Search

White blood cells (WBCs) are crucial microscopic defenders of the human immune system in combating transmittable conditions triggered by germs, infections, and various other human pathogens. Timely and appropriate WBC detection and classification are decisive for comprehending the immune system's standing and its feedback to various pathologies, assisting in diagnosing and monitoring illness. Nevertheless, the manual classification of WBCs is strenuous, extensive, and prone to errors, while automated approaches can be cost-prohibitive. Within artificial intelligence, deep learning (DL) approaches have become an appealing option for automating WBC recognition. The existing DL techniques for WBC classification face several limitations and computational difficulties, such as overfitting, limited scalability, and design complexity, often battling with function variety in WBC images and requiring considerable computational resources. This research study recommends an ingenious hybrid inception-xception Convolutional Semantic network (CNN) designed to deal with constraints in existing DL versions. The proposed network incorporates inception and depth-separable convolution layers to successfully catch attributes across many ranges, therefore minimizing concerns related to model complexity and overfitting. In contrast to traditional CNN designs, the proposed network lessens the layers made use of and increases their function removal capacities, hence enhancing the performance of WBC classification, which needs a wide variety of attribute abilities. Furthermore, the proposed model was trained, validated and tested on three popular and widely recognized datasets, namely, Leukocyte Images for Segmentation and Classification (LISC), Blood Cell Count and Detection (BCCD), and Microscopic PBS (PBS-HCB), where it demonstrates the generalization and robustness and superiority of our proposed model. The model depicted an outstanding average accuracy rate of 99.25%, 99.65%, and 98.6% on a five-fold cross-validation test for the respective datasets, surpassing existing models as detailed. The model's robustness and superior performance, validated across diverse datasets, underscore its potential as an advanced tool for accurate and efficient WBC classification in medical diagnostics. [ABSTRACT FROM AUTHOR]

Recently, deep learning has known a remarkable mutation in computer vision, which has been optimally exploited to solve various complex tasks and improve their results in the medical image analysis field, especially medical image segmentation (MIS). In this regard, convolution neural networks, particularly U-Net-based architectures, have been widely proposed to create several automatic systems for MIS. However, they are still constrained by certain limitations in terms of long-range context information because of the limited kernel size of the convolution layer, sensitivity to rotation and affine transformation, and the discard of the positional information due to the pooling operation. To address these limitations, transformers and capsule neural network have been utilized to model long-range contextual information based on the self-attention mechanism on the one hand and better representation learning based on dynamic routing algorithm on the other hand. To this end, we proposed a deep learning architecture for brain tumor segmentation called Swin transformer capsule pyramid U-Net. Indeed, the encoder consists of four hierarchical features extracted based on shifted window multi-head self-attention used in Swin transformers (ST) blocks. Next, the features are introduced to the proposed residual inception capsule pyramid network (RICapsPN) to encode each spatial relation of features in each encoder depth. Depending on the top-down connection between layers, this network builds a high-level semantic feature at all scales. Furthermore, RICapsPN used inception capsule blocks to test several capsule kernels and optimize the number of parameters. Additionally, the residual connection employed aims to consider the features extracted at each ST depth to enhance feature representation from the encoder part. Finally, the output of RICapsPN has been introduced to the ST decoder to get the final segmentation of different sub-regions of the brain tumor. The experiment results of our method showed a compelling performance on the BraTS 2020 dataset compared with the state-of-the-art methods by achieving 92.80 % , 85.63 % , and 80.14 % of dice similarity coefficient for the whole tumor, core tumor, and enhancing tumor sub-regions, respectively. Ablation experiments also indicate the effectiveness of the designed modules. [ABSTRACT FROM AUTHOR]

Rolling bearings are integral to the operation of various mechanical systems, where their condition directly impacts equipment reliability and performance. Accurate fault diagnosis is essential for preventing unexpected failures and minimising downtime in industrial settings. This study presents a novel diagnostic model that combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks, enhanced by an improved Inception module. This integrated approach captures both spatial and temporal features of vibration signals, leading to superior diagnostic accuracy under diverse operating conditions. Experimental results using the Case Western Reserve University (CWRU) bearing dataset demonstrate an impressive average fault diagnosis accuracy of 99.83%, outperforming conventional models. The robustness of the proposed model against noise and its adaptability to varying operational environments underscore its practical value for real-world engineering applications, offering a reliable solution for maintaining the safety and efficiency of critical machinery. [ABSTRACT FROM AUTHOR]

Early diagnosis methods of Alzheimer's disease seem to be necessary due to the high costs of care and treatment, the indeterminacy of existing treatment methods, and the worrying future of the patient. This study was conducted in order to diagnose Alzheimer's disease from MRI images using artificial intelligence. In this study, a computer system for early diagnosis of Alzheimer's disease with the help of machine learning algorithms is presented in the framework of the computer-aided diagnosis process. Conditional random field and Inception deep neural network have been adapted to diagnose this disease on brain MRI images. Since the hippocampus tissue is one of the first tissues to be affected by Alzheimer's disease; Therefore, for the early diagnosis of this disease, first, the hippocampus was determined between other brain tissues and then, according to the extent of this tissue being affected, the disease was diagnosed. Conditional random field was able to extract hippocampus pieces with different shapes from all three brain sections with great accuracy. These pieces are the basis for feature extraction by the deep network. This method was tested on ADNI standard data and its efficiency was shown. The Inception network used is a network pre-trained on the very large ImageNet dataset. One of the important steps is to transfer knowledge to the problem at hand. To facilitate this, data augmentation designed according to the shape and structure of the hippocampus was used. The method implemented in this study achieved 98.51% accuracy in the case of Alzheimer's two-class versus healthy control and 93.41% for the two-class case of mild cognitive impairment versus healthy control, which is an increase of 2.56% and 8.41% respectively. It is compared to competing methods introduced in other articles. The results of this study showed that the use of artificial intelligence according to MRI images is highly accurate in diagnosing Alzheimer's disease. [ABSTRACT FROM AUTHOR]

