International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
ECG Lead Selection for Disease Diagnostics Using CNN-Transformer
Full text linkElectrocardiography (ECG) is crucial for diagnosing cardiovascular diseases (CVDs), which cause millions of deaths each year. This study addresses the challenge of CVD diagnosis in rural areas, where there is a shortage of skilled healthcare professionals and medical equipment. This study proposes a novel method to systematically compare different ECG leads using Deep Learning techniques, specifically a 1D CNN Transformer, to detect anomalies from minimal disturbances. The analysis was conducted using the PTB-XL dataset and further validated with Holter ECG-based records from the St. Petersburg INCART database. Minimal pre-processing was applied, limited to baseline wander removal, to maintain the intrinsic information of each lead. The results indicate that utilizing all leads significantly improves the F1 score, although lead II, V1, and V2 also provide comparable results in the INCART database. This study demonstrates that fewer leads can be effectively used to diagnose diseases, facilitating the creation of low-cost ECG machines suitable for deployment in rural areas. The code is publicly available at https://github.com/nabeelraza-7/ecg-lead-selection
IoT-Based Non-Invasive Monitoring of Blood Sugar Levels with Early Warning Mechanism
Full text linkThis research presents the design and implementation of a non-invasive sugar level monitoring system with an early warning mechanism using embedded systems and Internet of Things (IoT) technologies. The system integrates an Arduino Uno microcontroller with sensors such as the MLX90614 infrared temperature sensor, MAX30102 blood oxygen and heart rate sensor to monitor vital health parameters. The system correlates temperature, blood oxygen levels, heart rate, and glucose levels to provide early warnings for high or low sugar conditions. Experimental results demonstrate the system\u27s accuracy, reliability, and effectiveness in providing real-time health data. Also, this research highlights the potential of non-invasive health monitoring systems in diabetes management and paves the way for future advancements in IoT-based healthcare solutions
MatLab Bvp4c Technique to Compute Thermophoresis and Brownian Motion in Nanofluid Flow Over a Transient Stretching Sheet
Full text linkThis physical phenomenon examined the transport mechanisms of heat and mass within a nanofluid thin film. The nanofluid thin film is situated over an unsteady stretching sheet, which is one of the pioneering contributions to the field, focusing specifically on the flow dynamics of nanofluid thin films. This foundational framework is established by Buongiorno’s fluid model. The mathematical model is applied for the evaluation of the nanofluid film, which adeptly weaves in significant phenomena, including Brownian motion as well as thermophoresis. The mathematical model is achieved in the form of non-linear partial differential equations (PDEs) for computation with the help of computer applications. Firstly, the analytical framework of similarity transformations is applied to non-linear PDEs to convert them into ordinary differential equations (ODEs). Secondly, these ODEs have been critically examined and prepared for coding in MatLab by reducing their high order into first order. The software Mathematica and MatLab have been employed to solve the boundary value problem (BVP). The built-in BVP4c solver is applied to obtain accurate solutions in the form of graphs and numerical values. The current analysis yields significant results revealing that both the free surface temperature and the volume fraction of nanoparticles tend to increase in response to variations in both unsteady conditions and magnetic parameters. Furthermore, the outcomes demonstrate that the interaction among diverse nanofluid variables with the phenomenon of viscous energy loss contributes to a reduction in the overall heat transfer rate. The potential effect of these proficient thermal management techniques is crucial, especially in microelectronics and energy systems
Industry 5.0: An Energy-Efficient Smart Task Offloading Mechanism for Multi-Access Edge Computing
Full text linkThe industry 5.0 heralds a transformation of industrial systems by integrating artificial intelligence (AI), the Industrial Internet of Things (IIoT), and Multi-Access Edge Computing (MEC) to foster resilience, efficiency, and sustainability. However, managing the massive volume of computation-intensive tasks generated by heterogeneous IIoT devices presents major challenges, particularly in optimizing both latency and energy consumption under dynamic industrial conditions. This research proposes a hybrid task offloading framework Computational Genetic Particle Swarm Optimization Algorithm (CGPCA) to intelligently balance energy efficiency and latency in MEC-enabled IIoT networks. CGPCA integrates the global search capability of Genetic Algorithms (GA) with the fast convergence of Particle Swarm