for individual authentication and verification but are still vulnerable to 3D masks and adversarial attacks. The VSR system can be added to existing face based verification systems as a second level authentication technique to identify a person with liveness. The working ideology of the VSR system will be based on the challenge response technique, where a person has to pronounce the passcode silently displayed on the screen. The VSR model assesses its effectiveness using word error rate (WER), which matches the pronounced passcode to the one presented on the screen. Overall, the proposed work aims to enhance the accuracy of VSR so that it can be combined with existing face based authentication systems. The proposed system outperforms the existing VSR system and obtained 1.3% WER. The significance of the proposed hybrid model is that it efficiently captures temporal dependencies, enhancing context embedding, improving robustness to input variability, reducing information loss, and enhancing performance and accuracy in modeling and analyzing passcode pronunciation patterns.
