Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

30,411 Article Results

Advanced IoT-integrated real-time fire detection and automated mitigation system

10.11591/ijict.v15i2.pp861-868
Rama Krishna Peddarapu , Ajimera Abhinav , Gnana Sathwika V. N. V. , Poosa Brijesh , Amrutha Varshini Ravula
In the field of industry and commerce safety, tackling the most challenging and ongoing fire threats requires the advance internet of things (IoT) integrated real-time fire detection and automated mitigation system. Leveraging IoT and multi-modal sensing in fire safety, the system combines flame, gas, and humidity sensors and cameras to provide continuous real time monitoring and appropriate management of the threats. Real-time automated hazard interventions, such as sprinkler system engagement and geocoded alerts to fire departments, significantly improve life safety outcomes of the system. Active damage mitigation IoT devices provide integrated damage mitigation safety and individual IoT device remote monitoring. In the scope of industry and commerce, this system is a demonstration of the impact of IoT on improving fire safety.
Volume: 15
Issue: 2
Page: 861-868
Publish at: 2026-06-01

Exploring player interaction and team cooperation in MMOG playability enhancement

10.11591/ijict.v15i2.pp644-654
Gong Xiaoxue , Lili Nurliyana Abdullah , Azrul Hazri Jantan , Noris Mohd Norowi , Fatimah Sidi , Gulmira Abildinova
The massively multiplayer online games (MMOGs) continue to grow in popularity, and it has become particularly important to understand the key factors that influence team playability. While existing research has focused primarily on system functionality and individual player experience, insufficient attention has been paid to the role of team dynamics in player satisfaction. This study focuses on the core variables that influence team playability, including teamwork, task dependency, team loyalty (TLO), and team relationships (TR), and explores how these variables work together to influence player experience. This study used a combination of exploratory research (multi-variates) and a questionnaire survey (N=1064) to initially construct a team playability model, which was validated by structural equation modeling (SEM). The results show that TR have a significant positive effect on teamwork efficiency, and captains with transformational leadership (TL) styles not only enhance TR but also further improve overall team effectiveness (TE) and player satisfaction. This study provides MMOG developers with theoretical support for designing game mechanics centered on team interaction to enhance overall playability and player stickiness.
Volume: 15
Issue: 2
Page: 644-654
Publish at: 2026-06-01

Real-time emotion prediction system using big data analytics

10.11591/ijict.v15i2.pp869-879
Manpreet Kaur Dhaliwal , Rohini Sharma , Rajbinder Kaur
Emotions are an inseparable part of human existence. Emotions have a big impact on the success and failure of the human race. Comprehending human emotions could prove beneficial in creating improved systems for education, security, market sales, production, healthcare and other areas. Big data analytics applied to streamlined real time emotion sensor’s data can give new insights to anticipate stress before it arises and help in making significant choices that improve people's quality of life. This work proposes a framework for big data management and analysis of GSR sensor’s data in real-time for predicting emotions in human participants. Supervised learning techniques, ensemble boosted tree, neural network, Naïve Bayes, support vector machine, decision tree, K-nearest neighbor, and quadratic discriminant analysis are applied to the collected data. Two distinct criteria have been utilized for testing on real-time data one is trained on all participant data, resulting in a generalized system, while the other is trained on participant-specific data, resulting in a personalized system. Hence, the personalized system achieves an accuracy of up to 80.64% across all classes and 100% for binary classes as compare to generalized system achieves 78.12% accuracy. It is concluded that for the purpose of predicting emotions, the personalized model performs better than the generalized model.
Volume: 15
Issue: 2
Page: 869-879
Publish at: 2026-06-01

Deep learning-based optimization techniques for network lifetime enhancement in wireless sensor networks

