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

Computationally efficient pixelwise deep learning architecture for accurate depth reconstruction for single-photon LiDAR

10.11591/ijece.v15i6.pp5934-5941
Yu Zhang , Yiming Zheng
This work introduces a compact deep learning architecture for depth image reconstruction from time-resolved single-photon histograms. Unlike most deep learning approaches that mainly rely on 3D convolutions, our network is implemented purely with 1D convolutions without assistance from other sensors or pre-processing. Both synthetic and real datasets were used to evaluate the accuracy of our model for challenging signal-to-background ratios (SBRs), ranging from 5:1 to 1:1. Conventional maximum likelihood (ML) and another photon-efficient optimization-based algorithm were adopted for performance comparisons. Results from synthetic data show that our model achieves lower mean absolute error (MAE). Additionally, results from real data indicate that our model exhibits better reconstruction for high-ambient effects and provides better spatial information. Unlike existing 3D deep learning models, we process pixel-wise histograms continuously, rather than splitting the point cloud and stitching them afterward, which saves memory and computational resources, thereby laying a foundation for real-world embedded applications.
Volume: 15
Issue: 6
Page: 5934-5941
Publish at: 2025-12-01

Edge-aware distilled segmentation with pseudo-label refinement for autonomous driving perception

10.11591/ijra.v14i4.pp528-538
Novelio Putra Indarto , Oskar Natan , Andi Dharmawan
Achieving precise semantic segmentation is essential for enabling real-time perception in autonomous systems, yet leading approaches typically require substantial annotated data and powerful hardware, restricting their use on devices with limited resources. This work introduces an efficient segmentation framework that integrates pseudo-label refinement, knowledge distillation, and entropy-based confidence filtering to train compact student networks suitable for edge deployment. High-quality pseudo-labels are first produced by a robust teacher network, then further improved using a dense conditional random field to boost spatial consistency. An entropy-based selection mechanism removes unreliable predictions, ensuring that only the most trustworthy labels guide the student model's training. The use of knowledge distillation effectively transfers detailed semantic understanding from the teacher to the student, enhancing accuracy without added computational overhead. Experimental results with multiple EfficientNet backbones reveal that this pipeline improves segmentation accuracy and output clarity, while also supporting real-time or near real-time inference on CPUs with limited processing power. Extensive ablation and qualitative studies further confirm the method's robustness and flexibility for real-world edge applications.
Volume: 14
Issue: 4
Page: 528-538
Publish at: 2025-12-01

Enhancing semantic segmentation with a boundary-sensitive loss function: a novel approach

10.11591/ijece.v15i6.pp5327-5335
Ganesh R. Padalkar , Madhuri B. Khambete
Semantic segmentation is crucial step in autonomous driving, medical imaging, and scene understanding. Traditional approaches leveraging manually extracted pixel properties and probabilistic models, have achieved reasonable performance but suffer from limited generalization and the need for expert-driven feature selection. The rise of deep learning architectures has significantly improved segmentation accuracy by enabling automatic feature extraction and capturing intricate object details. However, these methods still face challenges, including the need for large datasets, extensive hyperparameter tuning, and careful loss function selection. This paper proposes a novel boundary-sensitive loss function, which combines region loss and boundary loss, to enhance both region consistency and edge delineation in segmentation tasks. Implemented within a modified SegNet framework, the approach proposed in the paper is evaluated with the semantic boundary dataset (SBD) dataset using standard segmentation metrics. Experimental results indicate improved segmentation accuracy, substantiating to proposed method.
Volume: 15
Issue: 6
Page: 5327-5335
Publish at: 2025-12-01

6G internet of things networks for remote location surgery also a review on resource optimization strategies, challenges, and future directions

