Protein-protein interaction (PPI) network analysis holds significant promise for cancer diagnosis and drug target identification. This paper introduces a novel random walk-based method called essential cancer protein identification using graph-based random walk with restart (EPI-GBRWR) to address this gap. This proposed method incorporates local and global topological features of proteins, enhancing the accuracy of essential protein identification in PPI networks. Starting with meticulous preprocessing of cancer gene datasets from NCBI, including breast, lung, colorectal, and ovarian cancers, and identifying a core set of common genes. The proposed method constructs PPI networks to capture complex protein interactions from these common cancer genes. Topological analysis, including a centrality measures matrix, is generated to perform the analysis to identify essential nodes. The study revealed that 40 essential proteins among breast, colorectal, lung and ovarian cancer showcase the potency of integrative methodologies in unravelling cancer complexity, signalling a transformative era in cancer research and treatment. The strength of the findings from the study has direct clinical relevance in cancer diseases. It contributes to the field of precision medicine to guide personalized treatment strategies.

Mental health issues such as stress, depression, and anxiety have risen notably in recent years, particularly among young adults and working professionals. Conventional diagnosis often depends on self-reporting and interviews, which can be delayed due to stigma and limited access to care. This work introduces a multimodal machine learning framework that integrates text, speech, and behavioral signals for early detection of mental health patterns. Language cues are analyzed using NLP techniques, acoustic features are captured through CNN-based speech models, and behavioral interactions provide additional context. Evaluations on DAIC-WOZ, RAVDESS, and PHQ-9-annotated data demonstrate that attention-based multimodal fusion outperforms unimodal approaches while maintaining model transparency through interpretability tools.

The stock market is one of the pillars of the international financial system, which has a significant impact on the stability of the economy as a whole and on the performance of individual investors. However, stock price forecasting is notoriously hard, hidden by volatility and noisy data, which prevents model accuracy. To overcome these challenges, we propose, in this research, to use a new hybrid model: PCA-SVR-PSO. Initially the data is preprocessed by the use of Principal Component Analysis (PCA): redundant variables are eliminated and computation is made more straightforward. At the core of it all, Support Vector Regression or SVR solves the problem of nonlinear relation and delivers a high level of forecast accuracy. Finally, PSO is used for optimization of hyper parameters to extract the maximum possible performance. The proposed model is applied for predicting the stock prices with the help of a comprehensive data set of 3543 records, obtained from Bombay Stock Exchange (BSE) over a time span of two decades (2003 to 2023). The experimental results show that there is a significant improvement in the forecast accuracy compared to the current models, proving the effectiveness of the proposed framework. This approach allows individual investors to make informed decisions and contributes to the advancement of theoretical knowledge about stock market behavior, which results in powerful financial analytics.

Agriculture supports food security by producing the crops and livestock needed to feed the population. It provide employment to a large share of the population, especially in rural areas. This work present a Hybrid Quatnum integrated with CNN model compare with Hybrid CNN-Transformer model for classify soil image. Then suggest best corp with fertilizer according to predicted soil type. There used soil type are Alluvial, Black, Clayey, Red and Sandy. There evaluate accuracy, confusion matrix, classification report and mismatch detection of both model to find best model. Among them the HQCNN model achieved 94% training accuracy with 92% validation accuracy and also 93% test accuracy. There used a excel dataset including Urea, DAP, Potash, and SSP. Developed a friendly web application for farmer to get advantage of this proposed work.

Design Science Research Process (DSRP) suggests an upbeat approach that helps researchers who require recommendation to carry out research and science in information systems (IS). It has developed a conceptual framework for how DSR in IS should proceed. However, despite the expansion of educational systems, scholars don't pay attention to this technique. This paper provides guidance for methodological approach on DSRP for developing hybrid recommender prototype in e-learning. In terms of technology exploitation and accomplishment of DSRP-relied procedure in e-learning, this tactic serves as fundamental building blocks for system. Six junctures of DSRP are modified by creating a prototype for an ingenious e-learning recommendation system that will help researchers in IS. DSRP relied elements were effective in identifying frameworks for ML, clustering, collaborative filtering and finding similarities among hybrid procedures.