The agriculture industry has an enormous influence on a nation's economy. Loss of yield due to plant diseases remains a reason, reducing crop quantity and quality. Incorrect diagnosis of crop diseases can result in improper application of chemical pesticides, which promotes immune microbial strains, raises expenses, and triggers fresh outbreaks that are harmful to the economy and the ecosystem. Despite the potential of Machine Learning (ML) and Deep Learning (DL) approaches in plant disease detection, their limited effectiveness results in poor or late disease detection. Resolving this issue is critical, requiring the development of more accurate disease detection methods. This research introduces an innovative approach for the detection of apple leaf diseases utilizing the CNN-based Inception-v3 model. The dataset comprises images taken on location without having any control over the image-capturing settings may provide better relevance to real-world scenarios. The proposed method integrates canny edge detection and watershed transformation to achieve accurate image segmentation, thereby enhancing the identification of disease regions. Additionally, exploratory data analysis was performed, and channel distributions were visualized to understand the dataset's characteristics. To ensure robust evaluation, the model's performance underwent stratified 5-fold cross-validation. The model classified plant images with 84.60% precision, 87.40% recall, 85.00% F1-score, and 94.76% accuracy. Experimental results substantiate the efficacy of the proposed approach, surpassing existing methods in disease classification.

This work focuses on a novel lightweight machine learning approach to the task of plant disease classification, posing as a core component of a larger grow-light smart monitoring system. To the extent of our knowledge, this work is the first to implement lightweight convolutional neural network architectures leveraging down-scaled versions of inception blocks, residual connections, and dense residual connections applied without pre-training to the PlantVillage dataset. The novel contributions of this work include the proposal of a smart monitoring framework outline; responsible for detection and classification of ailments via the devised lightweight networks as well as interfacing with LED grow-light fixtures to optimize environmental parameters and lighting control for the growth of plants in a greenhouse system. Lightweight adaptation of dense residual connections achieved the best balance of minimizing model parameters and maximizing performance metrics with accuracy, precision, recall, and F1-scores of 96.75%, 97.62%, 97.59%, and 97.58% respectively, while consisting of only 228,479 model parameters. These results are further compared against various full-scale state-of-the-art model architectures trained on the PlantVillage dataset, of which the proposed down-scaled lightweight models were capable of performing equally to, if not better than many large-scale counterparts with drastically less computational requirements.

Environmental Sound Classification (ESC) is a challenging and crucial task with various important real-world applications. Challenges arise from both inherent sound complexities and limitations in training data. Sound complexities in ESC comes from the fact that some audio frames can be misleading, requiring careful understanding of the full sound context. Additionally, data imbalances, limited samples, and large set of classes further complicate model training and generalization power. This paper proposes a novel Residual Self-Attention (RSA) model for robust end-to-end ESC. The proposed RSA model builds upon the Convolutional Self-Attention (CSA) architecture by incorporating residual connections between self-attention layers. This addition enhances information flow and facilitates faster convergence, reducing training time by 26% compared to CSA. Mel-frequency cepstral coefficients (MFCC) were used as input features and Softmax was used for classification. The proposed RSA model is evaluated on the three benchmark datasets: imbalanced UrbanSound8k, limited-sample ESC-10, and ESC-50 which have 50 classes. Remarkably, the proposed RSA model achieves impressive accuracies of 97.8%, 96.25%, and 93.31% on these datasets respectively, demonstrating its effectiveness in addressing diverse ESC challenges. [ABSTRACT FROM AUTHOR]

The agriculture industry has an enormous influence on a nation's economy. Loss of yield due to plant diseases remains a reason, reducing crop quantity and quality. Incorrect diagnosis of crop diseases can result in improper application of chemical pesticides, which promotes immune microbial strains, raises expenses, and triggers fresh outbreaks that are harmful to the economy and the ecosystem. Despite the potential of Machine Learning (ML) and Deep Learning (DL) approaches in plant disease detection, their limited effectiveness results in poor or late disease detection. Resolving this issue is critical, requiring the development of more accurate disease detection methods. This research introduces an innovative approach for the detection of apple leaf diseases utilizing the CNN-based Inception-v3 model. The dataset comprises images taken on location without having any control over the image-capturing settings may provide better relevance to real-world scenarios. The proposed method integrates canny edge detection and watershed transformation to achieve accurate image segmentation, thereby enhancing the identification of disease regions. Additionally, exploratory data analysis was performed, and channel distributions were visualized to understand the dataset's characteristics. To ensure robust evaluation, the model's performance underwent stratified 5-fold cross-validation. The model classified plant images with 84.60% precision, 87.40% recall, 85.00% F1-score, and 94.76% accuracy. Experimental results substantiate the efficacy of the proposed approach, surpassing existing methods in disease classification. [ABSTRACT FROM AUTHOR]

