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

30,376 Article Results

Forecasting business exceptions in robotic process automation with machine learning

10.11591/ijra.v14i3.pp450-458
Igor Saez , Sara Segura , Mónica Gago
Business exceptions interrupt robotic process automation (RPA) workflows and oblige costly human intervention. This paper explores the application of machine learning (ML) time series forecasting techniques to predict business exceptions in RPA. Using RPA robot logs from a financial service company, we employ ARIMA, SARIMAX, and Prophet statistical models, comparing their performance with ML models such as XGBoost and LightGBM. Furthermore, we explore hybrid approaches that combine the strengths of statistical models with ML techniques, specifically integrating Prophet with XGBoost and LightGBM. Our findings reveal that a hybrid LightGBM model substantially outperforms traditional methods, achieving a 40% reduction in the weighted absolute percentage error (WAPE) when compared to the top-performing statistical model. These results suggest the potential of ML forecasting in optimizing RPA operations through the analysis of log-generated data.
Volume: 14
Issue: 3
Page: 450-458
Publish at: 2025-12-01

A method integral sliding mode control to minimize chattering in sliding mode control of robot manipulator

10.11591/ijra.v14i3.pp345-355
Mai Hoang Nguyen , Truc Thi Kim Nguyen
This paper presents an improved sliding mode control (SMC) strategy for robotic manipulators by introducing a novel exponential integral-based adaptive gain law, referred to as integral sliding mode control (ISMC). The proposed approach dynamically adjusts the switching gain KKK in real-time, based on the accumulated system error, thereby effectively reducing chattering while preserving system robustness. Unlike many existing methods, the ISMC strategy eliminates the need for state observers or complex estimation techniques, simplifying implementation. Theoretical analysis is provided using Lyapunov stability theory, ensuring global convergence. Simulation results on 2-DOF and 3-DOF robotic arms demonstrate superior tracking accuracy and smoother control signals compared to conventional SMC approaches. This work contributes a lightweight yet effective SMC enhancement with practical benefits for real-world robotic applications.
Volume: 14
Issue: 3
Page: 345-355
Publish at: 2025-12-01

FIND-ROUTE: Fourier series integrated deep learning model for energy efficient routing in Internet of Things-wireless sensor network

10.11591/ijra.v14i3.pp468-478
Shobanbabu Ramaswamy Jaganathan , Sathya Rajendran , Karthikeyan Ramamoorthy
The Internet of Things (IoT) relies on wireless sensor networks (WSNs) to transmit data across a wide range of applications. However, the commonly encountered primary challenges in IoT-enabled WSNs are high energy consumption during data transmission, which insists energy optimized routing to prolong the network lifetime. To address these challenges, a novel Fourier series integrated deep learning-based routing (FIND-ROUTE) framework has been proposed for energy-aware communication among IoT nodes in WSN. Initially, a hybrid clustering approach forms an adaptive cluster for efficient data aggregation with reduced energy consumption. After clustering, stable cluster heads (CHs) are elected by a Fourier series-based metaheuristic optimization algorithm for balancing the energy usage with extended network lifetime. Finally, an Intelligent neural network dynamically selects the optimal path and transmits the data efficiently with reduced latency for reliable communication in IoT-WSN. The FIND-ROUTE framework is simulated by using MATLAB, and it is validated by using the WSN-DS dataset. The proposed FIND-ROUTE framework is evaluated based on several parameters, including energy consumption, packet delivery ratio (PDR), network lifetime (NL), time complexity, throughput, number of alive nodes, packet loss ratio (PLR), and space complexity. In comparison, the proposed FIND-ROUTE framework achieves a PDR of 90%, whereas MLBDARP, LQEER, and NBSHO-DRNN achieve 70%, 60%, and 67% respectively.
Volume: 14
Issue: 3
Page: 468-478
Publish at: 2025-12-01

Clinical dental students' perceptions of difficulties in fixed prosthodontics bridgework denture preparation: a pilot study

10.11591/ijphs.v14i4.24623
Aditya Pratama Sarwono , Khairunnisa Febianti
Preparing abutment teeth for fixed bridgework presents varying challenges to dental students, impacting their training effectiveness and clinical outcomes. Understanding the most difficult stages can help improve educational strategies. This study aims to rank the difficulty of each stage in abutment tooth preparation using student evaluations, identifying the greatest challenges. A quantitative approach was used, analyzing perceptions of 155 clinical dental students from 2021-2023 cohorts at Faculty of Dentistry, Universitas Trisakti, through the non-parametric Friedman’s ANOVA Test. Student evaluations covered seven stages of abutment tooth preparation, identifying variability in perceived difficulty from most difficult to easiest. Results indicate the most difficult stage is proximal reduction (mean rank: 3.01), followed by cervical preparation (mean rank: 3.28), and lingual reduction (mean rank: 3.35). The stages with the lowest difficulty are finishing (mean rank: 5.35), followed by alignment of preparation between 2 abutment teeth (mean rank: 4.85), buccal reduction (mean rank: 4.13), and occlusal reduction (mean rank: 4.03). Proximal reduction is particularly difficult due to the need for high technical skills and precision, requiring accurate space estimation and careful reduction without damaging adjacent teeth. This difficulty is compounded by natural variations in tooth shapes and positions among patients. Findings highlight the importance of refining educational strategies to tackle these challenges, enhancing student learning and clinical skills. This research provides crucial data on which stages need greater emphasis in the curriculum, aiding the creation of more efficient and focused training methods.
Volume: 14
Issue: 4
Page: 1730-1737
Publish at: 2025-12-01

Interventions to improve resilience in breast cancer patients: a systematic review

10.11591/ijphs.v14i4.26206
Dwi Retnaningsih , Nursalam Nursalam , Hanik Endang Nihayati
Breast cancer patients with low resilience may experience adverse psychological outcomes, including stress, anxiety, depression, emotional dysregulation, and difficulties in recovery. This systematic review aims to evaluate the effectiveness of various interventions in improving resilience among breast cancer patients and to provide practical guidance for healthcare practitioners in implementing these interventions. Following the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines and PICOS framework, a comprehensive search was conducted across PubMed, Scopus, ScienceDirect, and Google Scholar for studies published between 2018-2024. Two independent reviewers screened eligible studies in two stages (title/abstract and full-text). The methodological quality of included studies was assessed using the Joanna Briggs Institute Critical Appraisal Tool. A total of 20 studies met the inclusion criteria. Interventions identified include music therapy, mindfulness, family and social support programs, cognitive behavioral therapy, digital-based interventions, and psychoeducation. Most interventions demonstrated a significant positive impact on patients’ psychological resilience, coping ability, and quality of life. Evidence suggests that resilience-focused interventions can be effectively integrated into supportive care for breast cancer patients. Healthcare practitioners should consider incorporating these strategies to address psychosocial needs. Further studies are recommended to evaluate long-term impacts and cost-effectiveness in diverse settings.
Volume: 14
Issue: 4
Page: 1710-1719
Publish at: 2025-12-01

Development of a leakage detection and alert system for liquefied petroleum gas via a mobile application

10.11591/ijaas.v14.i4.pp1099-1110
Wael A. Salah , Anees Abu Sneineh
Nowadays, ensuring the comfort and safety of house users is a top priority, and this may be accomplished by implementing smart technology to lead a convenient and safe life. Leakage of liquefied petroleum gas (LPG), which is mostly utilized in the home kitchen for cooking, is one of the frequent risks. Using a gas sensing device, a gas control system, and wireless communication units, the goal of this study is to create an LPG gas leakage warning and management system to prevent the gas from exploding by detecting the leak. When LPG gas is brought near the sensor, it detects the leakage and the buzzer is activated by activating the audio-visual alarm and closing the gas cylinder valve. The system also generates alert messages and sends them to the fire station when the LPG gas leakage has reached a critical level. Testing results of the proposed LPG leakage system show a satisfactory performance of the developed device with a quick response to LPG gas leakage. In addition, powerful audio and visual alarms are activated. An immediate message was sent to homeowners and the fire station department regarding the leakage incident to prevent the risk of gas leakage.
Volume: 14
Issue: 4
Page: 1099-1110
Publish at: 2025-12-01

Reproductive tract infections among geriatric population in a block of West Bengal: knowledge and risk behaviour assessment

10.11591/ijphs.v14i4.24994
Kuntala Ray , Shalini Pattanayak , Somnath Naskar , Mausumi Basu
Reproductive tract infections (RTIs) among the geriatric population remains neglected, causing increase in morbidity. This study aimed to elicit knowledge, identify risk behaviour for RTIs among the elderly residing in a block of West Bengal, to determine any associations between sociodemographic profile with knowledge and risk behaviour respectively, and to assess any correlation between knowledge and risk behaviour. A community-based study was conducted using multistage sampling, among 158 geriatric residents of a rural block in West Bengal, India for a period of 3 months in 2023. Face-to-face interviews were carried out using an interview schedule. Overall median scores were calculated separately for knowledge and risk behaviour domains. Score < median score was categorized as ‘inadequate knowledge’ and score ≥ median was classified as ‘high risk’ behaviour. Nearly 30% reportedly had ‘inadequate knowledge’ while 77% had ‘high risk’ behavior for RTIs. Higher odds of inadequate knowledge and high-risk behavior were observed among those who were employed and those who availed of any social security scheme(s). Moderately positive correlation was obtained between knowledge and risk behavior.
Volume: 14
Issue: 4
Page: 1675-1685
Publish at: 2025-12-01

Adaptive fuzzy logic controller based BLDC motor to improve the dynamic performance for electric tractor application

10.11591/ijpeds.v16.i4.pp2186-2196
Ashwini Yenegur , Mungamuri Sasikala
Permanent magnet brushless DC (PMBLDC) motors are widely used in a variety of industrial applications due to their high-power density and ease of regulation. The three-phase power semiconductors bridge is the standard way for controlling these motors. In order to initiate the inverter bridge and switch on the power devices, rotor position sensors must be provided with the correct commutation sequence. The power devices commutate progressively 60 degrees, depending on the location of the rotor. The right speed controllers are necessary for the motor to run as efficiently as possible. PI controllers are commonly employed with permanent magnet motors to achieve speed control in simple manner. Nevertheless, these controllers provide challenges in managing control complexity, including nonlinearity, parametric fluctuations, and load disturbances. PI controllers need accurate linear mathematical models. To overcome this, in this paper adaptive fuzzy logic controller (FLC) for controlling the speed of a BLDC motor is presented. When the motor drive system uses the adaptive FLC technology for speed control, it exhibits better dynamic behavior and is more resistant to changes in parameters and load disturbances. The main objectives of this work are to analyze and appraise the functioning of an electric tractor driven by a PMBLDC motor drive using adaptive FLC. The PMBLDC motor drive controllers are simulated using MATLAB/Simulink software.
Volume: 16
Issue: 4
Page: 2186-2196
Publish at: 2025-12-01

Mixed attention mechanism on ResNet-DeepLabV3+ for paddy field segmentation

10.12928/telkomnika.v23i6.26829
Alya; University of Indonesia Khairunnisa Rizkita , Masagus Muhammad; University of Indonesia Luthfi Ramadhan , Yohanes Fridolin; University of Indonesia Hestrio , Muhammad Hannan; University of Indonesia Hunafa , Danang Surya; National Research and Innovation Agency Candra , Wisnu; University of Indonesia Jatmiko
Rice cultivation monitoring is crucial for Indonesia, where paddy field areas de clined by 2.45% according to the Central Bureau of Statistics due to land func tion changes and shifting crop preferences. Regular monitoring of paddy field distribution is essential for understanding agricultural land utilization by farmers and landowners. Satellite imagery has become increasingly common for agricul tural land observation, but traditional neural networks alone provide insufficient segmentation accuracy. This study proposes an enhanced deep learning architec ture combining residual network (ResNet)-DeepLabV3+ with coordinate atten tion (CA) and spatial group-wise enhancement (SGE) modules. The attention mechanisms establish direct connections between context vectors and inputs, enabling the model to prioritize relevant spatial and spectral features for precise paddy field identification. The CA module enhances spectral feature discrim ination, whereas the SGE improves spatial characteristic representation. The experimental results demonstrate superior performance over the baseline meth ods, achieving intersection over union (IoU) of 0.85, dice coefficient of 0.89, and accuracy of 0.95. The proposed mixed attention mechanism significantly improves the accuracy and efficiency of automatic crop area identification from satellite imagery.
Volume: 23
Issue: 6
Page: 1611-1625
Publish at: 2025-12-01

Optimization of maternal healthcare at the village level in reducing maternal mortality in Bali, Indonesia

10.11591/ijphs.v14i4.26820
Panca Dwi Prabawa , I Ketut Widnyana , Ni Putu Pandawani , Wayan Maba
Although maternal mortality rates in Bali have declined, the achievement remains below the government’s target, highlighting the need to strengthen the role of villages as the frontline of development. This study aims to identify alternative strategies to accelerate maternal mortality reduction by examining the supply of maternal healthcare services and the demand reflected in women’s utilization of these services at the village level. Using the analytic hierarchy process (AHP) to map accessibility across villages and servqual model to evaluate women’s perceptions of maternal healthcare services provided through integrated services post (posyandu) and village health post (Poskesdes), the study reveals significant disparities in accessibility across villages, particularly in Tabanan, Bangli, and Karangasem Regencies. While overall perceptions of healthcare quality are positive, the largest and most significant service quality gaps occur in tangibility and responsiveness. Based on these findings, the study recommends prioritizing villages with limited access to maternal healthcare services by ensuring health coverage for pregnant women from low-income households and guaranteeing the availability of midwives in villages through incentive schemes, while adopting community-based approaches to effectively reach migrant populations and improve their utilization of maternal healthcare services.
Volume: 14
Issue: 4
Page: 1765-1778
Publish at: 2025-12-01

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

10.11591/ijra.v14i3.pp439-449
Loga Priyadarshini Kathirmalaiyan , Nithya Muthu
Load balancing in the Internet of Things (IoT) enhances the efficiency of the system by dynamically allocating tasks across devices and cloud resources. However, task scheduling struggles with unpredictable tasks, scalability, security risks, and unauthorized access control. To overcome these limitations, a novel security-based hybrid autonomous deep learning network for load balancing in cloud (SHIELD) framework has been proposed for secure task scheduling in cloud resources. Initially, the data received from the IoT devices is passed under certain security constraints to ensure the authenticity of the data. These privacy-preserved data are fed to the task scheduling module, which is employed by the dual DL Network to generate a schedule for resource management. Finally, cloud resources employ optimal allocation of tasks based on the generated schedule to ensure secure load balancing. The proposed framework is simulated by using Cloud Simulator 7G (CloudSim7G). The SHIELD framework is assessed by such metrics, including accuracy, recall, precision, F1-score, and specificity. In comparison, the proposed SHIELD framework achieves a privacy overhead of 14% outperforms the existing QODA-LB, Best-KFF, SPSO-TCS, and VMMISD techniques by achieving 10%, 11%, 12%, and 13% respectively.
Volume: 14
Issue: 3
Page: 439-449
Publish at: 2025-12-01

Detection of heavy metals concentration in vegetables and analyze the health risks

10.11591/ijphs.v14i4.26823
Solomon Legesse Gurmu , Fekede Weldekidan Mengistu , Atsedu Yeshwalul Beyene , Bizunesh Ketema , Birhanu Million Tadesse
Heavy metals are elements found in Earth’s crust but introduced into soil and water bodies by human activities. They are not biodegradable, so they persist for a long time in the environment. Heavy metals are incorporated into to human body through the food chain, resulting in various health problems. Akaki Rivers, which are major water sources in Addis Ababa, are contaminated with various wastes, including heavy metals. This research aimed to detect heavy metal concentration in cabbage, potato, tomato, and beetroot irrigated with the Akaki Rivers and evaluate associated health risks. Following the vegetable sample collection, a laboratory-based study was used in sample processing, digestion, and heavy metal detection. Mean concentration (mg/kg dry weight) of Cd (26.11-26.34), Pb (17-33.84) in all samples, and Hg (0.124) in beetroot exceeded the permissible limits set by WHO/FAO. The HRI of Cd (28.3-140.96), Pd (10.9-27.35), both in adults and children, and Hg (1.727 for children) exceeded the safe limit (<1). The health of adults and children is at risk due to Cd, Pb, and Hg, with children facing approximately 2.5 times higher. Minimization of the release of wastewater into the Akaki Rivers, and dietary diversification should be encouraged, and the health of permanent consumers should be checked.
Volume: 14
Issue: 4
Page: 1849-1856
Publish at: 2025-12-01

A survey on convolutional neural network hardware acceleration through approximate computing multiple and accumulates unit

10.11591/ijra.v14i3.pp366-375
Suvitha Pathiyadan Sudhakaran , Aathmanesan Thangakalai
Convolutional neural networks (CNNs) are applied to a different range of real-world complex tasks to provide effective solutions with high accuracy. Based on the application's complexity, CNN demands a lot of processing units and memory spaces for its effective implementation. Bringing this computational task to hardware for processing the data to enhance the acceleration helps in achieving real-time performance improvement. Recent studies focused on approximation methodology to overcome this problem. This proposed survey analyzes various recent methods involved in implementing approximating computing-based processing elements and their usage in CNNs. Primarily, the survey focuses on multiple and accumulates (MAC) unit and their various approximation methods, which acts as a fundamental block as a processing element in the CNN layers. Secondly, it focuses on various CNN hardware acceleration architectures and their layers designed using different methods and their wide range of applications. Some of the recent design methods applied to various ranges of applications are also analyzed in the proposed survey. This detailed analysis gives an outlook on effective approximation blocks and the CNN architecture to be effectively used in various designs, with a scope of area in which future improvement can be made.
Volume: 14
Issue: 3
Page: 366-375
Publish at: 2025-12-01

Influence of potassium bromide phosphor on optical properties of white light-emitting diodes

10.11591/ijaas.v14.i4.pp1359-1366
Pham Hong Cong , Nguyen Thi Phuong Loan , Nguyen Doan Quoc Anh , Hsiao-Yi Lee
Conventional phosphor-converted light-emitting diodes (LEDs) using silicone binders often suffer from yellowing, moisture degradation, and limited spectral tunability, restricting their performance in high-power street lighting. To overcome these limitations, this study aims to develop an advanced LED illumination system integrating a KBr-doped sol-gel/silica phosphor with total internal reflection (TIR) lenses and a reflective housing, encapsulated by an atomic layer deposition (ALD)-coated minilens panel. The sol-gel matrix, synthesized from MTEOS, TEOS, and silica granules, was engineered to achieve uniform KBr particle dispersion, reduced thermal quenching, and improved chromatic stability. The ALD laminate provides an additional moisture and heat barrier, sealing micro-defects and minimizing stress-induced cracking. Optical performance was quantitatively assessed using Monte Carlo beam-tracking simulations under various street configurations, including focal, zigzag, and single-plane pole layouts. Results demonstrated enhanced luminous efficacy, precise glare control, and high uniformity in street illumination. Overall, this integrated sol-gel/ALD LED design effectively addresses the durability and color instability problems of traditional silicone systems, offering a scalable and energy efficient solution for next-generation street lighting.
Volume: 14
Issue: 4
Page: 1359-1366
Publish at: 2025-12-01

AI-integrated pharmacy systems: bridging technology, ethics, and patient care

10.11591/ijaas.v14.i4.pp1305-1321
Adi El-Dalahmeh , Nevien Nedal , Khulood Abu Maria , Sara Abu Tarboosh
The operation of pharmacy systems undergoes transformation through artificial intelligence (AI), which advances from manual procedures to intelligent adaptive tools. These technologies enhance daily operations through prescription verification, drug interaction alerts, and inventory management while decreasing human mistakes. Through AI, patients gain access to customized medication recommendations, automatic appointment alerts, and virtual support services. The advancement of technology creates multiple new difficulties for healthcare systems. The increasing integration of AI in healthcare creates growing concerns about data privacy alongside algorithmic bias and the requirement for decision-making explanations. This paper evaluates AI systems against conventional pharmacy methods through an assessment of their precision and speed and their impact on patient safety and ethical preparedness. The adoption of AI systems requires strong ethical protections together with defined regulatory frameworks to maintain human clinical decision-making authority in patient care.
Volume: 14
Issue: 4
Page: 1305-1321
Publish at: 2025-12-01
1 2 3
...
2025 2026
Show 97 of 2026

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