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

30,185 Article Results

Ontology-based semantic link prediction for enhancing academic collaboration through knowledge management

10.11591/ijeecs.v41.i3.pp1040-1048
Pham Thi Thu Thuy , Thinh Thi Thuy
This paper introduces a novel ontology-based semantic link prediction framework that unifies structural, temporal, and semantic signals from heterogeneous scholarly sources to enhance academic collaboration forecasting. By integrating AMiner, DBLP, and Mendeley datasets into a unified SKOS- and Dublin Core-aligned ontology, the framework enables semantic enrichment, cross-source reasoning, and contextualized link prediction. Unlike previous studies that focus solely on structural features or basic content similarity, our approach leverages ontology-based semantic feature engineering and graph-based learning for robust and interpretable predictions. Experimental results show that random forest and graph neural networks significantly outperform traditional models, achieving high accuracy and ranking precision. This work contributes to knowledge management by enabling expert recommendation, trend identification, and semantic integration for strategic academic planning.
Volume: 41
Issue: 3
Page: 1040-1048
Publish at: 2026-03-10

Enhanced prediction of chronic kidney disease onset through machine learning techniques

10.11591/ijeecs.v41.i3.pp966-976
Samuel John Parreño , Maria Cristine Joy Anter
Chronic kidney disease (CKD) is a global health concern that often progresses silently to severe complications. This study aims to enhance CKD prediction using machine learning models: support vector machines (SVM), extreme gradient boosting (XGBoost), k-nearest neighbors (k-NN), and a stacking model. The dataset, sourced from the UCI machine learning repository, includes clinical and demographic attributes from 200 patients. After preprocessing, the final dataset comprised 161 samples and 143 features. SVM achieved perfect classification performance with 100% accuracy, precision, and recall. XGBoost followed closely with an accuracy of 97.44% and a kappa statistic of 0.9451. The k-NN model delivered strong performance, achieving 92.31% accuracy. The stacking model outperformed all individual models, achieving perfect accuracy. The models demonstrated high sensitivity and specificity, indicating their effectiveness in distinguishing CKD from non-CKD cases. These findings emphasize the potential of machine learning in CKD diagnosis. Early detection can lead to improved clinical outcomes by enabling timely interventions and personalized treatment strategies. Future research should emphasize comprehensive feature engineering and larger, more diverse datasets to improve predictive accuracy and generalizability. Incorporating machine learning models in nephrology could significantly advance CKD detection and management.
Volume: 41
Issue: 3
Page: 966-976
Publish at: 2026-03-10

Classification of DoS/distributed DoS threats in software defined networks using advanced deep belief network-long short term memory architecture

10.11591/ijeecs.v41.i3.pp1000-1016
Manjula Maraiah , Venkatesh Venkatesh
With the evolution of telecommunication core and access networks, the next generation networks leverages software defined networks (SDN) to provide flexi bility, scalability and centralized control. Denial of service (DoS)/distributed DoS (DDoS) attacks have been a major threat to next generation networks especially to the centralized architecture of SDNs. The ever-changing and dynamic nature of the DoS/DDoS attacks makes it challenging to detect and resolve them. The existing models to handle DoS/DDoS attacks often suffer from false positive rates and adaptability. In order to solve these problems, this study aims to create and apply sophisticated deep learning framework namely adversarial DBN-LSTM to accurately detect and classify various DoS/DDoS attack types. The proposed adversarial DBN-LSTM model is based on the generative adversarial networks. The proposed model uses generator to generate the adversarial attack and discrim inator to detect the attacks. The adversarial DBN-LSTM model is evaluated using a dataset specifically generated in a Mininet-based SDN controller environment to ensure relevance and practical applicability. The performance of the adver sarial DBN-LSTM is compared with other prevalent models. The adversarial DBN-LSTMmodelachieves accuracy about 99.4%. The proposed work achieves a breakthrough in identifying and preventing DoS/DDoS threats in relation to SDNenvironment.
Volume: 41
Issue: 3
Page: 1000-1016
Publish at: 2026-03-10

Thermal effects of curing parameters on the natural frequency of GNP/Ag ink composites