Cancer is one of the most prevalent diseases worldwide. Its extreme heterogeneity and complexity make it a challenging subject of study. The use of ‘omics’ technologies, such as genomics, proteomics, transcriptomics, and metabolomics, has revolutionized the understanding of cancer. By integrating data from these ‘omics’ technologies and conducting comprehensive analyses, researchers can gain a more comprehensive understanding of the molecular basis of cancer. This knowledge can lead to the essential cancer protein identification for early detection, prognosis, and the development of targeted therapies. Understanding cancer at the molecular level is crucial, as it allows for the development of targeted therapies and personalized treatment strategies. This book chapter describes a comprehensive overview of cancer protein identification and the application of the PPI network in cancer research. The comprehensive emphasis on PPI network topology fundamentals and PPI network biology-based approaches in cancer research is indeed essential. PPI network topology helps researchers identify key nodes that play critical roles in cancer disease development. The network biology approach involves integrating data from various high-throughput omics technologies, such as genomics, proteomics, transcriptomics, and metabolomics, into a single conceptual framework. Network biology-based approaches uncover the intricate relationships between genes, proteins, and other biomolecules involved in cancer development. Exploring the central role of PPI networks played as a biological network model. These PPI networks intricately map the interactions between proteins, unraveling the complexity of cellular processes and signaling pathways. Understanding the critical significance of protein interactions lays the foundation for their application in cancer diagnosis. The role of PPI network in cancer disease diagnosis offers insights into the evolving landscape of cancer diagnosis and precision medicine, highlighting the potential of PPI networks to revolutionize early detection, patient stratification, and personalized therapeutic interventions in the fight against cancer. Furthermore, we address the challenges and future directions in harnessing PPI networks for enhanced cancer disease diagnosis, underscoring their importance in the pursuit of more precise, effective, and timely diagnostic strategies.

Traditional healthcare systems frequently become overcrowded and unable to provide timely treatment due to the continual rise in patient numbers caused by the rapid global population growth. Digital technology integration, and the Internet of Things (IoT) in particular, has the ability to revolutionise healthcare by offering up the opportunity to the establishment of smart healthcare systems. Patients, no matter where they live, will have better access to healthcare systems, which allow for remote monitoring, real-time tracking, and less reliance on in-person hospital visits. But there are a lot of challenges to overcome when putting these systems into action. For example, there are concerns about the security of sensitive medical data, vulnerabilities in inexpensive smart devices, and centralized IoT designs that are prone to single points of failure. Furthermore, high data processing demands are also introduced by the exponential rise of IoT devices. To address these issues, we proposed a unique Blockchain-Edge-IoT framework called Smart Scalable Medical Infrastructure (SSMI) for the establishment of smart healthcare systems. To reduce the load on cloud servers and data processing times, SSMI uses edge computing to handle patient data close to its source, making it scalable, secure, immutable, and decentralised. Smart contracts are included in the architecture to facilitate the enforcement of privacy policies and the establishment of conditional access for untrusted parties. Additionally, researchers have implemented a Device Monitor to regulate and track inexpensive and vulnerable smart gadgets. The experimental results illustrate that the proposed framework is more efficient in terms of processing latency, data throughput, and security resilience than the existing healthcare models.

This study introduces a Deep learning framework of DenseNet201 for multiclass histopathological classification of bladder tissue into four classes: High-Grade Cancer (HGC), Low-Grade Cancer (LGC), Normal Stromal Tissue (NST), and Normal Transitional Layer (NTL). A total of 1,754 histopathological images were preprocessed by normalization, resizing, and noise reduction for consistency and high data quality. The dataset was divided into training, validation, and test data in a ratio of 80:10:10, and the DenseNet201 architecture - which was pre-trained on ImageNet - was finetuned using the Adam optimizer and binary cross-entropy loss for 20 epochs. The model had an overall accuracy of 89%, which showed good precision, recall, and F1-scores, especially in the HGC and NST classes. Confusion matrix analysis showed small misclassification between HGC and LGC categories, confirming that the discriminative power was high. These results make DenseNet201 a promising backbone for AI-assisted diagnostic systems with improved efficiency and interpretability for histopathological image analysis. Future work will explore data augmentation, attention mechanisms, and explainable AI to further improve model generalization and clinical applicability.

