Neuromorphic VLSI Accelerator for Edge-Aware AI Processing Using Hybrid Spiking Neural Architectures

Ravi Shankar; S.; Gokul; K.; A.; S.

doi:https://doi.org/10.54216/JISIoT.170228

International Journal of Neutrosophic Science | 2025

Using Neutrosophic Theory to Analyze Lexical Entries: A Fresh Approach to Developing an Educational Lexicon

This study aims to apply Neutrosophic Theory in analyzing monolingual and bilingual lexical entries as an approach capable of accurately representing semantic ambiguity, phonological values, and developmental values. This is because lexical meaning is a vital component of the semantic system, responsible for conveying and clarifying meaning. However, despite its importance, it is insufficient for fully conveying meaning. Lexical entries lack crucial values, especially the recognition of probable meanings. The network of semantic relationships in any dictionary addresses meaning in a binary way. In a language that relies heavily on metaphor or derivation, like Arabic, dictionaries tailored to the Arabic language fail to provide probable meanings for words such as (eye - heart - hand), whose contextual and metaphorical meanings sometimes do not align with the body-part indication but include other potential meanings. This study is based on the hypothesis that the linguistic dictionary in general and Arabic in particular, still require an approach that allows observing the meanings across three dimensions: truth (T), indeterminacy (I), and falsehood or negation (F). By integrating phonological, semantic, and evolutionary analysis within a neutrosophical framework, a more comprehensive lexical model can be developed that captures the interaction between language, usage, context, and history. This research adopted a mixed descriptive–analytical method, combining qualitative linguistic analysis with quantitative Neutrosophic modeling.

groups

Obaid Mohammad Abdelhalim Abdelgawad mail -

Ahmed Moussa Abdalla Seifeldin mail -

Saziye Yaman mail -

Hilal Abdul-Raziq Sadiq mail

link https://doi.org/10.54216/IJNS.260422

Volume & Issue

Vol. Volume 26 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2025

Enhancing the Quality and Innovation of Higher Education through Neutrosophic and Network Interaction Frameworks

The goal of the study is to provide the context, substantiation and formation of a strategic model for development of an innovative educational environment in higher education based on application network interaction principles. The study adopts a holistic systems theoretical approach that integrates systemic, institutional and network theories within a neutrosophy based decision-making model to deal with uncertainties and indeterminacy involved in innovation management at HEI level. The study is based on data collected from different universities and institutions with different profiles in terms of innovation potential. The results lead to a strategic model of networked scientific and innovative activity, including mechanisms for knowledge exchange, technology transfer, and collaborating with industry and government. The model together enabling universities’ effectiveness in producing, disseminating and applying new knowledge proposes three levels of interacting channels. This study is new in merging neutrosophic logic with network interaction theory to develop a flexible decision-making model for strategic development of higher education sector. The paper offers policy consolidators, university heads and academic consultants with practical tips aimed at improving innovation-management as well as educational quality, deepening the synergies between education-sciences-business worlds at Universities.

groups

Marina Sagatovna Abdurashidova mail -

Saziye Yaman mail

link https://doi.org/10.54216/IJNS.260423

Volume & Issue

Vol. Volume 26 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2026

Digitalization and Structural Transformation in Education and Economy: A Neutrosophic Evaluation Approach

The research analyses the impact of digitalisation levels on structural transformations in regional economies and the education sector, highlighting their reciprocal relationship in generating sustainable and inclusive growth. This study assesses the multi-dimensional mediation of digitalization with economic performance and learning modernization in education. It also analyzes the efficacy and efficiency of digital policies and institutional strategies as data, as well as offers databased policy recommendations for a more balanced and knowledge based regional development. A full mixed-methodological approach is employed consisting of statistical (correlation and regression between regional digitalization and economic variables) and neutrosophic multi-criteria evaluation of the education system dynamics. Crosscutting comparisons between regions and higher education end-users with various degrees of digital maturity are analysed, enabling to understand more in depth how digital infrastructure and the enactment of policies can contribute to structural transformation as both economy and educational institutions move forward. Under the light of the findings, the paper calls for focused digital and educational policies to strengthen regional and institutional capabilities through increased investment in digital infrastructure, the professional capacities of educators and the integration of digital competences into curricula. The study also offers a strategic approach to align educational digitalization with regional innovation systems, so that the benefits of digital transformation truly and in a balanced way support both economic modernisation and the development of human capital. A strategic framework, based on neutrosophy, is contributed for policymakers, university managers and development planners to formulate sustainable digitally enabled-smart ecosystems building up the link between economic growth and education development.

