Telematique

Severity Aware Early Diabetes Prediction Using Hybrid Machine Learning and Deep Learning Techniques

2026-01-10T07:07:56+00:00

In the recent trend and in medical domain, diabetes stands out as one of the most predominant disease and unfortunately considering as a life-threatening disease. Early prediction of diabetes plays a pivotal role in initiating prompt treatment and halting the progression of the condition. The proposed methodology not only aids in predicting the future diabetes but also finds its severity scores. By presenting this issue as a multi-class classification problem, hybrid machine learning (ML) and deep learning (DL) techniques are used to build the new hybrid model. This helps in incorporating both structural feature learning of ML and deep temporal pattern recognition of DL for better performance. The hybrid ML+DL for diabetes prediction used XGBoost, LightGBM, CatBoost ML models and Temporal Convolutional Network (TCN) as base layer, Logistic Regression (LR) as a meta-classifier. The model is evaluated and fine-tuned for effective diabetes disease prediction with its score of severity. The experimental findings underscore the effectiveness of each component in the framework and its impact on the accuracy. The proposed work proves the sufficient amount of accuracy as 99.4%, and HML+DL compared with the recent studies in prediction of early stage of diabetes.

Mapping Research Themes and Future Directions in Learning Style Detection Research: A Bibliometric and Content Analysis

2026-01-12T08:55:03+00:00

This study aims to provide a comprehensive overview of the current state and potential future research in learning style detection. With the increasing number and diversity of research in this area, a quantitative approach is necessary to map out current themes and identify potential areas for future research. To achieve this goal, a bibliometric and content analysis will be conducted to map out the existing research and identify emerging topics and directions for future research. The study analyzes 1074 bibliographic sources from Scopus and visualizes the results of the bibliometric analysis through cooccurrence and thematic map analysis using VOSviewer and BibliometriX software. Content analysis is then conducted based on the results of the co-occurrence analysis. The findings reveal a significant increase in publications and citations in the field, with popular research topics including classification, adaptive learning, and MOOCs, and the most frequently used learning style models being Felder-Silverman, VARK, and Kolb. Emerging research topics include the use of EEG signals, online learning, and feature extraction. Future research may focus on classification, intelligent tutoring systems, MOOCs, online learning, adaptive learning, and deep learning. This study provides valuable insights into the current and future research trends in learning style detection, which can support the development of adaptive e-learning systems, intelligent tutoring systems, and MOOCs. By identifying popular research topics and emerging areas of study, this research can guide the design and implementation of effective online learning environments. Additionally, the study advances the field of e-learning knowledge by providing a comprehensive overview of the most frequently used learning style models and potential research areas. It sheds light on the ongoing development of learning style detection research and the potential for future advancements in the field, ultimately contributing to the growth and improvement of e-learning practices.

A study of Radiological Image-Based Bone sarcoma Detection Using Transfer Learning

2026-01-15T05:29:34+00:00

Bone sarcoma occurs primarily in children, adolescents and adults. Diagnostic assessment has traditionally involved subjective and often time-consuming assessments of imaging modalities such as X-ray, MRI and CT scans. This paper introduces a framework based on deep learning for automated classification of Bone Sarcoma from standard imaging modalities. The modernization utilizes MobileNetV2, a labeled dataset trained on ImageNet, to efficiently extract significant features while limiting computation. Preprocessing of the dataset included image normalization, resizing and augmentation using flipping, rotation, changing the zoom level and adding contrast. The dataset had a split of 80% affected and remaining 20% unaffected, respectively. During the fine-tuning phase the last layers of the model were unfrozen, and models trained at a reduced learning rate to accommodate the imaging data specific to Bone Cancer. The model trained with Adam optimizer and binary cross-entropy loss function with about 93% training accuracy and over 90% validation accuracy. Using evaluations from precision, recall, F1, and confusion matrix, the results verified the model robustness with minimal false negative rates being crucial for medical diagnostic. The results indicated that the suggested approach also provides a reliable, lightweight, and accurate diagnostic support for radiologists.

Optimization of Pumping Station Units Operation

2026-01-17T07:24:36+00:00

This article provides a complete analysis of the current operational condition of pumping stations and the operating modes of water transmission channels. The most dangerous processes of changing the operating mode at pumping stations caused by a sudden interruption of energy supply to the engine are studied. The issues of using advanced, modern systems during operation of pumping stations, as well as replacing outdated, serviceable equipment at pumping stations with significantly reduced efficiency of economical equipment with new ones are analyzed. A new effective method for determining the optimal operating mode of pumping units has been developed. The obtained results on reducing stress in transient modes of pumping units, adjusting operating modes and optimizing operating modes are analyzed.

Design of Experiment-Based Rp-Hplc Bioanalytical Method Development and Validation for the Estimation of Linagliptin and Dapagliflozin in Bulk and in Their Combined Dosage Form

2026-01-27T05:55:33+00:00

The aim of this study was to develop and optimize a simple, cost-effective, and robust Bioanalytical RP-HPLC method by Design of Experiment based Box–Behnken design for the simultaneous estimation of Linagliptin and Dapagliflozin in human plasma. The optimal chromatographic separation was achieved having C18 (Thermo) column (250 mm × 4.6 mm, 5 μ) and using mobile phase as Methanol and 0.1 % OPA (80:20) with a flow rate 0.9 ml/min and UV detection at 242 nm. A Box-Behnken design was used to test robustness of the method with describes the interrelationship of Mobile phase, Flow rate and Wavelength at three different levels. The method was found to be linear in the range of 2-10 μg/mL (R² >0.9997) and 4-20 μg/mL (R² >0.9994) for Linagliptin and Dapagliflozin, respectively. The developed bioanalytical method was validated as per recommended ICH guidelines which revealed the high degree of linear, precise, accurate, sensitive and robust method over the existing RP-HPLC method for Vildagliptin and Pioglitazone hydrochloride.

A Bibliometric Analysis for UPI Acceptance and Uses for Indian Customers and Business Community

2026-02-02T05:32:55+00:00

The Unified Payments Interface (UPI) has revolutionized India’s financial landscape, transitioning the nation toward a cashless economy. This study conducts a bibliometric analysis to examine UPI's adoption and usage patterns among Indian customers and businesses. By analyzing 2,560 articles with over 50,000 citations, this research identifies key trends, including user adoption determinants, technological advancements, and socio-economic impacts. It highlights the pivotal role of trust, perceived usefulness, and financial inclusion in driving UPI adoption, while addressing barriers like digital literacy and cybersecurity challenges. Using co-authorship, co-citation, and keyword mapping, this study uncovers thematic clusters and collaborations in global UPI research. Findings underscore UPI's transformative role in fostering financial inclusion, streamlining transactions for micro, small, and medium enterprises (MSMEs), and supporting government-led digital initiatives. This research provides valuable insights into the scholarly evolution of UPI, setting the stage for future explorations into its global scalability and integration with emerging technologies.

Enhancement Algorithms to Improve the Class of Endoscopy Images to Advance Gastrointestinal Track Disease Detection

2026-02-13T05:37:49+00:00

Gastro Intestinal (GI) track diseases are major health concern which require accurate detection for early diagnosis and treatment. One of the primary methods of GI track disease detection is to use endoscopic images of digestive track system. However, these images often are degraded by the presence of noise and poor contrast, which directly affect the diagnostic accuracy. Enhancing the quality of the degraded endoscopic images can greatly help physicians during diagnostics and treatment plan. In this work a unified approach which combines denoising and contrast variation correction is proposed. Denosing is executed using a fusion algorithm that pools discrete wavelet transformation and singular value decomposition that is combined with non-local means denoising algorithm. The contrast variation correction is performed using an adaptive gamma correction algorithm enhanced using particle swarm optimization method. Experiments proved that the proposed unified approach improves the visual quality while preserving significant image, edge and structure details. This method can therefore be used safely by GI track disease detection and classification system to improve its diagnostic accuracy.