In this work, a Saliency-Guided ResNet34 model is introduced for the classification of corn leaves as healthy and infected. The dataset contains 4226 images collected from Kaggle and was divided into training, validation, and test subsets. Preprocessing steps such as resizing, normalization, and data augmentation were used to improve generalization, and transfer learning using ImageNet weights was used to take advantage of ResNet34's powerful feature extraction ability. The overall accuracy of the model was 91% after 15 epochs, with precision, recall, and F1 scores exceeding 0.90 for both classes. Confusion matrix analysis showed a great balance between sensitivity and specificity with fewer misclassifications. Furthermore, the saliency mapping was used to provide interpretability in terms of localizing symptomatic leaf regions that were consistent with the visual pathology and ensuring transparency to decision-making. These results validate that deep learning models, particularly ResNet34 with saliency guidance, can be an important part of early disease detection and precision agriculture. Additional research on multi-class classification, integration with IoT-based systems, and real-world deployment using mobile and drone-assisted platforms will be identified for further development of sustainable and intelligent crop health monitoring.

Anemia remains a major global health challenge, particularly in under-resourced settings where access to laboratory testing is limited. Non-invasive detection methods using computer vision provide a scalable alternative, but many existing approaches either rely on full-face analysis, require manual preprocessing, or depend on computationally heavy architectures unsuitable for real-world deployment. In this work, we propose ConjAnNet, a two-stage deep learning framework that combines U-Net-based segmentation of the conjunctiva with MobileViT for anemia classification. This end-to-end pipeline ensures clinically guided feature extraction and enables deployment on mobile and edge devices. Experimental evaluation on a balanced dataset of conjunctival images from Kaggle demonstrates strong performance, achieving a Dice coefficient of 0.8612 and IoU of 0.7815 for segmentation, and 96.5 % accuracy with an ROC-AUC of 0.987 for classification outperforming baseline CNN and MobileNet models. While these results highlight the potential of conjunctiva-specific analysis for automated anemia screening, the dataset's lack of demographic diversity and acquisition details represents a limitation. Future work will focus on validation with clinically acquired, diverse datasets and extension toward multiclass anemia grading.

This study presents a deep learning-based framework based on DenseNet169 for the classification of oral cancerous and non-cancerous conditions using lips and tongue images. In order to overcome the data scarcity and alleviate the overfitting, the Oral Cancer Images (OCI) dataset, consisting of 131 clinically validated samples, was increased to 1310 images using a ninefold augmentation strategy. Preprocessing - resizing, normalization, and augmentation to improve robustness were used. The DenseNet169 model showed an accuracy of 94%, with a precision, recall, and F1-score of 0.94, 0.95, and 0.95, respectively, to diagnose the cancerous cases, showing that the model is sufficient to diagnose the disease. Saliency-based visualization further enhanced interpretability by localizing lesion regions consistent with clinical observations. These results confirm the promise of DenseNet169 in supporting automated oral cancer screening, with potential to serve as an assistive tool in clinical decision-making and preventive oncology care.

One of the main causes of death for women globally is breast cancer, and better treatment results depend on early and precise identification. In order to classify breast cancer using medical imaging data, this study compares machine learning (ML) with deep learning (DL) approaches. Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN) algorithms were used to classify the features that were retrieved using the Gray Level Co-occurrence Matrix (GLCM) in the machine learning technique. Among these techniques, the best accuracy attained was 85.17%. Using pre-trained architectures like VGG16 and ResNet16, convolutional layers were used in the DL technique to automatically extract features. These models performed quite well, with a maximum accuracy of 96.55%. The findings unequivocally show that deep learning models perform better than conventional machine learning methods that depend on manually created features since they can instantly learn intricate patterns from photos. This study supports the incorporation of DL into computer-aided diagnostic systems for clinical usage and emphasizes its potential to improve breast cancer diagnosis.