groups

Aliya T. Akhmedieva mail -

Abdurashid M. Kadyrov mail -

Bahtiyor H. Mamurov mail -

Svetlana Yu. Shatokhina mail -

Saziye Yaman mail

link https://doi.org/10.54216/IJNS.270128

Volume & Issue

Vol. Volume 27 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2026

Financial Innovation and Microfinance Effectiveness: A Neutrosophic Econometric Evaluation

This work analyzes the econometric efficiency in the use of finance instruments applied by microfinance institutions, using a Neutrosophic methodological framework; it develops with emphasis in terms of financial performance and social impact for 2018-2023. The study aims to fill important gaps in understanding how alternative financial instruments affect operational efficiency, poverty mitigation and institutional sustainability within a changing regulatory and development context. The mixed-methods was used by combining the N-MCDM and DEA technique with panel data regression analysis techniques. The sample consisted of 89 MFIs (including traditional and alternative-finance-based ones) in all 14 administrative regions. The method used for efficiency estimation was two-stage DEA, GMM was used to estimate the dynamic panel model, and Tobit regression model a set of key explanatory variables for performance. Input data were institutional annual financial reports, operation indicators, borrower information as well as macro-prudential regulatory metrics from central financial authorities. The outcomes indicate that microfinance institutions (MFIs) using alternative finance have higher social efficiency at 0.863 compared with their Conventional counterparts (at 0.741), while they conserve the same financial efficiency (0.694 versus 0.708). Murabaha-type financing models had a 26% better portfolio quality so that portfolio-at-risk percentages were as high as 2.6% compared to conventional frameworks of 3.5%. Musharaka-utilizing systems captured 21% higher likelihoods of loan recovery, whereas Ijarah-based models showed 18% lower odds of default. Moreover, rural outreach efficiency improved by 34% and women’s participation ratio became 81% instead of 64%, in conventional institutions. With marginally lower average ROA (1.97% compared to 2.24%), alternative-finance players revealed a higher level of alignment with priorities on value-creating expansion and impact on society. In conclusion, the results highlight the power of neutrosophic econometric analysis for assessing trade-offs among complex financial and social decisions, providing a strong decision-support system for policymakers and financial regulators aiming to design the optimal balance between profitability, efficiency and social welfare in microfinance schemes.

groups

Muhammad Eid Balbaa mail -

Olim Astanakulov mail -

Tonguc Cagin mail -

Akhmedova Ugilshod Musurmonkul mail

link https://doi.org/10.54216/IJNS.270129

Volume & Issue

Vol. Volume 27 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

Blockchain-Augmented Zero Trust Architecture for Intrusion Detection in Decentralized IoT Networks

The exponential growth of the Internet of Things (IoT) ecosystem has amplified concerns regarding data privacy, trust management, and cyber resilience in decentralized environments. Traditional perimeter-based security models are inadequate for heterogeneous IoT networks that operate across multiple domains. To address these challenges, this paper proposes a Blockchain-Augmented Zero Trust Architecture (BZTA) integrated with a hybrid intrusion detection mechanism for achieving secure, verifiable, and adaptive threat mitigation in decentralized IoT frameworks. The proposed BZTA employs blockchain-based identity verification to ensure device authenticity and policy-driven Zero Trust enforcement to validate every access request dynamically. A federated intrusion detection model built using Long Short-Term Memory (LSTM) and Graph Attention Networks (GAT) identifies anomalous communication patterns, while smart contracts facilitate tamper-proof logging and automated response coordination. The integration of Proof-of-Trust (PoT) consensus enhances scalability by minimizing latency during transaction validation. Experimental evaluations conducted on simulated IoT network datasets demonstrate a detection accuracy of 98.6%, false positive rate of 1.8%, and an average latency reduction of 22% compared to traditional IDS and standalone blockchain systems. The proposed BZTA framework effectively balances security, scalability, and interoperability, providing a resilient foundation for next-generation decentralized IoT infrastructures.