Networks, Legacies and Continuity In Indian Family Businesses

2026-02-16T07:10:53+00:00

This study develops an extended theory of change explaining how family firms convert networks into performance. Drawing on an abductive, multiple-case qualitative design with eight Indian family businesses, and using Gioia-style coding, we distinguish what different ties accomplish, when their benefits turn negative, and how organizational scaffolds convert access into repeatable results. The analysis yields eight propositions that are consistent with the evidence: bonding/“as-if-family” density underwrites resilience but exhibits diminishing returns beyond an over-embeddedness threshold; non-kin diversity across industries and geographies predicts growth and co-creation; digital enablement amplifies the payoffs to bridging; governance and learning routines (partner ownership, review cadence, after-action notes) mediate the translation of diversity into scalable pipelines; and institutional bridging (banks, universities, government, associations) complements business networks, particularly in regulated or capital-intensive sectors. Three family-specific levers further refine the account: formalization of AIFB expedites funding decisions, reputation and community trust support price premiums and repeat business, and diaspora ties compress time-to-foreign-entry. We integrate these mechanisms into a four-stage network maturity ladder:S1 Kin-Centred Foundations, S2 Boundary Opening, S3 Structured Brokerage, S4 Orchestrated Partnerships—with observable progression triggers and leading indicators (deal velocity, referral yield, alliance revenue share, time-to-funds, price premium, time-to-foreign-entry). The contribution is a testable mid-range theory that specifies mechanisms and contingencies in family-firm networking while offering a practitioner-ready diagnostic and progression roadmap.

Advanced AI-Driven Techniques for Prostate Cancer Prediction

2026-02-23T06:16:14+00:00

Prostate Cancer (PCa) is one of the most common causes of malignancy and death in men worldwide, with a higher prevalence and mortality in developing countries. Factors such as age, family history, race and certain genetic mutations are some of the factors contributing to the occurrence of PCa in men. Prostate cancer is a growth of cells that starts in the prostate. Prostate is a small gland placed below the bladder to make semen, as a part of male reproductive system. Prostate cancer is one of the most common types of cancer. Prostate cancer is usually found early, and it often grows slowly. Most people with prostate cancer are cured. People diagnosed with early prostate cancer often have many treatment options. Treatments may include surgery, radiation therapy or carefully watching the prostate cancer to see if it grows. This study aims to review various machine-learning models, which are for the prediction and early detection of prostate cancer using clinical data. Machine-learning focuses on enabling systems to learn from data and improve their performance over time without explicit programming.

Enhanced Multi-Scale Attention 3D Deep Network (EMA-3DNet++) for Segmentation, Classification, and Severity Grading of Knee Injuries

2026-02-23T06:23:43+00:00

Sports-related knee injuries such as anterior cruciate ligament (ACL) tears, meniscal degeneration, and cartilage defects demand precise and early diagnosis to prevent long-term functional impairment. Although deep learning–based medical image analysis has significantly improved automated knee assessment, existing 3D convolutional models often suffer from limited global contextual reasoning, inadequate cross-structure modeling, and poor generalization across heterogeneous clinical datasets. To address these limitations, this research work proposes EMA-3DNet++, a next-generation Federated Multi-Scale Transformer–Graph Hybrid 3D Deep Network designed for accurate, explainable, and privacy-preserving sports knee analysis. EMA-3DNet++ integrates self-supervised pre-trained 3D encoders with multi-scale convolutional feature extraction and Swin Transformer blocks to capture both fine-grained anatomical details and long-range spatial dependencies in volumetric MRI data. A Graph Neural Network (GNN) module explicitly models structural relationships among knee components—ACL, PCL, meniscus, cartilage, tibia, and femur—enhancing multi-label injury classification and structural consistency. To further improve robustness, a hybrid temporal refinement unit incorporating LSTM and energy-efficient spiking neural layers captures motion dynamics in sequential scans. The framework adopts a multi-task learning strategy, simultaneously performing segmentation, injury classification, and severity grading.

To overcome data scarcity and privacy constraints, EMA-3DNet++ supports federated learning with secure aggregation, enabling collaborative training across institutions without data sharing. An advanced explainability layer combining 3D Grad-CAM++, attention rollout, and uncertainty estimation enhances clinical interpretability. Experimental evaluation on benchmark datasets including MRNet, SKI10, and OAI demonstrates that EMA-3DNet++ achieves superior Dice coefficient (94–96%), improved sensitivity and specificity, and enhanced cross-domain generalization compared to state-of-the-art 3D CNN baselines. The proposed framework represents a scalable, clinically deployable, and energy-efficient solution for next-generation AI-assisted sports knee diagnostics.