This study addresses the critical challenge of real-time identification of tomato leaf diseases using edge computing. Traditional plant disease detection methods rely on centralized cloud-based solutions that suffer from latency issues and require substantial bandwidth, making them less viable for real-time applications in remote or bandwidth-constrained environments. In response to these limitations, this study proposes an on-the-edge processing framework employing Convolutional Neural Networks (CNNs) to identify tomato diseases. This approach brings computation closer to the data source, reducing latency and conserving bandwidth. This study evaluates various pre-trained models, including MobileNetV2, InceptionV3, ResNet50, and VGG19 against a custom CNN, training and validating them on a comprehensive dataset of tomato leaf images. MobileNetV2 demonstrated exceptional performance, achieving an accuracy of 98.99%. The results highlight the potential of edge AI to revolutionize disease detection in agricultural settings, offering a scalable, efficient, and responsive solution that can be integrated into broader smart farming systems. This approach not only improves disease detection accuracy but can also provide actionable insights and timely alerts to farmers, ultimately contributing to increased crop yields and food security. [ABSTRACT FROM AUTHOR]

Retinal disorders pose a serious threat to world healthcare because they frequently result in visual loss or impairment. For retinal disorders to be diagnosed precisely, treated individually, and detected early, deep learning is a necessary subset of artificial intelligence. This paper provides a complete approach to improve the accuracy and reliability of retinal disease identification using images from OCT (Retinal Optical Coherence Tomography). The Hybrid Model GIGT, which combines Generative Adversarial Networks (GANs), Inception, and Game Theory, is a novel method for diagnosing retinal diseases using OCT pictures. This technique, which is carried out in Python, includes preprocessing images, feature extraction, GAN classification, and a game-theoretic examination. Resizing, grayscale conversion, noise reduction using Gaussian filters, contrast enhancement using Contrast Limiting Adaptive Histogram Equalization (CLAHE), and edge recognition via the Canny technique are all part of the picture preparation step. These procedures set up the OCT pictures for efficient analysis. The Inception model is used for feature extraction, which enables the extraction of discriminative characteristics from the previously processed pictures. GANs are used for classification, which improves accuracy and resilience by adding a strategic and dynamic aspect to the diagnostic process. Additionally, a game-theoretic analysis is utilized to evaluate the security and dependability of the model in the face of hostile attacks. Strategic analysis and deep learning work together to provide a potent diagnostic tool. This suggested model's remarkable 98.2% accuracy rate shows how this method has the potential to improve the detection of retinal diseases, improve patient outcomes, and address the worldwide issue of visual impairment. [ABSTRACT FROM AUTHOR]

Automatic detection of a medical disease is a need of the hour as it helps doctors diagnose diseases and provide fast medical reports. COVID-19 is a deadly disease for which an automated detection system may be helpful. This study proposes a unique hybrid deep learning model, COVIDet, based on CNN and the speeded-up robust features (SURF) extraction approach to diagnose COVID-19 using chest x-ray images. SURF is utilized in this work to extract features, and the output is then transferred to a 25-layer CNN for detection using the extracted features. This investigation employed 4623 COVID-19 positive X-ray pictures or 8055 total. The suggested hybrid model also contrasts with the study's VGG19, Resnet50, Inception, Xception, and traditional CNN models. The proposed model had a 98.01% accuracy, a 97.03% F1-score, a 98.65% sensitivity, a 99% precision, and a 95.65% specificity. The proposed model can be further improved when more datasets are available and can help doctors to diagnose patients quickly and efficiently. Using chest X-ray pictures, a secured web application is also developed to identify COVID-19. The user sends the application a chest X-ray image, and in return, it determines whether an individual is COVID-19 positive or not, cutting down on testing time. In Covid times, when people are standing in long queues and waiting for their turns, this application would greatly help. The application uses the pre-trained COVIDet model in the backend. [ABSTRACT FROM AUTHOR]

In response to the limitations of the traditional convolutional neural network (CNN) method in spatiotemporal feature extraction, an improved joint model combining Inception and bi-directional long short-term memory (BiLSTM) was proposed to comprehensively learn spatial and temporal information from vibration signals. First, an Inception module with multi-scale receptive fields was constructed to adaptively extract spatial features at different scales. Secondly, temporal features were serialized using BiLSTM to deeply mine temporal correlations. Finally, damage identification of steel frame structures was achieved through global average pooling and a softmax classifier. To evaluate the model's robustness to noise, Gaussian white noise was introduced as interference. Additionally, a transfer learning strategy was employed to assess the model's generalization ability under different intensity excitations and small sample sizes, ensuring applicability to diverse damage identification tasks. The results demonstrate that compared with the traditional CNN method, the model maintains 100% recognition accuracy under noise-free conditions and when the signal-to-noise ratio exceeds 25 dB. This approach effectively addresses the practical challenges of insufficient sample size and varying excitation intensities in civil engineering applications. Through fine-tuning the parameters of the pre-trained model, knowledge transfer and generalization under different intensity incentives and small sample sizes are achieved, thereby enhancing the model's practical applicability. [ABSTRACT FROM AUTHOR]

