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

31,456 Article Results

Attention-enhanced VGG-16 architecture for precision weed detection in wheat fields

10.11591/ijict.v15i3.pp1303-1312
Akanksha Bodhale , Seema Verma , Aishwary Bodhale
This study delineates five advanced convolutional neural network designs that employ deep learning for the classification of wheat weeds. The dataset consists of greyscale photos taken in agricultural fields, enhanced with RGB lighting and cropped to 256×256×3 pixels. Normalization, batch-wise augmentation, contrast stretching, or histogram equalization were all part of the preprocessing that improved picture quality and model learning efficiency. These enhancements developed feature extraction by increasing picture contrast and homogeneity. A VGG16-based model with further Conv2D layers and spatial attention is one of the five models recommended. An additional design, inspired by ResNet50 that applies residual blocks and worldwide average pooling. A hybrid RNN integrated ICNA-CNN or LSTM for spatial-temporal content learning is another. Lastly, InceptionResNetV2 is enhanced with CNN layers and a query-key attention mechanism. We used the Adam optimizer and categorical cross-entropy to estimate the loss throughout the training for the round. At the end, all the models had ReLU activation, batch normalization, MaxPooling2D, and a dropout charge of 0.5 to keep them from overfitting. Upon evaluating their performance based on accuracy, recall, reliability, and training loss, VGG16 emerged as the standout model, achieving an impressive 99.07% precision and a remarkably low training loss of just 0.0079. The study determined that VGG16 is the optimal choice for precise wheat–weed categorization because to its superior generalizability and accuracy.
Volume: 15
Issue: 3
Page: 1303-1312
Publish at: 2026-09-01

Machine learning models for predicting daily profitability in Mauritanian digital banking operations: a case study

10.11591/ijict.v15i3.pp925-934
Mohamed Lemine Sidibba , Mohamedou Cheikh Tourad , Ahmad Outfarouin , Nema Sidi Mohamed Mawloud , Mohamedade Farouk Nanne
This article presents a case study on predicting daily profitability in Mauritanian digital banking operations using machine learning models. We utilized a dataset containing detailed information on daily operations to assess predictive models and predict profitability. The study assesses various machine learning models like logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), and multi-layer perceptron classifier (MLPClassifier), in order to identify the most precise model for predicting daily profitability. A systematic approach guides the analysis of banking transactions by performing detailed preprocessing operations which include type conversions, feature selection and missing value management. The dataset receives systematic partitioning into three parts for training, validation and testing to establish model reliability. LR had a recall rate of 99% and an F1-score of 99%, SVM had a recall rate of 53% and an F1-score of 54%, KNN had a recall rate of 96% and an F1-score of 95%, and MLPClassifier had a recall rate of 94% and an F1-score of 97%. The findings show that the LR model performed better than the other models in terms of both recall and F1-score. Future research will investigate both deep learning approaches and hybrid models to enhance prediction accuracy.
Volume: 15
Issue: 3
Page: 925-934
Publish at: 2026-09-01

Performance evaluation of a solar-driven IoT water quality monitoring system using descriptive and ANOVA analysis

10.11591/ijict.v15i3.pp1385-1394
Suziana Ahmad , Arfah Ahmad , Muhammad Uwais Mohammad Raffee , Amirul Syafiq Sadun , Aminurrashid Noordin , Mohd Firdaus Mohd Ab Halim
Water quality monitoring is vital for protecting aquatic ecosystems and ensuring sustainable water resource management. Traditional manual sampling methods are often costly, time-consuming, and unsuitable for real-time assessment. This study presents a newly designed solar-powered IoT-based water quality monitoring system for remote and continuous data collection. The system utilizes an ESP32 microcontroller integrated with pH, temperature, and total dissolved solids (TDS) sensors, powered by a 10W solar panel. Data is transmitted to a cloud-based platform wirelessly, enabling remote access and visualization via a mobile app. Performance evaluation included descriptive statistics and one-way ANOVA across four sampling sites. ANOVA results showed statistically significant differences (p < 0.05) in water quality parameters among locations, confirming the system’s sensitivity. Sensor accuracy was validated against standard meters, revealing mean relative errors below 5% for pH and TDS. The system reliably provides real-time, accurate data, supporting proactive water quality management. Integrating IoT with renewable energy offers a cost-effective, scalable, and energy-efficient solution for environmental monitoring in remote or resource-limited areas.
Volume: 15
Issue: 3
Page: 1385-1394
Publish at: 2026-09-01

