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

The influence of sentiment analysis in enhancing early warning system model for credit risk mitigation

10.11591/ijai.v14.i3.pp1829-1838
Angel Karentia , Derwin Suhartono
One important source of bank income is interest income from credit activities, another part of which is obtained from fee-based income. Rapid credit growth is directly proportional to an increase in potential credit risk (counterparty default). In addition to comprehensive credit assessment at the initial stage of credit initiation, banks need to monitor the condition of existing debtors. Empirically, difficulties in handling non-performing loans often occur due to delays in detection and preparation of action plans. In this case, losses due to non-performing loans can have implications for the bank's reputation and worsen its financial performance. This research aims to determine the effect of sentiment analysis (external sentiment prediction model [positive, neutral, and negative] with certain keywords) on the level of accuracy of the early warning system (EWS) model in predicting the credit quality of bank debtors in the coming months. This study found that upgrading EWS with sentiment analysis will give better accuracy levels compared to traditional EWS models. In addition, the predictive power of EWS (traditional and upgraded) is inversely proportional to the prediction period, the longer the target prediction time, and the less predictive power of the EWS model.
Volume: 14
Issue: 3
Page: 1829-1838
Publish at: 2025-06-01

Semantic based medical visual question answering with explainable artificial intelligence

10.11591/ijai.v14.i3.pp2169-2177
Sheerin Sitara Noor Mohamed , Kavitha Srinivasan , Raghuraman Gopalsamy
The medical visual question answering (MVQA) system takes the advantage of both computer vision (CV) and natural language processing (NLP) to accept the medical image and corresponding question as input and generates the respective answer as output. One step further, the MVQA system capable of generating the answer based on the semantics has a distinct place and hence semantic based medical visual question answering (SMVQA) system is proposed in this research. In SMVQA, the semantics for input image and question are generated using layerwise relevance propagation explainable artificial intelligence (LRP XAI) technique and the answer is derived using deductive reasoning method. For this, seven MVQA datasets are used for model creation, testing and validation. The training phase of the SMVQA system is implemented using VGGNet, long short-term memory (LSTM), LRP XAI, ResNet and bidirectional encoder representations from transformers (BERT) to generate a model file. Then the inference is derived in the testing phase based on the generated model file for the test set. Finally, the answer is derived from the inference using natural language toolkit (NLTK) library, term frequency-inverse document frequency (TF-IDF), cosine similarity, best match25 (BM25) techniques along with deductive reasoning. As a result, the proposed SMVQA system gives improved performance then the existing MVQA system especially for abnormality type samples.
Volume: 14
Issue: 3
Page: 2169-2177
Publish at: 2025-06-01

Factors influencing modern contraceptive use among rural married women of reproductive age in Myanmar

10.11591/ijphs.v14i2.25731
Myint Moh Soe , Nithat Sirichotiratana , Seo Ah Hong , Utoomporn Wongsin , Chardsumon Prutipinyo
This study aimed to identify factors associated with the use of modern contraceptive service among rural married women of reproductive age in Myanmar. A cross-sectional quantitative study was conducted among 648 married women aged 18-49 years (4 townships with the lowest contraceptive prevalence (n=316) and 4 townships with the highest prevalence (n=332). This study found that women in townships with low prevalence of modern contraceptive use were more likely to be illiterate and manual workers or farmers, to have lower education and no regular income, other religions than Buddhism, and higher number of family members and children, compared to those with high prevalence. In addition, they responded negatively to the accessibility, availability, affordability and acceptability of contraceptive services, and lower satisfaction with the services. This study suggests that the Myanmar government should promote contraceptive services more aggressively for women of reproductive age in rural areas that reflect ethnic minority cultures.
Volume: 14
Issue: 2
Page: 718-728
Publish at: 2025-06-01

Artificial intelligence for automatic moderation of textual content in online chats and social networks