groups

M. Mohan mail -

R. Vijayakarthika mail -

M. Balakrishnan mail -

R. Sundar mail -

T. Chithrakumar mail -

Vaishnavi V. mail

link https://doi.org/10.54216/JISIoT.170126

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

Integrating Visual Sentiment Analysis with Textual Data for Enhanced Social Media Insights

Social media platforms have become pivotal arenas for the public to express emotions, opinions, and sentiments. While traditional sentiment analysis methods predominantly focus on textual data, they often overlook the rich emotional context embedded in images shared alongside posts. This paper presents a novel framework that integrates Visual Sentiment Analysis (VSA) with Natural Language Processing (NLP) techniques to enhance the understanding of public sentiment in social media content. By leveraging deep learning-based feature extraction from images (using pre-trained CNN models) and combining them with transformer-based text analysis (such as BERT), the proposed multimodal sentiment analysis model captures nuanced emotional expressions more effectively than unimodal approaches. Experiments conducted on benchmark datasets, including Twitter and Instagram posts, demonstrate a significant improvement in sentiment classification accuracy and contextual interpretation. The study highlights the potential of integrated sentiment analysis systems in applications such as brand monitoring, political opinion tracking, and mental health detection.

groups

M. Sivasankar mail -

K. Murugan mail -

P. Gouthami mail -

G. Balambigai mail -

Kalaivani T. mail

link https://doi.org/10.54216/JISIoT.170127

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

Real-Time Gesture Recognition Using Attention-Based CNN-RNN Framework for Human-Robot Interaction

Gesture recognition serves as a key enabler for natural and intuitive human–robot interaction (HRI) in smart automation and assistive systems. However, achieving real-time performance with high recognition accuracy remains a significant challenge due to dynamic background variations, occlusion, and complex spatio-temporal dependencies in gesture sequences. This paper presents a real-time attention-based CNN-RNN framework for robust gesture recognition and adaptive HRI in dynamic environments. The proposed system utilizes Convolutional Neural Networks (CNNs) for spatial feature extraction from sequential video frames and Bidirectional Recurrent Neural Networks (BiRNNs)—integrated with an attention mechanism—for modeling temporal dependencies and focusing on discriminative motion cues. The attention layer enhances interpretability by prioritizing salient gestures and reducing background noise. A hybrid optimization strategy, combining adaptive learning rate scheduling and regularized dropout, ensures computational stability and generalization across gesture datasets. Experiments conducted on benchmark datasets such as NVIDIA Dynamic Gesture (NvGesture) and ChaLearn IsoGD demonstrate superior performance, achieving an accuracy of 97.8% and a real-time inference speed of 34 FPS, outperforming baseline CNN, 3D-CNN, and LSTM architectures. The proposed framework effectively balances accuracy, latency, and interpretability, making it suitable for real-world HRI applications, including service robotics, industrial automation, and assistive technologies.

groups

R. Poorni mail -

Chinnathambi Kamatchi mail -

Y. Dharshan mail -

K. Kowsalya mail -

R. Vijay mail -

M. Balakrishnan mail

link https://doi.org/10.54216/JISIoT.170128

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

Emotion-Aware Recommendation Systems: Deep Sentiment Modeling for Consumer Behavior Understanding

Traditional recommendation systems primarily rely on user behavior, ratings, and content-based preferences to suggest products or services. However, they often overlook the nuanced emotional context that significantly influences consumer decision-making. This paper proposes a Sentiment-Enhanced Recommendation System (SERS) that integrates sentiment analysis with collaborative and content-based filtering to better capture the affective dimensions of user preferences. By analyzing user-generated content such as reviews, comments, and social media posts using deep learning-based sentiment classifiers, the proposed model quantifies emotional polarity and intensity. These sentiment signals are then incorporated into the recommendation pipeline using hybrid matrix factorization and attention mechanisms, enabling dynamic adaptation to users' emotional states. Experimental evaluations conducted on datasets from Amazon and Yelp demonstrate significant improvements in precision, recall, and user satisfaction scores compared to traditional models. The findings highlight the critical role of emotions in shaping consumer behavior and underscore the importance of affect-aware personalization in modern recommendation systems.