A pilot review of the Google cluster workload trace 2019, methodology and its alternatives: analysis of workload in large scale data centres

10.11591/ijict.v15i3.pp1167-1178
Akash Patel , Amit Nayak , Khushi Patel , Anand Patel
Cloud data centres require shared services that are highly available, elastic capacity, managed operations, and robust recovery capabilities to facilitate the next generation of efficient, reliable, and diverse connected computing environments. Nevertheless, large-scale cloud infrastructures continue to fail regularly despite their availability, scalability, and cost efficiency, primarily due to low resource utilisation and inadequate early-stage failure management. The key to effective resource management and minimizing failures in such settings is understanding the nature of the workload and its failure modes. The current review considers the Google cluster workload trace 2019 to investigate workload and failure patterns and to generalise the results of 24 articles. The analysis is also compared with other major datasets, such as Microsoft Azure Trace, Tencent Trace, and Alibaba Trace. The paper establishes the relevance of Google cluster traces, describes the key contents of the 2019 dataset, and contrasts prior literature with respect to research objectives, trace datasets, significant results, and limitations. Moreover, it briefly describes methods for analyzing and modeling cluster traces and identifies gaps in the research that should be addressed to advance the study of cluster traces.
Volume: 15
Issue: 3
Page: 1167-1178
Publish at: 2026-09-01

Car parking lot availability detection using the faster R-CNN method

10.11591/ijict.v15i3.pp1038-1046
Andi Riansyah , Alif Hakim Al Faruq , Badieah Badieah
Parking demand continues to rise as private vehicle use increases, making timely information about available spaces essential for efficient parking management. Many existing monitoring approaches still rely on fixed slot sensors or visual detectors that report accuracy without examining how confidence settings affect the final availability decision. This work investigates Faster region-based convolutional network (Faster R-CNN) with a ResNet-50 backbone for image-based parking availability detection using a public parking-lot dataset annotated in Pascal visual object classes (VOC) format. The experiment evaluates several confidence thresholds to determine how each setting changes the balance among accuracy, precision, recall, and F1-score. The most balanced setting was obtained at a threshold of 0.5, where the model achieved 95% accuracy and 97.3% for precision, recall, and F1-score. These results show that threshold configuration is an important factor in reducing missed detections and false alarms, although validation using real campus CCTV data and direct comparison with lightweight detectors remain necessary before practical deployment.
Volume: 15
Issue: 3
Page: 1038-1046
Publish at: 2026-09-01

Wavelet-based spectrum sensing with improved thresholding for enhanced detection in cognitive radio networks

10.11591/ijict.v15i3.pp1123-1134
Nur Hanis Abdul Rani , Mas Haslinda Mohamad , Nurusolihah Zamri , Nor Khairiah Ibrahim
Cognitive radio (CR) technology is an adaptive, intelligent radio and network technology that can automatically detect available channels in a wireless spectrum. Spectrum sensing is the most important component in CR due to its ability to sense and recognize parameters related to the radio channel characteristics. However, there are some spectrums that are not used known as spectrum holes. It is challenging to accurately identify these spectrum holes, especially when employing traditional energy detection techniques, which suffer from incorrect threshold selection at low signal-to noise ratio (SNR) levels. This work suggests a wavelet-based spectrum sensing technique in conjunction with an enhanced thresholding method to improve detection accuracy and decrease noise to overcome this constraint. MATLAB simulations are used for evaluating three threshold functions: hard, soft, and improved. The results indicate that the improved threshold achieves superior denoising performance and a higher detection probability compared to the traditional energy detection method. In this study, the energy detection technique was also implemented for comparison with the wavelet-based approach. The findings reveal that wavelet-based sensing consistently provides a higher detection probability (𝑃𝐷𝐸𝑇), demonstrating its effectiveness and reliability for cognitive radio (CR) application.
Volume: 15
Issue: 3
Page: 1123-1134
Publish at: 2026-09-01

Design a Gaussian mixture-based clustering model for enhancing accuracy and robustness in smart homes

10.11591/ijict.v15i3.pp1047-1057
Kanaka Raju Rajana , Shanmuk Srinivas Amiripalli
Nowadays, smart homes have become quite complicated systems. Thus, an appropriate technique for controlling all those devices is necessary, especially considering that certain nodes are likely to be broken. In that connection, we have proposed two algorithms related to Gaussian mixture models (GMM): GMM equal and GMM unequal. They were compared with graph neural network (GNN) equal, GNN unequal, and the LucasWheel algorithms. The peculiarity of the GMM equal algorithm consists in the fact that all clusters should have similar sizes and shapes, which is quite useful for routing and balancing purposes, while the clusters in the GMM unequal algorithm can have various sizes and shapes depending on the data distribution. All five models were analyzed using 843 nodes, where failure rates ranged from zero to fifty percent. The surprising outcome of this analysis is that GMM equal performed better than the other four models in every aspect. Efficiency was steady and steadily increased in accordance with the rising failure rate. The Wiener index gradually fell from its initial value to nearly zero, suggesting a dense connection among the nodes and an evenly spread-out network. Furthermore, GMM equal attained the highest modularity among the five models at every failure level. In combination, these results indicate that GMM equal is the most balanced topology, with the best balance between reliability, efficient communication, and scalability when applied to the internet of things and smart homes.
Volume: 15
Issue: 3
Page: 1047-1057
Publish at: 2026-09-01

Bridging the linguistic divide: recent developments in machine translation for Indian languages

10.11591/ijict.v15i3.pp1272-1289
Jayanand A. Kamble , Shivajirao M. Jadhav , Vinod J. Kadam
Significant advances have been achieved in machine translation (MT) in recent times, particularly state of the art (SOTA) models for languages like English and Indian having distinct grammatical structures and limited monolingual training data. This paper analyses various recent state-of-the-art variants of large language models (LLMs) and neural machine translation (NMT) for Indian languages in comparison to statistical machine translation (SMT). It tackles key questions, such as idiomatic expressions, morphologically complex grammar or the scarceness of parallel corpora. Furthermore, it studies bytewise BPE, compares translation models in terms of BLEU scores using separate and shared-vocabulary representation with copy actions between the BPE translations, and analyses how multitask learning (Caruana (1997)) and attention mechanisms can contribute to the quality of translation. In summary, it provides directions for future work by suggesting new avenues of research including better curated datasets, more efficient approaches for lowresource languages and culturally aware translations.
Volume: 15
Issue: 3
Page: 1272-1289
Publish at: 2026-09-01

Classification of encryption attacks and strategies for mitigation

10.11591/ijict.v15i3.pp1238-1253
Anas Maaifi , Khalid Zine-Dine
Cryptography is essential for securing digital communications, yet it remains vulnerable to various malicious attacks. These attacks can be classified based on the type of cryptography they target symmetric or asymmetric. This paper presents a comprehensive classification of encryption attacks, examining the specific vulnerabilities associated with each cryptographic approach. By analyzing these attack vectors, the study shows the importance of understanding weaknesses in cryptographic systems. Furthermore, it proposes several mitigation strategies to strengthen defenses and enhance protection of sensitive information in the digital domain.
Volume: 15
Issue: 3
Page: 1238-1253
Publish at: 2026-09-01

Insight invest: sentiment-aware stock prediction using LSTM and conversational interface