10.11591/ijece.v15i6.pp5968-5977
Md Asif , Tan Kaun Tak , Pravin R. Kshirsagar
Remote location surgery presents stringent requirements for wireless communication, particularly in terms of reliability, speed, and low latency. The emergence of sixth-generation (6G) wireless networks is expected to address these challenges effectively. With the rapid expansion of internet of things (IoT) applications in healthcare, maintaining real-time connectivity has become essential. Ensuring such performance in 6G-enabled IoT networks relies heavily on the implementation of advanced resource optimization techniques. Recent studies have focused on improving key performance metrics, including latency, reliability, energy efficiency, spectral efficiency, data rate, and bandwidth usage. Comprehensive reviews of these techniques reveal a growing emphasis on multi-objective optimization strategies to balance conflicting requirements. Research has also highlighted limitations in existing approaches, suggesting the need for further innovation, particularly for mission-critical applications like remote surgery. Within this context, 6G IoT systems have demonstrated the potential to maintain high data rates and stable throughput, both of which are essential for safe and responsive surgical operations conducted over long distances. These findings underscore the importance of continued development in resource management to fully enable remote healthcare delivery through advanced wireless technologies.
Volume: 15
Issue: 6
Page: 5968-5977
Publish at: 2025-12-01

Charaterization of Candida species isolated from pregnant women with vaginal discharge attending anternatal clinic in parts of Edo State, Nigeria

10.11591/ijphs.v14i4.26670
Marcellinus Okodua , Dorcas Aderibigbe , Daniel Oyewole Oni , Valentine Imade Oni , Faith Unuabonah , Osamuyimen Iserhienrhien , Aidevbo Otuyoma Eyaufe
During pregnancy, women are more prone to vaginal infections due to immunological changes. These infections are mainly caused by different species of Candida, a reality that makes distinguishing Candida species vital since non-albicans strains often resist common antifungals, making accurate diagnosis key to better maternal outcomes. Therefore, this study aimed at isolating and characterizing Candida species from pregnant women with vaginal discharge. The sample size consisted of 220 subjects (151 pregnant and 69 non-pregnant women). Samples were collected following standards guidelines and analyzed for Candida by culturing on Sabouraud dextrose agar (SDA) and CHROMagerTM Candida (CAC). The overall prevalence of vulvovaginal candidiasis (VVC) was 34.55%, and VVC infection was more common among women >30 years. VVC infection was more common in women in their second trimester (48.05%). There was a significant difference with gestational age (p≤0.05). Candida albicans was the most common cause of VVC in both pregnant (75.86%) and non-pregnant (77.78%) subjects. There was no significant variation (p>0.05) in the species of Candida isolated from pregnant and non-pregnant women. Overall, C. albicans was the most common species isolated from pregnant women. This was followed by Candida krusei (10.34%), Candida dublinensis, Candida. glabrata (5.17% each) and Candida parapsilosis (1.72%); while mixed infection, both C. dublinensis and C. parapsilosis were found in 1.72%. Among the non-pregnant women, C. albicans was the most common species isolated, followed by C. dublinensis and C. glabrata (11.11% each). C. krusei and C. parapsilosis were not isolated from non-pregnant women. Routine screening of vulvovaginal candidiasis and other vaginal infections should be conducted during antenatal visits to enable early detection and treatment.
Volume: 14
Issue: 4
Page: 1757-1764
Publish at: 2025-12-01

Intuitive effectiveness degree of research methodologies for spectrum sensing in cognitive radio network

10.11591/ijece.v15i6.pp5699-5707
Pushpa Yellappa , Dr.Keshavamurthy Keshavamurthy
The phenomenon of spectrum sensing plays an essential role in cognitive radio network (CRN) that is performed in real-time for better adaptability to dynamic usage of spectrum. However, efficient decision-making is often noted to be affected by dynamic environmental condition, interference, and noise leading to declination in performance. In recent times, there are proposals for various methodologies addressing such issues targeting towards improving spectrum sensing along with machine learning and energy detection approach, which is gaining its pace for technical research implementation. Irrespective of this advancement, ambiguity shrouds regarding the contrast effectiveness associated with these methods and their appropriateness in different situation. Hence, this manuscript presents a comprehensive and yet crisp review work to offer concise assessment of latest methodologies towards spectrum sensing used in CRN ecosystem. The paper has an inclusion of existing techniques, presents their potentials and shortcomings, exhibited evolving trends of research, extracts key gaps and challenges. The prime intention of this review work is towards guiding the future researchers and scholars by facilitating deeper insight towards the recent state of technologies in spectrum sensing.
Volume: 15
Issue: 6
Page: 5699-5707
Publish at: 2025-12-01

Machine and deep learning classifiers for binary and multi-class network intrusion detection systems