groups

N. B. Mahesh Kumar mail -

Subbulakshmi M. mail -

T. Baranidharan mail -

Mohana Sundharam M. mail -

Geetha M. P. mail

link https://doi.org/10.54216/JISIoT.170226

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

Adaptive Image Enhancement Using Hybrid Deep Learning and Traditional Filtering Techniques

Image enhancement remains a fundamental challenge in computer vision, particularly in scenarios involving low contrast, uneven illumination, and noise interference. While traditional spatial and frequency domain techniques efficiently address specific distortions, they often fail to generalize across diverse image conditions. To overcome these limitations, this paper proposes an Adaptive Hybrid Image Enhancement Framework that integrates deep learning-based enhancement networks with classical filtering algorithms for optimal visual restoration and detail preservation. The proposed method employs a Convolutional Neural Network (CNN) enhanced with an attention-guided residual block to learn fine-grained illumination patterns, followed by adaptive fusion with traditional filters such as Gaussian smoothing, histogram equalization, and bilateral filtering. This hybrid approach ensures a balance between structural clarity and natural color consistency. A dynamic weighting mechanism is applied to adjust enhancement intensity based on local luminance and texture statistics. Experimental validation on benchmark datasets such as MIT-Adobe FiveK, BSD500, and LIME demonstrates significant improvement over state-of-the-art methods. The proposed hybrid model achieves an average PSNR of 32.8 dB, SSIM of 0.95, and naturalness index improvement of 18%, outperforming standalone deep learning and filtering techniques. The adaptive framework effectively enhances visibility in underexposed, blurred, and noisy conditions, making it ideal for applications in medical imaging, autonomous vision, and surveillance systems.

groups

Karthikram Anbalagan mail -

Ravikanth Garladinne mail -

K. Ananthi mail -

M. Jeba Paulin mail -

Vairaprakash Selvaraj mail -

Jayalalakshmi G. mail

link https://doi.org/10.54216/JISIoT.170227

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

Neuromorphic VLSI Accelerator for Edge-Aware AI Processing Using Hybrid Spiking Neural Architectures

The rapid proliferation of edge-AI systems in IoT, autonomous robotics, and biomedical monitoring demands ultra-low-power, latency-aware intelligence that conventional deep neural networks struggle to provide due to heavy computation and memory overheads. Neuromorphic computing offers a promising biological-inspired alternative by processing information through sparse spiking events, enabling energy-efficient on-device learning and inference. This paper presents a neuromorphic VLSI accelerator based on a hybrid spiking neural architecture that combines Leaky-Integrate-and-Fire (LIF) neurons, adaptive threshold spiking units, and synaptic plasticity circuits to support both supervised and unsupervised learning modes at the edge. A hierarchical crossbar-memory topology integrated with non-volatile memristive synapses provides dense weight storage and real-time synaptic updates, reducing off-chip memory access by 78%. A pipelined event-driven computation engine and clock-gated spike scheduler minimize dynamic switching, achieving 61% reduction in power and 2.4× throughput improvement compared to conventional CMOS DNN accelerators. The proposed system performs dynamic visual-feature encoding, spike-based temporal fusion, and on-chip learning for anomaly and object detection tasks in low-power sensor nodes. Fabricated in 28-nm CMOS, the prototype achieves 0.29 mW power, 0.42 pJ/spike energy, and 94.3% inference accuracy, outperforming state-of-the-art neuromorphic platforms. Results demonstrate that hybrid spiking architectures integrated with VLSI-efficient plasticity circuits can deliver high-accuracy, self-adaptive AI within stringent edge constraints, enabling next-generation smart-sensing and autonomous micro-robotic intelligence.

groups

Ravi Shankar P. mail -

S. Balaji mail -

Gokul C. mail -

K. Nagarajan mail -

A. Arulkumar mail -

S. Venkatesh mail

link https://doi.org/10.54216/JISIoT.170228

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new