10.11591/ijict.v15i3.pp1115-1122
Ankit Pande , Aakhyan Jeyush , Abhishek K. Lakhote , Saket A. Rathi , Manoj B. Chandak
The volatile nature of financial markets requires sophisticated tools that integrate advanced analytics with accessible interfaces to facilitate informed investment decisions. This research introduces Insight Invest, an intelligent investment assistant that combines sentiment analysis with time-series forecasting to deliver comprehensive stock market insights. The platform introduces the emotional quotient (EQ), a novel metric derived from the sentiment analysis of financial news, to quantify market sentiment and align it with historical stock price data. Leveraging long short-term memory (LSTM) models, the system provides precise predictions of future stock trends. Automated data collection and processing are achieved through a Flask-based backend, while an OpenAI-powered chatbot delivers intuitive interpretations of predictions and EQ values. The user-centric design, implemented using Next.js, ensures a seamless and responsive experience. By integrating state-of-the-art machine learning techniques with intuitive interfaces, Insight Invest bridges the gap between complex predictive analytics and practical usability, offering a robust framework for informed investment strategies.
Volume: 15
Issue: 3
Page: 1115-1122
Publish at: 2026-09-01

Enhanced anomaly detection in IoT networks via feature fusion and learning-based echo state networks

10.11591/ijict.v15i3.pp1154-1166
P. Palpandi , B. Sakthivel , M. Ponnrajakumari , M. Indirani , S. Govindaraju , S. Deivasigamani
The fast development of internet of things (IoT) networks has led to an increased probability of cyberattacks. Intrusion detection systems (IDS) are needed for identifying unauthorised access and malicious activities in such dynamic environments. However, existing machine learning (ML) models failed to handle the complexity and variability of modern cyber threats. In this work, a hybrid deep learning (DL)-based anomaly detection model is presented for IoT cybersecurity. The model combines three types of features: (i) supervised feature extraction using linear discriminant analysis (LDA) to extract the most discriminative features, (ii) unsupervised feature learning through autoencoders to capture latent representations of the input data, and (iii) statistical features such as mean, variance, skewness, and kurtosis to learn input characteristics. The fused feature matrix is fed into a learning based echo state network (LBESN) for final detection. The parameters of the LBESN model are tuned using black eagle optimizer (BEO). Experimental results on standard intrusion detection datasets such as UNSW-NB15, KDD99, and InSDN show that the proposed model achieves superior performance in terms of accuracy, precision, recall, and F1-score compared to conventional DL techniques.
Volume: 15
Issue: 3
Page: 1154-1166
Publish at: 2026-09-01

Advanced encryption standard with asymmetric key exchange for text encryption

10.11591/ijict.v15i3.pp1263-1271
Ravindra K Reddy , Vijayalakshmi P
When creating communication systems, securing data is crucial and improved randomization in creating secret keys contributes to more secure systems. Unfortunately, the symmetric ciphers used for data encryption, such as the advanced encryption standard (AES), may be subject to attacks that exploit timing measurements to deduce the secret key used for encryption, resulting in a significant lack of research on the security of hybrid implementations (usually defined as incorporating AES and asymmetric ciphers) for AES encryption. We introduce a new hybrid encryption method that combines the AES encryption standard with elliptic curve cryptography (ECC). In this hybrid form of encryption, ECC is utilized to facilitate secure encryption and transmission of the AES key and cycle through 16 rounds of AES to encrypt the majority of the data. We provide a performance comparison between the new algorithm and the AES-128 encryption standard. Our findings indicate that the new hybrid encryption method produced an average encryption time of 0.0002 seconds for 10MB files, significantly faster than the AES-128 encryption standard, which takes an average of 0.0016 seconds. The new hybrid method exhibits significant resistance to cryptanalytical attempts, experiencing an average avalanche effect of 49.84%, while maintaining the AES nonlinearity value at 112. As such, we conclusively state that the new hybrid encryption method utilizing ECC and AES will provide effective security for user data against timing side-channel attacks while remaining an efficient method for performing encryption.
Volume: 15
Issue: 3
Page: 1263-1271
Publish at: 2026-09-01

Social media interaction of halal fashion brand in Indonesia: a netnographic study of image management