10.11591/ijeecs.v41.i3.pp845-858
Khirwizam Md Hkhir , Nor Azmmi Masripan , Cholatee Photong , Alan Watson , Mohd Azli Salim
This research examines how curing temperature and duration influence the electrical and mechanical behavior of hybrid graphene nanoplatelet and silver (GNP/Ag) conductive ink. The ink was formulated from GNPs, silver flakes and silver acetate printed on copper substrates, then cured 240 °C, 250 °C, and 260 °C for one to three hours. Electrical resistance was measured using a Two-Point probe, while natural frequency was obtained from experimental modal analysis (EMA) on stainless-steel (SUS304) cantilever beams laminated with printed ink. The results show that the higher curing temperature and longer curing time reduce resistivity and increase natural frequency, with the best performance observed at 260 °C for 3 hours (8.4×10⁻⁶ Ω.m and a 4.2 Hz increase). These findings confirm that a direct relationship between conductivity and stiffness, where conditions that promote stronger particle bonding also raise structural rigidity. The main contribution of this research is the joint evaluation of curing effects on both electrical and vibrational responses, offering a combined electro-mechanical perspective that is not often explored in GNP/Ag ink research. The results provide practical guidance for selecting curing conditions based on the required balance between conductivity and mechanical stability in flexible and stretchable electronic applications.
Volume: 41
Issue: 3
Page: 845-858
Publish at: 2026-03-10

Leveraging CNN to analyze facial expressions for academic engagement monitoring with insights from the multi-source academic affective engagement dataset

10.11591/ijeecs.v41.i3.pp977-999
Noora C. T. , P. Tamil Selvan
The dynamics of student engagement and emotional states significantly influence learning outcomes. Positive emotions, stemming from successful task completion, contrast with negative emotions arising from learning struggles or failures. Effective transitions to engagement occur upon problem resolution, while unresolved issues lead to frustration and subsequent boredom. Facial engagement monitoring is crucial for assessing students’ attention, interest, and emotional responses during learning. Recent advancements in convolutional neural networks (CNNs) show promise in automatically analyzing facial expressions to infer engagement levels. This study proposes a CNN-based approach utilizing the multi-source academic affective engagement dataset (MAAED) to categorize facial expressions into boredom, confusion, frustration, and yawning. By extracting features from facial images, this method offers an efficient and objective means to gauge student engagement. Recognizing and addressing negative affective states, such as confusion and boredom, is fundamental in creating supportive learning environments. Through automated frame extraction and model comparison, this study demonstrates reduced loss values with improving accuracy, showcasing the effectiveness of this method in objectively evaluating student engagement. Facial engagement monitoring with CNNs, using the MAAED dataset, is pivotal in understanding human behavior and enhancing educational experiences. The CNN model, trained on MAAED annotated facial expressions, accurately classifies engagement categories. Experimental results underscore the CNN-based approach’s efficacy in monitoring facial engagement, highlighting its potential to enrich educational environments and personalized learning experiences.
Volume: 41
Issue: 3
Page: 977-999
Publish at: 2026-03-10

A microservice-oriented machine learning framework for cold chain management in perishable fish logistics

10.11591/ijeecs.v41.i3.pp1070-1081
Maun Jamaludin , Arief Ginanjar , Leni Herdiani , Toto Ramadhan , Muhammad Alif Naufal , R. Ismet Rohimat
This study proposes a microservice-oriented machine learning framework to enhance intelligence and scalability in perishable fish cold chain logistics. Unlike conventional monitoring-centric systems, the framework integrates edge–cloud computing with multimodal machine learning models, including random forest for anomaly detection, long short-term memory (LSTM) for spoilage risk prediction, and convolutional neural network (CNN) for visual fish quality classification. The research adopts a design science approach combining literature analysis, field observations at cold storage facilities in Indramayu, Indonesia, and simulation-based validation. Experimental results demonstrate the feasibility of distributed analytics, modular deployment, and real-time inference within heterogeneous logistics environments. The proposed framework provides a deployable architectural reference for intelligent fisheries cold chain management and supports future large-scale, multi-stakeholder implementation.
Volume: 41
Issue: 3
Page: 1070-1081
Publish at: 2026-03-10