10.11591/ijece.v15i3.pp3396-3409
Solomiia Liaskovska , Rex Bacarra , Yevhen Martyn , Volodymyr Baidych , Jamil Alsayaydeh
The article explores fundamental techniques for converting text into numerical data for machine learning algorithms. It meticulously examines various methods, including word vector representation via neural networks like Word2Vec, and explains the principles behind linear models such as logistic regression and support vector machines. Convolutional neural networks (CNN) and long short-term memory (LSTM) methods are also discussed, covering their components, mechanisms, and training processes. The research extends to developing and testing software for spam detection, hate speech identification, and recognizing offensive language. Using two datasets—one for labeled text messages and another for Twitter posts—the study analyzes data to address challenges like imbalanced data. A comparative analysis among linear models, deep neural networks, and single-layer models, using pre-trained bidirectional encoder representations from transformers (BERT) network, reveals promising results. The convolutional neural network stands out with a remarkable accuracy of 0.95. The study also adapts neural network architectures for hate speech and offensive language classification.
Volume: 15
Issue: 3
Page: 3396-3409
Publish at: 2025-06-01

Influence of community factors on formal care use among older Chinese adults

10.11591/ijphs.v14i2.24703
Zihan Zhang , Chieko Kato
Community plays a pivotal role in older adults' well-being and long-term care issues. This study investigates how community factors, including community support and social participation, with self-assessment of health as an intervening variable, influence the use of formal care. Further, how a community contributes to older adults' well-being has also been discussed. Data was collected from older adults (men 150, women 150, age>60 y/o) and was analyzed by using structural equation modeling (SEM). This study used health as an intervening variable to investigate community factors' influence on formal care use. The results find a significant negative influence of social participation and self-assessment of health on the use of formal care. While community support was not found to influence the use of formal care significantly, both community support and social participation could negatively influence the use of formal care by positively influencing the self-assessment of health. Cohabitation has also been found to influence community support significantly positively. In China, where formal care still needs to be more developed, reducing over-reliance on formal care follows Chinese cultural values and economic considerations. Moreover, older people living alone need to be attended to by the community.
Volume: 14
Issue: 2
Page: 959-966
Publish at: 2025-06-01

Multilayer stacking for polycystic ovary syndrome diagnosis

10.11591/ijai.v14.i3.pp1968-1975
Kazi Abu Taher , Samia Ahmed , Jannatul Ferdous Esha , Md. Sazzadur Rahman , A. S. M. Sanwar Hosen
Polycystic ovary syndrome (PCOS) is a complicated hormonal condition that is experienced by women. Despite extensive research, the precise reason be hind PCOS remains unknown, and effective treatments are still lacking. Thus, early diagnosis and treatment have a significant positive impact on the health of women. Recently, there has been remarkable performance demonstrated by machine learning (ML)-based detection models for PCOS identification. They are fast and low cost compared to the traditional processes. In this work, a multi stacking PCOS detection model is proposed using K-fold cross validation. The model uses three different ML algorithms namely: na¨ıve Bayes (NB), ran dom forest (RF), and logistic regression (LR) as base classifiers and a neural network, multi-layer perception (MLP) as meta model. This approach utilizes two feature selection techniques and compares the performances on the stack ing methods. Among the two feature selection techniques, Pearson correlation approach performed better with average 98.79% accuracy, 99.17% sensitivity, 98.40% specificity, and 98.79% f1-score.
Volume: 14
Issue: 3
Page: 1968-1975
Publish at: 2025-06-01

Optimizing rice leaf disease classification through convolutional neural network architectural modification and augmentation techniques