10.11591/ijict.v15i3.pp1395-1407
Azhar Alam , Fatmawati Fatmawati , Muhamad Al Bagir , Raisa Aribatul Hamidah
Research on halal fashion has largely focused on consumer purchase decisions, with limited attention to how halal fashion brands interact with consumers and manage their brand image on social media platforms such as Instagram. This study addresses this gap by examining brand interaction patterns and image management strategies among leading halal fashion brands in Indonesia. Using a netnographic approach, it analyzed 1,321 Instagram posts from six halal fashion brands over six months (July–December 2022), applying content and image‑management codes to classify post types (photos and videos) and representation strategies (personalized, contextual, and celebrity use). The findings show a slightly higher proportion of photo posts (51%, 674 posts) than video posts (49%, 647 posts), with hijab fashion brands more active than Muslim and sports fashion brands in producing content. Across all brands, image management relied predominantly on personal context and non‑celebrity representation, while professional context and celebrity‑based posts were used less frequently. These results suggest that halal fashion brands strategically emphasize relatable, personalized, and non‑celebrity content to build brand image and engagement on Instagram, offering practical guidance for brand managers in designing effective social media strategies and contributing novel empirical evidence on brand interaction and image management in the halal fashion sector.
Volume: 15
Issue: 3
Page: 1395-1407
Publish at: 2026-09-01

Prognosis of vector borne dengue disease outbreak in urban areas using multivariate analysis

10.11591/ijict.v15i3.pp1066-1077
Pratik S. Machchar , Purvi N. Ramanuj , Rajan Patel , Jitendra Bhatia , Kuntesh Jani
Vector borne disease like dengue continues to pose a significant climate-sensitive public health challenge in tropical regions such as Brazil, Peru, and India. This study examines the feasibility of predicting dengue outbreaks using weekly multivariate time-series data from San Juan (SJ), Puerto Rico and Iquitos (IQ), Peru. Dengue incidence was analyzed alongside meteorological, environmental, and vegetation-based variables to capture key climatic influences. Several machine learning and deep learning approaches were evaluated, including LightGBM. Model performance was assessed using root mean square error (RMSE) and mean absolute error (MAE). The results show that LightGBM achieved the low est RMSE/MAE, indicating strong short-term predictive accuracy and excellent interpretability. Feature importance analysis and principal component analysis (PCA) identified precipitation, dew point temperature, and humidity as the most influential predictors of dengue incidence. The study demonstrates that advanced machine learning models can serve as reliable early warning systems for vector-borne diseases. While this research focuses on dengue, the methodology is adaptable to other vector-bone datasets and diseases, offering a flexible tool for public health authorities to predict and mitigate outbreaks in diverse urban contexts.
Volume: 15
Issue: 3
Page: 1066-1077
Publish at: 2026-09-01

A recent hybrid of IoT with adaptive extended Kalman filter fuzzy logic for children’s health dietary

10.11591/ijict.v15i3.pp1217-1225
Noorrezam Yusop , Massila Kamalrudin , Mohd Nazrien Zaraini , Siti Fairuz Nurr Sardikan
The increasing prevalence of childhood obesity highlights the critical need for intelligent dietary monitoring systems that are tailored to individual nutritional requirements. This work describes the creation and testing of an internet of things (IoT) hybrid using an adaptive extended Kalman filter and fuzzy logic (AEKFFL-IoT) model aimed at providing personalised food calorie prediction for children. The system uses IoT devices to collect real-time sensor data, such as height, weight, and BMI, and then employs extended Kalman filter (EKF) algorithms to denoise signals and anticipate trends. Fuzzy logic inference is then utilised to adaptively calculate caloric requirements based on biometric data. Experimental results reveal that the proposed AEKFFL model has a training root mean square error (RMSE) of 21.43 kcal and a testing RMSE of 22.35 kcal, exceeding existing rule-based, wearable, and ANN-driven models in terms of accuracy and generalisation. Furthermore, the system achieves high classification accuracy (94.5%) for BMI categorisation and fuzzy rule application. Comparative examination confirms the model’s adaptability, real-time integration, and mobile deployment capability. This study presents a scalable and intelligent approach for child-centered dietary monitoring, paving the path for personalised digital health interventions.
Volume: 15
Issue: 3
Page: 1217-1225
Publish at: 2026-09-01
1 2 3
...
2097 2098
Show 34 of 2098

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