Arich and balanced phonetics corpus for modern standard Arabic ASR systems

10.11591/ijeecs.v41.i3.pp1049-1059
Youssef Boutazart , Naouar Laaïdi , Abderrahim Ezzine , Hassan Satori , Mohamed Taj Bennani
This research delves into the creation of an innovative Modern Standard Ara bic corpus, aiming for a comprehensive balance and richness while adhering to Zipf’s law. Building a phonetically diverse Arabic sentence collection yields significant advantages in terms of efficiency, cost-effectiveness, and storage ca pacity compared to conventional corpora. The corpus undergoes meticulous seg mentation into graphemes, which are then manually converted into phonemes, resulting in a total of 19769 phonemic units. Among these phonemes, conso nants like ’Laam- l’ account for 10%, while ’Fatha- A’ vowels constitute 20%. Evaluation of this corpus using an automatic speech recognition (ASR) system reveals a sentence error rate (SER) of 30% and a word error rate (WER) of 15%. Furthermore, statistical analysis unveils that diacritic marks encompass 47.59% of the corpus, with graphemes comprising the remaining 52.41%. These dia critized marks provide valuable insights into the precise phonetic transcription of the corpus. Additionally, the study provides detailed breakdowns of consonants based on their place and manner of articulation, enhancing our understanding of phonetic structures.
Volume: 41
Issue: 3
Page: 1049-1059
Publish at: 2026-03-10

Antibiotic susceptibility profile of uropathogens in pregnant women with asymptomatic bacteriuria in tertiary care hospital: a cross-sectional study

10.11591/ijphs.v15i1.26813
K. Murugesh , Harvick P. Gowda , K. Pushpalatha , J. V. Sathish
Urinary tract infections (UTIs) are common during pregnancy due to physiological and anatomical changes that predispose women to infections. One such condition, asymptomatic bacteriuria (ASB), if left undiagnosed and untreated, can lead to serious maternal complications such as pyelonephritis, postpartum UTI, and hypertensive disorders, as well as neonatal complications including preterm birth, low birth weight, and intrauterine growth restriction. This study aimed to determine the prevalence of ASB, identify the major uropathogens, and analyze their antibiotic susceptibility patterns in pregnant women, to guide effective antenatal care and treatment. This cross-sectional study was conducted on 100 midstream urine samples, which were cultured using standard microbiological techniques. The bacterial isolates obtained were identified, and their antibiotic susceptibility was determined following standard guidelines. Out of 100 samples, 14 (14%) were positive for significant bacteriuria. The most common isolates were Staphylococcus aureus (42.8%), followed by Escherichia coli (28.6%) and Klebsiella species (28.6%). ASB was most prevalent in women aged 21-30 years (64.3%), during the first trimester (64.2%), and among multigravida women (57.2%). The isolated organisms showed good susceptibility to Ceftazidime/Clavulanic acid, Ciprofloxacin, Vancomycin, Amikacin, Piperacillin–Tazobactam, Imipenem, Teicoplanin, and Linezolid. Early detection and treatment can significantly reduce adverse outcomes, making bacteriuria screening an essential part of routine antenatal care.
Volume: 15
Issue: 1
Page: 132-139
Publish at: 2026-03-05

Nipah virus as an emerging threat: mutational dynamics, pathogenesis, and advances in vaccine development- a systematic review

10.11591/ijphs.v15i1.22365
Sadia Afrin , Md. Rezwan Ahmed Mahedi , Asma Akhter Radia , Joti Devi
Nipah virus (NiV) is an emerging zoonotic pathogen with significant pandemic potential. Large outbreaks, such as in Malaysia, required the culling of over one million pigs to control transmission. However, the epidemiology of NiV among animal hosts, including pigs, horses, and bats, remains incompletely understood. NiV infection primarily affects the respiratory and nervous systems, causing severe pneumonia, vasculitis, and meningitis, while encephalitis may be mild or infrequent in some cases. This systematic review summarizes current evidence on NiV mutational variation, pathogenesis, treatment strategies, and vaccine development up to 2022. Data were collected from major databases, including PubMed, PMC, and Cochrane Library. Due to limited therapeutic options, NiV management relies mainly on supportive care, as no approved vaccines or specific antiviral treatments are available for humans or livestock. Preventive strategies focus on reducing zoonotic transmission, particularly by minimizing contact between livestock and bat-contaminated food sources, and improving farm management practices. Early detection and continuous surveillance of high-risk populations and animal reservoirs are essential for outbreak control. Current vaccine research targets viral antigens using subunit and vector-based approaches. Overall, further studies are urgently needed to develop effective vaccines and antiviral therapies for NiV infection.
Volume: 15
Issue: 1
Page: 197-207
Publish at: 2026-03-05

Association between risky dietary behaviors and academic achievement among adolescent girls: a cross-sectional study in Surabaya, Indonesia