Optimization (PSO), forming a two-layer optimization approach for effective task-device associations and power-bandwidth allocation. The framework is evaluated using iFogSim and Edgelands simulation environments, reflecting realistic industrial scenarios with variable workloads, device capabilities, and server conditions. Results indicate that CGPCA reduces average latency by up to 24%, lowers energy consumption by 18–25%, and maintains a task offloading success rate of 94% surpassing conventional GA, PSO, and heuristic baselines. The framework also achieves improved load balancing and faster convergence time, confirming its suitability for time-sensitive and energy-constrained IIoT environments. This study contributes to the realization of Industry 5.0 by offering an adaptive, intelligent solution that enhances computational efficiency while supporting sustainable and human-centered industrial automation. Future directions include extending CGPCA to highly mobile IIoT contexts and integrating predictive analytics for further performance gains
Design Evolution and Feature Enhancement Strategies for Advanced Digital Stethoscopes
Full text linkA stethoscope is a fundamental auscultation and diagnostic device that plays a major role in medication and assists in the identification of sounds inside the body to predict cardiovascular and respiratory diseases. The advent of electronic and artificial intelligence (AI)-enhanced digital stethoscopes is prompted by the limitations of traditional auscultation performance, such as the need for a clinician\u27s experience, failure to detect the required sounds in noisy conditions, and the inability to store patient data. This study focuses on the evolution in the design, relative performance characteristics, and areas of future improvement of stethoscopes, including digital devices that incorporate AI. Several studies show the employment of advanced filters to acquire important auscultating frequency bands, a high-gain amplifier to boost low-frequency internal body sounds, a noise cancellation circuit to block out background noise, Bluetooth for data sharing in real-time signal processing, and syncing with other medical devices. Key features that could be introduced in future versions are adaptive frequency filters, AI-based clustering to classify the sound, remote diagnostic functionality, and an improved data storage system. Protection circuits that take the form of lithium-ion batteries, wireless modules, and processing based on a microcontroller are some of the resource components highlighted in terms of portability and efficiency. This research seeks to develop stethoscopes by incorporating innovations while managing limitations, ultimately enhancing tools for healthcare professionals
Bridging the Divide of Formal and Informal Transit in Urban Areas - Considering Multidimensional Aspects of Sustainability
Full text linkPublic transport in cities across the developing world is fundamentally shaped by the dualism of formal and informal services. Informal transport modes, including minibusses, shared taxis, and auto-rickshaws, are not merely supplementary but are essential components of the urban mobility ecosystem, providing critical connectivity for marginalized communities. Contemporary scholarship advocates for a multifaceted evaluation of these systems to capture their full socio-economic, environmental, and operational impact. This paper conducts a systematic literature review to synthesize existing assessment frameworks for public transport. The findings reveal a significant gap: current methodologies often fail to integrate the core dimensions of sustainability—social, economic, and environmental—with emerging imperatives like climate resilience and comprehensive regulatory and technological considerations. By mapping the state of the art, this review underscores the necessity for a more holistic evaluation paradigm, focusing on frameworks that move beyond a simple formal-informal divide to foster comprehensive understanding and strategic integration
Parallel Electric Fields Associated with Double Layers in Kappa Distributed Space Plasmas
Full text linkParallel electric field structures associated with double layers (DLs) provide the best explanation for the physical mechanism underlying charged particle energization acceleration at sites of magnetic reconnection. In-situ measurements of reconnection sites by various satellites such as MMS, THEMIS, and FAST confirmed the connection of charged particle energization with the large parallel electric fields in the auroral regions, Earth\u27s plasma sheet, and the separatrix region of the magnetosphere. We employed the fully nonlinear Sagdeev potential technique and multi-fluid theory for electron-ion plasma to find double-layer solutions and the accompanying electric field at the reported sites. Considering electrons to be kappa distributed, we have taken into account the ion inertial effect. Specifically, at non-Maxwellian effective temperature scales, parallel electric fields related to the Alfvénic double layer have been studied and compared with the observations. We have shown that the nonthermal parameter kappa and Alfvénic Mach number ????A considerably alter the properties of DLs and the associated electric field of kinetic Alfvén waves
