Depression is a psychological illness characterized by the recurrent occurrence of a negative emotional state. The common cause of the rise in suicide cases that appear globally is major depressive disorder (MDD). Therefore, proper diagnosis and therapy are necessary to lessen the impact of depression. MDD is a serious and common ailment that causes functional frailty. However, its exact symptoms remain unknown. Therefore, the task of manually detecting MDD is challenging and subjective. Although electroencephalogram (EEG) signals have demonstrated potential in diagnosis, we still need to enhance their accuracy, clinical value, and efficiency. This study employs a unique method known as Blended Multilevel Features with Constraint Fusion Network (BMFCNet) to identify MDD. The residual-inception (RI) module of the BMFCNet extracts the most pertinent and discriminative characteristics from the high-level (HL) and low-level (LL) features. To combine improved LL and HL traits, a constraint fusion technique is introduced to weigh and fuse the LL and HL features adaptively. Furthermore, we demonstrate the effectiveness of our method by analogizing it with sixteen state-of-the-art (SOTA) methodologies utilizing two benchmark datasets.

Inverse kinematics, crucial in robotics, involves computing joint configurations to achieve specific end-effector positions and orientations. This task is particularly complex for six-degree-of-freedom (six-DoF) anthropomorphic robots due to complicated mathematical equations, nonlinear behaviours, multiple valid solutions, physical constraints, non-generalizability and computational demands. The primary contribution of this work is to address the complex inverse kinematics problem for six-DoF anthropomorphic robots through the systematic exploration of AI models. This study involves rigorous evaluation and Bayesian optimization for hyperparameter tuning to identify the optimal regressor, balancing both accuracy and computational efficiency. Utilizing five-fold cross-validation on a publicly available dataset, the selected model demonstrates exceptional performance in predicting six joint angles for end effector configuration, yielding an average mean square error of 1.934 × 10−3 to 3.522 × 10−3. Its computational efficiency, with a prediction time of approximately 1.25 ms per sample, makes it a practical choice. Additionally, the study employs Explainable AI, using SHAP (SHapley Additive exPlanations) analysis to gain an understanding of feature importance. This analysis not only enhances model interpretability but also reaffirms the efficacy in this challenging multi-input multi-output predictive task. This research advances state-of-the-art models and neural networks by prioritizing computational efficiency alongside accuracy—a critical yet often overlooked factor. Pioneering a significant advancement in anthropomorphic robot kinematics, it balances accuracy and efficiency, offering practical robotic automation solutions.

Schizophrenia (SCZ) is a severe neurological and physiological syndrome that perverts a patient’s perception of reality. SCZ exhibits several symptoms, including hallucinations, delusions, aberrant behavior, and thinking. It affects their professional, academic, personal, and social lives. Neurologists use a variety of verbal and visual tests to determine SCZ. However, these methods are laborious, time-consuming, superficial, and vulnerable to mistakes. Therefore, it is necessary to create an automated model for SCZ detection. Convolutional neural networks have swiftly established themselves in the field of mental health care due to the growth of deep learning in recent decades. Electroencephalogram (EEG) data records the variations in the neural dynamics of human memory. Using EEG data, this study proposes an automatic SCZ detection method using separable convolution attention network (SCZ-SCAN). The proposed network employs depth-wise separable convolution and attention networks on high-level and low-level to aggregate characteristics of 2-D scalogram images acquired from the continuous wavelet transform. The depth-wise separable convolutions help to create a lightweight framework, while attention techniques concentrate on significant features and reduce futile computations by removing the transmission of irrelevant features. The proposed approach has an average classification accuracy of 99% and 95% on the IBIB-PAN and EEG data from the basic sensory task in SZ dataset. Moreover, statistical hypothesis testing is performed using Wilcoxon’s Rank-Sum test to signify the model performance and it proves that SCZ-SCAN is statistically efficient to nine cutting-edge methods.

Experimental results show that the PSFAN statistically defeats 11 contemporary methods, proving its effectiveness for medical industrial applications.