Study of Professional Hazards in Chefs through Ayurvedic Perspective

2026-02-23T10:12:56+00:00

Introduction:
Chefs face unique occupational hazards such as prolonged heat exposure, irregular eating habits, physical strain, and psychological stress. In Ayurveda, these factors correspond to Nidana like Atapa sevana, Ati-ushna-tikshna ahara, Vishama ahara, Vega-dharana, and Manasika nidana, leading to Vata-Pitta aggravation, Agnimandya, Aama formation, and Srotodushti.

Methods:
A narrative review was conducted using PubMed, Google Scholar, Scopus, AYUSH portals, and classical Ayurvedic texts. Literature linking chef occupational hazards with disease outcomes was identified and mapped to Ayurvedic concepts of Nidana, Dosha, and Srotas.

Results:
Occupational hazards identified in chefs included heat and steam exposure, irregular dietary intake, prolonged standing, repetitive strain, and high job stress. In Ayurvedic interpretation, these hazards aggravate Vata and Pitta doshas and vitiate Rasavaha, Annavaha, Mamsavaha, and Manovaha srotas. Modern studies report corresponding conditions such as gastritis, obesity, musculoskeletal disorders, varicose veins, and burnout.

Discussion:
Ayurveda offers preventive strategies including Pitta-pacifying diet, Abhyanga, Sheetali pranayama, Rasayana herbs (Amalaki, Guduchi, Shatavari), and ergonomic modifications. Integrating Ayurvedic measures with occupational safety practices may reduce disease burden and improve overall well-being in chefs.

Therapetic uses of Vidanga Leha in Children W.S.R. Krimi. A Case Series

2026-02-23T10:18:54+00:00

Krimi have been considered a major public health problem through out the world according to WHO, 1967. In our country this problem is equally significant. The helminths and bacteria discussed today are somewhat comparable to the Krimi described in ancient texts. According to CCRAS 1987 reports, it affects youngsters more often than adults. Krimi impairs a person's growth and development, causes malnutrition, and lowers immunity; therefore, an efficient remedy to this issue is required. Of all the herbs used in treating worm infestation, Vidanga leha (Embelia ribes) was used for the present study. 30 patients were randomly selected for the study. factors like Vivarnata (Skin Pigmentation), Udarshul (Abd pain ), Gudkandu (itching near anal region), MalaVishtambhata (constipation), Aganimandya (Anorexia) were observed in this study. These clinical conditions had been described by Acharya Charaka under the Lakshana of Krimi and it has been also described in Rasavaha Srotodusti Lakshanas as well. In 15 days of study, observations were recored 0n 0^th, 7^th, and 15^th day and doses were administrated according to body weight of the patients.

Objective: To evaluate the efficacy of vidanga leha in krimi betwenn the age group of 1-12 years.

Conclusion: This study revealed notable alterations in the Krimi patients. Relief had been observed in the various parameters chosen for the study.

Assessment of Moisture Content in the Form of an Indicator of Ahara Samskara Effect

2026-02-25T06:14:47+00:00

This study aims to scientifically validate the Ayurvedic principle of Ahara Samskara (food processing) by analyzing the changes in the moisture content of Shashtik Shali (a 60-day rice variety) following Kala Samskara (time-based storage) and Agni Samskara (heat processing). The research employs the oven-drying method, a standard technique in modern food science, to quantitatively assess the physicochemical transformations. Freshly harvested Shashtik Shali showed a moisture content of 4.4%. After being stored for eight months and subsequently dry-roasted, the grains' moisture content was reduced to 4.0%. This quantifiable reduction serves as a tangible metric that correlates with the qualitative changes described in Ayurveda. The fresh grain's higher moisture content reflects a predominance of Jala and Prithvi Mahabhutas, making it highly nourishing (Brimhana), but potentially contributing to Ama (toxins) in individuals with weak digestion. The processed grain, with its reduced moisture, reflects a shift towards Agni and Vayu Mahabhutas, acquiring qualities that are lighter (Laghu), drying (Ruksha), and more stimulating to the digestive fire (Dipana), making it therapeutically beneficial for managing conditions like Mandagni (weak digestion) and Kapha Dosha aggravation. The findings bridge ancient Ayurvedic wisdom with contemporary analytical methods, demonstrating that traditional food processing techniques are sophisticated interventions that purposefully modulate a food's properties for specific therapeutic and health-promoting effects.