10.11591/ijict.v15i2.pp623-633
Abhay Raghunath Gaidhani , Amol D. Potgantwar
Wireless sensor networks (WSNs) are integral to applications like environmental monitoring, healthcare, and surveillance, yet they face the critical challenge of limited energy resources, which shortens the network's operational lifespan. Addressing this issue, this paper explores deep learning-based optimization techniques as a solution to enhance network lifetime by efficiently managing energy consumption. We present a detailed review of the existing challenges in WSNs and examine various deep learning methods, including neural networks, deep reinforcement learning (DRL), and generative adversarial networks, specifically tailored for WSN optimization. In this study, we introduce a new reinforcement learning (RL) based optimization algorithm to prolong the network lifetime. The proposed technique is intended to smartly distribute the energy consumption among the network elements, leading to desirable performance with regard to the battery lifetime. The paper ends with a summary of design aspects and future research directions to improve the WSN performance further based on deep learning.
Volume: 15
Issue: 2
Page: 623-633
Publish at: 2026-06-01

Can machines imagine? Critical thinking and cultural reasoning in multimodal-multilingual AI

10.11591/ijict.v15i2.pp823-838
Mohammad Awad AlAfnan , Siti Fatimah MohdZuki , Shefa Mohammad AlAfnan
Effective communication across languages and cultures is essential in today’s interconnected world. Multimodal-multilingual language models (MMMLMs) aim to advance this goal by integrating text, speech, and visual understanding across diverse linguistic contexts. This study evaluates four leading MMMLMs-GIT, mPLUG, CLIP, and Whisper + GPT-4V-on cross lingual and cross-modal tasks, including image captioning, visual question answering, speech-to-image generation, and idiomatic translation. Performance was assessed in high-resource (English, Arabic), medium resource (Malay), and low-resource (Macedonian) settings. Results show strong performance in structured tasks but notable limitations in cultural reasoning, figurative language interpretation, and semantic grounding in low-resource environments. GIT delivered the most consistent multilingual results, while Whisper + GPT-4V excelled in fluency yet lacked cultural sensitivity. To address these gaps, the study proposes culturally informed evaluation protocols that integrate quantitative metrics such as BLEU, CIDEr, and F1 with qualitative, community-centered approaches. These include cross-cultural annotation panels, inter-rater reliability validation using Cohen’s kappa, and a novel “cultural fidelity” metric to measure alignment with culturally specific norms. The findings emphasize the need for inclusive datasets, ethical development, and interdisciplinary collaboration to ensure MMMLMs support equitable and culturally aware global communication.
Volume: 15
Issue: 2
Page: 823-838
Publish at: 2026-06-01

Intelligent home automation framework using sensor fusion and machine learning for energy efficiency and thermal comfort

10.11591/ijict.v15i2.pp545-552
Franklin Ovuolelolo Okorodudu , Gracious Chukwuweike Omede , Etinosa Eugene Osawe
This paper presents an innovative, intelligent home automation framework integrating sensor fusion and machine learning to promote energy efficiency and thermal comfort in residential settings. Utilising low-cost hardware such as the Arduino Uno R3, passive Infrared (PIR) sensors, KY-018 photoresistors, and KY-028 temperature sensors, the system achieves a human presence detection accuracy of 95.3% via a random forest classifier. Over a three-month period, testing in several homes showed that the system is 99.7% reliable, responds in 1.2 seconds, and costs 85% less than commercial options. This research lays the groundwork for sustainable smart homes by providing a mathematical model for optimizing energy use and a unified modeling language (UML) model of the system architecture. These results show how important it is to have open-source technology that is cheap and could help smart building systems spread around the world. The study utilized a controlled experimental design featuring five families, with sensor data gathered at 10-second intervals over a three-month period. A random forest classifier trained on 10,000 labeled data points could correctly guess whether or not a person was present 94.8% of the time and 95.7% of the time. The framework is useful because it combines cheap sensors with a lightweight machine-learning pipeline that can work on small microcontrollers. This solves the long-standing problem of the cost performance gap seen in prior smart-home deployments.
Volume: 15
Issue: 2
Page: 545-552
Publish at: 2026-06-01

Semantic interoperability in IoT for Industry 4.0: Review, taxonomy, challenges, and future research