Environmental microbes are certainly present in our surroundings since they are essential to the growth and survival of human advancement. The detailed analysis of environmental microorganisms (EMs) is very important to recognize, understand and make use of microbes as well and prevent damage. Extracting the discriminatory features from a limited-size dataset is very challenging for a deep learning model and a pure transformer-based network cannot achieve good classification results on a limited-size dataset due to the lack of muti-scale features. In this study, a novel vision transformer-based deep neural network is proposed by integrating the transformer with CNN for the classification of EM using microscopic images. The proposed network EMViT-Net has three main modules: a transformer module, a CNN module and a multilayer perceptron module. The transformer model extracted multiscale features to generate more discriminatory information from the images. A new separable convolutional parameter-sharing attention (SCPSA) block is integrated with the CNN module in the core of EMViT-Net, which makes the model robust to capture the local and global features, and simultaneously reduces the computational complexity of the model. The data augmentation is performed to introduce the variability in the dataset and counter the problem of overfitting and data imbalance. After extensive experiments and detailed analysis, it has been determined that the proposed model EMViT-Net outperforms the other existing methods and achieves state-of-the-art results with an accuracy of 71.17% which proves the effectiveness of the model for the classification of environmental microbes.

Facial expression analysis plays a crucial role in various fields, such as affective computing, marketing, and clinical evaluation. Despite numerous advances, research on facial expression recognition (FER) has recently been proceeding from confined lab circumstances to in-the-wild environments. FER is still an arduous and demanding problem due to occlusion and pose changes, intra-class and intensity variations caused by illumination, and insufficient training data. Most state-of-the-art approaches use entire face for FER. However, the past studies on psychology and physiology reveals that mouth and eyes reflect the variations of various facial expressions, which are closely related to the manifestation of emotion. A novel method is proposed in this study to address some of the issues mentioned above. Firstly, modified homomorphic filtering is employed to normalize the illumination, then the normalized face image is cropped into five local regions to emphasize expression-specific characteristics. Finally, a unique blended feature attention network (BFAN) is designed for FER. BFAN consists of both residual dilated multi-scale feature extraction module and spatial and channel-wise attention modules. These modules help to extract the most relevant and discriminative features from the high-level and low-level features. Then, both feature maps are integrated and passed on to the dense layers followed by a softmax layer to compute probability scores. Finally, the Choquet fuzzy integral is applied to the computed probability scores to get the final outcome. The superiority of the proposed method is exemplified by comparing it with eighteen existing approaches on seven benchmark datasets.

Content-based medical image retrieval (CBMIR) systems can assist and help doctors and radiologists in reliable diagnosis by retrieving relevant medical cases from past cases that share similarities with the current case. Therefore, there is a need for improved retrieval accuracy in CBMIR systems. Retrieving similar Brain Tumor magnetic resonance imaging (MRI) slices from the same class as the query is inherently challenging. For different types of tumors, there is no class-specific structure, size or shape. Further, MRIs being present in multiple views increase discrepancy in interview retrieval. This leads to high inter-class similarity but at the same time high intra-class variations. Skewed data quantities for Brain Tumor types like Meningioma further add to another challenge. It is necessary to formulate rich and generic MRI representations to address these issues. Toward the same, it is essential to model spatial contexts on a multi-scale across the tumor-affected regions and enhances the feature representational learning by extracting generic features. Hence, we propose a Weight Initialization Framework with Densely Connected Networks to improve generalization for Brain Tumor MRI retrieval. The proposed framework uplifts DenseNet-based models for feature extraction as they incorporate feature reuse and feature learning in a multi-scale manner. Further, a weight Initialization Framework (WIF) is used for improvising the representational learning. Specifically, WIF initializes weights of the DenseNet model by transfer learning-based adaptation, which then involves freezing the initial few layers. The freezing step ensures rich low-level features, even for long-tailed classes like Meningioma, while the remaining trainable layers are fine-tuned to incorporate domain-inherent feature learning. The proposed approach outperforms state-of-the-art by a margin of 1.70% and 1.69% on standard mAP and p@10, respectively. Concretely, when DenseNet and WIF are jointly employed, a stark increment in performance for the Meningioma class is observed, suggesting the generalizability of the framework.

Visually impaired people (VIPs) encounter various challenges in their daily lives, and there is a need for portable, user-friendly device for real-time assistance to give them guidance regarding their surroundings. This article presents an artificial-intelligence-based innovative wearable assistive device—artificial intelligence (AI)-SenseVision—to analyze visual and sensory information about the objects and obstacles present in the scene to perceive the surrounding environment. The device is a complete amalgamation of sensor and computer-vision-based technologies that generate auditory information with the name of identified objects or audio warnings for detected obstacles. The performance of the trained deep-learning model is rigorously tested in complex and real-life scenarios using various statistical parameters for experimental validation. Moreover, the trained deep-learning models have been integrated into a low-cost single-board processor to make a standalone cost-effective device. All data processing is done within an optimized single hardware setup, and the user can easily access different modes, such as indoor and outdoor mode, while also enabling object counting in observed scenes. The proposed system has low-cost sensors, multiple operational modes, easy integration, and small volume, making this assistive device helpful for VIPs for independent navigation and collision prevention.

