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

A detection model of aggressive driving behavior based on hybrid deep learning

10.11591/ijai.v13.i4.pp4883-4894
Noor Walid Khalid , Wisam Dawood Abdullah
Modern transportation faces a crucial challenge in ensuring road safety by addressing driving behavior concerns. This paper introduces an innovative deep learning model derived from a cellphone-collected Driving Behavior dataset, focusing on detecting and classifying aggressive driving. Using a cohort-based dataset, a hyper-deep learning model categorizes drivers into normal, slow, and aggressive groups. The system employs pre-processing methods and two methodologies, directly inputting data and incorporating feature selection. The hyper-CNN-Dense model, used for training, shows promising results. Feature selection techniques like SVD6 and MI6 achieve optimal outcomes, with a 100% accuracy rate in detecting aggressive driving. Notably, SVD6 boasts a short processing time of just 43 seconds. This research successfully identifies aggressive driving behavior with impeccable accuracy and in a remarkably short timeframe.
Volume: 13
Issue: 4
Page: 4883-4894
Publish at: 2024-12-01

The effects of mobile technologies on the level of student involvement

10.11591/ijere.v13i6.29726
Ludmila Abazova , Zhansurat Gutaeva , Madina Kochesokova
In the modern world, there is a conscious interest in improving education quality with the help of modern information technologies. Innovative m-learning technology expands the possibilities and increases the effectiveness of training. Experiments conducted in European countries showed that the use of mobile devices positively affected academic performance, discipline, and interpersonal relationships among participants in the educational process. However, currently, practical research only generally concerns the issue of increasing foreign student involvement in the educational process. The purpose of the study is to experiment and obtain new data confirming the effectiveness of mobile technologies in increasing foreign student involvement in the educational process. The developed mobile technology-based course was introduced into the educational system of the university. The program included traditional and practical classes. The study confirms the effectiveness of mobile learning technology. A statistical data analysis showed positive dynamics in the indicators of the experimental group. The final data of the experimental group differed significantly from the initial ones: the average indicator of 2.9 (average involvement level) increased to 4 (+1.1). Based on the developed course using mobile learning, it is possible to create and practically implement new educational programs for universities.
Volume: 13
Issue: 6
Page: 4321-4329
Publish at: 2024-12-01

Frayer model-based assessment for detecting students’ conceptual understanding in evolution

10.11591/ijere.v13i6.29423
Ramadanti Prativi , Murni Ramli , Yudi Rinanto
This study aimed to test the validity, reliability, and difficulty level of items developed based on the Frayer model and detect conceptual understanding of high school students in biology evolution. The test method evaluated 35 multiple-choice questions on evolution for 55 high school students. Rasch analysis was performed to assess the validity, reliability, difficulty level of items, and students’ ability level. Two experts empirically tested and analyzed the validity of the items. The assessment developed was discovered to be valid based on expert and empirical analyses. Furthermore, the construct validity test indicated that only two of the 35 questions were deemed invalid. The assessment exhibited reliability with an item reliability score of 0.92. The item difficulty levels were equally spread across the normal curve, encompassing questions ranging from very difficult to very easy categories, as depicted in the variable map. After analyzing the map, it was observed that variations in students’ proficiency levels at answering questions were evident, indicating diverse levels of ability. Students performed well in handling formal and superordinate-subordinate level questions. However, their performance differed when dealing with identity and principle-level concepts.
Volume: 13
Issue: 6
Page: 3686-3695
Publish at: 2024-12-01

Relationship between anxiety, loneliness, and sleep-disorders with social media addiction among adolescent

10.11591/ijphs.v13i4.24204
Rika Sarfika , Zahratul 'Alini , Randy Refnandes , Nindi Eka Wijaya , I Made Moh. Yanuar Saifudin
In the digital era, social media usage has become an integral part of daily life, particularly among adolescents. This study investigates the relationship between anxiety, loneliness, sleep disorders, and social media addiction among adolescents. A cross-sectional study involving 290 X and XI-grade students utilized standardized instruments: the Bergen Social Media Addiction Scale (BSMAS), Zung Self-Rating Anxiety Scale (SAS/SRAS), UCLA Loneliness Scale Version 3, and Pittsburgh Sleep Quality Index (PSQI). Bivariate analysis was conducted using the Chi-square test (p<0.05). Findings revealed 10.7% severe social media addiction, 21.4% severe anxiety, 4.8% significant loneliness, and 74.5% poor sleep quality. Significant associations were found between anxiety (p=0.013), loneliness (p=0.010), sleep disturbance (p=0.033), and social media addiction. Higher anxiety, loneliness, and poor sleep quality correlate with increased susceptibility to social media addiction among adolescents. This underscores the importance of addressing psychological well-being in interventions aimed at mitigating social media addiction.
Volume: 13
Issue: 4
Page: 1647-1655
Publish at: 2024-12-01