Pathway analysis is crucial for deciphering the molecular mechanisms underlying cancer by identifying essential proteins within biological pathways. This study introduces a comprehensive framework for pathway analysis to uncover proteins associated with cancer pathogenesis. A computational approach exploring protein-protein interaction (PPI) networks and cancer gene datasets is applied to identify critical proteins involved in cancer progression. The methodology includes preprocessing gene data, using centrality metrics to detect vital proteins, and conducting pathway enrichment analysis to uncover dysregulated cancer pathways. This study identifies 44 critical proteins in PPI networks linked to breast, lung, colorectal, and ovarian cancers. These proteins span ten key pathways for regulating cell cycles, growth, and differentiation. The research emphasizes the significant roles of proteins like TP53, BRCA1, RPS27A, PCNA, CDK1, and CTNNB1 in cancer development, offering important insights into their functional impact on cancer-related pathways. The pathway analysis approach elucidates the molecular basis of cancer and advances precision oncology research. The study examines major cellular pathways, highlighting potential targets for therapeutic intervention and personalized treatment strategies. Future endeavours aim to translate identified essential cancer proteins into clinical practice through multidisciplinary collaboration and implementation strategies, promising the development of effective cancer treatment strategies.

Abstract: Protein–protein interaction (PPI) networks serve as invaluable repositories, shedding light on the intricate web of protein interactions within living organisms. Traditional methods for identifying essential proteins fail to capture the complex dynamics of these networks. This research aims to introduce a novel quantum-inspired centrality-based approach for identifying essential proteins in PPI networks (Quantum-EPI), leveraging quantum walk principles and a sequential pattern algorithm. A composite score for each protein is calculated by leveraging centrality measures, including degree, betweenness, closeness, and clustering coefficient. The algorithm, inspired by quantum interference and superposition, employs composite scores as a sorting mechanism. A quantum walk-inspired thresholding strategy distinguishes essential proteins, introducing a quantum-inspired probabilistic selection. The approach is exemplified using a set of centrality values and validated through permutation and enrichment tests. The Quantum-EPI approach prioritizes candidate cancer proteins and identifies nine proteins as the most significant disease-causing proteins through local and global topological analysis, correlation analysis, and ranking strategies. The simulation results, along with the validation through permutation and enrichment tests, demonstrate the superiority of the Quantum-EPI approach over existing state-of-the-art methods, providing a strong foundation for its efficacy in pinpointing essential proteins crucial to PPI network connectivity. The Quantum-EPI approach not only contributes to the field of network medicine but also sets the stage for innovative methodologies in protein identification and pathway analysis. The findings of this research hold significant promise for cancer research, drug design, and disease prevention, offering a new paradigm for essential protein discovery in biological systems.

The applications of centrality measures in protein-protein interaction (PPI) network analysis are diverse and encompass fundamental biological insights; cancer disease-related discoveries, and practical implications for drug development. This multidimensional approach in PPI network analysis provides a comprehensive understanding of the pivotal elements and their impact on biological systems. Analyzing centrality measures in PPI networks enables the identification of essential proteins, hub and bottleneck proteins that occupy strategic positions within the PPI network structure. Essential proteins in PPI networks are significant elements that indicate their importance in maintaining PPI network integrity and functionality. Studying centrality measures can reveal hidden patterns and relationships within these PPI networks. This paper identifes PPI networks with a high degree of connectivity ("hubs") and proteins with high betweenness centrality (bottlenecks), along with closeness centrality and clustering coefficient. This measure's significance in PPI networks has implications for various felds. The proposed approach successfully identifed and characterized infuential proteins and found the top 20 essential proteins. These proteins likely hold significant functional importance through hubs and bottlenecks and serve as potential targets for further investigation. This approach has the potential to identify essential proteins involved in cancer diseases. Leveraging centrality measures in the analysis of PPI networks ofers a multifaceted approach to understanding cancer biology and its implications for personalized medicine, drug design, and the development of innovative cancer therapies.

This paper presents an innovative graph-based method for identifying essential proteins within PPI networks, explicitly targeting cancer-related genes in breast, lung, col- orectal, and ovarian cancers. The proposed approach explores centrality measures, utilizing betweenness centrality to distin- guish essential proteins from non-essential ones. The methodology begins by identifying common genes through a sequential pattern algorithm, a crucial step that helps select genes for further analysis. This is followed by constructing a PPI network for each cancer type. Network analysis is conducted to extract essential cancer proteins. A total of 15 top essential proteins are identified, with validation performed through permutation analyses to ensure the reliability of the findings. These proteins were mapped to significant cellular pathways, playing vital roles in cancer progression. Grouping these proteins into specific path- ways highlights their functional importance and the underlying molecular mechanisms driving cancer. The results of this study have significant implications for cancer research, particularly in the realm of precision medicine. The identification of essential proteins not only enhances our understanding of cancer but also opens avenues for developing targeted, personalized treatment strategies.

Cancer is a heterogeneous disease that can spread to any body part. Breast cancer is one of the most dangerous cancers among women, contributing significantly to mortality worldwide. This research proposed a novel method for predicting breast cancer using Support Vector Machine (SVM) classification. The dataset is obtained from the University of California Irvine machine learning repository (UCI) Machine Learning repository from the University of Wisconsin Hospitals. It comprises 699 instances, of which 458 are benign and 241 are malignant, with 11 key attributes. The Radial Basis Function (RBF) kernel is used for the SVM classification to map the input data into a higherdimensional space. This model achieved 97 % an impressive accuracy and shows its potential to accurately detect breast cancer early. Thus offering a valuable tool for early diagnosis and treatment. Python was utilized for all implementations, enabling efficient processing and analysis of the dataset. This approach highlights the effectiveness of SVM in medical diagnostics, particularly for breast cancer prediction.

Pathway analysis is crucial for revealing the molecular mechanisms of cancer, as it emphasizes the important proteins that participate in various biological pathways. This study introduces a comprehensive framework leveraging protein-protein interaction (PPI) networks and cancer gene datasets to uncover essential proteins in cancer progression. The methodology encompasses preprocessing cancer gene data, applying centrality measures to identify critical proteins, and conducting pathway enrichment analysis to explore dysregulated pathways. The research identifies 44 essential cancer proteins associated with breast, lung, colorectal, and ovarian cancers, which are distributed across ten vital pathways related to cell cycle control, growth, and differentiation. Notable proteins such as TP53, BRCA1, RPS27A, PCNA, CDK1, and CTNNB1 are highlighted for their significant contributions to cancer initiation and progression. This approach enhances our understanding of the functional roles of these proteins and their influence on cancer pathways, advancing precision oncology by identifying potential therapeutic targets and personalized treatment strategies. Future efforts will translate these findings into clinical practice for more effective cancer treatment.

Pathway analysis is essential for understanding cancer's molecular mechanisms by identifying key proteins within biological pathways. This study presents a comprehensive framework using protein-protein interaction (PPI) networks and cancer gene datasets to uncover essential proteins involved in cancer progression. The methodology includes preprocessing cancer gene data, applying centrality measures to pinpoint crucial proteins, and conducting pathway enrichment analysis to explore dysregulated pathways. Results reveal 44 essential cancer proteins linked with breast, ovarian, lung, and colorectal cancers, spread across ten crucial pathways for cell cycle regulation, growth, and differentiation. Notable proteins like TP53, BRCA1, RPS27A, PCNA, CDK1, and CTNNB1 are highlighted for their significant roles in cancer pathogenesis. This approach provides a deeper understanding of the functional roles of these proteins and their impact on cancer pathways, advancing precision oncology by identifying potential therapeutic targets and personalized treatment strategies. Future efforts will focus on translating these findings into clinical practice for effective cancer treatment.

The essential protein identification on the protein–protein interaction (PPI) network can have crucial applications in cancer disease diagnosis and drug target cell identification. The study uses a graph-based approach to identify essential proteins in protein–protein interaction networks. Despite significant advancements in cancer research, identifying essential cancer proteins within PPI networks remains still a major challenge. The advantages of using PPI networks are the interconnectedness of cancer proteins and prioritize with the most significant impact on cancer disease progression. The proposed approach introduces an innovative way of identifying essential cancer proteins within PPI networks associated with breast, lung, colorectal, and ovarian cancers. This study commenced with an organized sequence of analytical procedures using cancer gene datasets from the National Center for Biotechnology Information (NCBI) about breast, lung, colorectal, and ovarian cancers. A graph-based random walk with restart (EPI-GBRWR), a novel method is introduced for exploring essential proteins that integrates topological and biological properties within PPI networks. A pivotal moment ensued with the implementation of an essential protein identification using graph-based random walk with restart, shedding light on the hierarchical influence of proteins within the PPI network. The outcomes of this investigation substantiate and contextualize the functional ramifications of the identified proteins through rigorous statistical assessments, including permutation and enrichment tests. The application of pathway analysis to these findings illuminates interconnected molecular pathways in cancer. This work underscores the potency of integrative methodologies in deciphering the complexity of cancer, presenting a transformative era in cancer research and treatment. The computational results confirm EPI-GBRWR’s efficiency in predicting essential proteins. Compared to other state-of-the-art methods for identifying essential proteins, EPI-GBRWR outperforms various evaluation criteria, marking a significant advancement in precision oncology.