10.11591/ijece.v15i3.pp3429-3438
Mohamad Firdaus , Kusrini Kusrini , I Made Artha Agastya , Rodrigo Martínez-Béjar
This research focuses on advancing the accuracy of rice leaf disease classification through the integration of convolutional neural network (CNN) and deep learning models. With Indonesia ranking third in global rice production, effective crop management is crucial for sustaining agricultural output. This study employs innovative data augmentation techniques, including random zoom and others, to enhance model training robustness. The experimentation involves eight scenarios with varied architectural configurations applied to a residual network-50 (ResNet50) layers model, aiming to optimize disease classification performance. Featuring random zoom without the multilayer perceptron (MLP) component, emerges as the most effective, demonstrating superior accuracy and performance metrics. A grid search is conducted to optimize MLP layers, revealing a three-layer configuration as most effective. We found that the data augmentation and MLP layer can increase the accuracy of the disease classification task. The method proposed in this study is likely to have a much higher proportion of correct disease classification by combining MLP and zoom augmentation. Specifically, the model with three MLP layers and zoom augmentation demonstrated significantly higher accuracy, achieving a test accuracy, precision, recall, and F1-score of 0.92, 0.94, 0.92, and 0.92, respectively.
Volume: 15
Issue: 3
Page: 3429-3438
Publish at: 2025-06-01

Robust deep learning approach for accurate detection of brain tumor and analysis

10.11591/ijece.v15i3.pp3226-3237
Lanke Pallavi , Thati Ramya , Singupurapu Sai Charan , Sirigadha Amith , Thodupunuri Akshay Kumar
Usually, one of the foremost predominant and intricate therapeutic conditions. As broadly perceived, brain tumors are among the foremost significantly harmful circumstances that can radically abbreviate a person’s life expectancy. Various methods are lacking for observing the assortment of tumor sizes, shapes, and areas. When merged with strategies of profound learning, generative adversarial networks (GANs) are competent of catching the measurements, areas, and structures of tumors. Profound learning frameworks will move forward upon the shortage of datasets. It can moreover progress photographs with determination. Classifying and partitioning brain tumors productively is significant. GANs are used in conjunction with an overarching learning handle. A profound learning design called NeuroNet19, could be an intercross of visual geometry group (VGG19) and inverted pyramid pooling module (IPPM) which is utilized to recognize brain tumors. It is clear that, NeuroNet19 employments the foremost exact technique in comparison to all models (DenseNet121, MobileNet, ResNet50, VGG16). The exactness examination gave a Cohen Kappa coefficient of 99% and a F1-score of 99.2%
Volume: 15
Issue: 3
Page: 3226-3237
Publish at: 2025-06-01

Understanding HIV transmission and prevention among men who have sex with men in a sexual health clinic

10.11591/ijphs.v14i2.24552
Suriya Kumareswaran , Bala Murali Sundram
This comprehensive study investigates the knowledge, attitudes, and practices (KAP) concerning human immunodeficiency virus (HIV) transmission and prevention among men who have sex with men (MSM) in a sexually transmitted infections (STI)-friendly clinic in Johor, Malaysia. Utilizing a cross-sectional design, the study analyses data from 421 MSM patients, emphasizing the critical role of sociodemographic factors in influencing HIV-related behaviours. The majority of participants, mostly with tertiary education, displayed a sound understanding of HIV, with 71% showing good knowledge on HIV prevention and transmission. However, there remain gaps in knowledge, particularly among those with lesser education, and in practices related to condom use and pre-exposure prophylaxis (PrEP). The study highlights a stark disparity in HIV-related attitudes and practices based on education level, employment status, and income. Notably, those with higher education and income levels demonstrate more responsible practices and better knowledge, underscoring the need for tailored educational programs. The findings call for comprehensive and targeted interventions, considering the diverse backgrounds of individuals, to effectively mitigate the risk of HIV infection. This research is vital in the absence of a definitive cure for HIV and acquired immune deficiency syndrome (AIDS), emphasizing preventive measures based on accurate information and positive attitudes towards the disease.
Volume: 14
Issue: 2
Page: 569-575
Publish at: 2025-06-01

Antioxidant and anticancer activity of Canarium ovatum Engl. (Pili) ethanolic leaf extracts

10.11591/ijphs.v14i2.25343
Rafael Joseph Itao Terrazola , Djamae Librado Manzanares , Lady Jane Gacasan Morilla , Loren Grace Jaranilla Anunciado , Lilybeth Flores Olowa , Olive Anies Amparado
The Pili (Canarium ovatum Engl.) tree, native to the Philippines, has been reported to have medicinal properties because of the biological and chemical properties it exhibits. This paper aimed to investigate the presence of phytochemicals, antioxidant, and anticancer activities of the ethanolic leaf extract of C. ovatum. To determine the phytochemicals, present in the extract, standard procedures for qualitative phytochemical screening were performed. The antioxidant activity of the extract was assessed in vitro using 2,2-Diphenyl-1-picrylhydrazyl (DPPH) free radical scavenging assay. The anticancer activity of the extract was assessed in vitro using 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) cell viability assay against the HCT116 cancer cell line. Phytochemical screening of C. ovatum ethanolic leaf extract detected alkaloids, steroids, flavonoids, saponins, and tannins. The extract had extremely high antioxidant activity (IC50=11.44 mg/L). The MTT assay revealed moderate cytotoxic activity of the leaf extract to HCT116 cancer cell line (IC50=94.43 mg/L). These findings suggest that the C. ovatum ethanolic leaf extract has therapeutic potential because of the presence of beneficial phytochemicals, strong antioxidant activity, and anticancer capacity. Futher research is recommended to comprehensively evaluate the medicinal potential of Pili leaf extracts, including exploring other biological activities using various assays and employing different solvents for leaf extraction.
Volume: 14
Issue: 2
Page: 827-835
Publish at: 2025-06-01

Enhancing e-commerce personalization with review-based adaptive feature matching: a real-time approach

10.11591/ijai.v14.i3.pp2178-2184
Noorbasha Zareena , Tarakeswara Rao Balaga
The widespread evolution of e-commerce platforms necessitates advanced personalization techniques to enhance user experience and satisfaction. Our paper introduces the review-based adaptive feature matching (R-AFM) algorithm, an innovative approach to real-time personalization in e-commerce settings. Leveraging the rich data from user reviews and product metadata available in the Amazon product review dataset, R-AFM dynamically adapts to user preferences and behaviors through a sophisticated feature matching process. The methodology encompasses data collection, feature extraction, user preference modeling, real-time recommendation generation, and an adaptive feedback loop. By analyzing historical review data alongside real-time user interactions, R-AFM updates preference weights for product features, thereby refining the personalization mechanism. This process culminates in the generation of highly personalized product recommendations. Comparative analysis with existing personalization methods-collaborative filtering (CF), content-based filtering (CBF), hybrid recommender systems (Hybrid RS), and deep learning-based recommender systems (DL-RS)-demonstrates R-AFM's superior performance improvement varying between 2 to 8% in terms of accuracy, precision, recall, and F1-score. The algorithm's unique capability to incorporate real-time feedback significantly enhances the e-commerce personalization landscape, offering promising avenues for future research and practical application.
Volume: 14
Issue: 3
Page: 2178-2184
Publish at: 2025-06-01

A systematic review on software code smells

10.11591/ijece.v15i3.pp3010-3027
Mohammed Ghazi Al-Obeidallah , Dimah Al-Fraihat
This paper provides a systematic review of code smell detection studies published from 2001 to 2023, addressing their significance in identifying underlying issues in software systems. Through stringent inclusion criteria, 116 primary studies were analyzed, focusing on various aspects such as publication venue, code smell categories, subject systems, supported programming languages, evaluation criteria, and detection techniques. The analysis reveals that 50% of the papers were conference proceedings, with 80% utilizing Java-supported techniques and commonly used subject systems like Apache Xerces, GanttProject, and ArgoUML. Metrics-based methods (33%) and search-based approaches (32%) were predominantly employed, with machine learning emerging in 20% and rule-based methods in 15% of the studies. Notably, recent studies have shown an increased adoption of machine learning techniques. The identified code smells include god class, feature envy, long method, and data class, with precision and recall being the most commonly used evaluation metrics. This review aims to inform future research directions and aid the software engineering community in developing novel detection techniques to enhance code quality and system reliability.
Volume: 15
Issue: 3
Page: 3010-3027
Publish at: 2025-06-01

Maternal and child factors of stunted children: a case control study

10.11591/ijphs.v14i2.24473
Apriyani Puji Hastuti , Tintin Sukartini , Yuni Sufyanti Arief , Nursalam Nursalam , Ratna Roesardhyati , Elyk Dwi Mumpuningtias , Syaifurrahman Hidayat , Ardhiles Wahyu Kurniawan
Due to the transition or weaning process and infant feeding patterns, infants under the age of five (IYCF) are susceptible to nutritional problems, especially with regard to food diversity, diet quality, availability, and accessibility. According to fundamental health research, the mother’s capacity to supply nourishment (sources from animal and vegetable protein) and the main meal as an energy source during the first two years of life is associated. Community based case-control study was conducted among children 6-24 month. The study participant used multistage random sampling procedure, with a sample size of 180 mothers who have stunted children. This study used a questionnaire as its data research instrument, which was examined for validity and reliability utilizing data analysis methods like linear regression and SPSS 16.0 statistical software. Factor associated the role of mothers in the feeding of stunted children to nutritional status are age, educational level, occupation, motivation, mobility, decision making, knowledge, self-esteem, self-efficacy, family type, family role, stress of family, coping of family, family social support, weight of birth, responsive feeding. The all of factors can affected roles of mothers in the feeding of stunted children to nutritional status with p-value <0.005. While the child’s age, birth length, breastfeeding, feeding children are not factors associated with the role of mothers in the feeding of stunted children to nutritional status.
Volume: 14
Issue: 2
Page: 852-859
Publish at: 2025-06-01

Enhancing cybersecurity awareness strategies in organization using Delphi technique

10.11591/ijece.v15i3.pp2986-2997
Anawin Kaewsa-Ard , Nattavee Utakrit
Cybersecurity concerns were once primarily perceived as technical issues, prompting many organizations to prioritize investments in security technologies. However, it has become increasingly evident that cybersecurity is not solely a technical matter. In fact, a significant number of cybersecurity breaches arise from users' lack of awareness about secure technological practices. This research aims to develop a cybersecurity awareness strategy using the Delphi technique over three rounds, involving 15 cybersecurity experts. The findings indicate a consensus among experts that cybersecurity awareness training is an effective strategy to enhance an organization's overall cybersecurity posture. However, the true essence of cybersecurity lies in fostering secure technology usage practices among all users within the organization. To address this, the researcher developed systematic training content for cybersecurity awareness, which was evaluated and refined by experts using the Delphi technique to ensure its effectiveness in promoting genuine cybersecurity awareness.
Volume: 15
Issue: 3
Page: 2986-2997
Publish at: 2025-06-01

Optimized wireless power transfer for moving electric vehicles by real-time modification of frequency and estimation of coupling coefficient

10.11591/ijece.v15i3.pp2706-2712
Kazuya Yamaguchi , Haruto Terada , Ryusei Okamura , Kenichi Iida
In order to prevent global warming, electric vehicles are increasingly recommended than gasoline-powered vehicles that have been widely used in the past. However, problems peculiar to electric vehicles exists, and their widespread utilize is not progressing in Japan and other developed countries. This study performed wireless power transfer assuming that electric vehicles are stationary on a road at some distance from an AC power supply. Frequency of a power supply has significant influence on efficiency of wireless power transfer, and it is important to adjust this value on any situation. Therefore, an experiment was conducted based on the optimal frequency expression derived in the past to confirm the correctness of the expression, finally it achieved 60% transport efficiency. Moreover, since the expression includes coupling coefficient between transmission and receiving inductors, its value must be estimated accurately. In this study, an experiment was conducted to estimate value of coupling coefficient using current and voltage values measured from outside circuits, and it was compared with a theoretical expression obtained from laws on electromagnetics.
Volume: 15
Issue: 3
Page: 2706-2712
Publish at: 2025-06-01
1 2 3
...
2097 2098
Show 283 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