A new hyperspectral image classification algorithm based on deep learning is constructed to solve the problems of redundant band information, neglect of local details, and insufficient spatial and spectral feature extraction in hyperspectral image classification tasks. The model uses the improved 3D inception structure as a multi-scale feature extractor to enhance the attention to local information, and 3D convolution mixed with 2D convolution (3D-2D) is used as the main feature extractor to improve the conversion and fusion of spatial and spectral features. In addition, a compression-and-excitation network is used as the connecting mechanism for feature transfer to reduce the redundancy of band information and ultimately to realize the effective classification of hyperspectral images. In this paper, the proposed method was validated on three public datasets (Pavia University, Salinas, and Indian Pines), and the results show that the classification accuracies of the proposed method were 99.75, 99.99, and 98.77%, respectively, which are better than the mainstream methods. These results are of great significance for the performance of hyperspectral image classification tasks. [ABSTRACT FROM AUTHOR]

Optical character recognition (OCR) for regional languages is difficult due to their complex orthographic structure, lack of dataset resources, a greater number of characters and similarity in structure between characters. Telugu is popular language in states of Andhra and Telangana. Telugu exhibits distinct separation between characters within a word, making a characterlevel dataset sufficient. With a smaller dataset, we can effectively recognize more words. However, challenges arise during the training of compound characters, which are combinations of vowels and consonants. These are considered as two or more characters based on associated vattus and dheerghams with the base character. To address this challenge, each compound character is encoded into a numerical value and used as input during training, with subsequent retrieval during recognition. The segmentation issue arises from overlapping characters caused by varying handwritten styles. For handling segmentation issues at the character level arising from handwritten styles, we have proposed an algorithm based on the language's features. To enhance word-level accuracy a dictionary-based model was devised. A neural network utilizing the inception module is employed for feature extraction at various scales, achieving word-level accuracy rates of 78% with fewer trainable parameters. [ABSTRACT FROM AUTHOR]

This work focuses on a novel lightweight machine learning approach to the task of plant disease classification, posing as a core component of a larger grow-light smart monitoring system. To the extent of our knowledge, this work is the first to implement lightweight convolutional neural network architectures leveraging downscaled versions of inception blocks, residual connections, and dense residual connections applied without pretraining to the PlantVillage dataset. The novel contributions of this work include the proposal of a smart monitoring framework outline; responsible for detection and classification of ailments via the devised lightweight networks as well as interfacing with LED grow-light fixtures to optimize environmental parameters and lighting control for the growth of plants in a greenhouse system. Lightweight adaptation of dense residual connections achieved the best balance of minimizing model parameters and maximizing performance metrics with accuracy, precision, recall, and F1-scores of 96.75%, 97.62%, 97.59%, and 97.58% respectively, while consisting of only 228,479 model parameters. These results are further compared against various full-scale state-of-the-art model architectures trained on the PlantVillage dataset, of which the proposed down-scaled lightweight models were capable of performing equally to, if not better than many large-scale counterparts with drastically less computational requirements. [ABSTRACT FROM AUTHOR]

As the biopharmaceutical industry looks to implement Industry 4.0, the need for rapid and robust analytical characterization of analytes has become a pressing priority. Spectroscopic tools, like near‐infrared (NIR) spectroscopy, are finding increasing use for real‐time quantitative analysis. Yet detection of multiple low‐concentration analytes in microbial and mammalian cell cultures remains an ongoing challenge, requiring the selection of carefully calibrated, resilient chemometrics for each analyte. The convolutional neural network (CNN) is a puissant tool for processing complex data and making it a potential approach for automatic multivariate spectral processing. This work proposes an inception module‐based two‐dimensional (2D) CNN approach (I‐CNN) for calibrating multiple analytes using NIR spectral data. The I‐CNN model, coupled with orthogonal partial least squares (PLS) preprocessing, converts the NIR spectral data into a 2D data matrix, after which the critical features are extracted, leading to model development for multiple analytes. Escherichia coli fermentation broth was taken as a case study, where calibration models were developed for 23 analytes, including 20 amino acids, glucose, lactose, and acetate. The I‐CNN model result statistics depicted an average R2 values of prediction 0.90, external validation data set 0.86 and significantly lower root mean square error of prediction values ∼0.52 compared to conventional regression models like PLS. Preprocessing steps were applied to I‐CNN models to evaluate any augmentation in prediction performance. Finally, the model reliability was assessed via real‐time process monitoring and comparison with offline analytics. The proposed I‐CNN method is systematic and novel in extracting distinctive spectral features from a multianalyte bioprocess data set and could be adapted to other complex cell culture systems requiring rapid quantification using spectroscopy. [ABSTRACT FROM AUTHOR]

BackgroundPneumonia and tuberculosis are prevalent pulmonary diseases globally, each demanding specific care measures. However, distinguishing between these two conditions imposes challenges due to the high skill requirements for doctors, the impact of imaging positions and respiratory intensity of patients, and the associated high healthcare costs, emphasizing the imperative need for intelligent and efficient diagnostic methods.MethodThis study aims to develop a highly accurate automatic diagnosis and classification method for various lung diseases (Normal, Pneumonia, and Tuberculosis). We propose a hybrid model, which is based on the InceptionV3 architecture, enhanced by introducing Deepwise Separable Convolution after the Inception modules and incorporating the Squeeze-and-Excitation mechanism. This architecture successfully enables the model to extract richer features without significantly increasing the parameter count and computational workload, thereby markedly improving the performance in predicting and classifying lung diseases. To objectively assess the proposed model, external testing and five-fold cross-validation were conducted. Additionally, widely used baseline models in the scholarly community were constructed for comparison.ResultIn the external testing phase, the our model achieved an average accuracy (ACC) of 90.48% and an F1-score (F1) of 91.44%, which is an approximate 4% improvement over the best-performing baseline model, ResNet. In the five-fold cross-validation, our model’s average ACC and F1 reached 88.27% ± 2.76% and 89.29% ± 2.69%, respectively, demonstrating exceptional predictive performance and stability. The results indicate that our model holds promise for deployment in clinical settings to assist in the diagnosis of lung diseases, potentially reducing misdiagnosis rates and patient losses.ConclusionUtilizing deep learning for automatic assistance in the diagnosis of pneumonia and tuberculosis holds clinical significance by enhancing diagnostic accuracy, reducing healthcare costs, enabling rapid screening and large-scale detection, and facilitating personalized treatment approaches, thereby contributing to widespread accessibility and improved healthcare services in the future.