This paper presents PACE-Net (Progressive Attention and Convolutional Embedding Network), a novel deep learning architecture designed for fine-grained classification of wall surface defects. Accurately identifying subtle wall surface defects is critical for structural maintenance, especially across varied materials, aging conditions, and environments; limited computational resources further complicate this task. This work proposes an efficient deep learning architecture that balances precision and computational cost for real-world applications. PACE-Net combines progressive attention, shifted depth-wise convolutions, and dynamic patch merging to capture both global context and fine detail for accurate defect recognition. A multi-stream fusion framework dynamically integrates complementary features from attention, convolutional, and residual streams. This adaptive fusion boosts the robustness of the model in distinguishing six defect categories as well as normal surfaces under varying conditions. The model achieves 98.04% accuracy on a diverse surface defect dataset, with only 161 k parameters and 16.07  ms inference latency. Grad-CAM visualizations support interpretable defect localization for deployment in real-world inspections across diverse materials, structural ages, and lighting conditions. Grad-CAM-based localization achieved a mean IoU of 0.8210, while Monte Carlo dropout-based uncertainty analysis confirmed high prediction reliability under variable lighting and viewpoint conditions. The combination of progressive attention, shifted convolutions, dynamic patch merging, and adaptive multi-stream fusion establishes PACE-Net2 as an efficient and powerful solution for real-time infrastructure inspection, enabling high-precision defect classification across common construction materials and surface types.

Machine learning (ML) and artificial intelligence have emerged as essential tools in numerous fields in the current century. In this context, the role of ML in predicting the performance parameters for energy storage devices has been explored which has investigated the potential of ML to enhance the performance of Mo2CTx MXene based supercapacitors significantly. As an initial investigation, data obtained from electrochemical studies (Cyclic Voltammetry (CV), and Galvanostatic Charge Discharge (GCD) is utilized for predictive analysis. Various ML models, are trained and applied to the prepared datasets with input paramters (pH, mass loading and scan rate for CV and current density for GCD) to predict the output in terms of specific capacitance. Various trials of experiments are performed for building the optimal model for the material and the predicted values has provided promising results that aligns well with the experimental data. Utilizing a suite of ML algorithms, including ANN, SVR, and RF, we are aiming to precisely predict and compare the performance of the CV and GCD studies and subsequently optimize key performance indicators.

Image captioning, which generates natural language descriptions for images, has gained significant attention. However, existing models typically separate factual and stylized (romantic or humorous) outputs, often encountering out-of-vocabulary and repetition issues. This work introduces a Unified Multi-Head Attention Caption Summarization Transformer (CapSumT) framework, integrating factual captions (via MAA-FIC) and stylized captions (via SF-Bi-ALSTM for romance and humor). By summarizing both factual and stylistic descriptions, CapSumT produces coherent, style-rich captions. Also, transformer summarizes different linguistic styles efficiently by incorporating proposed word embedding fastText with Attention Word Embedding (fTA-WE) and pointer-generator network with coverage mechanism concept to solve the out-of-vocabulary issues and repetition problem. Extensive experiments are conducted on Flickr8K and a subset of FlickrStyle10K with supporting ablation studies to prove the efficiency and efficacy of the --CapSumT. Code is available at: https://github.com/dhruvsharma09/UnMA-CapSumT.git.

Tuberculosis (TB), caused by Mycobacterium tuberculosis, remains a major global health concern, especially due to multi-drug resistance. Resistance often arises from single nucleotide mutations in drug-target genes, making early prediction vital for effective treatment. Genomic sequencing enables resistance profiling, but accurate prediction requires advanced computational models. This study presents RGTFormer, a novel deep learning model combining a categorical gated transformer with a Relational Graph Convolutional Network (RGCN), to predict whether mutations confer resistance to first-line anti-TB drugs. It utilizes both sequence and structural features from mutations across six key resistance genes. The RGCN captures dependencies between mutations, while the transformer learns complex feature interactions. Evaluated via 10-fold cross-validation and an independent test set, RGTFormer achieved 98.67 % test accuracy and 97.15 % cross-validation accuracy, outperforming traditional machine learning and deep learning baselines. Ablation studies confirmed that the integration of RGCN with gated attention significantly enhances performance. RGTFormer provides a robust, interpretable, and efficient framework for mutation-driven drug resistance prediction in TB. It holds promise for supporting personalized treatment strategies and optimizing drug selection for resistant strains by providing biologically interpretable resistance predictions relevant to clinical decision-making.