10.11591/ijai.v14.i6.pp4814-4827
Ahmad Aloqaily , Emad Eddien Abdallah , Esraa Abu Elsoud , Yazan Hamdan , Khaled Jallad
The rapid proliferation of the internet and advancements in communication technologies have significantly improved networking and increased data vol ume. This phenomenon has subsequently caused a multitude of novel attacks, thereby presenting significant challenges for network security in the intrusion detection system (IDS). Moreover, the ongoing threat from authorized entities who try to carry out various types of attacks on the network is a concern that must be handled seriously. IDS are used to provide network availability, confidentiality, and integrity by employing machine learning (ML) and deep learning (DL) algorithms. This research aimed to study the impacts of the binary and multi-attack instances label by establishing IDS that leverages hybrid algorithms, including artificial neural networks (ANN), random forest (RF), and logistic model trees (LMTs). The paper addresses challenges such as data pre processing, feature selection, and managing imbalanced datasets by applying synthetic minority oversampling technique (SMOTE) and Pearson’s correlation methodologies. The IDS was tested using network security laboratory knowledge discovery datasets (NSL-KDD) and catalonia independence corpus intrusion detection system (CIC-IDS-2017) datasets, achieving an average F1-score of 96% for binary classification on NSL-KDD and 85% for binary classification on CIC-IDS-2017, while for multi-classification, the proposed model achieved an average F1-score of 82% and 96% for NSL-KDD and CIC-IDS-2017 successively.
Volume: 14
Issue: 6
Page: 4814-4827
Publish at: 2025-12-01

A systematic review of heuristic and meta-heuristic methods for dynamic task scheduling in fog computing environments

10.11591/ijece.v15i6.pp5986-6000
Hamed Talhouni , Noraida Haji Ali , Farizah Yunus , Saleh Atiewi , Yazrina Yahya
The distributed fog node network and variable workloads make task distribution difficult in fog computing. Optimizing computing resources for dynamic workloads with heuristic and metaheuristic algorithms has shown potential. To address changing workloads, these algorithms enable real-time decision-making. This systematic review examines heuristic, meta-heuristic, and real-time dynamic job scheduling strategies in fog computing. Static methods like heuristic and meta-heuristic algorithms can help modify dynamic task scheduling in fog computing situations. This paper covers a current study area that stresses real-time approaches, meta-heuristics, and fog computing environments' dynamic nature. It also helps build reliable and scalable fog computing systems by spotting dynamic task scheduling trends, patterns, and issues. This study summarizes and analyzes the latest fog computing research on task-scheduling algorithms and their pros and cons to adequately address their issues. Fog computing task scheduling strategies are detailed and classified using a technical taxonomy. This work promises to improve system performance, resource utilization, and fog computing settings. The work also identifies fog computing job scheduling innovations and improvements. It reveals the strengths and weaknesses of present techniques, paving the way for fog computing research to address unresolved difficulties and anticipate future challenges.
Volume: 15
Issue: 6
Page: 5986-6000
Publish at: 2025-12-01

Association between body shaming and body image in nursing students: implications for health education from Indonesia

10.11591/ijphs.v14i4.24985
Citra Windani Mambang Sari , Rizky Chintya Dewi , Hendrawati Hendrawati
During emerging adulthood, the difference between the ideal body standard and one’s actual body often leads to body-shaming treatment. Persistent experiences of body shaming can significantly harm an individual’s body image. This study aims to identify the association between body-shaming acts and body image in university students. The study population consisted of students aged 18-25 who had experienced body shaming (n = 841). Using a non-probability total sampling method, 448 respondents were included. Data were collected using a body-shaming acts questionnaire and the MBSRQ-AS questionnaire, then analyzed with univariate and bivariate analysis employing the Chi-square test. The results showed a significant relationship between body-shaming acts and body image. Most students received body-shaming treatment at a low level (50.9%), while most body image categories were negative (50.9%). These findings highlight the importance of health workers’ involvement in preventing body-shaming acts and improving students’ body image.
Volume: 14
Issue: 4
Page: 1747-1756
Publish at: 2025-12-01

Exploring feature engineering and explainable AI for phishing website detection: a systematic literature review

10.11591/ijece.v15i6.pp5863-5878
Norah Alsuqayh , Abdulrahman Mirza , Areej Alhogail
Detecting phishing websites is a rapidly evolving field aimed at identifying and mitigating cyberattacks targeting individuals, organizations, and governments. Ongoing progress in artificial intelligence (AI) has the potential to revolutionize phishing detection by enhancing model accuracy and improving transparency through eXplainable AI (XAI). However, significant challenges remain, particularly in integrating feature engineering with XAI to address sophisticated phishing strategies including zero-day attacks, that evade traditional detection mechanisms. To overcome these challenges, this examines the impact of feature engineering and XAI in phishing detection, emphasizing their ability to enhance accuracy while providing interpretability. By integrating feature extraction with interpretable models, these techniques improve decision-making transparency and system robustness. This paper presents the first systematic literature review (SLR) focusing on the impact of feature engineering and XAI on state-of-the-art phishing detection approaches. Additionally, it identifies critical research gaps and challenges, including scalability issues, the evolution of phishing techniques, and balancing complexity with interpretability. The findings provide valuable academic insights while offering practical recommendations for developing accurate and interpretable phishing detection systems, aiding organizations in strengthening cybersecurity measures.
Volume: 15
Issue: 6
Page: 5863-5878
Publish at: 2025-12-01

SHIELD: Security based hybrid autonomous deep learning network for load balancing in cloud

10.11591/ijra.v14i4.pp591-601
Loga Priyadarshini Kathirmalaiyan , Nithya Muthu
Load balancing in the Internet of Things (IoT) enhances the efficiency of the system by dynamically allocating tasks across devices and cloud resources. However, task scheduling struggles with unpredictable tasks, scalability, security risks, and unauthorized access control. To overcome these limitations, a novel security-based hybrid autonomous deep learning network for load balancing in cloud (SHIELD) framework has been proposed for secure task scheduling in cloud resources. Initially, the data received from the IoT devices is passed under certain security constraints to ensure the authenticity of the data. These privacy-preserved data are fed to the task scheduling module, which is employed by the dual DL Network to generate a schedule for resource management. Finally, cloud resources employ optimal allocation of tasks based on the generated schedule to ensure secure load balancing. The proposed framework is simulated by using Cloud Simulator 7G (CloudSim7G). The SHIELD framework is assessed by such metrics, including accuracy, recall, precision, F1-score, and specificity. In comparison, the proposed SHIELD framework achieves a privacy overhead of 14% outperforms the existing QODA-LB, Best-KFF, SPSO-TCS, and VMMISD techniques by achieving 10%, 11%, 12%, and 13% respectively.
Volume: 14
Issue: 4
Page: 591-601
Publish at: 2025-12-01

Machine learning-based classification of local muscle fatigue using electromyography signals for enhanced rehabilitation outcomes

10.11591/ijece.v15i6.pp5954-5967
Zhanel Baigarayeva , Assiya Boltaboyeva , Baglan Imanbek , Kassymbek Ozhikenov , Nurgul Karymssakova , Roza Beisembekova
Muscle fatigue is a key factor affecting rehabilitation progress, safety, and patient engagement. Accurate detection of fatigue during physical activity remains a challenge, particularly in clinical and remote settings. This study presents the development of an Internet of things-based system for classifying local muscle fatigue using surface electromyography (EMG) signals and machine learning. A wearable device was used to collect real-time EMG data and subjective fatigue ratings from 10 healthy participants during sustained isometric grip exercises. Feature extraction was performed on-device, and the data were transmitted wirelessly for analysis. Machine learning models including logistic regression, decision tree (DT), random forest, and extreme gradient boosting (XGBoost) were trained to classify fatigue states. The DT model achieved the highest accuracy of 90.7%, with a precision of 90.7% and a recall of 90.9%. SHAP analysis revealed time under load, smoking, and alcohol use as the most influential factors in fatigue classification. These results show that wearable EMG devices combined with smart algorithms are effective for real-time fatigue monitoring during rehabilitation.
Volume: 15
Issue: 6
Page: 5954-5967
Publish at: 2025-12-01

Likely uptakers of the COVID-19 vaccinations in Cross River South Senatorial District, Nigeria

