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

Exploring new feedback practices paradigm in higher education: students’ perspectives

10.11591/ijere.v14i2.29819
Marlina Ummas Genisa , Haryanti Putri Rizal , Hasri Hasri , Andi Agussalim
Feedback has recently shifted from being received to being an interaction process, raising considerable interest among educators. This study aims to examine whether current feedback practices in higher education have led to active student interaction processes, and how individual and contextual factors are considered in practice based on gender and university perspectives. An online questionnaire was used to collect data from 418 students from three Indonesian universities, Universitas Negeri Makassar (UNM), Universitas Muhammadiyah Palembang (UMP), and Universitas Sulawesi Barat (USB). The data was analyzed descriptively-quantitatively. Results indicate that current feedback practices do not adequately direct students to actively participate in the processing feedback. The feedback received is dominated by general feedback (UNM and USB), while detailed and discussed feedback is generally received by UMP students. Additionally, the expected and effective feedback obtained the same pattern that individuals and groups must interact which is in line with the new paradigm. The results also showed the ideal time for providing feedback is 5-10 days for various types of assignments and 15-20 days for theses. These results provide educators with information on strategies and approaches in feedback practices that are relevant and effective in enhancing student learning based on the new paradigm.
Volume: 14
Issue: 2
Page: 1124-1133
Publish at: 2025-04-01

Implementation of a prototype to prevent childhood accidents in dangerous domestic environments using ESP 32 Wi-Fi module

10.11591/ijeecs.v38.i1.pp88-98
Jenner Lavalle-Sandoval , Paul Córdova-Cardenas , Sheyla Rivera-Quispe , Laberiano Andrade-Arenas
Robotics has significantly advanced human evolution by optimizing tasks in fields such as medicine, engineering, and mechanics, enhancing daily life through various robotic prototypes. These innovations help prevent accidents and injuries, whether at home or in hazardous environments. For instance, sensors can detect gas leaks, fires, and other potential disasters. This research aims to design a prototype adaptable to any home environment that poses risks to infants, such as kitchens, bathrooms, or stairs. The proposed prototype incorporates gas, motion, and sound sensors connected to a Wi-Fi ESP 32 module, which alerts parents to any potential danger to their children. The research is developed in six phases: component selection, circuit simulation, prototype design, three-dimensional (3D) printing, code programming, and final testing. The results demonstrate a positive impact, improving the control and care of infants by alerting parents to hazards such as gas leaks, crying, or movement in risky areas. The conclusion confirms the effectiveness of the prototype in providing timely alerts to safeguard infants in potentially dangerous situations.
Volume: 38
Issue: 1
Page: 88-98
Publish at: 2025-04-01

Shaping competence of intercultural communication during the COVID-19

10.11591/ijere.v14i2.29636
Saya Ayazbayeva , Bazarbek Mukushev , Maral Yessekeshova
Shaping intercultural communication competencies during the educational process in higher education institutions is a crucial criterion for modern global education. This study considers using digital learning technologies in foreign language teaching as an efficient pedagogical strategy for developing intercultural communicative competence during the COVID-19 pandemic. The research methodology was based on a pedagogical experiment. A total of 43 students from the People’s Republic of China, Kyrgyz Republic, Republic of India, and Turkmenistan participated in three study groups. Before the experiment, the indicators of digital competence and willingness to engage in intercultural communication were low, with a high correlation between them. During the one-year academic experiment, the students studied foreign languages using digital technologies. They were involved in cultural immersion programs, master’s classes on intercultural communication, language exchange programs, virtual intercultural events, and online cultural resources. This contributed to improving intercultural communication and, at the same time, students’ digital competence.
Volume: 14
Issue: 2
Page: 879-886
Publish at: 2025-04-01

Next-generation offloading using hybrid deep learning network for adaptive mobile edge computing

10.11591/ijece.v15i2.pp1924-1932
P. Anusha , V. Mary Amala Bai
Deploying mobile application tasks that require a lot of computing and are time-sensitive to distant cloud-based data centers has become a popular method of working around the limitations of mobile devices (MDs). Deep reinforcement learning (DRL) techniques for offloading in mobile edge computing (MEC) environments struggle to adapt to new situations due to low sample efficiency for each new context. To address these issues, a novel computational offloading in mobile edge computing (COOL-MEC) algorithm has been proposed that combines the benefits of attention modules and bi-directional long short-term memory. This algorithm improves server resource utilization by lowering the cost of assimilating processing latency, processing energy consumption, and task throughput of latency-sensitive tasks. The experiment's findings show that, when used as intended, the recommended COOL-MEC algorithm minimizes energy consumption. When compared to the current deep convolutional attention reinforcement learning with adaptive reward policy (DCARL-ARP) and DRL techniques, the energy consumption of the proposed COOL-MEC is decreased by 0.06% and 0.08%, respectively. The average time per channel utilized for the execution of the proposed COOL-MEC also decreased by 0.051% and 0.054% when compared with existing DCARL-ARP and DRL methods respectively.
Volume: 15
Issue: 2
Page: 1924-1932
Publish at: 2025-04-01

A hybrid machine learning approach for improved ponzi scheme detection using advanced feature engineering

10.11591/ijict.v14i1.pp50-58
Fahad Hossain , Mehedi Hasan Shuvo , Jia Uddin
Ponzi schemes deceive investors with promises of high returns, relying on funds from new investors to pay earlier ones, creating a misleading appearance of profitability. These schemes are inherently unsustainable, collapsing when new investments wane, leading to significant financial losses. Many researchers have focused on detecting such schemes, but challenges remain due to their evolving nature. This study proposes a novel hybrid machine-learning approach to enhance Ponzi scheme detection. Initially, we train an XGBoost classifier and extract its features. Meanwhile, we tokenize opcode sequences, train a gated recurrent unit (GRU) model on these sequences, and extract features from the GRU. By concatenating the features from the XGBoost classifier and the GRU, we train a final XGBoost model on this combined feature set. Our methodology, leveraging advanced feature engineering and hybrid modeling, achieves a detection accuracy of 96.57%. This approach demonstrates the efficacy of combining XGBoost and GRU models, along with sophisticated feature engineering, in identifying fraudulent activities in Ethereum smart contracts. The results highlight the potential of this hybrid model to offer more robust and accurate Ponzi scheme detection, addressing the limitations of previous methods.
Volume: 14
Issue: 1
Page: 50-58
Publish at: 2025-04-01

Exploring topic modelling: a comparative analysis of traditional and transformer-based approaches with emphasis on coherence and diversity

10.11591/ijece.v15i2.pp1933-1948
Ayesha Riaz , Omar Abdulkader , Muhammad Jawad Ikram , Sadaqat Jan
Topic modeling (TM) is an unsupervised technique used to recognize hidden or abstract topics in large corpora, extracting meaningful patterns of words (semantics). This paper explores TM within data mining (DM), focusing on challenges and advancements in extracting insights from datasets, especially from social media platforms (SMPs). Traditional techniques like latent Dirichlet allocation (LDA), alongside newer methodologies such as bidirectional encoder representations from transformers (BERT), generative pre-trained transformers (GPT), and extra long-term memory networks (XLNet) are examined. This paper highlights the limitations of LDA, prompting the adoption of embedding-based models like BERT and GPT, rooted in transformer architecture, offering enhanced context-awareness and semantic understanding. The paper emphasizes leveraging pre-trained transformer-based language models to generate document embedding, refining TM and improving accuracy. Notably, integrating BERT with XLNet summaries emerges as a promising approach. By synthesizing insights, the paper aims to inform researchers on optimizing TM techniques, potentially shifting how insights are extracted from textual data.
Volume: 15
Issue: 2
Page: 1933-1948
Publish at: 2025-04-01

Embedded systems and artificial intelligence for enhanced humanoid robotics applications

10.11591/ijece.v15i2.pp1912-1923
Jalal Hdid , Oussama Lamsellak , Ahmad Benlghazi , Abdelhamid Benali , Ouafae El Melhaoui
This paper presents a method for collecting precise hand gesture (HG) data using a low-cost embedded device for an embedded artificial intelligence (EAI)-based humanoid robotics (HR) application. Despite advancements in the field, challenges remain in deploying cost-effective methods for accurately capturing and recognizing body gesture data. The ultimate objective is to develop humanoid robots (HRS) capable of better understanding human activities and providing optimal daily life support. In this regard, our approach utilizes a Raspberry Pi Pico microcontroller with a 3-axis accelerometer and a 3-axis gyroscope motion sensor to capture real- time HG data, describing ten distinct real-world tasks performed by the hand in experimental scenarios. Collected data is stored on a personal computer (PC) via a micro-python program, forming a dataset where tasks are classified using ten supervised machine learning (SML) models. Two classification experiments were conducted: the first involved predicting raw data, and the second applied normalization and feature extraction (FE) techniques to improve prediction performance. The results showed promising accuracy in the first phase (89% max), with further improvements achieved in the second phase (94% max). Finally, by employing similar methods, we can integrate highly trained machine learning (ML) models into embedded humanoid robotic systems, enabling real-time human assistance.
Volume: 15
Issue: 2
Page: 1912-1923
Publish at: 2025-04-01

Exploring diverse prediction models in intelligent traffic control

10.11591/ijeecs.v38.i1.pp393-402
Sahira Vilakkumadathil , Velumani Thiyagarajan
Traffic congestion is a major challenge that affects excellence of life for numerous people across world. The fast growth in many vehicles contributes to congestion during peak and non-peak hours. The vehicle traffic resulted in many issues like accidents and inefficiency in traffic flow. Many traffic light control systems operate on fixed time intervals leads to inefficiency. The fixed-time signals cause unnecessary delays on roads with minimum number of quantity vehicles. Intelligent transport systems (ITS) introduce new comprehensive framework that combine the advanced technologies to improve the transportation network efficiency and to optimize the traffic management. The high-traffic routes are forced to wait excessively. Machine learning (ML) methods have designed to examine the traffic control. However, the accurate detection and vehicle tracking are essential one for effective ITS. In order to mention these problems, ML and deep learning (DL) methods are introduced to improve prediction performance.
Volume: 38
Issue: 1
Page: 393-402
Publish at: 2025-04-01

Tilted fiber Bragg grating based optical sensor for simultaneous measurement of vital signs: a novel approach

10.11591/ijece.v15i2.pp1434-1445
Ramya Arumugam , Ramamoorthy Kumar , Samiappan Dhanalakshmi
Vital signal monitoring acts as a highly significant diagnostic method. Continuous monitoring of vital signs like temperature, heart rate, and blood pressure aids in easy and fast disease diagnosis. Existing methods that enable continuous monitoring, such as smart watches, are not accurate enough to be used as a benchmark for diagnosing diseases. In this paper, we propose simultaneous temperature and heart rate measurement using tilted fiber Bragg grating (TFBG) which enables concurrent measurement of measurands due to its intrinsic optical property. Temperature and heart rate were considered for measurement. The proposed TFBG-based optical sensor has a sensitivity of 11.81 pm/°C and 1.73 pm/µε towards variation in temperature and strain, respectively. The sensitivity was determined by a shift in the wavelength of core mode resonance for temperature and a differential change in the wavelength of cladding mode resonance for heart rate. The average response time of the proposed TFBG sensor was found to be 3 seconds. Accuracy of 99.68% and 98.42% were achieved in temperature and heart rate measurements by the proposed TFBG sensor. The acceptability of the proposed TFBG sensor was analyzed using the Bland- Altman plot.
Volume: 15
Issue: 2
Page: 1434-1445
Publish at: 2025-04-01

Modeling and enhancing inverse kinematics algorithms for real-time target tracking in inertial stabilization systems

10.11591/ijece.v15i2.pp1544-1556
Abderahman Kriouile , Soufiane Hamida , Abdoul Latif Abdou Moussa
This study develops a two-axis gimbal system designed to maintain a target within its field of view by compensating for motion of either the target or the platform. The focus is on inertial stabilization platforms (ISPs), where accurate, real-time tracking is essential for applications such as surveillance, navigation, and scientific observation. The research prioritizes the design and optimization of inverse kinematics algorithms to enhance system performance. A detailed analysis of mathematical models underpins the development, addressing challenges in real-time processing with advanced optimization techniques to minimize latency and maximize accuracy. The proposed algorithms achieve a mean tracking error of 0.002 m and a mean convergence time of 2.12 seconds, surpassing traditional methods in precision and efficiency. Performance is evaluated within a simulation framework using Simscape Multibody, testing the algorithms under various conditions. Validation extends to real-world scenarios to ensure robustness and practical applicability. The results demonstrate significant improvements in tracking accuracy and responsiveness, offering a reliable solution for dynamic environments. This work paves the way for more efficient gimbal systems, contributing to advancements in technologies requiring stable and precise tracking in dynamic and challenging settings.
Volume: 15
Issue: 2
Page: 1544-1556
Publish at: 2025-04-01

Three-phase hybrid active power filter: an overview

10.11591/ijece.v15i2.pp1361-1371
Le Quang Binh , Chau Minh Thuyen
Hybrid active power filter (HAPF) is considered an effective solution for filtering harmonics and compensating reactive power in power systems. It is a combination of passive power filters and an active power filter to form many different structures depending on the system voltage and load characteristics. This paper aims to introduce an overall picture of the results of research on three-phase HAPF systems, such as: HAPF models, advantages, disadvantages, and scope of application of each model; methods for determining parameters of passive power filters; structure, response time, resonance, power loss and cost of types of output filters; inverter structure and commonly used pulse width modulation methods in HAPF; control strategies and used controllers are also listed and compared; the DC Link voltage stabilization is also summarized and analyzed. Finally, the existing problems and the development trends of HAPF.
Volume: 15
Issue: 2
Page: 1361-1371
Publish at: 2025-04-01

Recognition of plant leaf diseases based on deep learning and the chemical reaction optimization algorithm

10.11591/ijeecs.v38.i1.pp447-458
Nghien Nguyen Ba , Nhung Nguyen Thi , Dung Vuong Quoc , Cuong Nguyen Cong
Agriculture plays a crucial role in developing countries such as Vietnam, where 70 percent of the population is employed in agriculture, and 57 percent of the social labor force works in the agricultural sector. Therefore, crop productivity directly affects the lives of many people. One of the primary reasons for reduced crop yields is plant leaf diseases caused by bacteria, fungi, and viruses. Hence, there is a need for a method to help farmers identify leaf diseases early to take appropriate action to protect crops and shift to smart agricultural production. This paper proposes lightweight deep learning (DL) models combined with a support vector machine (SVM), with hyperparameters fine-tuned by chemical reaction optimization (CRO), for detecting plant leaf diseases. The main advantage of the method is the simplicity of the architecture and optimization of the DL model’s hyperparameters, making it easily deployable on low hardware devices. To test the performance of the proposed method, experiments are performed on the PlantVillage dataset using Python. The superiority of the proposed method over the well-known visual geometry group-16 (VGG-16) and MobileNetV2 models is demonstrated by a 10% increase in accuracy prediction and a decrease of 5% and 66% in training time, respectively.
Volume: 38
Issue: 1
Page: 447-458
Publish at: 2025-04-01

Cost-effective IoT-based automated vehicle headlight control system: design and implementation

10.11591/ijict.v14i1.pp325-333
Momotaz Begum , Nayeem Ullah , Mehedi Hasan Shuvo , Towhidul Islam , Thofazzol Hossen , Jia Uddin
The current world would be difficult without vehicles, which offer vital advantages for social connectivity, mobility, and technical advancement. Though motor vehicles provide benefits to passenger transportation, they also present certain challenges in their use. A major issue is nighttime traffic accidents caused by headlamps from automobiles traveling in reverse directions, that's why there is a high probability of accidents due to the glare on the driver's eyes. The phrase "Troxler effect" refers to an unexpected glare that a motorist recognizes. In this paper, we will provide an optimal solution to this challenge/Troxler effect. The primary objective of this paper is to design an internet of things (IoT)-based smart headlight control model. Our system introduced a cost-effective vehicle’s headlights controlled by light detection. According to this paper, a vehicle’s headlights are automatically rotated down when the sensor detects lights from the opposite direction of the vehicle headlights. We tried to reduce the road accident rate with our proposed system. This type of technology will prove useful in the motor vehicle sector and offer an innovative approach that ensures driver safety as well as increasing economic development.
Volume: 14
Issue: 1
Page: 325-333
Publish at: 2025-04-01

Logistic regression of online risks on academic stress and performance undergraduates

10.11591/ijere.v14i2.30147
Sigit Permansah , Munawir Yusuf , Subagya Subagya , Muhtar Muhtar , Cicilia Dyah Sulistyaningrum Indrawati , Dede Rusmana
The progression of technology could lead to online risks, such as accidental exposure to harmful content by undergraduates. Investigating how this exposure affects their mental health, particularly academic stress, and in turn, their academic performance, is critically important. This study aims to examine the impact and predictability of online risks on undergraduates’ academic stress and performance, using logistic regression as the main method of analysis. The findings show that online risks have a significant effect on academic stress (p<0.05), but there is no significant impact on academic performance (p>0.05). Students who frequently encounter scam or bullying content are 2.317 and 2.400 times more likely, respectively, to suffer from academic stress compared to those who encounter it less. Additionally, demographic factors, especially gender, are significant (p<0.05) in terms of academic stress and performance. The analysis predicts that females are 4.210 times more likely to experience academic stress than males, while males are 2.768 times (in model 4) and 2.601 times (model 5) more likely to achieve cum laude honors than females. This research provides valuable insights for academic policy makers to improve education quality and offers a basis for further studies in this area.
Volume: 14
Issue: 2
Page: 825-836
Publish at: 2025-04-01

Managing cyber resilience literacy for consumers

10.11591/ijict.v14i1.pp122-131
Tatiana Antipova , Simona Riurean
It seems inevitable that digitalization will have a profound and irreversible impact on our lives, and it seems reasonable to suppose that our world will never be the same again. Objectives of this study is to gain insight into consumers’ understanding of cyber security threats and their willingness to enhance their cyber resilience. To achieve this, a survey was conducted using AI tools such as Open ChatGPT, Copilot and PI. The survey was distributed selectively among consumers via Google Form. The results of the survey conducted during the study indicated that the majority of respondents (72%) expressed interest in attending online interactive seminars to gain more knowledge about managing cybersecurity threats. However, respondents with the lowest cyber resilience knowledge did not express the same level of interest. With technology becoming an increasingly important aspect in our everyday lives, it is becoming ever clearer that cybersecurity posture relies on the behavior consumers and organizations. Based on the rule that ‘never trust, always verify’ we designed ‘cybersecurity zero-trust framework model’ for consumers that allows them to protect themselves against cybersecurity threats. In an ever-shifting landscape of cybersecurity, it is important to recognize the value of continuous education as a necessity, not just an option.
Volume: 14
Issue: 1
Page: 122-131
Publish at: 2025-04-01
1 2 3
...
2097 2098
Show 312 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