10.11591/ijphs.v15i1.26877
Tatarini Ika Pipitcahyani , Ervi Husni , Dina Isfentiani , Nina Primasari , Halimatus Sa'diyah , Mohammad Zamroni
Risky dieting is an unbalanced eating pattern increasingly practiced by adolescent girls and has the potential to impact cognitive function and academic achievement. However, previous research has focused more on the impact of risky dieting on nutritional status and physical health, while empirical evidence regarding its relationship with academic achievement in adolescent girls is still limited, particularly in the context of higher education. This study aimed to analyze the relationship between risky dieting and academic achievement in adolescent girls. The study used a quantitative design involving 70 adolescent girls. Data were collected through a peer counselor-based questionnaire to measure risky dietary habits and academic achievement. Data analysis was performed using Fisher's exact test. The results showed p-values of 0.05 and 0.023, respectively, indicating a significant relationship between risky dieting and academic achievement. Adolescent girls who engaged in risky dieting tended to have lower semester GPAs (11%) and cumulative GPAs (4%). The study concluded that risky dieting contributes to decreased academic achievement. This study contributes by expanding empirical evidence regarding the impact of risky dieting on academic achievement and emphasizes the importance of integrating nutrition interventions and health education in strategies to improve academic achievement in adolescent girls.
Volume: 15
Issue: 1
Page: 92-98
Publish at: 2026-03-05

Evaluating the performance of TAG-IT for prediabetes detection in Indonesian population

10.11591/ijphs.v15i1.26887
Yaltafit Abror Jeem , Rahma Yuantari , Hajar Admira Widiatninda , Russy Novita Andriani , Siti Solichatul Makkiyyah
Early detection of prediabetes plays a critical role in preventing type 2 diabetes mellitus (T2DM), especially within primary care, where access to laboratory testing may be constrained. Non-laboratory-based risk assessment instruments, including the tool to assess the likelihood of fasting glucose impairment (TAG-IT), can facilitate preliminary risk screening. This study sought to determine the diagnostic accuracy of the TAG-IT questionnaire in detecting prediabetes, using the oral glucose tolerance test (OGTT) as the reference standard. A cross-sectional design was implemented across three community health centers in the Special Region of Yogyakarta, Indonesia. Although 308 individuals were initially enrolled, only 93 participants with complete datasets were eligible for final analysis. The discriminative capacity of TAG-IT was evaluated through receiver operating characteristic (ROC) curve analysis along with a contingency table. Among the participants analyzed, 24.7% (23/93) were classified as having prediabetes. The TAG-IT tool exhibited modest discriminatory performance, yielding an AUC of 0.656 (95% CI 0.525-0.786; p = 0.026). Using the identified optimal threshold, sensitivity reached 52.2% while specificity was 67.1%. The negative predictive value was 81.0%, indicating better performance in excluding low-risk individuals. Overall, TAG-IT demonstrated moderate utility as a preliminary screening instrument in primary healthcare, particularly for identifying individuals unlikely to have prediabetes.
Volume: 15
Issue: 1
Page: 32-42
Publish at: 2026-03-05

Empathy and forgiveness on student victims of toxic relationships

10.11591/ijphs.v15i1.24037
Felani Omie Timpal , Arthur Huwae
A toxic relationship shows a negative impact on the physical and mental condition of individuals who have undergone the subject. Even though the students have experienced unpleasant conditions in life, to continue her life journey, the student needs to make peace and build a concept of forgiveness for the circumstances that are formed through empathy. This research aims to determine the relationship between empathy and forgiveness in students who have been victims of toxic relationships. The method used is quantitative correlational. An equal number of 355 students who had been victims of toxic relationships came to be participants in this study, with the sampling technique used, specifically, incidental sampling. This study uses a scale, namely the Interpersonal Reactivity Index (α = 0.863) and Transgression-Related Interpersonal Motivations -18 (α = 0.843). The research data analysis method uses the product-moment correlation test from Karl Pearson. The results show that there was a significant positive relationship between empathy and forgiveness (r = 0.228 and sig = 0.000 (p<0.01). Empathy contributed 5.2% to forgiveness. It appears that empathy is one of the factors associated with increased forgiveness in students who have been victims of a toxic relationship.
Volume: 15
Issue: 1
Page: 274-282
Publish at: 2026-03-05

Physical activity and associated factors among Indonesian pregnant women: a mixed-method study

10.11591/ijphs.v15i1.24497
Feva Tridiyawati , Dg Marshitah Pg Baharuddin , Nicholas Pang
Exercise is recommended for pregnant women, but many are sedentary. Studies on barriers to physical activity and exercise among pregnant women in West Java Province, Indonesia, are scarce. This study aims to identify and explore the underlying factors associated with physical activity during pregnancy in West Java, Indonesia. This study was conducted using a mixed-methods strategy that integrates quantitative and qualitative data. The study surveyed pregnant women in West Java, Indonesia, from January to March 2023. The study involved 18-year-olds, married women, and fluent Bahasa participants. It used a questionnaire to assess physical pregnancy activity intention, and analyzed data using descriptive, correlation withp<0.025 included in linear regression analysis. While in a qualitative study used semi-structure interview. A study of 200 pregnant women found that age negatively correlated with total metabolic equivalent of task (MET), while gestational age, education level, body mass index (BMI), and pregnancy complications positively impacted it. Pregnancy symptoms, limited time, and low social support were identified as themes impacting adhering to physical activity recommendations. The study reveals that factors such as age, gestational age, education level, BMI, and pregnancy complications significantly influence total MET in pregnant women, suggesting the need for personalized interventions.
Volume: 15
Issue: 1
Page: 118-125
Publish at: 2026-03-05

Effectiveness of delivery mode of pharmacist intervention to improve medication adherence and clinical outcomes in people with depression: a systematic review

10.11591/ijphs.v15i1.25537
Yosi Febrianti , Ika Puspita Sari , Anna Wahyuni Widayanti , Diana Setiyawati
Depression is a treatable mental health condition with various medication options available. For patients with major depressive disorder (MDD), adherence to antidepressants is essential for effective treatment. However, low medication adherence remains a significant challenge, particularly in individuals with depression. Pharmacists play a crucial role in managing these patients. This systematic review evaluated the impact of pharmacist-led interventions, focusing on the effectiveness of delivery modes (in-person vs. online) in improving medication adherence and clinical outcomes for patients with depression. Randomised and non-randomised controlled trials were included. Data were sourced from PubMed, Scopus, ScienceDirect, and Google Scholar using keywords such as "pharmacist intervention," "education," "medication adherence," "depression," and "medication compliance." Three reviewers independently screened and selected articles, and methodological quality was assessed using the Joanna Briggs Institute Randomized Controlled Trial Checklist. From an initial pool of 791 publications, 364 underwent a comprehensive review, and 14 met the inclusion criteria. The most successful interventions were those conducted face-to-face (83%), compared to those conducted through video and phone calls (16%). However, neither method could improve the severity of depression significantly. Pharmacist interventions can enhance patient adherence to antidepressant medication in patients with depression. Compared to virtual methods, face-to-face techniques are more effective at improving adherence. However, they were not able to improve the symptoms of depression.
Volume: 15
Issue: 1
Page: 99-109
Publish at: 2026-03-05

Game on for health: designing gamified campaigns to drive behavioral change

10.11591/ijphs.v15i1.26232
Nurul Hidayah Mat Zain , Anita Mohd Yasin , Zainab Othman , Siti Nuramalina Johari , Norshahidatul Hasana Ishak , Siti Rahayu Abdul Aziz
An awareness campaign aims to reach out to the public, measure the outreach accurately, and motivate the public to act. In other words, awareness campaigns deliver messages on the importance and effects of the promoted event to the audience. However, studies that examine the users’ perception of design for behavior change through gamified health awareness campaigns are limited, especially in combating the coronavirus disease 2019 (COVID-19) outbreak. Subsequently, analysis of such perceptions is crucial in supporting game designers in developing engaging games for health awareness campaigns. Thus, the current study explores users’ perceptions based on elements in the GAMEBC Model: Autonomy, Relatedness, Competence, and Engaging. A total of 180 students from UiTM Cawangan Melaka (UiTMCM), Jasin Campus, participated in the study. The data was evaluated using conventional descriptive statistical methods. The findings revealed users’ perceptions of the design for behavior change in the context of a gamified health awareness campaign. The study offers a valuable understanding of the necessity of creating a comprehensive gamified campaign that promotes behavioral change for improved quality of life.
Volume: 15
Issue: 1
Page: 72-80
Publish at: 2026-03-05
1 2 3
...
2012 2013
Show 36 of 2013

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