Emotion is a psychological and physiological response to an event or stimulus. Understanding students' emotions helps teachers and educators interact more effectively with students and create a better learning environment. The importance of understanding students' emotions in the learning process has led to exploring the use of facial emotion classification technology. In this research, an ensemble approach consisting of ResNet, MobileNet, and Inception is applied to identify emotional expressions on the faces of school students using a dataset that includes emotions such as happiness, sadness, anger, surprise, and boredom, acquired from students of Darul Imarah State Junior High School, Great Aceh District, Indonesia. Our dataset is available publicly, and so-called USK-FEMO. The performance evaluation results show that each model and approach has significant capabilities in classifying facial emotions. The ResNet model shows the best performance with the highest accuracy, precision, recall, and F1-score, which is 86%. MobileNet and Inception also demonstrate good performance, indicating potential in handling complex expression variations. The most interesting finding is that the ensemble approach achieves the highest accuracy, precision, recall, and F1-score of 90%. By combining predictions from the three models, the ensemble approach can consistently and accurately address emotion variations. Implementing emotion classification models, individually and in an ensemble format, can improve teacher-student interactions and optimize learning strategies that are responsive to students' emotional needs.

Motivation: Crop diseases pose a critical threat to global food security, causing substantial agricultural yield losses. Manual disease identification is labor-intensive and requires expertise, hindering timely and accurate detection. Problem Gap: Traditional methods for identifying plant diseases are time-consuming and demand specialized knowledge. The need for a more efficient, automated, and accurate approach is evident to minimize crop losses and ensure food security. Contribution: This research paper addresses the challenge of plant disease detection by proposing a novel approach that combines image processing and deep learning techniques. The primary contribution is a sophisticated deep neural network ensemble model, which integrates Residual Network, MobileNet, and Inception models. This ensemble architecture is designed to maximize accuracy and robustness in disease classification. The model is trained on an extensive dataset containing images of both healthy and infected potato leaves. It accomplishes the precise categorization of leaves into three classes: healthy potato leaves, infected potato leaves (two classes). The model's proficiency lies in its ability to discern intricate leaf features, colors, and types, enabling it to differentiate between healthy and potentially diseased leaves. This research makes a significant contribution to the development of automated disease detection systems. By bridging the gap between manual identification and advanced technology, it presents a promising solution for early disease detection and prevention. Ultimately, this approach can foster increased agricultural productivity, ensuring enhanced food security on a global scale. Results: Results demonstrate the proposed model's effectiveness, achieving an impressive overall accuracy of 98.86%. This high accuracy attests to the model's competence in precisely detecting and classifying potato diseases. By harnessing the potential of ensemble-based deep learning and image processing, this research introduces an innovative tool for agriculturalists and researchers. [ABSTRACT FROM AUTHOR]

Featured Application: The roller bearing and the through shaft bearing are the rotating and load-bearing components of the annealing kiln roller system, which operate at different locations and under different working conditions. Their health status is significant for maintaining the stable operation of the glass production line. In order to improve the efficiency of bearing condition monitoring, this paper proposes a variable-scale attention mechanism guided time-frequency feature fusion transfer learning method, which is used for bearing fault diagnoses at different installation locations in the annealing kiln roller system. It effectively achieves the intelligent diagnosis of roller bearing and through shaft bearing faults in the annealing kiln roller system. Effective real-time health condition monitoring of the roller table and through shaft bearings in the annealing kiln roller system of glass production lines is crucial for maintaining their operational safety and stability for the quality and production efficiency of glass products. However, the collected vibration signal of the roller bearing system is affected by the low rotating frequency and strong mechanical background noise, which shows the width impact interval and non-stationary multi-component characteristics. Moreover, the distribution characteristics of monitoring data and probability of fault occurrence of the roller bearing and through shaft bearing improve the difficulty of the fault diagnosis and condition monitoring of the annealing kiln roller system, as well as the reliance on professional experience and prior knowledge. Therefore, this paper proposes a variable-scale attention mechanism guided time-frequency feature fusion transfer learning method for a bearing fault diagnosis at different installation positions in an annealing kiln roller system. Firstly, the instinct time decomposition method and the Gini–Kurtosis composed index are used to decompose and reconstruct the signal for noise reduction, wavelet transform with the Morlet basic function is used to extract the time-frequency features, and histogram equalization is introduced to reform the time-frequency map for the blur and implicit time-frequency features. Secondly, a variable-scale attention mechanism guided time-frequency feature fusion framework is established to extract multiscale time-dependency features from the time-frequency representation for the distinguished fault diagnosis of roller table bearings. Then, for through shaft bearings, the vibration signal of the roller table bearing is used as the source domain and the signal of the through shaft bearing is used as the target domain, based on the feature fusion framework and the multi-kernel maximum mean differences metric function, and the transfer diagnosis method is proposed to reduce the distribution differences and extract the across-domain invariant feature to diagnose the through shaft bearing fault speed under different working conditions, using a small sample. Finally, the effectiveness of the proposed method is verified based on the vibration signal from the experimental platform and the roller bearing system of the glass production line. Results show that the proposed method can effectively diagnose roller table and through shaft bearings' fault information in the annealing kiln roller system. [ABSTRACT FROM AUTHOR]