Machine Translation of Quranic Verses: A Transformer-Based Approach to Urdu Rendering
Full text linkTranslate Quranic Arabic into Urdu is a Challenge due to linguistics and theological differences. While machine translation has advanced significantly, transformer-based Neural Machine Translation (NMT) models have not yet been utilized for Quranic Arabic to Urdu translation. This study addresses this gap by developing a transformer-based model that ensures accurate and context-sensitive translation of Quranic verses. A dataset has been initialized that contains Quranic Arabic text and Urdu translation of respected. I performed preprocessing on the dataset by applying it towards tokenization, stemming, and lemmatization, without compromising the theological nature of the theme. To enrich the model to mine the linguistic and stylistic cues, transformer architectures such as Helsinki NLP/MiarinMT were used with the transfer learning. Finally, the model was evaluated for theological correctness by Islamic scholars, and, secondly, by some automated metrics (BLEU, Rouge, and Cosine Similarity). Results show that the transformer model is a better model by far that provides better translation quality in the sense that meanings are preserved, that is, contextual meaning as well as religious meaning, implying better accessibility to Urdu-speaking Muslims. This research proposes a new approach to the problem of translating sacred texts and solves, albeit theologically correct, otherwise unsolvable problems in Quranic translation, computational linguistics, and AI development. This research introduces a novel approach to Quranic translation, and Future work will explore multimodal learning for deeper contextual understanding
CHEESE Net: A Feature-Optimized Hybrid Learning Model
Full text linkIntelligent cheese selection is critical in the dairy industry to address rising consumer demand for personalized nutrition and health-conscious choices. This study introduces the novel integration of supervised learning, unsupervised clustering, and deep learning autoencoders to dynamically optimize feature representation and recommendation quality, a previously unaddressed approach in dairy informatics. The system employs Random Forest Regression for caloric prediction, PCA for dimensionality reduction, and deep autoencoders to capture non-linear nutrition relationships. Recommendations are generated via cosine similarity and Euclidean distance, supported by clustering techniques to refine cheese categories. Cheese net achieved exceptional predictive accuracy with a Mean Absolute Error (MAE) of 14.46 and an R² Score of 0.98, outperforming traditional models. Advanced visualizations (heatmaps, t-SNE, PCA plots) uncovered latent nutritional patterns while clustering enhanced recommendation precision by aligning suggestions with user-specific dietary profiles. The hybrid model’s interpretability enables stakeholders to decode correlations between fat, protein, carbohydrates, and moisture content, facilitating data-driven decisions for producers and consumers. By unifying machine learning with explainable AI, Cheese Net reduces MAE by 31% compared to standalone regression models. This framework pioneers a scalable, data-driven solution for personalized cheese selection, bridging nutritional science and consumer needs in the digital dairy era
AI-Based Resource Efficient Image Classifier for Skin Lesions
Full text linkSkin cancer and other skin diseases are significant health concerns, and early diagnosis is essential for effective treatment. Traditional diagnostic methods, such as clinical examination and histopathological analysis, are time-consuming, require specialized expertise, and often cause delays in treatment. AI models have the potential to transform this process. While previous research has primarily focused on skin cancer or specific skin diseases, this study takes a broader approach by introducing a novel multiclass classification model. We created a unique dataset combining images from publicly available datasets and new images collected using mobile cameras. The dataset consists of three types of skin cancer and six categories of skin diseases, with both mobile camera and dermoscopic images included. In total, we gathered 6,820 skin lesion images, 4,957 from public datasets, and 1,863 new images to enhance the dataset. Various deep learning models, including VGG16, ResNet50, DenseNet121, MobileNet, and a custom CNN, were tested. While these models performed well with dermoscopy images, they struggled with mobile images. To address this, we implemented a new classification model, YOLOv11, for multiclass classification. This model achieved an impressive 97.5% overall accuracy, with an F1 score of 0.97503, and 99% accuracy for each class, handling both dermoscopy and mobile images effectively