10.11591/ijphs.v14i4.26130
Veronica Akwenabuaye Undelikwo , Glory Eteng Bassey , Nkoyo Patrick Bassey , Lilian Otu Ubi , Mathew Mike Egong
The COVID-19 outbreak resulted in widespread concern and disruption globally. The development of vaccines was a significant focus in mitigating the impact of the deadly virus. However, vaccine uptake in many regions has been challenging, including the Cross River South Senatorial District. This study examines the socio-demographic variables influencing the adoption of the COVID-19 vaccine. Data was collected from 750 respondents through the questionnaire. Bivariate analysis using Chi-square statistics was used to evaluate the association between COVID-19 vaccination and covariates, including age, sex, location, occupation status, religion, educational status, and availability of COVID-19 vaccination sites. A logistic regression model was used to ascertain this connection. Based on the findings, COVID-19 uptake was 32.3%. Employment status was the only variable statistically significant with the uptake of the COVID-19 vaccine. When promoting the use of vaccines, consideration should be given to variables other than personal characteristics. With the low uptake of the COVID-19 vaccines, continued efforts are needed to improve the vaccination uptake rate by all segments of the study population.
Volume: 14
Issue: 4
Page: 1857-1865
Publish at: 2025-12-01

Multidrug-resistant Escherichia coli carriage and associated risk factors among healthy individuals in Rural Southwestern Nigeria

10.11591/ijphs.v14i4.26808
Odetoyin Babatunde , Akinde Oluwatoyin
Antimicrobial resistance (AMR), driven by multidrug-resistant (MDR) Escherichia coli, poses a significant public health threat, silently spreading through asymptomatic carriers. Limited data from rural areas highlight the need for focused studies to guide resistance control efforts. This study aimed to isolate faecal Escherichia coli (E. coli) from apparently healthy individuals in a rural community in Southwestern Nigeria, determine their antimicrobial resistance profiles, and evaluate risk factors associated with MDR E. coli carriage. A total of 347 stool samples were collected from healthy, consenting individuals. E. coli was isolated and identified using standard microbiological techniques. Antimicrobial resistance was assessed via the Kirby-Bauer disc diffusion method. Isolates were screened phenotypically for the extended spectrum beta-lactamase (ESBL) production and genotypically for ESBL genes (CTX-M, SHV, TEM). The data were analyzed using WINPEPI. E. coli was isolated from 269 participants (77.5%), yielding 555 isolates. High resistance rates were observed against sulphamethoxazole (94.0%), ampicillin (85.0%), and tetracycline (83.2%), while imipenem showed the lowest resistance (6.7%). Twenty-seven isolates (5%) were confirmed as ESBL producers. Among these, 17 (63%) carried at least one ESBL gene-TEM being the most common (44.4%). Additionally, 50.1% of the isolates were classified as MDR, with MDR E. coli carriage significantly associated with self-medication (p=0.05). The widespread presence of MDR E. coli among healthy rural dwellers, coupled with its association with self-medication, highlights serious public health concerns and raises the urgent need for more evidence-based strategies to combat AMR.
Volume: 14
Issue: 4
Page: 1866-1875
Publish at: 2025-12-01

Image-based assessment of cattle manure-induced soil erosion in grazing systems

10.11591/ijece.v15i6.pp5360-5370
Cristian Gómez-Guzmán , Yeison Alberto Garcés-Gómez
Extensive livestock farming significantly impacts soil erosion, necessitating accurate monitoring and assessment to mitigate environmental damage and enhance sustainable pasture management. This study employs unsupervised classification of high-resolution drone imagery to detect and quantify soil erosion associated with cattle manure in pastures, focusing on evaluating classification algorithms, identifying relevant spectral and textural features, and quantifying the extent and severity of erosion. The results demonstrate the effectiveness of unsupervised classification in identifying erosion zones and their impact on soil health and water quality. Field validation confirms the accuracy of the analysis, emphasizing the need for sustainable management practices such as controlled manure redistribution and soil conservation to mitigate erosion and protect natural resources. This approach offers practical tools for mitigating the environmental impacts of semi-extensive livestock farming and promoting more sustainable management. The findings provide practical recommendations for sustainable pasture management, contributing to environmental conservation and the long-term health of live-stock systems.
Volume: 15
Issue: 6
Page: 5360-5370
Publish at: 2025-12-01
1 2 3
...
2097 2098
Show 172 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