Recent developments in deep learning have revolutionized the field of activity recognition by humans and other entities. These advancements allow models to learn complex representations and hierarchies from raw data, hence increasing recognition accuracy. Many machine learning algorithms, such as support vector machines and histogram of gradients with k-nearest neighbor classifiers, have lost part of their appeal due to the extensive feature engineering and data preparation required. The objective of this research is to construct an efficient and robust ensemble model by utilizing the strengths of Convolutional neural networks (CNN), Visual Geometry Group (VGG16), Inception model, and Residual Networks 50 (ResNet50) model in order to boost the resilience and predicted accuracy of human activity recognition from raw visual data. This work makes use of a large and diverse dataset that includes over 12,000 annotated photos illustrating various human activities and methodology yields promising results while removing the need for sophisticated feature manipulation. Furthermore, the results show how the ensemble model is better at Human Action Recognition (HAR). [ABSTRACT FROM AUTHOR]

In this work, a dataset of chest posteroanterior X-ray images has been used to categorise the images into three classes Covid-19, Normal and Pneumonic conditions. This paper addresses the Covid-19 classification problem by the application of Machine Learning (ML) and Deep Learning (DL) techniques. Active research work is ongoing in this area to aid and provide support to doctors treating patients. Several pre-trained models in a deep convolution network have been used. Introduction of a concatenation of pre-trained models based on its earlier work on the same dataset has been done. Transfer learning (TL) is a powerful computer vision technique that helps us to produce accurate models efficiently. Here, three customized pre-trained models, mainly Xception net, InceptionV3, and ResNext50, have been established and combined with model convolution neural networks with appropriate parameters. With the proposed model we have achieved improved results with this data set by applying feature extraction, selection, and concatenation the features generated by all three models. In the experimental results, the Xception model gave the best results as compared to the remaining two for Covid-19 detection. Application of all the three models collectively with our proposed approach has improved the classification accuracy score to around 98.44%. Which is an improvement of 4.44% on the previous work (Jain et al. Appl Intell 51(3):1690–1700, 2021). [ABSTRACT FROM AUTHOR]

Alzheimer's disease is a disease that causes cognitive impairment. There is no cure for Alzheimer's disease, but the progression can be slowed down or halted. It is possible to treat the symptoms of Alzheimer's disease through the use of different drugs or non-drugs, thereby improving the health of the patient. To treat alzheimer patients at different stages, various techniques have been employed. As a result, it is crucial to predict and classify the various stages of Alzheimer's disease. In conjunction with electronic health records, Machine Learning and Deep Learning algorithms are used to assist in disease detection. The Convolution Neural Network is one of the most effective methods for predicting and diagnosing diseases in the field of deep learning technology. In this paper, several convolution neural network techniques are discussed and their accuracy for the early diagnosis of Alzheimer's disease is compared. It is concluded that this work provides a better accuracy result for CNN algorithms (ResNet50, ResNet101, ResNet50V2, ResNet101V2, InceptionV3, and Inception-ResNetV2) for the prediction of alzheimer disease in different conditions. [ABSTRACT FROM AUTHOR]

Today, specific convolution neural network (CNN) models assigned to specific tasks are often used. In this article, the authors explored three models: MobileNet, EfficientNetB0, and InceptionV3 combined. The authors were interested in investigating how quickly an artificial intelligence model can be taught with limited computer resources. Three types of training bases were investigated, starting with a simple base verifying five colours, then recognizing two different orthogonal elements, followed by more complex images from different families. This research aimed to demonstrate the capabilities of the models based on training base parameters such as the number of images and epoch types. Architectures proposed by the authors in these cases were chosen based on simulation studies conducted on a virtual machine with limited hardware parameters. The proposals present the advantages and disadvantages of the different models based on the TensorFlow and Keras libraries in the Jupiter environment based on the Python programming language. An artificial intelligence model with a combination of MobileNet, proposed by Siemens, and Efficient and Inception, selected by the authors, allows for further work to be conducted on image classification, but with limited computer resources for industrial implementation on a programmable logical controller (PLC). The study showed a 90% success rate, with a learning time of 180 s. [ABSTRACT FROM AUTHOR]