Identifying essential proteins within cancer-related PPI networks is a significant challenge due to the heterogeneity and complexity of cancer diseases. Identifying these proteins is crucial for developing effective therapeutic strategies and understanding cancer biology. This study introduces a novel graph-based approach to identify essential cancer proteins within PPI networks, focusing on breast, lung, colorectal, and ovarian cancers. The proposed methodology involves a multi-step process beginning with identifying and preprocessing common genes associated with breast, colorectal, lung, and ovarian cancers. The PPI networks are constructed using these common genes. The PPI networks are analyzed to find the shortest paths using centrality measures. Centrality measures, particularly betweenness centrality, prioritize proteins with the highest impact on cancer progression. Betweenness centrality is used as a threshold to exclude nonessential proteins. The identified proteins are validated and categorized into cancer-related pathways through permutation and enrichment tests. The proposed approach successfully identified 64 essential proteins across breast, lung, colorectal, and ovarian cancers. These proteins were categorized into 14 cancer-related pathways, including cell cycle regulation, Wnt/β-Catenin signaling, RTK/RAS/RAF/MEK/ERK signaling, and PI3K/AKT/mTOR signaling. The identified pathways highlight complex interactions of these proteins, pivotal functions in cancer progression, and therapeutic targets. The validation process, through permutation and enrichment tests, confirmed the robustness and relevance of these findings, indicating their significant impact on understanding and potentially treating cancer. Identifying essential cancer proteins using this novel graph-based approach has significant clinical relevance, particularly for precision medicine. These findings can guide personalized treatment strategies and enhance the understanding of cancer biology. Future research will extend this methodology to other types of cancers and clinical applicability.

This systematic review aims to provide a comprehensive overview of graph-based methodologies utilized in the analysis of protein–protein interaction (PPI) networks. The primary objective is to synthesize existing literature and identify key methodologies, resources, and best practices in the field, with a focus on their application in uncovering essential cancer proteins. A systematic literature search was conducted across various databases to identify relevant studies focusing on graph-based explorations of PPI networks. The selected articles were critically reviewed, and data were extracted regarding the methodologies employed, resources utilized, and best practices identified. The review proceeds to outline a workflow that illustrates the systematic process from the compilation of gene/protein datasets to the generation of essential cancer proteins. A case study on “uncovering essential cancer proteins in breast cancer” was included to exemplify the application of graph-based methodologies in a real-world scenario. The review revealed various graph-based methodologies utilized in PPI network analysis, including centrality measures, pathway enrichment analyses, and network visualization techniques. Essential resources such as databases, software tools, and repositories were identified, along with best practices for data preprocessing, network construction, and analysis. The synthesis of findings, complemented by the case study, provides researchers with a comprehensive understanding of the current landscape of graph-based PPI network analysis and its application in cancer research. This systematic review contributes to the field by offering a holistic overview of graph-based explorations in PPI network research, with a specific focus on cancer protein identification. By synthesizing existing knowledge and identifying essential resources and best practices, this review serves as a valuable resource for researchers, facilitating informed decision-making and enhancing research quality and reproducibility. The inclusion of the case study underscores the practical application of graph-based methodologies in uncovering essential cancer proteins.

Identifying essential cancer proteins is critical in cancer research, as targeting these proteins can lead to effective cancer treatments. The proposed method is primarily intended to design a novel approach for identifying essential cancer proteins in the PPI network using a graph-based method. This method is used to find the shortest path on a biological network. The network is analysed using centrality measures, and a threshold value of betweenness centrality filters out nonessential proteins from the list of candidate proteins. The proposed graph-based method revealed that 50 essential proteins are selected from the list of proteins. Finally, the permutation test is performed to validate the findings. The proposed graph-based method identifies disease-related proteins in various contexts by performing common gene identification, PPI network construction, network analysis and validation. This method can be adapted and applied to different cancer types by adjusting the gene selection criteria, network construction methods, and validation stratcgies.