10.11591/ijict.v15i2.pp909-924
Devamekalai Nagasundaram , Erum Ashraf , Selvakumar Manickam , Shams Ul Arfeen Laghari , Shankar Karuppayah
Semantic interoperability is a critical enabler for achieving the Industry 4.0 vi sion, ensuring that heterogeneous IoT devices, systems, and applications can ex change and interpret data consistently. Despite its importance, achieving seman tic interoperability continues to pose significant challenges due to the diversity of data formats, standards, and ontologies used across industrial IoT environ ments. This paper presents a comprehensive review and taxonomy of semantic interoperability within Industry 4.0, analyzing existing frameworks, protocols, and ontological models. We classify current approaches based on their architec tural layers, semantic technologies, and application domains. Additionally, this study identifies the limitations of prevailing solutions, highlights open research challenges, and proposes future directions for enhancing semantic interoperabil ity in industrial IoT systems. The insights provided aim to support researchers and practitioners in developing scalable, secure, and semantically aligned IoT ecosystems for Industry 4.0.
Volume: 15
Issue: 2
Page: 909-924
Publish at: 2026-06-01

Multiclass classification using variational quantum circuit on benchmark dataset

10.11591/ijict.v15i2.pp578-587
Muhammad Hamid , Bashir Alam , Om Pal
Classification is a major task in data science. Data classification is required in many industries such as healthcare, transport, and finance. Noisy intermediate-scale quantum (NISQ) era. Quantum computers are capable of solving complex data challenges and can be used for the classification of the data with minimum features. In this regard, quantum neural networks are being used extensively for data classification. In this paper, we employ variational quantum circuits for the task of multiclass classification. A hybrid approach is used for building the neural network. In which quantum circuits are used for the feedforward architecture, while in back-propagation, parameters are updated using a classical optimizer on classical computers. We have successfully demonstrated multiclass classification using the proposed approach on benchmark data sets. Our results show that variational quantum circuit (VQC) are a promising candidate for classification problems with fewer features. We have performed experiments on International Business Machines Corporation (IBM) quantum hardware and simulators.
Volume: 15
Issue: 2
Page: 578-587
Publish at: 2026-06-01

Performance improvement of DC microgrids via adaptive neuro-fuzzy inference system -optimized AI-tuned fractional order proportional-integral-derivative controllers

10.11591/ijict.v15i2.pp797-804
Debani Prasad Mishra , Sarita Samal , Manas Ranjan Sahu , Sonna Murari , Piyuskant Das , Surender Reddy Salkuti
This paper presents a novel approach to enhance the dynamic performance of direct current (DC) microgrids using an artificial intelligence (AI)-tuned fractional order proportional-integral-derivative (FO-PID) controller, further optimized through an adaptive neuro-fuzzy inference system (ANFIS). Conventional PID controllers tend to fail when it comes to dealing with microgrid environment-related non-linearities and uncertainties, particularly under changing load and generation situations. To remedy this, the suggested approach combines AI-tuned tuning algorithms for selecting initial parameters, and then ANFIS optimization to fine-tune the FOPID gains adaptively for better control precision. The performance of the hybrid control approach is tested through MATLAB simulations on a generic DC microgrid model that includes distributed energy resources, power electronic converters, and dynamic loads. Comparative evaluation against standard PID and independent FOPID controllers verifies remarkable advantages in terms of voltage regulation, stability, and transient response in various operating conditions. Amongst the achieved outcomes, it highlights the strength of the proposed ANFIS-optimized AI-tuned FOPID controller as a smart and robust strategy for real-time control of DC microgrids.
Volume: 15
Issue: 2
Page: 797-804
Publish at: 2026-06-01

Trust-based secure routing in IoT networks using machine learning for enhanced anomaly detection and risk mitigation

