Search

In this paper, we propose a novel unsupervised pre-training method for point cloud deep learning models using multimodal contrastive learning. Point clouds, which consist of a set of three-dimensional coordinate points acquired from 3D scanners, lidars, depth cameras, etc. play an important role in representing 3D scenes, and understanding them is crucial for implementing autonomous driving or navigation. Deep learning models based on supervised learning for point cloud understanding require a label for each point cloud data that corresponds to the correct answer in training. However, generating these labels is expensive, making it difficult to build large datasets, which is essential for good model performance. Our proposed unsupervised pre-training method, on the other hand, does not require labels and can serve as an initial value for a model that can alleviate the need for such large datasets. The proposed method is characterized as a multimodal approach that utilizes two modalities for point clouds: the point cloud itself and an image rendering of the point cloud. By using images that directly render the point clouds, the shape information of the point clouds from various viewpoints can be obtained from the images without additional data such as meshes. We pre-trained the model with the proposed method and conducted performance comparison on ModelNet40 and ScanObjectNN datasets. The linear classification accuracy of the point cloud feature vector extracted by the pre-trained model was 91.5% and 83.9%, and after fine-tuning for each dataset, the classification accuracy was 93.3% and 86.9%, respectively. [ABSTRACT FROM AUTHOR]

Handwritten character recognition (HCR) remains a challenging pattern recognition problem despite decades of research, and lacks research on script independent recognition techniques. This is mainly because of similar character structures, different handwriting styles, diverse scripts, handcrafted feature extraction techniques, unavailability of data and code, and the development of script-specific deep learning techniques. To address these limitations, we have proposed a script independent deep learning network for HCR research, called HCR-Net, that sets a new research direction for the field. HCR-Net is based on a novel transfer learning approach for HCR, which partly utilizes feature extraction layers of a pre-trained network. Due to transfer learning and image augmentation, HCR-Net provides faster and computationally efficient training, better performance and generalizations, and can work with small datasets. HCR-Net is extensively evaluated on 40 publicly available datasets of Bangla, Punjabi, Hindi, English, Swedish, Urdu, Farsi, Tibetan, Kannada, Malayalam, Telugu, Marathi, Nepali and Arabic languages, and established 26 new benchmark results while performed close to the best results in the rest cases. HCR-Net showed performance improvements up to 11% against the existing results and achieved a fast convergence rate showing up to 99% of final performance in the very first epoch. HCR-Net significantly outperformed the state-of-the-art transfer learning techniques and also reduced the number of trainable parameters by 34% as compared with the corresponding pre-trained network. To facilitate reproducibility and further advancements of HCR research, the complete code is publicly released at https://github.com/jmdvinodjmd/HCR-Net. [ABSTRACT FROM AUTHOR]

Renal Cell Carcinoma (RCC) is the most common malignant tumor (85%) of kidney cancer and has a complex histological pattern and nuclear structure. The manual diagnosis of kidney cancer or any other cancer from histopathology image depends on the knowledge and experience of pathologists, and the pathologist's experience influences the results. According to studies, the kind of histology in kidney cancer is related to the prognosis and course of treatment. Since the kind of histology, molecular profile, and stage of the disease all affect how the disease is treated, there is an essential need to develop an automated system that can precisely analyze the histopathological images of the disease. This work demonstrates how a deep learning framework can be used to predict and classify associated grades of RCC from provided haematoxylin and eosin (H &E) images. The proposed model focuses on two important tasks- First to capture and extract associated features from the H &E images of five different grades. Second, to classify the new set of unseen H &E images into five separate grades using the obtained features. The proposed architecture has been tested and experimented on two independent datasets containing H &E stained histopathology images. The proposed architecture has been examined using the following performance metrics namely precision, recall, F1 - score, accuracy, Floating-point operations (FLOPs), and the total number of parameters. The obtained results show that the proposed architecture attains better results over seven state-of-the-art deep learning architectures on two different H &E stained histopathology image datasets. [ABSTRACT FROM AUTHOR]

Nutrient deficiency identification in plants is crucial for precision agriculture. Over the past decade, the application of digital imagery and deep learning has been utilized to tackle challenges related to this task. Nevertheless, the constraints inherent in current models have significantly heightened the difficulty of this task. To overcome these limitations, this study proposes an ensemble transfer learning method for nutrient deficiency identification and yield-loss prediction in crops using plant-leaf images. The proposed method is evaluated through two experiments. The initial experiment canters on the classification of images according to their nutrient deficiency, while the second experiment determines the yield loss based on the severity of the deficient nutrient. The proposed ensemble transfer learning methodology achieves remarkable accuracy rates of 99% and 94% for the groundnut and rice datasets, respectively. Furthermore, the severity-based crop yield prediction method predicts yield loss of 32.5% and 28.34% for the rice and groundnut datasets, respectively. The study utilizes two different crop datasets that represent actual environmental conditions. The first dataset contains 4399 leaf images of the rice plant, while the second dataset contains 4550 leaf images of the groundnut plant. The proposed method outperforms existing models and demonstrates that digital imagery and Deep learning can play a significant role in addressing agricultural challenges within the context of precision agriculture. [ABSTRACT FROM AUTHOR]

Otitis media is a medical concept that represents a range of inflammatory middle ear disorders. The high costs of medical devices utilized by field experts to diagnose the disease relevant to otitis media prevent the widespread use of these devices. This makes it difficult for field experts to make an accurate diagnosis and increases subjectivity in diagnosing the disease. To solve these problems, there is a need to develop computer-aided middle ear disease diagnosis systems. In this study, a deep learning-based approach is proposed for the detection of OM disease to meet this emerging need. This approach is the first that addresses the performance of a voting ensemble framework that uses Inception V3, DenseNet 121, VGG16, MobileNet, and EfficientNet B0 pre-trained DL models. All pre-trained CNN models used in the proposed approach were trained using the Public Ear Imagery dataset, which has a total of 880 otoscopy images, including different eardrum cases such as normal, earwax plug, myringosclerosis, and chronic otitis media. The prediction results of these models were evaluated with voting approaches to increase the overall prediction accuracy. In this context, the performances of both soft and hard voting ensembles were examined. Soft voting ensemble framework achieved highest performance in experiments with 98.8% accuracy, 97.5% sensitivity, and 99.1% specificity. Our proposed model achieved the highest classification performance so far in the current dataset. The results reveal that our voting ensemble-based DL approach showed quite high performance for the diagnosis of middle ear disease. In clinical applications, this approach can provide a preliminary diagnosis of the patient's condition just before field experts make a diagnosis on otoscopic images. Thus, our proposed approach can help field experts to diagnose the disease quickly and accurately. In this way, clinicians can make the final diagnosis by integrating automatic diagnostic prediction with their experience. [ABSTRACT FROM AUTHOR]

Ocular diseases can have debilitating consequences on visual acuity if left untreated, necessitating early and accurate diagnosis to improve patients' quality of life. Although the contemporary clinical prognosis involving fundus screening is a cost-effective method for detecting ocular abnormalities, however, it is time-intensive due to limited resources and expert ophthalmologists. While computer-aided detection, including traditional machine learning and deep learning, has been employed for enhanced prognosis from fundus images, conventional deep learning models often face challenges due to limited global modeling ability, inducing bias and suboptimal performance on unbalanced datasets. Presently, most studies on ocular disease detection focus on cataract detection or diabetic retinopathy severity prediction, leaving a myriad of vision-impairing conditions unexplored. Minimal research has been conducted utilizing deep models for identifying diverse ocular abnormalities from fundus images, with limited success. The study leveraged the capabilities of four Swin Transformer models (Swin-T, Swin-S, Swin-B, and Swin-L) for detecting various significant ocular diseases (including Cataracts, Hypertensive Retinopathy, Diabetic Retinopathy, Myopia, and Age-Related Macular Degeneration) from fundus images of the ODIR dataset. Swin Transformer models, confining self-attention to local windows while enabling cross-window interactions, demonstrated superior performance and computational efficiency. Upon assessment across three specific ODIR test sets, utilizing metrics such as AUC, F1-score, Kappa score, and a composite metric representing an average of these three (referred to as the final score), all Swin models exhibited superior performance metric scores than those documented in contemporary studies. The Swin-L model, in particular, achieved final scores of 0.8501, 0.8211, and 0.8616 on the Off-site, On-site, and Balanced ODIR test sets, respectively. An external validation on a Retina dataset further substantiated the generalizability of Swin models, with the models reporting final scores of 0.9058 (Swin-T), 0.92907 (Swin-S), 0.95917 (Swin-B), and 0.97042 (Swin-L). The results, corroborated by statistical analysis, underline the consistent and stable performance of Swin models across varied datasets, emphasizing their potential as reliable tools for multi-ocular disease detection from fundus images, thereby aiding in the early diagnosis and intervention of ocular abnormalities. [ABSTRACT FROM AUTHOR]