The Coronavirus pandemic devastatingly affected worldwide social prosperity, and general well-being, deadening the human way of life all around the world and undermining our security. Due to the increasing number of confirmed cases associated with COVID-19, it is more important to identify the healthy and infected patients so the control of spread and treatment of infected patients can be done effectively. This work aims to correlate the presence of Covid-19 with the help of both chest X-ray images and CT Scan Images. Deep ensemble learning models take advantage of the different deep learning models, combine them, and produce a model with better performance. The proposed system involves Data augmentation and preprocessing of CT scan images. The same process is applied for Chest X-ray Images, compares the evaluation metrics amongst the models, and suggests the best use of CT scan and Chest X-ray for better Results and accuracy. The features extracted from the Inception V3 model are combined with the features extracted from the Xception model. The inception model convolves the same input tensor with the help of multiple filters, and the results are concatenated. The pre-trained Xception model is capable of depth-wise separable convolutions. The proposed framework works in Covid-19 diagnosis with an accuracy of 96% in Xception and 98% while combining Xception and InceptionV3 models. The final results showed that the Convolutional Neural Network Classifier built with the ensemble of Inception and Xception models that use X-ray images efficiently collects the essential features related to the infections of COVID-19. [ABSTRACT FROM AUTHOR]

Face recognition in general scenarios has been saturated in recent years, but there is still room to enhance model performance in extreme scenarios and fairness situations. Inspired by the successful application of Transformer and ConvNet in computer vision, we propose a FIN-Block, which gives a more flexible composition paradigm for building a novel pure convolution model and provides a foundation for constructing a new framework for general face recognition in both extreme scenarios and fairness situations. FIN-Block-A uses a combination of stacked large-size convolution kernels and parallel convolution branches to ensure a large spatial receptive field while improving the module's deep feature embedding and extraction capabilities. FIN-Block-B takes advantage of stacked orthogonal convolution kernels and parallel branches to balance model size and performance. By applying FIN-Block with an adapted convolution kernel size in different stages, we built a reasonable and novel framework Face-Inception-Net, and the performance of the model is highly competitive with ConvNeXt and InceptionNeXt. The models were trained on CASIA-WebFace and MS-wo-RFW databases and evaluated on 14 mainstream benchmarks, including LFW, extreme scene, and fairness test sets. The proposed Face-Inception-Net achieved the highest average TAR@FAR0.001 of 95.9% in all used benchmarks, fully demonstrating effectiveness and generality in various scenarios. [ABSTRACT FROM AUTHOR]

Copyright of Al-Adab / Al-ādāb is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

We propose a blind image quality assessment (BIQA) method of using the multitask-learningbased end-to-end convolutional neural network (CNN) approach. The architecture of the proposed method is integrated by two streams. In the first stream, multiscale image features are extracted by using the inception and pyramid pooling modules. Natural scene statistics (NSS)-based features are extracted in the second stream. The two streams are then integrated into fully connected layers to estimate the image quality score. The performance of the proposed method is validated with four public IQA databases and the obtained experimental results show the superiority of the proposed method over conventional IQA methods. [ABSTRACT FROM AUTHOR]

We examine whether time-varying investor demand affects hedge fund companies' decision to start new funds. We find significantly more fund inceptions in hot markets than in cold markets. Funds opened in hot markets exhibit weaker long-term performance, shorter survival time, and greater fraud risk. Investor clientele also varies with market conditions. Investors in hot markets appear to be less sophisticated, which may provide opportunities for more low-quality funds to enter the industry. Overall, inceptions due to high investor demand are not in the best interest of investors. [ABSTRACT FROM AUTHOR]

Humans can carry various diseases, some of which are poorly understood and lack comprehensive solutions. Such a disease can exists in human eye that can affect one or both eyes is diabetic retinopathy (DR) which can impair function, vision, and eventually result in permanent blindness. It is one of those complex complexities. Therefore, early detection of DR can significantly reduce the risk of vision impairment by appropriate treatment and necessary precautions. The primary aim of this study is to leverage cutting-edge models trained on diverse image datasets and propose a CNN model that demonstrates comparable performance. Specifically, we employ transfer learning models such as DenseNet121, Xception, Resnet50, VGG16, VGG19, and InceptionV3, and machine learning models such as SVM, and neural network models like (RNN) for binary and multi-class classification. It has been shown that the proposed approach of multi-label classification with softmax functions and categorical cross-entropy works more effectively, yielding perfect accuracy, precision, and recall values. In particular, Xception achieved an impressive 82% accuracy among all the transfer learning models, setting a new benchmark for the dataset used. However, our proposed CNN model shows superior performance, achieving an accuracy of 95.27% on this dataset, surpassing the state-of-the-art Xception model. Moreover, for single-label (binary classifications), our proposed model achieved perfect accuracy as well. Through exploration of these advances, our objective is to provide a comprehensive overview of the leading methods for the early detection of DR. The aim is to discuss the challenges associated with these methods and highlight potential enhancements. In essence, this paper provides a high-level perspective on the integration of deep learning techniques and machine learning models, coupled with explainable artificial intelligence (XAI) and gradient-weighted class activation mapping (Grad-CAM). We present insights into their respective accuracy and the challenges they face. We anticipate that these insights will prove valuable to researchers and practitioners in the field. Our ambition is that this in-depth study and comparison of models will inform and inspire future research endeavors, ultimately leading to enhanced disease detection in medical imaging and thereby assisting healthcare professionals.

3-D CNNs have demonstrated their capability to capture intricate nonlinear relationships within hyperspectral images (HSIs). However, the computational complexity of 3-D CNNs often leads to slower processing speeds, limited generalization, and susceptibility to overfitting. In response to these challenges, this study introduces the concept of depthwise separable convolutions using (2+1)-D convolutions as an alternative to traditional 3-D convolutions for hyperspectral image classification (HSIC). The study observes that (2+1)-D convolutions can effectively approximate the complex relationships represented by 3-D convolutions while requiring fewer convolutional operations, thereby reducing the computational overhead associated with classification. Experimental results obtained from benchmark HSI datasets, including Indian Pines, Botswana, Pavia University, and Salinas, demonstrate that the proposed model yields results that are comparable to those achieved by various state-of-the-art models in the existing literature.

Recent advancements in activity recognition from sports videos have attracted wide scientific interest of the Computer Vision community. However, the activity recognition problem from cricket video sequences is largely under-represented in the literature. This paper aims to devise a convolutional neural network (CNN) based model for sports activity recognition. The model is trained on the pre-trained VGG16, VGG19, ResNet50, and Inception V3 Models and tested on the clustered cricket videos frames extracted from the data set especially prepared for this research. The clustering of the frames is done by using K-Mean clustering algorithm. K-Fold cross validation is done which gave an accuracy of 99% on clustered data and 91% on un-clustered data. The accuracy and time complexity of the proposed method is better as compared to the state of the art methods used for activity recognition from videos. [ABSTRACT FROM AUTHOR]

Wireless capsule endoscopy is one of the diagnostic methods used to record the video of the gastrointestinal tract. The endoscopy capsule stays in the digestive system for at least eight hours. It is difficult for gastroenterologists to examine such a lengthy video and identify the ailment. Convolutional neural networks (CNN) are a powerful solution to several computer vision problems. CNN can speed up the reviewing time of the recorded video by classifying video frames into various categories. The primary emphasis of this research paper is to examine and evaluate the performance of three different CNN architectures-VGG, inception, and MobileNet-in classifying the disease. Experimental results demonstrate that MobileNetV2's accuracy is 91%, whereas InceptionV3 and VGG16 have an accuracy of 94% which is better than the accuracy of MobileNetV3. However, MobileNeV2 performed relatively better than the other CNN models in terms of computational time and cost. The model's F-score, precision, and recall values are computed and compared also. [ABSTRACT FROM AUTHOR]

Object detection methods based on deep learning have been used in a variety of sectors including banking, healthcare, e-governance, and academia. In recent years, there has been a lot of attention paid to research endeavors made towards text detection and recognition from different scenesor images of unstructured document processing. The article's novelty lies in the detailed discussion and implementation of the various transfer learning-based different backbone architectures for printed text recognition. In this research article, the authors compared the ResNet50, ResNet50V2, ResNet152V2, Inception, Xception, and VGG19 backbone architectures with preprocessing techniques as data resizing, normalization, and noise removal on a standard OCR Kaggle dataset. Further, the top three backbone architectures selected based on the accuracy achieved and then hyper parameter tunning has been performed to achieve more accurate results. Xception performed well compared with the ResNet, Inception, VGG19, MobileNet architectures by achieving high evaluation scores with accuracy (98.90%) and min loss (0.19). As per existing research in this domain, until now, transfer learningbased backbone architectures that have been used on printed or handwritten data recognition are not well represented in literature. We split the total dataset into 80 percent for training and 20 percent for testing purpose and then into different backbone architecture models with the same number of epochs, and found that the Xception architecture achieved higher accuracy than the others. In addition, the ResNet50V2 model gave us higher accuracy (96.92%) than the ResNet152V2 model (96.34%). [ABSTRACT FROM AUTHOR]

Construction materials undergo appearance and textural changes during the construction process. Accurate recognition of these changes is critical for effectively understanding the construction status; however, recognizing the various levels of detailed material conditions is not sufficiently explored. The primary challenge in the detailed recognition of the conditions of the material is the availability of labeled training data. To address this challenge, this study proposes a novel state-of-the-art deep learning model that leverages transfer learning, utilizing the pretrained Inception V3 to transfer knowledge to the limited labeled data set in the construction context. This enables the model to learn meaningful representations from the limited training data, enhancing its ability to accurately classify material conditions. In addition, gray-level co-occurrence matrix (GLCM)–based texture features are extracted from the images to capture the appearance and textural changes in construction materials, which are then concatenated with the transferred convolutional neural network (CNN) features to create a more comprehensive representation of the material conditions. The proposed model achieved an overall classification accuracy of 95% and 71% with limited (208 images) and very small (70 images) data sets, respectively. It outperformed different experimental architectures, including CNN models developed using limited data with and without augmentation, CNN model with data augmentation and transfer learning, separate models using local binary pattern (LBP) and GLCM texture features with super learners trained using augmented limited data. The findings suggest that the proposed model, which combines transfer learning with GLCM-based texture features, is effective in accurately recognizing the conditions of construction materials, even with limited labeled training data. This can contribute to improved construction management and monitoring. There are several practical applications of the proposed model combining CNN architecture with GLCM textures in construction industry. The primary applications are in activities such as quality inspection and progress monitoring. By analyzing images of different material conditions, such as concrete, plaster, or masonry walls, the model can be used to automatically detect defects or inconsistencies. This enables construction practitioners to ensure the quality of their structures, detect issues early on, and make informed decisions for maintenance and repair. Additionally, the model can be used to monitor the progress of construction projects by analyzing images to track the status and completion of different building components to estimate delays or cost overruns comparing with the expected material condition at a given time of the schedule. Moreover, because the model does not depend on large training data set, it enables construction managers to develop their project specific data sets and automate material condition detection and monitoring. [ABSTRACT FROM AUTHOR]