10.11591/ijict.v15i2.pp839-849
Sangeetha Krishnaswamy , Arulanandam Karalagan
The rapid growth of the internet of things (IoT) has led to the development of new challenges in ensuring secure and reliable data transmission. This paper proposes a trust-based secure routing protocol (TBSRP) designed to mitigate security threats such as routing attacks in IoT networks. The core innovation lies in the dual-layer trust evaluation mechanism, which combines reputation-based trust and behavioral analysis to dynamically adjust routing decisions based on real-time performance and historical behavior of network nodes. To enhance security, the protocol incorporates an adaptive threshold mechanism that adjusts trust criteria based on observed network conditions and an anomaly detection system utilizing machine learning (ML) algorithms for real-time monitoring of node behavior. Experimental evaluation demonstrates that TBSRP outperforms existing protocols (such as Ad hoc on-demand distance vector (AODV), trust-based AODV (TB-AODV), energy-efficient secure routing (ESR), and Secure AODV (SEC-AODV)) in key performance metrics, including packet delivery ratio (PDR), end-to-end delay, throughput, and routing overhead. The proposed protocol exhibits strong resilience to the increasing number of malicious nodes and varying network conditions, making it highly effective for securing IoT networks. This work contributes to the development of adaptive, scalable, and secure routing protocols for IoT environments, with the potential for further optimization through advanced ML techniques and real-world implementation.
Volume: 15
Issue: 2
Page: 839-849
Publish at: 2026-06-01

A review of sensemaking design elements: towards an affordances typology

10.11591/ijict.v15i2.pp488-496
Fadzlin Ahmadon , Murni Mahmud , Muna Azuddin
This study explores the intersection of interaction design and sensemaking within digital systems, aiming to identify and categorize key affordances that enhance user sensemaking. Starting with a focused literature review, key design elements such as tagging and annotation are identified, important for effective sensemaking in interaction design. Drawing on Maier's construct of affordances, the behaviours of these design elements are analyzed to derive specific affordances integral to enhancing user experience. The primary objective is to develop a generalized affordance typology that supports sensemaking across various digital systems. This typology organizes the derived affordances into broad themes such as effortless discovery, expressive freedom, collaborative engagement, cognitive support, insight enhancement, and user empowerment. This typology serves as a tool for interaction designers, facilitating the application of these themes in various design scenarios to create more intuitive and effective digital environment for sensemaking.
Volume: 15
Issue: 2
Page: 488-496
Publish at: 2026-06-01

Hybrid deep neural network model for aspect and opinion extraction with multi-head attention-driven sentiment analysis

10.11591/ijict.v15i2.pp769-777
Abhinandan Shirahatti , Ramesh Medar , Vijay Rajpurohit , Sanjeev Kaulgud , Mrutyunjaya Mathad Shivamurthaiah
Finding and extracting significant features from review sentences is known as aspect triplet extraction, and it provides succinct information on the elements that users have addressed. This method makes sentiment analysis and opinion mining easier, which helps to provide an adequate understanding of user opinions in reviews. This research presents a novel approach to achieve aspect-sentiment triplet-extraction (ASTE) using a deep neural network and transformer-based multi-head attention model. The proposed hybrid model adopts a pipeline methodology, concurrently extracting opinions and aspects while performing sentiment classification. The study addresses the intricate challenge of identifying triplets that capture nuanced relationships between terms and sentences, employing a deep neural network for joint extraction of aspects and opinions using a sequential tagging method. Sentiment classification is seamlessly integrated into the pipeline, treating sentiment recognition as a classification task, and aspect and opinion extraction as text-extraction challenges. Evaluations was out experimentally on the SemEval 2016 restaurant dataset demonstrate the effectiveness of the model, despite issues with unequal distribution of data.
Volume: 15
Issue: 2
Page: 769-777
Publish at: 2026-06-01