Homonym and polysemy approaches with morphology extraction in weighting terms for Indonesian to English machine translation

10.11591/ijece.v14i6.pp7036-7045
Budi Harjo , Muljono Muljono , Rachmad Abdullah
Homonym and polysemy features can influence some errors in translation from a source language to another target language, for example, from Indonesian to English. A lemma or a morphology factor can cause the configuration of Indonesian homonym features. For example, the word beruang can mean an animal beruang (bear) and can mean a verb alternation ber+uang (has/have money). The Indonesian polysemy feature can also impact an error in the translation process because it can have a literal meaning and a symbolic meaning. For example, the terms bunga melati (jasmine flower) and bunga hati (lover), where bunga does not only mean flower. Therefore, the development machine translation (MT) method needs to capture homonym and polysemy features in the form of a word or a phrase. This research proposes homonym and polysemy approaches with morphology extraction in weighting terms for Indonesian to English MT. First, this research uses morphology extraction to detect sentences that contain prefixes, lemma, and suffixes. Then, the word similarity measurement functions to extract homonym and polysemy in the form of uni-gram and bi-gram using bidirectional encoder representations from transformers (BERT) embedding, named entity recognition (NER), synonym-based term expansion, and semantic similarity. This research uses neural machine translation for the translation process.
Volume: 14
Issue: 6
Page: 7036-7045
Publish at: 2024-12-01

Demographic factors affecting technological pedagogical content knowledge in Generation-Z preservice biology teachers

10.11591/ijere.v13i6.30355
Ahmad Kamal Sudrajat , Ibrohim Ibrohim , Herawati Susilo
Generation-Z dominating preservice biology teachers in this era. Teachers’ TPACK is influenced by factors such as demography. Technological, pedagogical and content knowledge (TPACK) is a framework used in teacher competence in Indonesia. This research will contribute to the training process of Generation-Z preservice biology teachers who have special characteristics. This study aims to determine the effect of demographic factors on the TPACK of Generation-Z preservice biology teachers. A total of 652 Generation Z preservice biology teachers from biggest ten Indonesian educational universities participated in this survey. The research results show that only gender has a relationship with TPACK in every aspect. Motivation to become a teacher influences TPACK, except for the technological knowledge (TK) aspect. In contrast, other aspects do not influence TPACK. Gender and motivation to become a teacher are factors that need attention in the training process for prospective biology teachers. Universities and the government can use these results to formulate suitable training programs for preservice biology teachers in Indonesia.
Volume: 13
Issue: 6
Page: 3796-3805
Publish at: 2024-12-01

Lifelong learning practices of primary school teachers: a systematic literature review

10.11591/ijere.v13i6.29597
Ros Faizah Mohd , Hafizhah Zulkifli , Mohd Isa Hamzah
The practice of lifelong learning among teachers involves continuous efforts to enhance their knowledge, skills, and competencies through various activities. Previous studies have explored different practices such as reading, collaboration, participation in courses, culturalizing learning, conducting research, and digital learning. However, there is a lack of systematic reviews of these practices. This an article aims to fill this gap by conducting a systematic review of lifelong learning practices among primary school teachers for 5 years since 2019 until 2023. The study integrates various research designs and follows the ROSES publication standard. Articles were selected from databases including Scopus, Web of Science (WoS), and ERIC. Thematic analysis revealed four key concepts: self-learning, continuous training, knowledge integration, and digital networks. Future research can focus on examining the resilience of teachers from diverse backgrounds in adapting to changes in the education system. This study serves as a valuable reference for teachers to assess their own lifelong learning practices and facilitate transformative growth towards becoming knowledgeable educators
Volume: 13
Issue: 6
Page: 3872-3883
Publish at: 2024-12-01

Batak Toba language-Indonesian machine translation with transfer learning using no language left behind

10.11591/ijaas.v13.i4.pp830-839
Cevin Samuel , Irsan Taufik Ali
This study focuses on neural machine translation (NMT) for low-resource languages (LRLs) pair, Batak Toba-Indonesian (bbc↔ind). The Batak Toba language is a critically endangered dialect of an Indonesian ethnic group, Batak. Recent advances in machine translation offer potential solutions, with transfer learning emerging as a promising approach for this language pair. We used a publicly available bbc↔ind parallel corpora from the Hugging Face datasets hub and employed the NLLB-200's distilled 600M variant model as the baseline model. Our models achieved sacreBLEU scores as follows: i) for bbc→ind, it achieved a score of 37.10 (+25.67, up from 11.43) and ii) for ind→bbc, it achieved a score of 30.84 (+25.82, up from 5.02). These results outperform all previous works in the task bbc↔ind machine translation and prove the validity of our approach.
Volume: 13
Issue: 4
Page: 830-839
Publish at: 2024-12-01

Systematic review: State-of-the-art in sensor-based abnormality respiration classification approaches

10.11591/ijece.v14i6.pp6929-6943
Nur Fatin Shazwani Nor Razman , Haslinah Mohd Nasir , Suraya Zainuddin , Noor Mohd Ariff Brahin , Idnin Pasya Ibrahim , Mohd Syafiq Mispan
Respiration-related disease refers to a wide range of conditions, including influenza, pneumonia, asthma, sudden infant death syndrome (SIDS) and the latest outbreak, coronavirus disease 2019 (COVID-19), and many other respiration issues. However, real-time monitoring for the detection of respiratory disorders is currently lacking and needs to be improved. Real-time respiratory measures are necessary since unsupervised treatment of respiratory problems is the main contributor to the rising death rate. Thus, this paper reviewed the classification of the respiratory signal using two different approaches for real-time monitoring applications. This research explores machine learning and deep learning approaches to forecasting respiration conditions. Every consumption of these approaches has been discussed and reviewed. In addition, the current study is reviewed to identify critical directions for developing respiration real-time applications.
Volume: 14
Issue: 6
Page: 6929-6943
Publish at: 2024-12-01

Real-time management and processing of RFID events based on a new RFID middleware architecture

10.11591/ijece.v14i6.pp6583-6599
Achraf Haibi , Kenza Oufaska , Khalid El Yassini , Hajar Bouazza , Mohammed Boulmalf , Mohsine Bouya
Radio frequency identification (RFID) is a contemporary technology that enables the identification of objects and facilitates the transmission of additional information, making it possible to achieve real-time object tracking in a mobile object network and to report information on the object's current state at each step. RFID devices continuously generate large amounts of data, and collecting, filtering, and consolidating these data are therefore crucial tasks, which characterize RFID data management by a set of challenges. However, one of the greatest challenges in this field is managing large volumes of data in complex applications, where real-time operation is vital, given that the volume and speed of RFID data often exceed the capacity of the existing technological infrastructure. The aim of this study is to propose an RFID middleware that manages both the RFID hardware network and the large amounts of data that are captured, in order to process and transmit the collected data under the right conditions for ultimate use by an information system. This new RFID middleware architecture, named BTMiddleware combines complex event processing (CEP) with a MongoDB database to offer large-volume data streaming, processing, and storage in real time, as well as better interoperability thanks to the use of the JavaScript object notation (JSON) format for data presentation.
Volume: 14
Issue: 6
Page: 6583-6599
Publish at: 2024-12-01

Aspect-based sentiment analysis: natural language understanding for implicit review

10.11591/ijece.v14i6.pp6711-6722
Suhariyanto Suhariyanto , Riyanarto Sarno , Chastine Fatichah , Rachmad Abdullah
The different types of implicit reviews should be well understood so that the developed extraction technique can solve all problems in implicit reviews and produce precise terms of aspects and opinions. We propose an aspect-based sentiment analysis (ABSA) method with natural language understanding for implicit reviews based on sentence and word structure. We built a text extraction method using a machine learning algorithm rule with a deep understanding of different types of sentences and words. Furthermore, the aspect category of each review is determined by measuring the word similarity between the aspect terms contained in each review and aspect keywords extracted from Wikipedia. Bidirectional encoder representations from transformers (BERT) embedding and semantic similarity are used to measure the word similarity value. Moreover, the proposed ABSA method uses BERT, a hybrid lexicon, and manual weighting of opinion terms. The purpose of the hybrid lexicon and the manual weighting of opinion terms is to update the existing lexicon and solve the problem of weighting words and phrases of opinion terms. The evaluation results were very good, with average F1-scores of 93.84% for aspect categorization and 92.42% for ABSA.
Volume: 14
Issue: 6
Page: 6711-6722
Publish at: 2024-12-01

Application of classification algorithms for smishing detection on mobile devices: literature review

10.11591/ijai.v13.i4.pp3750-3760
Dylan Faredh Calero Sinche , María Acuña Meléndez , Christian Ovalle
Smishing is a form of phishing carried out via mobile devices to steal confidential information from victims. The number of smishing attacks has increased in recent years due to the large number of users acquiring these easy-to-use and functional devices. This literature review objective is to examine the techniques and methods used in smishing attacks using classification algorithms. To do so, we conducted a manual search process and selected 155 articles from Scopus and 29 articles from access to research for development and innovation (ARDI). Of these, 36 articles met the inclusion criteria. In addition, the algorithms most commonly used by the studies were random forest classification techniques, decision trees, and neural networks. These studies analyzed various machine learning models for detecting phishing and smishing messages. The attack simulation scenarios included generating web pages, sending fake links (URLs), and installing malicious applications. The analysis evaluated web pages and SMS messages using a database containing legitimate as well as smishing messages. Based on the results, it is suggested to combine these methods to improve detection performance, making it more robust and promising.
Volume: 13
Issue: 4
Page: 3750-3760
Publish at: 2024-12-01

Grindulu fault cloud radon data for earthquake magnitude prediction using machine learning

10.11591/ijai.v13.i4.pp4572-4582
Thomas Oka Pratama , Sunarno Sunarno , Agus Budhie Wijatna , Eko Haryono
The study investigates the potential of integrating radon gas concentration telemonitoring systems with machine learning techniques to enhance earthquake magnitude prediction. Conducted in Pacitan, East Java, Indonesia, where the stations are near the active Grindulu fault, the research employs random forest (RF), extreme gradient boosting (XGB), neural network (NN), AdaBoost (AB), and support vector machine (SVM) methods. The study aims to refine earthquake magnitude prediction, utilizing real-time radon gas concentration measurements, crucial for disaster preparedness. The evaluation involves multiple metrics like mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), mean squared error (MSE), symmetric mean absolute percentage error (SMAPE), and conformal normalized mean absolute percentage error (cnSMAPE). XGB and SVM emerge as top performers, showcasing superior predictive accuracy with minimal errors across various metrics. XGB achieved MAE (0.33), MAPE (6.03%), RMSE (0.51), MSE (0.26), SMAPE (0.06), and cnMAPE (0.97), while SVM recorded MAE (0.34), MAPE (6.20%), RMSE (0.51), MSE (0.26), SMAPE (0.06), and cnSMAPE (0.97). The analysis reveals XGB as the most effective method, boasting the lowest error values. The study underscores the importance of expanding data availability to enhance predictive models, ultimately contributing to more precise earthquake magnitude predictions and effective mitigation strategies.
Volume: 13
Issue: 4
Page: 4572-4582
Publish at: 2024-12-01

Risk factors of metabolic syndrome in women of reproductive age at mining area

10.11591/ijphs.v13i4.24468
Novia Luthviatin , Onny Setiani , Bagoes Widjanarko , Mohammad Zen Rahfiludin , Apoina Kartini , Mursid Raharjo
Lead is one of the four most dangerous heavy metal pollutants, toxic to human health, and linked to metabolic syndrome (MetS). This research aimed to analyze the relationship between respondent characteristics, blood lead level (BLL), nutrition intake, and physical activity to MetS and its components in women of reproductive age at Pemali District Mining Area, Bangka Belitung Regency. This research was conducted with a case-control approach involving 70 women of reproductive age (35 cases and 35 controls). Data was analyzed using chi-square and Mann-Witney tests for bivariate analysis and regression test logistics for multivariate analysis. Based on bivariate analysis, there is a significant relationship between body mass index (BMI) (p=0.000), salt intake (p=0.017), and seasoning intake (p=0.017) to MetS; meanwhile, BLL is not associated with MetS (p=0.473) but are associated with high-density lipoprotein cholesterol (HDLC) (p=0.019). Multivariate test results show that BMI (p=0.000; OR=7.995) and salt intake (p=0.030; OR=6.812) are significant risk factors for MetS. Women of reproductive age must maintain BMI within normal levels and reduce daily salt intake to prevent the occurrence of MetS. BLL must be controlled to prevent decreased HDLC levels in women of reproductive age.
Volume: 13
Issue: 4
Page: 1960-1967
Publish at: 2024-12-01

Indonesian sentiment towards global economic recession in 2023 using optimized hyperparameters of support vector machine kernels

10.11591/ijai.v13.i4.pp4948-4956
Dairatul Maarif , Adinda Aulia Hafizha , Andi Kurniawan
The potential for the 2023 global recession has troubled people worldwide, particularly in light of the COVID-19 pandemic. This study employs a sentiment analysis approach to examine how the Indonesian internet community, particularly on Twitter, perceives the topics related to the global economic recession. We collected 11,017 uploaded tweets that were analyzed using support vector machine classifier with linear, radial basis function (RBF), sigmoid, and polynomial kernel schemes. Furthermore, we optimized the classifiers with C, Gamma, and degree hyperparameters. Empirical evidence indicates a lack of preparedness to face a global recession, evidenced by most responses towards 2023 global recession exhibiting concerns about high inflation and economic instability. The finding also suggests that the optimized RBF is a superior modeling kernel relative to others. Collectively, these results provide insights with significant implications for sentiment analysis, natural language processing, and the study of behavioural economics.
Volume: 13
Issue: 4
Page: 4948-4956
Publish at: 2024-12-01
1 2 3
...
2097 2098
Show 409 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