A question-answering (QA) system is a key application in the field of natural language processing (NLP) that provides relevant answers to user queries written in natural language. In factoid QA using knowledge bases, predicting the semantic category of answers, such as location, person, or numerical values, helps to reduce the search spaces and is an essential step in formal query construction for answer retrieval. However, finding the semantics in sequence data like questions is challenging. In this regard, Recursive neural networks based deep learning methods have been applied. But, they are inefficient in handling long-term dependencies. Recently, pre-trained language models employing transformers are proven effective and can generate context-dependent embedding for words and sentences from their encoders with attention mechanisms. However, to train an efficient transformer model for semantic category prediction requires a large dataset and high computational resources. Therefore, in this work, we employ a transfer learning approach using pre-trained transformer models by efficiently adapting them to predict the semantic category of answers from input questions. Here, embeddings from the encoders of the text-to-text transfer transformer (T5) model have been leveraged to obtain an efficient question representation and to train the classification model which is named as QcT5. Along with QcT5, an extensive experimental study on other recent transformer models - BERT, RoBERTa, DeBERTa, and XLNet, is conducted, and their performance is analyzed in various fine-tuning settings. Experimental results indicate that the QcT5 model significantly improves the performance compared to the selected state-of-the-art methods by achieving an f1-score of 98.7%, 89.9% on TREC-6, and TREC-50 datasets respectively. [ABSTRACT FROM AUTHOR]

One of the most severe cancers worldwide is Colorectal Cancer (CRC), which has the third-highest incidence of cancer cases and the second-highest rate of cancer mortality. Early diagnosis and treatment are receiving much attention globally due to the increasing incidence and death rates. Colonoscopy is acknowledged as the gold standard for screening CRC. Despite early screening, doctors miss approximately 25% of polyps during a colonoscopy examination because the diagnosis varies from expert to expert. After a few years, this missing polyp may develop into cancer. This study is focused on addressing such diagnostic challenges, aiming to minimize the risk of misdiagnosis and enhance the overall accuracy of diagnostic procedures. Thus, we propose an efficient deep learning method, DeepCPD, combining transformer architecture and Linear Multihead Self-Attention (LMSA) mechanism with data augmentation to classify colonoscopy images into two categories: polyp versus non-polyp and hyperplastic versus adenoma based on the dataset. The experiments are conducted on four benchmark datasets: PolypsSet, CP-CHILD-A, CP-CHILD-B, and Kvasir V2. The proposed model demonstrated superior performance compared to the existing state-of-the-art methods with an accuracy above 98.05%, precision above 97.71%, and recall above 98.10%. Notably, the model exhibited a training time improvement of over 1.2x across all datasets. The strong performance of the recall metric shows the ability of DeepCPD to detect polyps by minimizing the false negative rate. These results indicate that this model can be used effectively to create a diagnostic tool with computer assistance that can be highly helpful to clinicians during the diagnosing process. [ABSTRACT FROM AUTHOR]

Deep learning has brought essential improvement to image inpainting technology. Conventional deep-learning methods primarily focus on creating visually appealing content in the missing parts of images. However, these methods usually generate edge variations and blurry structures in the filled images, which lead to imbalances in quantitative metrics PSNR/SSIM and LPIPS/FID. In this work, we introduce a pioneering model called PTG-Fill, which utilizes a coarse-to-fine architecture to achieve smooth-variation image inpainting. Our approach adopts the novel Stable-Partial Convolution to construct the coarse network, which integrates a smooth mask-update process to ensure its long-term operation. Meanwhile, we propose the novel Distinctive-Gated Convolution to construct the refined network, which diminishes pixel-level variations by the distinctive attention. Additionally, we build up a novel Transformer bridger to preserve the in-depth features for image refinement and facilitate the operation of the two-stage network. Our extensive experiments demonstrate that PTG-Fill outperforms previous state-of-the-art methods both quantitatively and qualitatively under various mask ratios on four benchmark datasets: CelebA-HQ, FFHQ, Paris StreetView, and Places2. Code and pre-trained weights are available at https://github.com/zeyuwang-zju/PTG-Fill. [ABSTRACT FROM AUTHOR]

Precise and automatic plant disease detection represent a fundamental research topic. Indeed, traditional or manual disease detection can be laborious, inaccurate and time-consuming. In this work, a particular attention is given to automatic potato late blight disease detection. In fact, this devastating pathogen leads every year to a significant reduction in potato yields. In addition, since potatoes are a major food source for many nations, decreased production generate a real food insecurity. Therefore, considering these challenges, using advanced techniques in computer vision and machine learning allowed farmers to swiftly and accurately identify disease. The main objective of this research work is to generate a super-resolved labeled dataset (SRD) and evaluate its impact on plant disease detection. Three states of the art object detection methods (Faster-RCNN, Detr and Yolo V8) have been used to conduct an exhaustive evaluation on the effect of using a super-resolved dataset to perform detection. The obtained results show that the detection of potato late blight disease is enhanced using SRD. Training Yolo V8 model on SRD outperform other trained models in detecting very small lesions. In fact, training Yolo V8 on SRD reached higher mAP, lower Loss values and a reasonable inference time, making it suitable for real time applications. [ABSTRACT FROM AUTHOR]

Temporal action localization (TAL) is one of the most important tasks in video understanding. Weakly supervised temporal action localization (WTAL) involves classifying and localizing all the action instances in untrimmed videos under the supervision of only video-level category labels, which is a challenging task because of the absence of frame-level annotations. In this study, first, we review the development process of the WTAL task in recent years, summarize and analyze the main problems of WTAL. Second, we classify and compare the research approaches of existing models and thoroughly discuss methods based on multiple instance learning (MIL), feature erasing, the attention mechanism, similarity propagation, pseudo-ground truth generation, contrastive learning, and adversarial learning. Then, we present the datasets and evaluation criteria for the WTAL task. Finally, we discuss the main application areas and further developments in WTAL. [ABSTRACT FROM AUTHOR]

In recent times, deep learning-based steganalysis classifiers have become popular due to their state-of-the-art performance. Most deep steganalysis classifiers usually extract noise residuals using high-pass filters as preprocessing steps and feed them to their deep model for classification. It is observed that recent steganographic embedding does not always restrict their embedding in the high-frequency zone; instead, they distribute it as per embedding policy. Therefore, besides noise residual, learning the embedding zone is another challenging task. In this work, unlike the conventional approaches, the proposed model first extracts the noise residual using learned denoising kernels to boost the signal-to-noise ratio. After preprocessing, the sparse noise residuals are fed to a novel Multi-Contextual Convolutional Neural Network (M-CNET) that uses heterogeneous context size to learn the sparse and low-amplitude representation of noise residuals. The model performance is further improved by incorporating the Self-Attention module to focus on the areas prone to steganalytic embedding. A set of comprehensive experiments is performed to show the proposed scheme's efficacy over the prior arts. Besides, an ablation study is given to justify the contribution of various modules of the proposed architecture. [ABSTRACT FROM AUTHOR]

Reconstruction of multi-view 3-dimensional images is essential in robotics and computer vision to obtain an accurate 3-dimensional representation of objects by analyzing the 2-dimensional input data. For reconstructing the 3-dimensional image, it is mandatory to analyze the 3-dimensional geometry features from multiple viewpoints. It includes feature extraction and transformation from 2-dimensional features to 3-dimensional volumetric meshes. However, the existing research cannot produce consistent reconstruction results for the same input images with different orders. Therefore, the deep learning-based Residual Network-50 model is developed for 3-dimensional image reconstruction from multi-view images in the present work. The proposed system model comprises a 2-dimensional and 3-dimensional network and a backpropagation layer. From the input image, 2-dimensional features are computed using a 2-dimensional network. Then, the metaheuristic Adaptive School of Fish Optimization is used to improve the neural network's output, determining the optimal weight that gives less classification error. Then, the testing process uses the deep autoencoder, which decodes the output of the training model. Residual Network-50 is used to reconstruct 2-dimensional images to 3-dimensional using single or multi-views. Finally, the experimental analysis is performed in Python. The experiment is performed on the ShapeNet dataset and compared with the existing works. The proposed model yields better accuracy, F-score and Intersection-over-Union values of 99.3%, 0.893 and 0.734, respectively, which is more efficient than other existing models. [ABSTRACT FROM AUTHOR]

With the development of highways, there has been an increase in toll evasion by unscrupulous individuals who employ various means to avoid paying fees. This has made it essential for highway management to focus on effective methods to prevent and manage toll evasion, as well as regulate toll-related operations. However, traditional auditing techniques are heavily reliant on manual toll data and lack sufficient auxiliary data such as video and pictures, making big data analysis and in-depth data analysis difficult. Consequently, these methods can only identify a portion of evasion behavior, with a significant number of potential evasion cases remaining unidentified. To address this issue, we propose utilizing vehicle re-identification to enable cross-camera identification and continuous tracking of vehicles, allowing for accurate calculation of their operating mileage. However, vehicle re-identification using images captured by highway cameras is a challenging task, primarily due to the low resolution of the images and the lack of relevant datasets. To tackle these problems, we construct a large-scale, low-resolution dataset based on images captured by cameras on highways. We also propose a Part-guided Feature-combination Network (PFNet) to analyze the dataset. PFNet adopts a three-stage approach, wherein each stage of the network requires independent training. In the first stage, the Pyramid Scene Parsing Network (PSPNet) is improved to segment the entire vehicle into parts. In the second stage, based on a comparative learning approach, the Siamese Feature Extraction Module (SFEM) module was created to extract features of pairs of vehicle parts. To train the SFEM, pairs of positive samples, which consist of the same vehicle component pairs captured by different cameras, and pairs of negative samples, which consist of different vehicle component pairs are needed. To ensure that the positive sample pairs are closer to each other in the embedding space, and the negative samples are as far away as possible from each other, contrast loss is utilized. Moreover, The SFEM incorporates VGG16 and a Multi-period Convolutional Block Attention Module (MCBAM), which enhances the learning ability of the conventional Convolutional Block Attention Module (CBAM). In the third stage, information propagation among the vehicle parts is achieved using a Multi-layer Perceptron (MLP), which calculates the similarity after combining the features of all parts. Our self-built test set demonstrates that PFNet is effective for continuous monitoring of vehicles on highways under multiple cameras, resulting in improved accuracy of vehicle re-identification, with Top1 accuracy of 93.61% and Top5 accuracy of 99.44%. [ABSTRACT FROM AUTHOR]

Deep learning methods are leveraged in various computer science and artificial intelligence areas, including image classification. Convolutional neural network (CNN) is one of the most widely used deep neural networks for which, several highly effective architectures for image classification have been presented. In this paper, an improved version of the recently introduced CondenseNet is provided as a new network architecture. On the other hand, due to the necessity of reducing the dependence on labeled data in the training process of neural networks, a self-supervised learning method is also proposed for labeling unlabeled images. The results of the experiments show the proper performance of the proposed self-supervised CondenseNet method compared to the basic version of CondenseNet. The experiments are conducted on CIFAR_10 and CIFAR-100 datasets and show better accuracy of the proposed method. [ABSTRACT FROM AUTHOR]

A fricative sound is produced by the close proximity of two articulators, resulting in a partially obstructed airstream and turbulent airflow. The frequency spectrum of the majority of fricatives is similar to noise. This peculiarity presents a significant challenge in their numerical processing. Nonetheless, the literature contains a large number of works for fricatives, particularly those of Latin languages. However, very few are related to the Arabic language. The objective of this article is to create and validate a dataset of 14 Arabic fricatives using an acoustic characterization approach. We recorded a speech corpus from thirty speakers for this purpose, yielding 25 200 units of analysis. The data was then analyzed and validated using deep learning-based classification methods. As a result, two distinct approaches were proposed. The first approach is based on the use of three deep neural networks (Convolutional Recurrent Neural Network (CRNN), Vision Transformers (ViT), and ResNet50) whereas their input is one of three feature extraction techniques (spectrogram, Mel-spectrogram, and Mel-frequency Cepstral Coefficient (MFCC)) from speech units /Vowel-Consonant-Vowel/ (or /VCV/). The best classification rate observed when using the Mel spectrogram with the CRNN model was 94.07%, while the ViT model surpassed this with a rate of 95.64%. This rate was improved to 97.5% by proposing a second approach based on a hierarchical H-CRNN model with fricatives organized into categories (sibilance, voicing, and place of articulation). The obtained results surpassed the traditional approaches proposed in the literature for the classification of Arabic fricatives due to the hierarchical approach. [ABSTRACT FROM AUTHOR]

There is an ever-increasing number of public users of the internet just to remain learned and updated as well as distribute millions of posts, articles, and videos across platforms such as Twitter, Facebook and YouTube etc. The speedy acceptance of social media has forced to an explosive growth in information-distribution among users, with fake news becoming a fundamental intrusion of our digital day-to-day life. The spread of disinformation is in part associated to social media failing to verify the correctness of a news item. Although it is technically possible, it is challenging for a deep neural network to "attend to" the false alone portions of each news piece because the linguistics of fake news will approximate that of true news. In this paper, a Simple Shallow Perceptron Network (SSPN) has been proposed and will reduce the complications such as the curse of high dimensionality, high training time of Deep Neural Networks, over-fitting and over-thinking problem during network training. The effectiveness of the proposed SSPN model for false news identification using the benchmark LIAR dataset and the more recent FakeNewsNet dataset have also been examined. The proposed model outperformed all other existing models, with an F1-score of 0.73 for the LIAR dataset and 0.90 for the FakeNewsNet dataset. [ABSTRACT FROM AUTHOR]

High-resolution remote sensing images (RSI) refer to images captured from a distance, usually from an aircraft or satellite that provide details about the Earth's surface. It can be used in several application areas like environmental monitoring, urban planning, agriculture, and disaster response. In urban planning, high-resolution imagery is used to monitor the growth of urban areas or to recognize the area that requires infrastructure improvement. Vehicle detection is a significant way of understanding high-resolution RSIs. Vehicle detection and classification on high-resolution RSI is a difficult task that needs a group of computer vision (CV), image processing, and machine learning (ML) algorithms. Deep convolutional neural network (DCNN) based techniques have attained recent outcomes in many object detection datasets and have enriched several CV tasks. This article designed and developed a sparrow search optimization algorithm with deep learning for vehicle type detection and classification (SSOADL-VTDC) technique on high-resolution remote sensing images. The presented SSOADL-VTDC technique examines the high-quality RSIs for the accurate detection and classification of vehicles. To accomplish this, the SSOADL-VTDC technique employs a YOLOv5 object detector with a Residual Network as a backbone approach. In addition, the SSOADL-VTDC technique uses SSOA based hyperparameter optimizer designed for the parameter tuning of the YOLOv5 model. For the vehicle classification process, the SSOADL-VTDC technique exploits the softmax classifier. The simulation validation of the SSOADL-VTDC approach was validated on a high-resolution RSI dataset and the outcomes demonstrated the greater of the SSOADL-VTDC methodology in terms of different measures. [ABSTRACT FROM AUTHOR]

Glaucoma is an eye disease that damages the optic nerve (or retina) and impairs vision. This disease can be prevented with regular checkups, but this increases the workload for professionals and the time it takes to get results. So an automated method using deep learning would be helpful for detection of disease. In order to shorten the diagnosis time for glaucoma, this paper proposed a deep learning based method for automatic glaucoma detection. The experiments are conducted on glaucoma datasets available on Kaggle. This paper used transfer learning based pretrained models namely DenseNet169, MobileNet, InceptionV3, Xception, ReseNet152V2,and VGG19. Among all models DenseNet169 gives best result with accuracy 0.993590 and precision and recall of 0.993671 and 0.9935895 respectively. A comparison of the best model results with existing work shows that the proposed model provides better results. [ABSTRACT FROM AUTHOR]

Deep learning (DL) and big data analytics are powerful tools when combined for disease detection and healthcare applications. They enable the processing of vast amounts of medical data to uncover patterns, make predictions, and assist healthcare professionals in diagnosing diseases and improving patient care. Existing disease detection model often faces two challenging issues namely feature selection and insufficient hyperparameter tuning, which considerabley affects the performance and generalization abilities of DL models in disease detection. To resolve these issues, this article focuses on the design of a new Chaotic Red Deer Optimizer with Deep Learning based big data analytics for Disease Classification (CRDODL-BDADC) technique in the healthcare environment. The CRDODL-BDADC technique resolves the high dimensionality problem by the use of CRDO based feature selection approach. For disease detection process, convolutional bidirectional gated recurrent unit (CBGRU) is applied for disease diagnosis and its hyperparameters are selected by using Seeker Optimization Algorithm (SOA). Furthermore, Map Reduce is applied to manage healthcare BD. A widespread set of simulation outcomes occur on the PCOS database, from the Kaggle repository to illustrate the greater performance of the CRDODL-BDADC technique. The simulation values highlighted the enhanced efficiency of the CRDODL-BDADC method over other recent approaches under various measures. [ABSTRACT FROM AUTHOR]

The world population is growing very fast and the lifestyle of human beings is changing with time and place. So, there is a need for disease management which includes disease diagnosis, its detection and classification, cure and lastly for future disease prevention. The outermost protective layer of a human body is the skin. Skin not only impacts a person's health but also psychologically impacts one's life. Computer-aided systems are very helpful in skin disease detection and classification and their application is growing rapidly in healthcare. This literature review paper aims to help the researchers to get a synthesized and appropriate information for the same. We have included papers from 2021 to 2023 for the review from the Scopus database. 45 studies are selected for the review of which 32 studies use deep learning techniques, 11 use machine learning techniques and 2 studies use a hybrid approach. The studies are compared on various parameters like models, datasets, and performance metrics. The work also identified some of the challenges like dealing with noise and also explained disease symptoms. [ABSTRACT FROM AUTHOR]

With the increasing practice of using regional languages in social media platforms, hate speech detection in regional languages has received the attention of researchers. In India, hundreds of languages are spoken in various forms, which are dependent on their geography, culture, etc. Recently the number of active internet users has been rapidly increasing in India, and therefore social media has penetrated the common Indian population. Though the need for proper detection and timely removal of abusive or offensive texts has increased, well-organized and labeled data for Indian languages are scarce. Almost all the regional languages in India are low-resource languages. Hence, the objective of this study is to develop an approach that will learn from relatively small volumes of Indian language data and provide state-of-the-art results. A fusion of features extracted from a fined-tuned multilingual BERT (Bidirectional Encoder Representations from Transformers) and a fine-tuned Indic BERT has been proposed in this study. Since the BERT models that we have used for this work are pre-trained using a large volume of texts in multiple Indian languages, transfer learning solves the problem of low training data volume, and this makes the proposed model more generic. Three datasets for three different Indian languages namely, Bengali, Marathi, and Hindi have been considered in this study to evaluate the proposed approach. The proposed model achieved a weighted F1 score of 0.923, 0.815, and 0.924 for the Bengali, Hindi, and Marathi datasets respectively. In the Bengali and Marathi datasets, the obtained results are better than the existing best results. [ABSTRACT FROM AUTHOR]

Background: We review and analyze research on the application of machine learning (ML) and deep learning (DL) models to lymph node metastasis (LNM) prediction in patients with T1 colorectal cancer (CRC). Predicting LNM before radical surgery is important in patients with T1 CRC. However, current surgical treatment guidelines are limited. LNM prediction using ML or DL may improve predictive accuracy. The diagnostic accuracy of LNM prediction using ML- and DL-based models for patients with CRC was assessed. Methods: We performed a comprehensive search of the PubMed, Embase, and Cochrane databases (inception to April 30th of 2022) for studies that applied ML or DL to LNM prediction in T1 CRC patients specifically to compare with histopathological findings and not related to radiological aspects. Results: 33,199 T1 CRC patients enrolled across seven studies with a retrospective design were included. LNM was observed in 3,173 (9.6%) patients. Overall, the ML- and DL-based model exhibited a sensitivity of 0.944 and specificity of 0.877 for the prediction of LNM in patients with T1 CRC. Six different types of ML and DL models were used across the studies included in this meta-analysis. Therefore, a high degree of heterogeneity was observed. Conclusions: The ML and DL models provided high sensitivity and specificity for predicting LNM in patients with T1 CRC, and the heterogeneity between studies was significant. These results suggest the potential of ML or DL as diagnostic tools. However, more reliable algorithms should be developed for predicting LNM before surgery in patients with T1 CRC. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has proven to be important for computed tomography (CT) image denoising. However, such models are usually trained under supervision, requiring paired data that may be difficult to obtain in practice. Diffusion models offer unsupervised means of solving a wide range of inverse problems via posterior sampling. In particular, using the estimated unconditional score function of the prior distribution, obtained via unsupervised learning, one can sample from the desired posterior via hijacking and regularization. However, due to the iterative solvers used, the number of function evaluations (NFE) required may be orders of magnitudes larger than for single-step samplers. In this paper, we present a novel image denoising technique for photon-counting CT by extending the unsupervised approach to inverse problem solving to the case of Poisson flow generative models (PFGM)++. By hijacking and regularizing the sampling process we obtain a single-step sampler, that is NFE = 1. Our proposed method incorporates posterior sampling using diffusion models as a special case. We demonstrate that the added robustness afforded by the PFGM++ framework yields significant performance gains. Our results indicate competitive performance compared to popular supervised, including state-of-the-art diffusion-style models with NFE = 1 (consistency models), unsupervised, and non-DL-based image denoising techniques, on clinical low-dose CT data and clinical images from a prototype photon-counting CT system developed by GE HealthCare. [ABSTRACT FROM AUTHOR]

Hate speech on social media platforms poses a significant threat to individuals and society, necessitating robust automated detection systems. While existing approaches employ supervised machine learning with text mining elements, they often fall short in capturing the nuanced and evolving nature of hate speech, including subtle linguistic cues, implicit biases, and coded language. This study addresses these limitations by introducing two novel techniques: the feature-based dense convolutional neural network and the swift text word embedding technique. Our key contributions include the development of F-DenseCNN, a deep learning architecture designed to extract complex features from textual data, and the introduction of the swift text word embedding technique, offering efficient and context-aware word representations. Extensive experimentation and evaluation demonstrate that our proposed method significantly outperforms conventional approaches, achieving a 96.2% accuracy in hate speech detection. This substantial improvement in detection accuracy has important implications for content moderation systems, potentially enhancing their reliability and effectiveness in combating online hate speech. Our findings underscore the potential of advanced deep learning techniques in addressing the evolving challenges of hate speech detection on social media platforms. [ABSTRACT FROM AUTHOR]

The majority of people are using connecting media in recent times, like Facebook, Twitter, LinkedIn, etc. People like to communicate on social websites as compared to direct conversation due to the lack of time, fast communication, minimizing long distance, etc. but more fraud such as fake accounts, cloned attacks, etc. are generated due to growing data on social connecting media. In our proposed approach, we are using the Bernoulli RBM_RF Classifier (BRRC) to detect cloned attacks in connecting media. This model is based on deep learning algorithms and more research is under process but still, there is no such kind of model to provide high accuracy. In this model, we have used multiple algorithms Artificial Neural Networks (ANN), Logistic Regression, Decision Trees, K-Nearest Neighbour Classification, Random Forest, and Bernoulli RBM with extra add-on features of the random forest we have created a Bernoulli pipeline also known as BRRC. Our goal is to establish a clear neural network connection between our target attributes. Finally, we created a restricted Boltzmann machine using a RBM Bernoulli pipeline with additional add-on random forest features after using random forest, where we employed n number of decision trees for classification and provided the same in depth. Our model can extract higher-level features from the given data and helps in the dimensionality Reduction of the input data by learning a compressed representation. Accuracy can be improved by using a big dataset with particular connecting media attributes that are either not currently available or are only sparingly present. We can conclude that Bernoulli Restricted Boltzmann Machine is the best fit and suitable for our model with 93% accuracy. [ABSTRACT FROM AUTHOR]

Since many years ago, walnuts have been extensively available around the world and come in various quality varieties. The proper variety of walnut can be grown in the right area and is vital to human health. This fruit's production is time-consuming and expensive. However, even specialists find it challenging to differentiate distinct kinds since walnut leaves are so similar in color and feel. There aren't many studies on the classification of walnut leaves in the literature, and the most of them were conducted in laboratories. The classification process can now be carried out automatically from leaf photos thanks to technological advancements. The walnut data set was applied to the suggested deep learning model. There aren't many studies on the classification of walnut leaves in the literature, and the most of them were conducted in laboratories. The walnut data set, which consists of 18 different types of 1751 photos, was used to test the suggested deep learning model. The three most successful algorithms among the commonly utilized CNN algorithms in the literature were first selected for the suggested model. From the Vgg16, Vgg19, and AlexNet CNN algorithms, many features were retrieved. Utilizing the Whale Optimization Algorithm (WOA), a new feature set was produced by choosing the top extracted features. KNN is used to categorize this feature set. An accuracy rating of 92.59% was attained as a consequence of the tests. [ABSTRACT FROM AUTHOR]

In the context of India's evolving economy, where agriculture remains a vital yet limited sector, the challenge is to enhance productivity on finite cultivable land. This research addresses this imperative by introducing the Crop Yield Prediction Using Deep Learning (CYPBL) model, leveraging the Bi-Directional Long Short-Term Memory (Bi-LSTM) algorithm. Employing soil health and crop yield data from the Government of India, the CYPBL model is implemented through PySpark for scalability. Featuring 20 LSTM layers with a 12 × 1 input shape, including a bidirectional LSTM layer, the model achieves exceptional accuracy at 99.5 percent on test data. With a focus on real-time data, a batch size of 1 ensures optimal responsiveness. Beyond technological advancements, CYPBL emerges as a groundbreaking soil health monitoring system, bridging the gap between experts and farmers. By empowering farmers with insights into soil conditions, crop suitability, and improvement strategies, this research paves the way for data-driven, responsive agriculture in India and globally, contributing to the pressing issue of global food security. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) deals with the automatic recognition of physical activities and plays a crucial role in healthcare and sports where wearable sensors and intelligent computational techniques are used. We propose a HAR algorithm that uses the smartphones accelerometer data for human activity recognition. In particular, we present a recurrent convolutional neural network-based HAR algorithm that combines a Convolutional Neural Network (CNN) to extract temporal features from the sensor data, a Fuzzy C-Means (FCM) clustering algorithm to cluster the features extracted by the CNN, and a Long Short-Term Memory (LSTM) network to learn the temporal dependencies between the features. We evaluate the proposed methodology on two distinct datasets: the MotionSense dataset and the WISDM dataset. We evaluate the proposed CNN-FCM-LSTM model on the publicly available MotionSense dataset to classify ten activity types: 1) walking upstairs, 2) walking downstairs, 3) jogging, 4) sitting, 5) standing, 6) level ground walking, 7) jumping jacks, 8) brushing teeth, 9) writing, and 10) eating. Next, we evaluate the model's performance on the WISDM dataset to assess its ability to generalize to unseen data. On the MotionSense test dataset, CNN-FCM-LSTM achieves a classification accuracy of 99.69%, a sensitivity of 99.62%, a specificity of 99.63%, and a false positive rate per hour (FPR/h) of 0.37%. Meanwhile, it achieves a classification accuracy of 97.27% on the WISDM dataset. The CNN-FCM-LSTM model's capability to classify a diverse range of activities within a single architecture is noteworthy. The results suggest that the proposed CNN-FCM-LSTM model using smartphone inputs is more accurate, reliable, and robust in detecting and classifying activities than the state-of-the-art models. It should be noted that activity recognition technology has the potential to aid in studying the underpinnings of physical activity, designing more effective training regimens, and simulating the rigors of competition in sports. [ABSTRACT FROM AUTHOR]

For human beings, neck movement will be degraded due to aging, trauma, musculoskeletal disorders, or degenerative diseases. Cervical range of motion (CROM) measurement is one of the popular quantitative neck examinations. Despite radiography is considered as the gold standard, it suffers from invasiveness, radiation exposure, and expensiveness. Recently, vision-based methods have been applied for CROM measurement but achieve large errors and require depth camera. On the other hand, deep neural networks provide good performances on head pose estimation (HPE) from a single image, thus promising for medical CROM measurement. We propose to use CNN networks to extract pyramidal or multi-level image features, which are passed to cross-level attention modules for feature fusion and then to a modified ASPP module and a multi-bin classification/regression module for spatial-channel attention and Euler angle conversion/prediction, respectively. The proposed technique was evaluated on public datasets, such as 300W_LP, AFLW2000, and BIWI, to verify its superior performances (with mean MAE = 3.50°, 3.40°, and 2.31° for different experimental protocols) than state-of-the-art methods. Our pre-trained model was also evaluated with our own collected dataset from hospital for CROM measurement. It also achieved the lowest MAE of 4.58° among other methods and conformed with a medical standard of 5 degrees except the pitch angle (which has a MAE of 5.70°, larger than the standard and the yaw (MAE = 3.60°) and roll angles (MAE = 4.44°)). In general, HPE technique is feasible for CROM measurement and shows its advantages of speed, non-invasiveness, free of anatomical landmark and low cost of operation. [ABSTRACT FROM AUTHOR]

Image super-resolution, a technique for image restoration, has been the subject of extensive research. The challenge lies in converting a low-resolution image to recover its high-resolution information, a problem that researchers have been persistently exploring. Early physical transformation methods often resulted in high-resolution images with significant information loss, and the edges and details were not well recovered.With advancements in hardware technology and mathematics, deep learning methods have been employed for image super-resolution tasks. These range from direct deep learning models, residual channel attention networks, bi-directional suppression networks, to networks with transformer modules, all of which have progressively yielded satisfactory results.In the realm of multi-image super-resolution, the establishment of a multi-image super-resolution dataset has facilitated the evolution from convolution models to transformer models, thereby continuously enhancing the quality of super-resolution. However, it has been observed that neither pure convolution nor pure transformer networks can effectively utilize low-resolution image information.To address this, we propose a novel end-to-end CoT-MISR network. The CoT-MISR network compensates for local and global information by leveraging the strengths of both convolution and transformer techniques. Validation on an equal parameter dataset demonstrates that our CoT-MISR network has achieved the optimal score index. [ABSTRACT FROM AUTHOR]

Sign language serves as an alternative communication mode for those with limitations in hearing and speaking abilities. In India, an estimated population of around 2.7 million people have hearing or speech impairments. Among this population, a significant majority of 98% use sign language as their primary mode of communication. Unfortunately, the limited availability of human interpreters is a considerable obstacle in recognizing and identifying diverse sign languages. To tackle this issue, the present study aims to undertake a thorough examination of various computational methodologies used in various geographical areas for the purpose of categorizing and identifying discrete sign languages. Among the pool of 587 research papers deemed appropriate for qualitative assessment, a total of 95 studies were specifically focused on the categorization and identification of sign language using artificial intelligence-based techniques. The study examines prior research involving deep learning and machine learning methods for a systematic literature review of Sign Language Recognition (SLR). The categorization is made based on language, and the study investigates several facets, including sign type, signing modes, processing techniques, classification methodologies, and evaluation measures. The study reveals that extensive studies were carried out in Chinese, Arabic, and American sign languages. The findings of this review show that among the machine learning techniques, Support Vector Machine (SVM) exhibited higher performance measures, while Convolutional Neural Networks (CNN) exhibited higher performance among the deep learning techniques. [ABSTRACT FROM AUTHOR]

Deep learning-based models have recently shown a strong potential in Underwater Image Enhancement (UIE) that are satisfying and have the right colors and details, but these methods significantly increase the parameters and complexity of the image processing models and therefore cannot be deployed directly to the edge devices. Vision Transformers (ViT) based architectures have recently produced amazing results in many vision tasks such as image classification, super-resolution, and image restoration. In this study, we introduced a lightweight Context-Aware Vision Transformer (CAViT), based on the Mean Head tokenization strategy and uses a self-attention mechanism in a single branch module that is effective at simulating long-distance dependencies and global features. To further improve the image quality we proposed an efficient variant of our model which derived results by applying White Balancing and Gamma Correction methods. We evaluated our model on two standard datasets, i.e., Large-Scale Underwater Image (LSUI) and Underwater Image Enhancement Benchmark Dataset (UIEB), which subsequently contributed towards more generalized results. Overall findings indicate that our real-time UIE model outperforms other Deep Learning based models by reducing the model complexity and improving the image quality (i.e., 0.6 dB PSNR improvement while using only 0.3% parameters and 0.4% float operations). [ABSTRACT FROM AUTHOR]

For the safety and reliability of the system, Remaining Useful Life (RUL) prediction is considered in many industries. The traditional machine learning techniques must provide more feature representation and adaptive feature extraction. Deep learning techniques like Long Short-Term Memory (LSTM) achieved an excellent performance for RUL prediction. However, the LSTM network mainly relies on the past few data, which may only capture some contextual information. This paper proposes a hybrid combination of Convolution Neural Network (CNN) and LSTM (CNN+LSTM) to solve this problem. The proposed hybrid model predicts how long a machine can operate without breaking down. In the proposed work, 1D horizontal and vertical signals of the mechanical bearing are first converted to 2D images using Continuous Wavelet Transform (CWT). These 2D images are applied to CNN for key feature extraction. Ultimately, these key features are applied to the LSTM deep neural network for predicting the RUL of a mechanical bearing. A PRONOSTIA data is utilized to demonstrate the performance of the proposed model and compare the proposed model with other state-of-the-art methods. Experimental results show that our proposed CNN+LSTM-based hybrid model achieved higher accuracy (98%) with better robustness than existing methods. [ABSTRACT FROM AUTHOR]

The generalisability of deep neural network classifiers is emerging as one of the most important challenges of our time. The recent COVID-19 pandemic led to a surge of deep learning publications that proposed novel models for the detection of COVID-19 from chest x-rays (CXRs). However, despite the many outstanding metrics reported, such models have failed to achieve widespread adoption into clinical settings. The significant risk of real-world generalisation failure has repeatedly been cited as one of the most critical concerns, and is a concern that extends into general medical image modelling. In this study, we propose a new dataset protocol and, using this, perform a thorough cross-dataset evaluation of deep neural networks when trained on a small COVID-19 dataset, comparable to those used extensively in recent literature. This allows us to quantify the degree to which these models can generalise when trained on challenging, limited medical datasets. We also introduce a novel occlusion evaluation to quantify model reliance on shortcut features. Our results indicate that models initialised with ImageNet weights then fine-tuned on small COVID-19 datasets, a standard approach in the literature, facilitate the learning of shortcut features, resulting in unreliable, poorly generalising models. In contrast, pre-training on related CXR imagery can stabilise cross-dataset performance. The CXR pre-trained models demonstrated a significantly smaller generalisation drop and reduced feature dependence outwith the lung region, as indicated by our occlusion test. This paper demonstrates the challenging problem of model generalisation, and the need for further research on developing techniques that will produce reliable, generalisable models when learning with limited datasets. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have demonstrated promising accuracy in segmenting concrete cracks under controlled conditions. However, these existing methods usually are challenging in addressing multi-scale patterns or complex scenarios. To address this pervasive issue, a modified U-Net network was established in the current study. The proposed model, namely U-Net-ASPP-CBAM, integrates the convolutional block attention module after a convolution operator to selectively focus on the crack information while disregarding irrelevant background details during feature extraction. Furthermore, U-Net-ASPP-CBAM network replaces a pooling layer using the atrous spatial pyramid pooling module to explore and fuse features across multiple scales, enhancing information capture for the segmentation of small objects. The performance of the proposed model has been validated by a self-built dataset comprising crack images with diverse complex backgrounds. And the segmentation effectiveness is assessed through evaluation indices, including precision, recall, F1 score, pixel accuracy, and mean intersection over union. The results show the proposed U-Net-ASPP-CBAM model outperforms other segmentation models. [ABSTRACT FROM AUTHOR]

Nowadays, the web has emerged as an enormous multimedia data resource. Social media platforms are becoming the mass producers of user-generated multimedia content. Web search engines usually organize media-specific information, such as text, images, video, etc., in specialized data repositories (verticals), providing easy access to multimedia content. Web search engines have become efficient in retrieving data across various distinct verticals. However, users still need help formulating queries to retrieve the relevant multimedia results from verticals. Novice users often issue short-length ambiguous queries due to a lack of domain knowledge or query formulation experience, resulting in the retrieval of irrelevant results. The query formulation itself is a time-consuming process for the users. We presented an end-to-end deep-learning automatic query recommendation approach to address the associated issues. The proposed method autonomously extracts the domain knowledge using pseudo-relevance feedback, transforms it into a unified text-to-text summary, and assists users in generating non-ambiguous and well-balanced query recommendations. The proposed system employs Google's real-time dataset and is compared to the Google search engine. The evaluation consists of empirical and usability perspectives. The empirical evaluation of shorter query formulation and reformulation time obtained 89% accuracy scores in automated query recommendation. The usability testing (N=37) reveals 85.4% usefulness & ease-of-use, and "A" category proposed system usability. [ABSTRACT FROM AUTHOR]

In recent times, network-based applications have rapidly grown in the field of information and communication technology(ICT), which enables individuals and organizations to connect and share their sensitive information seamlessly. The security of these network-based applications is imperative to avoid cyber-attacks during the exchange of sensitive information. The identification of anomalies in network events can be highly challenging due to the complex nature of traffic flows. To solve the challenges, network intrusion detection system (NIDS) technology is used; any network can profit from this system because it can monitor traffic and detect any irregularities. The existing NIDS systems driven by machine learning models do not provide sufficient ability to handle heterogeneous data and realize performance degradation while detecting some types of attacks. Therefore, this paper proposes an innovative meta-heuristic optimization and deep learning-based methodology for improving the performance of NIDS systems. Initially, the raw captured traffic data is fed into the pre-processing phase to attain data standardization and data balancing. Further, an extended Pelican Optimization algorithm (Ex-Pel) is employed to select the set of features from the pre-processed data optimally. Finally, the Self-Attention Assisted Weighted Auto Encoder (SAttn_WAE) is executed to detect the attacks precisely through the set of optimal features. The execution of the proposed methodology is carried out in the Python platform, and performance evaluation is done using accuracy, precision, recall, FAR, and F1-score metrics. The proposed model achieved an accuracy of 99.23%, precision of 99.78%, FAR of 0.67%, recall of 99.13%, and F1-score of 99.32%, which is comparatively better than existing models. [ABSTRACT FROM AUTHOR]

Camouflaged object detection (COD) intends to find concealed objects hidden in the surroundings. COD is challenging for it has to discriminate the minor difference between foreground and background. In most existing methods, convolutional neural network (CNN)-based approaches are proposed to overcome this challenge. However, they have limitations in extracting semantic features of input images and learning global contexts. This study presents a novel Transformer and CNN-based Depth Context Aggregation network (call DCA-Net) for concealed object detection and segmentation. This network uses Swin Transformer as backbone to extract globalized semantic features. Dilated Reception (DR) module is designed to connect the encoder and decoder. A hybrid loss function is used for optimizing the model. In particular, to supplement the intersection over union (IOU) loss, Complementary (C) loss is introduced. By analyzing different metrics, comprehensive comparisons with previous methods are conducted on four public datasets, such as CAMO, CHAMELEON, COD10K, and NC4K. Experimental analysis proves that the proposed DCA-Net achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]

This study develops an active security control strategy for Cyber-Physical Systems (CPSs) that are subject to attacks known as Denial-of-Service (DoS), which can target both channels from the controller to the actuator and from the controller to the sensor. Due to attack cost restrictions, the linked channels are subject to a limit on the number of continuous DoS attacks. A proactive security control method is then developed to combat two-channel DoS attacks, depending on a method for identifying IoT intrusions. Using the CICIDS dataset for attack detection, we examined the effectiveness of the Deep Convolutional Network Model (DCNM), a suggested deep learning model. The addressed CPS can be asymptotically stable against DoS assaults under the security controller's active security control technique without sacrificing control performance. Recent tests and simulations show how effective the security control strategy is active. The proposed model gives better trade-off compared to existing approaches like Deep Belief Networks (DBN), Recurrent Neural Networks (RNN), Support Vector Machines (SVM), Supervised Neural Networks (SNN) and Feed Forward Neural Networks (FNN). The proposed model gives 99.3%, 99.5%, 99.5%, 99.6%, 99%, 98.9%, 99% accuracy with normal attack detection, botnet attack detection, Brute force attack detection, DoS attack detection, Infiltration attack detection, Portscan attack detection and web attack detection respectively. [ABSTRACT FROM AUTHOR]

Many people are affected by lung cancer and it kills a lot of people worldwide. Often times, lung cancer does not have symptoms in the early stage. Abnormal growths called pulmonary nodules may be found in the lungs. Some of the pulmonary nodules may be cancerous. So, identifying pulmonary nodules will help detect lung cancer at an early stage. V-3DResNets based on variants of residual network is proposed to improve the generalization capability of the pulmonary nodule detection system. A U-shaped encoder-decoder is used to effectively extract the features. Residual networks help to reduce the vanishing gradient problem in deep neural networks. A Slice Grouped Non Local (SGNL) module studies the relation among entities across Computed Tomography (CT) slices. The content-aware mechanism of the squeeze and excitation block assigns different weights to the channels and improves the performance of the nodule detection system. The proposed work is analyzed using the PN9 dataset that includes 8,798 CT Scans with nine types of pulmonary nodules which attained a Competition Performance metric (CPM) of 65.51%. [ABSTRACT FROM AUTHOR]

For Deepfake detection, many existing works use the cross-entropy loss to enforce the classifier network to learn the mapping relationship from the RGB domain to the class domain, lacking an explicit constraint to guide the feature extraction network to learn discriminative features from an input image. This constrains the feature representation capability to expose deepfake. In this work, we analyze the feature extraction network in terms of both difference and similarity capabilities and propose a new constraint called similarity loss (SL) to improve the detection performance of the convolutional neural network (CNN) based detector. Moreover, according to the experimental results of the SL on data augmentation effectiveness, we propose a simple yet efficient framework, which is called as efficient similarity representation learning (ESRL), for deepfake detection. Extensive experiments on three public datasets (namely FF++, DFDC, and Celeb-DF) show that the feature extraction network trained with the help of SL can map forged faces and real faces to different feature embedding and map the same type of forged faces to similar feature embedding. [ABSTRACT FROM AUTHOR]

Airway diseases cause significant challenges while diagnosing it accurately as well as timely. In current years, the combination of deep learning techniques with Explainable Artificial Intelligence (XAI), has emerged as a promising possibility to enhance the understanding as well as interpretability of complex medical data which are associated with these conditions. The study explores the usage of advanced convolutional neural networks (CNNs) on large-scale of Chest X-ray or CT scan image datasets and their application in the domain of medical imaging to detect as well as classify airway diseases such as pneumoconiosis, pulmonary embolism, Covid-19, tuberculosis, and Lung cancer. The visualization of the images have been enhanced by applying sharpening techniques and are later subsequently used to train various deep learning models which include InceptionResNetV2, MobileNet, Xception, ResNet152, EfficientNetV2M, and DenseNet169. Further, various parameters have been used for the evaluation of the performance of these models in determining the most optimal choice. During training the model, it has been found that the highest accuracy, precision, recall, and F1 score has been computed by InceptionResNetV2 with 99.15%, 98% and 99% (both) respectively on a loss of 0.0275. Besides this, a graphical user interface (GUI) has been also developed to improvise the interaction between the AI based model and end users. The GUI is based on the theory of XAI which after predicting the diseases provides in detail explanation of treatment as well as preventive measures of the disease. The motto of the research is to escalate the knowledge of deep learning techniques for various lung based issues as well as to enlighten with the significance of XAI in promoting interpretability as well as transparency. The findings of the research implies towards the advancement of decision support systems at various medical sectors to promote effective as well as personalized interventions in the realm of pulmonology. [ABSTRACT FROM AUTHOR]

The major goal of this research is to develop a Deep Learning (DL) based automatic identification and classification of white blood cells (WBCs) with high accuracy and efficiency. The first phase of research is pre-processing and is accomplished by the Improved Median Wiener Filter (IMWF), which effectively eliminates the noises. The image is resized into a standard image size before filtering. The segmentation process takes place using Color Balancing Binary Threshold (CBBT) algorithm to divide the WBCs and another non-relevant background to improve the classification performance. The features like shape, texture and color of the WBCs are extracted from the segmented images. Finally, the classification takes place, and this is processed by a fine optimal deep convolution residual network (Fine Optimal DCRNet). In addition, the bionic model is introduced to improve classification accuracy. The dataset used in this research is BCCD and LISC datasets. The performance of the proposed model is validated using existing methods of Support Vector Machine (SVM), K-Nearest Neighbor (KNN), VGG-16, VGG-19, ResNet-50, DensetNet-121, DensetNet-169, Inception-V3, InceptionResNet-V2, Xception, MobileNet-224, Mobile NasNet, Tree, Naive Bayes, Ensemble active contour model, k-means clustering and handcraft and deep learned features-scale-invariant feature transform (HCDL-SIFT) in terms of Accuracy, Precision, Recall, Specificity, F-score, Relative Distance Error (RDE), Over-Segmentation Rate (OSR), Under-Segmentation Rate (USR) and Overall Error Rate (OER). For the LISC dataset, the detection model attains an outcome of 99%, 98%, 98%, 99%, 98%, 1.143, 0.0125, 0.056 and 0.125, respectively. For the BCCD dataset, apart from RDE, OSR, USR and OER metrics, the performance is evaluated as 98%, 96%, 98%, 99% and 97%. [ABSTRACT FROM AUTHOR]

Over 50% of India's population relies on crop growing, making it the foundation of the country's economy. Differences in weather, temperature, and other environmental factors are now a significant threat to the continued success of agriculture. This makes it difficult to predict the crop yield appropriately. Hence, computer-based models are believed to be more predictive in analyzing crop yields. Machine learning (ML) and deep learning (DL) models play a vital role as the supporting tool for Crop Yield Prediction (CYP), which includes assisting decisions on which crops to plant and the measures to be taken for the growth of crops. This paper aims to propose a deep ensemble model for predicting crop yields more accurately. The steps followed are: Improved Log scaling-based pre-processing of data. Then, from the preprocessed data, the input features like higher-order features, Enhanced entropy-based features and correlation-based features are derived. Further, the optimal features are elected using the Integrated Bird Swarm and BOA (IBS-BOA) algorithm. Based on the selected features, prediction is done by the Deep Ensemble Model (DMO, Bi-GRU and CNN). Also, one of the models of Ensemble classifiers, CNN is trained by the IBS-BOA algorithm. Finally, the performance of the proposed DEC-IBSBOA is evaluated concerning varied error factors namely, MEAE, MAE, MALE, MAPE, ME and MSE. For the suggested system minimum error is obtained for MAE (~ 1.0) when compared to the other existing methods such as Bi-GRU, DMO, CNN, PLMDC, SVM, LSTM, SSTNN, EC + WOA, EC + BES, EC + BOA, EC + BMO and EC + BSA. [ABSTRACT FROM AUTHOR]

Speech emotion recognition holds significant importance as it enables machines to understand and respond to human emotions, enhancing human-computer interaction and personalized experiences. Accurate identification and interpretation of emotional states from speech signals enable various benefits, including enhanced personalized experiences, effective monitoring of mental health, and improved human-computer interfaces. However, recognizing emotions from speech is a difficult task primarily because there exists a significant disparity between acoustic features and human emotions. Both vocal cues and spoken words play significant roles in determining a person's emotional state. Therefore, in order to accurately identify human emotions from speech, it is essential to extract distinct and meaningful acoustic features. In this paper, we propose a novel approach to infer human emotional states. Human emotional state recognition has a wide range of applications ranging from customer service to mental health. Our proposed approach extracts a set of features from the speech signals, and employs a framework known as deep stride convolutional neural network using bi-directional LSTM. Our proposed model achieved a high accuracy of 95% which is almost 20% higher when compared to the state of the art on the RAVDESS dataset, while also minimizing the loss. [ABSTRACT FROM AUTHOR]

Brain–computer interfacing (BCI) research, fueled by deep learning, integrates insights from diverse domains. A notable focus is on steady-state visual evoked potential (SSVEP) in BCI applications, requiring in-depth assessment through deep learning. EEG research frequently employs SSVEPs, which are regarded as normal brain responses to visual stimuli, particularly in investigations of visual perception and attention. This paper tries to give an in-depth analysis of the implications of deep learning for SSVEP-adapted BCI. A systematic search across four stable databases (Web of Science, PubMed, ScienceDirect, and IEEE) was developed to assemble a vast reservoir of relevant theoretical and scientific knowledge. A comprehensive search yielded 177 papers that appeared between 2010 and 2023. Thence a strict screening method from predetermined inclusion criteria finally generated 39 records. These selected works were the basis of the study, presenting alternate views, obstacles, limitations and interesting ideas. By providing a systematic presentation of the material, it has made a key scholarly contribution. It focuses on the technical aspects of SSVEP-based BCI, EEG technologies and complex applications of deep learning technology in these areas. The study delivers more penetrating reporting on the latest deep learning pattern recognition techniques than its predecessors, together with progress in data acquisition and recording means suitable for SSVEP-based BCI devices. Especially in the realms of deep learning technology orchestration, pattern recognition techniques, and EEG data collection, it has effectively closed four important research gaps. To increase the accessibility of this critical material, the results of the study take the form of easy-to-read tables just generated. Applying deep learning techniques in SSVEP-based BCI applications, as the research shows, also has its downsides. The study concludes that a radical framework will be presented which, includes intelligent decision-making tools for evaluation and benchmarking. Rather than just finding a comparable or similar analogy, this framework is intended to help guide future research and pragmatic applications, and to determine which SSVEP-based BCI applications have succeeded at responsibility for what they set out with. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has significantly reshaped numerous fields and applications, fundamentally altering how we tackle a variety of challenges. Areas such as natural language processing (NLP), computer vision, healthcare, network security, wide-area surveillance, and precision agriculture have leveraged the merits of the deep learning era. Particularly, deep learning has significantly improved the analysis of remote sensing images, with a continuous increase in the number of researchers and contributions to the field. The high impact of deep learning development is complemented by rapid advancements and the availability of data from a variety of sensors, including high-resolution RGB, thermal, LiDAR, and multi-/hyperspectral cameras, as well as emerging sensing platforms such as satellites and aerial vehicles that can be captured by multi-temporal, multi-sensor, and sensing devices with a wider view. This study aims to present an extensive survey that encapsulates widely used deep learning strategies for tackling image classification challenges in remote sensing. It encompasses an exploration of remote sensing imaging platforms, sensor varieties, practical applications, and prospective developments in the field. [ABSTRACT FROM AUTHOR]

Timely estimation of earthquake magnitude plays a crucial role in the early warning systems for earthquakes. Despite the inherent danger associated with earthquake energy, earthquake research necessitates extensive parameter estimation and predictive techniques to account for uncertain trends in earthquake waveforms when determining earthquake magnitudes using a single station. This study introduces an effective solution to tackle the issue through the automatic magnitude deep network (AMagDN) model. The proposed model includes long short-term memory (LSTM), a bidirectional LSTM, an autocorrelation attention mechanism, and a machine learning block that can capture detailed information from the seismic waveform recorded during an earthquake. The unique feature of this model is the use of multivariate time series waveforms derived from recorded accelerograms specifically tailored to their energy significance with magnitude and seven fusion tabular parameters involving source and geospatial features. The proposed model's training, validation and testing are done using independent 15014, 1287 and 3448 records maintained by the Kyoshin network, Japan, for moderate to great impact earthquakes between 5.5 and 8.0 ( M JMA ). A comparative study shows that the proposed model outperforms recent state-of-the-art models and common linear relations, reducing mean absolute prediction error by 40% from the second-best model. The multi-stations data are also used for successfully forecasting the magnitudes of two significant earthquakes of 7.7 and 7.3 magnitude ( M JMA ) using the proposed model. The reliable prediction capabilities of the proposed model for both single and multi-station data clearly demonstrate its utility in reducing earthquake hazards. [ABSTRACT FROM AUTHOR]

The demand for accurate health status assessment of bearings in rotating electrical machines is rising. However, traditional fault diagnosis methods based on deep learning are not effective in efficiently and intelligently determining the health condition of the bearings and also requires large memory, hence constraining their use in low-cost microcontrollers. In this work, combination of short time Fourier transform (STFT) with Ostu's threshold method and MobileNet-V2 with U-Net (MV2UNet) is proposed for rolling bearing fault health status. The proposed method obtains the STFT images of the raw vibration signals from the laboratory experimental setup. Then the Ostu's threshold method is used to make the labels for STFT images. Finally, the proposed method is trained with these labelled images to detect the health status of each bearing fault. The proposed model achieved the Dice coefficient is 0.9834 and the intersection over union is 0.9479. The main advantage of the proposed model has low memory requirements, which makes it well-suited for implementation in affordable hardware devices like microcontrollers. Finally, the proposed method result is compared with U-Net, DeepLabV3+ with MobileNet-V2 and DeepLabV3+ with ResNet-50. [ABSTRACT FROM AUTHOR]