Diabetic retinopathy detection using SWIN transformer

10.11591/ijict.v15i2.pp750-758
Sheetal J. Nagar , Nikhil Gondaliya
Diabetic retinopathy (DR) is a diabetes related eye disorder that damages the retina. DR is among the most specific complications of diabetes. A vital challenge for automated detection systems in medical image diagnosis is to minimize the false negative rate for patients’ timely treatment. This paper presents a novel strategy employing the shifted window (SWIN) Transformer for efficiently modeling local and global visual information to address this challenge. We have proposed our work to maximize the true positive ratio and minimize the false negative ratio for the automated process of diagnosing the level of DR, so that patients with positive signs of DR can be predicted most accurately and can save vision. The results suggest that SWIN Transformer architecture, along with the contrast-limited adaptive histogram equalization (CLAHE) technique, provides a robust option for developing a reliable DR detection system. The results indicate that the proposed approach achieves 96% weighted recall across all the levels of DR detection and 97.45% validation accuracy for the eyePACS DR detection dataset, as well as 99% weighted recall across all the levels of DR detection, along with 99.26% validation accuracy for APTOS 2019 Blindness Detection dataset. Thus, this study aimed to develop a DR detection system focused on minimizing false negatives using the SWIN transformer.
Volume: 15
Issue: 2
Page: 750-758
Publish at: 2026-06-01

Enhancing support vector machine performance using particle swarm optimization for sentiment analysis

10.11591/ijict.v15i2.pp523-534
Christofer Satria , Anthony Anggrawan , Peter Wijaya Sugijanto , Husain Husain , I Nyoman Yoga Sumadewa , Victoria Cynthia Rebecca
Recently, social media has established itself as a leading platform in various sectors. Meanwhile, text extraction and sentiment analysis classification have attracted significant attention in research. Regrettably, traditional sentiment analysis often falls short of accurately capturing sentiment nuances. At the same time, machine learning has enabled more effective sentiment analysis, data mining, and classification, as well as the development of models that incorporate artificial intelligence. Therefore, the purpose of this study is to optimize sentiment analysis of public opinion in social media regarding Grand Prix motorcycle racing (MotoGP) and World Superbike (WSBK) events using machine learning and an optimized machine learning method. This study applies the support vector machine (SVM) machine learning method and enhances its performance through optimization by integrating it with the particle swarm optimization (PSO) algorithm. This study found that the SVM method achieved 80.15% accuracy, 75.63% recall, and 76.89% F1-score. In contrast, the SVM method combined with PSO achieves accuracies of 81.82%, 79.9%, and 79.62% for recall, precision, and F1-score, respectively, in classifying the sentiment of sporting events. The implications suggest that applying Hybrid SVM with PSO significantly enhances classification accuracy in sentiment analysis.
Volume: 15
Issue: 2
Page: 523-534
Publish at: 2026-06-01

Machine learning centered energy optimization in mobile edge computing: a review

10.11591/ijict.v15i2.pp465-476
Chandapiwa Mokgethi , Tshiamo Sigwele , Kabo Clifford Bhende , Aone Maenge , Selvaraj Rajalakshmi
Current literature reviews on machine learning-based approaches for mobile edge computing (MEC) energy optimization often lack in-depth gap analysis and fail to identify trends or offer actionable insights. Most focus narrowly on comparing MEC frameworks without critically evaluating or benchmarking prior research. This review contributes by addressings these gaps via analysis of existing reviews and related studies, with a focus on ML models, research objectives, evaluation metrics, datasets, tools, and gap identification. The review method follows a systematic literature review (SLR) using the PRISMA framework for transparency and reproducibility. Key findings reveal persistent challenges in energy consumption, computational overhead, cost, and poor performance in accuracy, QoS, latency, scalability, and carbon footprint. Deep reinforcement learning (DRL) emerges as the most commonly used model (55%), while TensorFlow (35%) is the most adopted tool, valued for its flexibility and robust community support. The AudioSet dataset is frequently used (28%) due to its compatibility. However, methodology limitations include dependency on study quality and exclusion of grey literature, context sensitivity. The review concludes by recommending advanced solutions such as serverless computing, liquid cooling, containerization, software-defined power, quantum computing, and blockchain to drive future MEC energy optimization.
Volume: 15
Issue: 2
Page: 465-476
Publish at: 2026-06-01
1 2 3
...
2027 2028
Show 2 of 2028

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration