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

31,377 Article Results

Integrating IoT for advancing agriculture: innovations and implications for future surveys

10.11591/ijict.v15i2.pp891-899
Debani Prasad Mishra , Rakesh Kumar Lenka , Aditya Kumar , Aditya Jasrotia , Surender Reddy Salkuti
The internet of things (IoT) is revolutionizing agriculture, offering a paradigm shift in how we cultivate crops and manage livestock. By integrating IoT devices such as sensors, drones, and smart machinery into farming practices, agricultural operations gain unprecedented levels of data driven insights and control. This abstract emphasizes the pivotal role of IoT in agriculture and its far-reaching implications for the future. IoT empowers farmers with real-time information on essential factors like moisture of soil, nutrient levels, weather patterns, and health of crops, helping make accurate decisions while optimizing resources. Through IoT-enabled monitoring and automation, farmers can remotely manage irrigation, pest control, and livestock health, reducing manual labor and minimizing environmental impact. The implications of IoT in agriculture extend beyond individual farms, shaping the future of food production on a global scale. With a burgeoning world population and climate change threatening traditional farming methods, IoT offers solutions for enhancing productivity, sustainability, and resilience in the face of emerging challenges. From precision agriculture to smart supply chains, the revolutionary prospect of IoT in agriculture promises to ensure food security, economic viability, and environmental stewardship for generations to come.
Volume: 15
Issue: 2
Page: 891-899
Publish at: 2026-06-01

Characteristics of biochar from agricultural residues produced by traditional combustion and its potential as a soil amendment

10.11591/ijaas.v15.i2.pp611-621
Ali Rahmat , Sukamto Sukamto , Santi Ari Respat , Fera Arum , Wiwiek Dwi Susanti , Yudia Azmi , Zurrahmi Wirda
Biochar is a carbon-rich material produced through pyrolysis. However, pyrolysis methods that generate high-quality biochar typically require expensive equipment and technical expertise. This study examines the characteristics of biochar produced from rice husk, cassava wood, and corn cobs using a traditional burning method as an alternative to pyrolysis. The research results showed that the carbon content of biochar produced using traditional methods was comparable to, or even higher than, biochar produced using more advanced pyrolysis methods. Corncob biochar had the highest carbon content among all samples. X-ray fluorescence (XRF) analysis revealed that rice husk biochar had the highest silica content, while cassava wood biochar showed higher percentages of calcium (Ca) and magnesium (Mg) than the other biochars. X-ray diffraction (XRD) characterization results indicated a higher degree of graphitic crystallinity in the corncob biochar, while Fourier transform infrared spectroscopy (FTIR) spectra confirmed the presence of hydroxyl groups, aromatic C=C, and cellulose residues in all samples. thermogravimetric–differential thermal analysis (TG-DTA) and differential scanning calorimetry (DSC) analyses provided insights into thermal behavior and carbonization levels, with corncob biochar having the highest carbon content and thermal resistance. The application of biochar to acidic soils has been shown to significantly increase soil pH and organic carbon content. The simple combustion method used in this study is capable of producing biochar with diverse physicochemical properties, thus offering a sustainable approach to soil improvement, increased nutrient retention, and carbon sequestration, while providing added value to agricultural waste and waste valorization strategy.
Volume: 15
Issue: 2
Page: 611-621
Publish at: 2026-06-01

Anomaly detection in containerized virtual environments using a process mining approach

10.11591/ijaas.v15.i2.pp656-663
Richard Angkawinata , I Made Murwantara
The growing adoption of container-based virtual environments in cloud computing introduces new challenges in anomaly detection due to the systems’ dynamic nature. Traditional monitoring approaches often fail to capture inefficiencies or security risks effectively. This study proposes a process mining approach to identify anomalies by analyzing event logs from containerized systems. Event data from the AIOps challenge 2020 was converted into extensible event stream (XES) format and processed using the inductive visual miner in the ProM tool to generate Petri Net models, accurately visualizing container activity flows. A conformance checking analysis was conducted to evaluate the alignment between modeled and actual behavior. Results demonstrated a high fitness score, confirming the model’s precision in reflecting true operational processes and its ability to reveal minor deviations indicative of potential anomalies. These findings highlight process mining as a promising method to enhance security, transparency, and performance monitoring in virtual environments. The research also recommends integrating process mining with real-time monitoring systems for proactive anomaly detection, thereby improving responsiveness and resilience in cloud-based infrastructures.
Volume: 15
Issue: 2
Page: 656-663
Publish at: 2026-06-01

SWOT-TOWS analysis of an electronic health referral system: basis for development strategy

10.11591/ijaas.v15.i2.pp804-819
Emmanuel Carlos Navarro , Cristina Enriquez Dumdumaya
Along with the implementing rules and regulations of Republic Act No. 11223 (Universal Health Care Act) and the national mandate for the digital transformation of basic services, the Philippine health sector faces the imperative to implement an interoperable electronic referral (eReferral) system. This study applies strengths, weaknesses, opportunities, threats (SWOT) and threats, opportunities, weaknesses, strengths (TOWS) to conduct a SWOT–TOWS strategic analysis of internal and external factors affecting the existing healthcare referral system and to generate evidence-based strategies for national eReferral system adoption. The analysis identifies strong policy support and institutional frameworks as key enablers, while fragmented information and communication technology (ICT) infrastructure, absence of Health Level Seven International (HL7)/Fast Healthcare Interoperability Resources (FHIR) interoperability standards, limited bandwidth in rural facilities, and insufficient technical personnel constitute primary barriers. Comparative benchmarking against the UK NHS eReferral service and US EHR-based referral systems highlights critical design gaps in the Philippine context. The proposed strategies, encompassing a centralized system architecture, ICT readiness investments, and compliance with ISO/IEC 27799 health informatics security standards, provide an actionable framework for policymakers, ICT planners, and healthcare administrators. This study contributes to health informatics literature by applying strategic analysis to health IT system design as a novel methodological intersection.
Volume: 15
Issue: 2
Page: 804-819
Publish at: 2026-06-01

Coastline segmentation on Landsat 8 OLI images using majority voting with deep learning models

10.11591/ijict.v15i2.pp588-596
Nur Nafiiyah , Salwa Nabilah , Nur Azizah Affandy , Rifky Aisyatul Faroh , Esa Prakasa
Coastlines are highly dynamic due to both natural processes and anthropogenic factors, including global warming and sea level rise. Accurate coastline segmentation is essential for effective monitoring and management. Although previous studies have applied deep learning for coastline detection, many existing models still suffer from instability across scenes, blurred boundaries, and segmentation artifacts, indicating that model generalization remains a challenge. This study aims to develop a more robust coastline segmentation approach by introducing an automated majority voting strategy that integrates three deep learning models: ResNet50, ResNet18, and MobileNet-V2. Landsat 8 OLI imagery is used for training and testing. The Jaccard index results show that ResNet18, ResNet50, and MobileNet-V2 achieved scores of 0.96, 0.98, and 0.95 respectively, while the proposed majority voting method also achieved 0.98. Despite the producing a similar numerical score to the best individual model (ResNet50), the ensemble method improves segmentation consistency by reducing artifacts such as unwanted peripheral shapes and cracks within land areas. These findings demonstrate that combining multiple segmentation outputs yields more stable and reliable coastline detection than using single models. Future work will apply this approach to broader Indonesian coastal regions to further assess its generalizability across diverse shoreline conditions.
Volume: 15
Issue: 2
Page: 588-596
Publish at: 2026-06-01

SmartCloud QR: a next-gen online attendance system leveraging QR code and cloud technology

10.11591/ijaas.v15.i2.pp594-610
Kriangsak Chanthinok , Palan Jantarajaturapath , Konkanok Donsophon
This study presents SmartCloud quick response (QR), a cloud-based attendance monitoring system designed to enhance efficiency, accuracy, and fraud prevention in educational institutions. Traditional paper-based attendance methods are time-consuming, error-prone, and vulnerable to proxy attendance. To address these limitations, the system was developed using a software-as-a-service architecture that integrates QR code technology with cloud computing, enabling scalable deployment without requiring dedicated institutional hardware infrastructure. The research was conducted in two phases: phase 1 involved user needs analysis to identify operational challenges in attendance management and phase 2 evaluated system effectiveness through large-scale implementation involving 27,070 participants. Statistical analyses, including independent samples t-tests and one-way analysis of variance (ANOVA), were performed to examine satisfaction differences across gender and user roles. The results demonstrated a high overall satisfaction rate (92.84%), with only minimal and practically negligible differences observed across demographic groups. The findings empirically support the technology acceptance model (TAM), indicating that perceived usefulness and ease of use are reinforced by fraud prevention mechanisms and infrastructure-light deployment. This study contributes to the applied educational informatics literature by introducing a scalable software-as-a-service attendance framework that enhances fraud prevention, reduces institutional hardware investment, and operationalizes privacy-by-design principles in large-scale real-world implementation.
Volume: 15
Issue: 2
Page: 594-610
Publish at: 2026-06-01

Advanced machine learning for enhanced abdominal organ segmentation

10.11591/ijict.v15i2.pp759-768
Rohini Pawar , Rohini Jadhav , Rohit Jadhav
This research evaluates the ResUnet model’s performance in using computed tomography (CT) images to segment various abdominal organs. Weak boundaries, computing efficiency, and anatomical diversity are the current obstacles in abdominal multi-organ segmentation. By merging residual networks with U-Net, ResUnet overcomes obstacles by increasing precision and effectiveness, which qualifies it for use in medicine. The model’s effectiveness was assessed on a number of organs, and the segmentation accuracy was measured using the dice similarity coefficient (DSC). The ResUnet model’s ability to precisely segment organs with distinct borders was proved by its exceptional accuracy in segmenting important organs, such as the liver (mean DSC: 0.880) and spleen (mean DSC: 0.830). However, the model struggled to separate the esophagus correctly (mean DSC: 0.000) and struggled with smaller and more complex organs like the pancreas (mean DSC: 0.429) and gallbladder (mean DSC: 0.143). These results highlight the method’s limitations when handling organs with asymmetrical shapes or hazy borders.
Volume: 15
Issue: 2
Page: 759-768
Publish at: 2026-06-01

Mobile device application design for ThingSpeak interface using flutter

10.11591/ijict.v15i2.pp850-860
Moehammad Sauqy Ihza Zuliandra , Tigor Hamonangan Nasution , Ainul Hizriadi
The rapid development of internet of things (IoT) is prompting many people to design applications, particularly for monitoring applications based on mobile apps. This includes research designs to monitor electrical parameters from PV and the development of health monitoring applications. Previous research required a separate application to scan each IoT device. In this research, a mobile app-based IoT monitoring system was built using flutter. With this, people no longer need to design separate mobile apps for various IoT devices. This application utilizes the flutter framework, while the cloud component uses ThingSpeak. These research results show that data from multiple IoT devices can be transferred to the user’s mobile app. This application enables the monitoring of various IoT devices through a single mobile app, thereby enhancing the efficiency of IoT device design and management.
Volume: 15
Issue: 2
Page: 850-860
Publish at: 2026-06-01

Comparison of thermal and non-thermal images for tomato fruit detection

10.11591/ijaas.v15.i2.pp451-461
Sulfayanti Faharuddin Situju , Wawan Firgiawan , Hironori Takimoto
Farmers use manual observation to sort, grade, and estimate tomato production results to meet market demands. However, this method requires a lot of energy and time, making it unsuitable for large-scale tomato cultivation utilizing the detection process. This study aims to develop the automatic tomato detection technology in an industrial environment based on a conveyor belt by using thermal or non-thermal imaging and you only look once version 8 (YOLOv8). The dataset consists of 570 images obtained from each thermal and non-thermal camera and has undergone augmentation techniques to enrich the data variety. The model was trained and validated using 640×640-pixel images for 40 epochs. In this paper, we conduct a comparative analysis of the tomato detection result using YOLOv8 on thermal and non-thermal imaging. The results indicate that the model trained with thermal data significantly outperformed the non-thermal model, achieving 99% precision, 98% recall, 98% F1-score, and 99% mean average precision (mAP)50 during validation. The thermal model received a 99% accuracy rate during validation, while the non-thermal model attained 94% accuracy, exhibiting a slightly poorer performance and committing several mistakes in detection. The use of thermal cameras on moving automation systems has demonstrated its capability and effectiveness, making it more optimal for application in the agricultural industry.
Volume: 15
Issue: 2
Page: 451-461
Publish at: 2026-06-01

PhyFizball: a game-based tool to enhance student’s understanding of force and motion

10.11591/ijaas.v15.i2.pp573-582
Muhammad Alfi Yusra Jalani , Adibah Abu Bakar , Syazwan Saidin
Difficulties in understanding the concepts of force and motion continue to challenge secondary school students due to the abstract nature of physics and the limited use of interactive teaching methods. This study introduces PhyFizball, a pinball-inspired, low-cost game-based learning (GBL) tool designed to make physics learning more engaging and concrete. The tool aims to help students visualize fundamental concepts such as Newton’s laws, friction, and the relationship between force and motion through hands-on and collaborative gameplay. A quasi-experimental pretest–posttest control group design was employed with 30 form two students from a Malaysian secondary school, divided equally into experimental (n =15) and control (n =15) groups. Over four weeks, the experimental group learned using PhyFizball, while the control group received conventional lecture-based instruction. A validated conceptual understanding test was administered before and after the intervention. Results from paired and independent t-tests revealed that the experimental group achieved significantly higher post-test scores than the control group (t(28) =3.282, p =0.003). The findings confirm that PhyFizball effectively enhances students’ conceptual understanding and engagement in learning physics. Its accessible design demonstrates potential as a cost-effective and scalable teaching tool for improving science learning outcomes in secondary education.
Volume: 15
Issue: 2
Page: 573-582
Publish at: 2026-06-01

Early prediction of myocardial infarction using proposed score tree algorithm

10.11591/ijict.v15i2.pp813-822
Nusrat Parveen , Utkarsha Pacharaney , Gayatri Hegde , Mohammad Rafique , Sana Firoj Nalband , Shamim Akhtar , Satish Devane
Early detection and diagnosis of a diseases will have a big impact on the medical field and help to prevent loss of life. This study begins by gathering information on myocardial infraction patients from hospitals and focuses on earlier diagnostics. In fact, the pre-processed, confirmed data from a qualified doctor is used for this research. Early prediction of myocardial infarction (MI) is proposed by many researchers. They have used Kaggle datasets that is not recent, and they work on post MI. We have proposed early myocardial infraction detection works on unsupervised datasets. To identify myocardial infraction, numerous machines learning supervised algorithms, including decision tree (DT), random forest (RF), are employed in the literature. In this study, we use the score tree algorithm (STA), which operates on an unsupervised dataset, to present a unique early MI prediction method.
Volume: 15
Issue: 2
Page: 813-822
Publish at: 2026-06-01

Validation of a child emotional learning activity kit using the fuzzy Delphi technique

10.11591/ijaas.v15.i2.pp854-860
Uzzairah Nabila Ahmad Tazli , Zaharah Osman , Nadia Shahira Amiruddin , Mazlina Che’ Mustafa
Early childhood is a critical period for socio-emotional development, yet parents often lack structured tools to reinforce these skills at home. The study aims to obtain the experts’ unanimous agreement on the contents and components of an emotional learning activity kit for children. This study used the fuzzy Delphi method (FDM) to gather feedback from 13 experts in early childhood education. The survey contained 27 items, which used the seven-point Likert scale. FDM data was analyzed using triangular fuzzy numbers (TFN). The results of the study demonstrated consensus of the construct is at a high level. The overall expert consensus agreement exceeds 75%, the overall value of the threshold (d) is 0.2, and the α-cut exceeds 0.5. The value of the learning contents showed that the expert agreement of this kit is highly acceptable. Findings also showed learning material in this kit has a high agreement value, and it can be used to empower teachers and parents to cultivate their children’s emotional learning, bridging the gap between curriculum and home-based learning. Future research should consider expanding the application of this emotional learning activity to children in preschool.
Volume: 15
Issue: 2
Page: 854-860
Publish at: 2026-06-01

Impact of heavy metal and pesticide contamination in water and soil on hemoglobin synthesis and lymphocyte counts

10.11591/ijaas.v15.i2.pp718-731
Artati Artati , Nuradi Nuradi , Herman Herman , Asyhari Asyikin , Nurisyah Nurisyah , Ratnasari Dewi , Rafidah Rafidah , Aan Yulianingsih , Asriyani Ridwan
Heavy metal and pesticide pollution represent a significant public health concern, particularly due to their detrimental effects on hematological health. This study investigates the levels of heavy metals, specifically lead (Pb), cadmium (Cd), and arsenic, and organophosphate pesticides in water and soil within five sub-districts of Jeneponto City, utilizing a quantitative descriptive analysis methodology with the simple random sampling over a six-month period. Analytical techniques employed include atomic absorption spectrophotometry (AAS) for heavy metals and UV-Vis spectrophotometry for pesticides, complemented by blood analyses for hemoglobin and lymphocyte counts. Results reveal that soil samples exhibited heavy metal concentrations exceeding regulatory thresholds, with copper (Cu) and Cd identified as particularly concerning. While most organophosphate pesticide levels were below established limits, concerns regarding potential residue accumulation persist. Exposure to these pollutants has been linked to disrupted hematopoiesis and immune system impairments, potentially resulting in anemia and heightened vulnerability to infections. This study underscores the critical need for continuous monitoring of heavy metal and pesticide levels in environmental matrices to mitigate adverse health outcomes and protect ecosystems. Regular assessments are vital for public health policy and environmental management strategies.
Volume: 15
Issue: 2
Page: 718-731
Publish at: 2026-06-01

Assessment of deep learning based Hindi Odia bidirectional machine translation system

10.11591/ijaas.v15.i2.pp687-695
Subhashree Satpathy , Smitaprava Mishra , Ajit Kumar Nayak
India is a vast nation with a diverse range of cultures and languages. Most Indians choose to use their native languages when communicating with machines. To integrate smart technologies into every facet of Indian society, efficient systems that can positively identify Indian languages must be established. Machine translation (MT) studies comprise most of the natural language processing (NLP) in the era of multilingual computer-human interaction. Till now, less emphasis has been placed to develop MT systems among Indian languages. Yet again, building a qualitative and quantitative corpus in these languages is challenging. This work focuses on two Indic languages for the development of a Hindi to Odia bidirectional machine translation system (HOBMT). Bilingual evaluation understudy (BLEU), word error rate (WER), character error rate (CER), and metric for evaluation of translation with explicit ordering (METEOR) evaluation metrics are used to assess the accuracy of the translation. The most advanced sequential deep learning (DL) models, such as recurrent neural network (RNN), long short term memory (LSTM), and gated recurrent unit (GRU), are used in this study. In this research, RNN is observed with improved translation results due to its sequential data handling with context preservation.
Volume: 15
Issue: 2
Page: 687-695
Publish at: 2026-06-01

MLP-DT: a deep learning model for early prediction of diabetes and thyroid disorders

10.11591/ijict.v15i2.pp778-788
Aouatef Chaib , Ouahiba Djama , Sabar Messaoudi
In this paper we present an intelligent and automated system for controlling diabetes and thyroid disorders. This system is designed to self-diagnose autoim mune diseases as early as possible in order to treat them quickly and thus slow down or stop their progression and thus provide a tool for self-control of dis eases. Our system is based on deep neural networks (DNNs), it contains several layers and it is classified as multi-layer perceptron (MLP). The proposed model called MLP model for early prediction of diabetes and thyroid disorders (MLP DT)uses a set of biomedical variables, allowing the system to formulate person alized treatment recommendations. To improve diagnostic accuracy and facili tate early screening, the system also incorporates machine learning techniques. The optimization in MLP-DT is provided by the adam optimizer algorithm, it is always applied to adjust the weights of the three hidden layers and the output layer (Sigmoid or Softmax). Experimental results demonstrate that the proposed MLP-DT model achieves reliable predictive performance and supports effective early screening of diabetes and thyroid disorders. These findings highlight the potential of the proposed approach as an intelligent decision-support tool for personalized healthcare and preventive medicine.
Volume: 15
Issue: 2
Page: 778-788
Publish at: 2026-06-01
1 2 3
...
2091 2092
Show 80 of 2092

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