Nowadays, researchers use vision-based measurement tools to record, detect, and monitor an atmospheric phenomenon called haze. It impedes the proper functioning of many outdoor industrial systems, such as autonomous driving, surveillance, satellite imagery, and so on. Conventional visibility restoration methods cannot accurately recover image quality due to inaccurate estimations of haze thickness and the presence of color-cast effects. Deep neural networks are evolving due to their ability to directly dehaze images from hazy scenes. Therefore, a unique attention-based end-to-end dehazing network named oval-net has been proposed in this study to restore clear images from its counterpart without employing the atmospheric scattering model. The oval-net is an encoder–decoder architecture that uses spatial and channel attention at each stage to focus on dominant and significant information while avoiding the transmission of irrelevant information from the encoder to the decoder, allowing quicker convergence. The proposed approach outperforms seven state-of-the-art algorithms in quantitative and qualitative assessments of a variety of synthetic and real-world hazy images, proving its effectiveness for vision-based industrial systems.

Predicting drug target binding affinity has huge relevance in Modern drug discovery and drug repositioning processes which assist doctors to come up with new drugs or even use the existing drugs for new target proteins. In silico models, using advanced deep learning techniques could further assist these prediction tasks by providing most prominent drug target pairs. Considering these factors, a deep learning based algorithmic framework is developed in this study to support drug target interaction prediction. The proposed SeqDPI model extract the relevant drug and protein features from the one dimensional Sequential representation of the dataset considered using optimized CNN networks that deploy convolutions on varying length of amino acid subsequence's to capture hidden pattern, the convolved drug- protein features obtained are then used as an input to L2 penalized feed forward neural network which matches the local residue patterns in protein classes with molecular fingerprints of drugs to predict the binding strength for all drug target pairs. The proposed model reduces the convolution strain typically encountered in existing in silico models that utilize complex 3D structures of drug protein datasets. The result shows that the SeqDPI model achieves a mean square error MSE of (0.167) across cross validation folds, outperforming baseline models such as KronRLS (0.406), Simboost (0.226), and DeepPS (0.214). Additionally, SeqDPI attains a high CI score of 0.9114 on the benchmark KIBA dataset, demonstrating its statistical significance and computational efficiency compared to existing methods. This gives the relevance and effectiveness of SeqDPI model in accurately predicting binding affinities while working with simpler one-dimensional data, making it a robust and computationally cost-effective solution for drug-target interaction prediction.

Breast cancer remains a leading cause of female mortality worldwide, exacerbated by limited awareness, inadequate screening resources, and treatment options. Accurate and early diagnosis is crucial for improving survival rates and effective treatment.

Objectives: This study aims to develop an innovative artificial intelligence (AI) based model for predicting breast cancer and its various histopathological grades by integrating multiple biomarkers and subject age, thereby enhancing diagnostic accuracy and prognostication.

Methods: A novel ensemble-based machine learning (ML) framework has been introduced that integrates three distinct biomarkers—beta-human chorionic gonadotropin (β-hCG), Programmed Cell Death Ligand 1 (PD-L1), and alpha-fetoprotein (AFP)—alongside subject age. Hyperparameter optimization was performed using the Particle Swarm Optimization (PSO) algorithm, and minority oversampling techniques were employed to mitigate overfitting. The model's performance was validated through rigorous five-fold cross-validation.

Results: The proposed model demonstrated superior performance, achieving a 97.93% accuracy and a 98.06% F1-score on meticulously labeled test data across diverse age groups. Comparative analysis showed that the model outperforms state-of-the-art approaches, highlighting its robustness and generalizability.

Conclusion: By providing a comprehensive analysis of multiple biomarkers and effectively predicting tumor grades, this study offers a significant advancement in breast cancer screening, particularly in regions with limited medical resources. The proposed framework has the potential to reduce breast cancer mortality rates and improve early intervention and personalized treatment strategies.