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

Optimized ensemble framework for predicting hydroponic stock and sales using machine learning

10.11591/ijai.v14.i5.pp3879-3886
Viktor Handrianus Pranatawijaya , Ressa Priskila , Putu Bagus Adidyana Anugrah Putra , Nova Noor Kamala Sari , Efrans Christian , Septian Geges , Novera Kristianti
The increasing global demand for food necessitates the adoption of sustainable agricultural practices. Hydroponic farming, while efficient in resource utilization, faces challenges in accurately predicting stock levels and sales due to dynamic, ever-changing factors. This research presents an optimized ensemble framework for forecasting hydroponic stock levels and sales by integrating linear regression (LR), random forest (RF), and XGBoost, further enhanced through an evolutionary algorithm (EA). The proposed framework is evaluated using root mean square error (RMSE) and mean absolute error (MAE), demonstrating significant accuracy improvements over individual models. The ensemble model achieves an RMSE reduction of 43.82% for stock prediction and 55.3% for sales forecasting compared to the best-performing individual model. Additionally, local interpretable model-agnostic explanations (LIME) are employed to offer stakeholders clear insights into decision-making processes, such as identifying "number of harvested crops" and "sales data" as key drivers of prediction outcomes. This framework supports sustainable development goals (SDGs) 9.3, 12.3, and 12.C by promoting resource efficiency, reducing food waste, and improving small-scale farmer market access. Future research will explore real-time data integration for dynamic adaptation and further model enhancements.
Volume: 14
Issue: 5
Page: 3879-3886
Publish at: 2025-10-01

Path planning of an elongated undulating fin using mutant particle swarm optimization

10.11591/ijeecs.v40.i1.pp10-17
Thi Thom Hoang , Thi Huong Le
This paper proposes a mutant particle swarm optimization algorithm (M-PSO) to optimize the power energy of a bio-mimetic robotic fish that comprises sixteen undulating fin-rays equipped to a fish robot. The main objective is to obtain the shortest path for the fish robot to achieve the desired position while minimizing power consumption. The proposed MPSO is a recent generation of particle swarm optimization (PSO) that employs the removal of the worst particles to accelerate the swarm, enabling particles to escape local minima and improve the propulsive efficiency of the fish robot. Simulation results demonstrate that the developed M-PSO consumes less energy and requires less time compared to the original PSO and genetic algorithm (GA). Moreover, the M-PSO was tested on a robotic fish navigating an unknown environment characterized by complex spatiotemporal parameters, showcasing its superiority over other methods in all case studies.
Volume: 40
Issue: 1
Page: 10-17
Publish at: 2025-10-01

Data-driven clustering and prediction of high school graduation rates in Indonesia (2015-2023) using machine learning

10.11591/ijai.v14.i5.pp3771-3780
Muhammad Salman Arrosyid , Marzuki Marzuki , Widihastuti Widihastuti , Haryanto Haryanto , Maria Angelina Fransiska Mbari
This study aims to analyze the graduation rate of senior high school education in 34 Indonesian provinces during the period 2015-2023 and identify patterns of educational disparities between regions. To achieve the objectives, this study applies a neural network to predict education completion patterns based on historical data, then the prediction results are analyzed using K-means clustering technique utilizing the elbow method to select the ideal number of clusters. The clustering results show three categories of provinces based on education completion rates: high, medium, and low. The provinces with high completion rates, generally, supported with good education infrastructure and effective policies, while the medium category faces challenges in resource distribution, but still potentially improve. In contrast, the low category suffers from limited access, geographical constraints, and socio-economic disparities. This research contributes to education policy-making by offering a machine learning-based approach to understanding education disparities between regions. The new insight offered by this study lies in the integration of neural network and K-means clustering in mapping education completion rates to support strategies for improving access and quality of education in Indonesia.
Volume: 14
Issue: 5
Page: 3771-3780
Publish at: 2025-10-01

Oxygen/sulphur self-doped tunnel-like porous carbon from yellow bamboo for advanced supercapacitor applications

10.11591/ijpeds.v16.i3.pp2030-2042
Erman Taer , Novi Yanti , Rahma Lia Putri , Apriwandi Apriwandi , Awaludin Martin , Julnaidi Julnaidi , Nidya Chitraningrum , Ahmad Fudholi , Rika Taslim
The 3D hierarchical pore structure with tunnel-like pores is essential to the performance of porous activated carbon (AC) materials used in symmetric supercapacitors. This study aimed to effect of adding (0.3, 0.5, and 0.7) M KOH reagent and heat treatment on the formation of 3D porous, tunnel-like AC derived from yellow bamboo (YB) through N2-CO2 pyrolysis at 850 °C. The AC produced had a high concentration of nanopores, becoming a valuable storage medium with favorable physical-electrochemical properties. The results showed that 0.5-YBAC had the best physical and electrochemical properties, with a carbon purity, 89.16%, micro crystallinity of 7.374 Å, and excellent amorphous porosity. Furthermore, 3D hierarchical pore structure, enriched naturally occurring heteroatoms, dopant of oxygen (10.14%) and sulfur (0.10%). A maximum surface area of 421.99 m² g⁻¹, along with a dominant combination of micro-mesopores. The electrochemical performance test of the 0.5-YBAC electrode showed a Csp of 214 F g⁻¹, with Esp 24.7 Wh kg⁻¹ and Psp 19.2 W kg⁻¹. In conclusion, this study showed the potential of YB stems to enhance the development of supercapacitors, offering superior porosity characteristics for efficient energy storage applications.
Volume: 16
Issue: 3
Page: 2030-2042
Publish at: 2025-09-01

Islanding detection of integrated DG system using rate of change of frequency over reactive power

10.11591/ijpeds.v16.i3.pp1637-1644
B. V. Seshu Kumari , Ambati Giri Prasad , S. Sai Srilakshmi , Karri Sairamakrishna Buchireddy , Ch. Rami Reddy
This paper offers a passive islanding detection method that is effective for distributed generation. When a distributed generator (DG) keeps a location powered even when access to the external electrical grid is lost, this circumstance is referred to as islanding. The power distribution system currently includes distributed generators (DGs), which provide inexpensive electricity and have fewer environmental impacts. Sometimes, these DGs continue to supply the nearby loads because of line outages and islands made by system separations. As a result, there are scenarios with unacceptable power quality. The islanding is identified if the result of the rate of change of frequency over reactive power exceeds the threshold value. The MATLAB test results from this study demonstrate the effectiveness of the suggested approach for different islanding and non-islanding scenarios.
Volume: 16
Issue: 3
Page: 1637-1644
Publish at: 2025-09-01

Solar cell-based garden light automation for environmentally friendly technology learning

10.11591/ijpeds.v16.i3.pp1457-1471
Afrizal Mayub , Fahmizal Fahmizal , Lazfihma Lazfihma
This research aims to: 1) Produce a prototype design for a solar cell-based automatic garden lighting system; 2) Determine the relationship between current, power, and voltage and light intensity; 3) Describe the feasibility of an environmentally friendly technology practicum guidebook; and 4) Describe teacher and student responses to the environmentally friendly technology practice guidebook. This research is R&D type Analysis, Design, Development, Implementation and Evaluation (ADDIE) Analysis, design, development, implementation and evaluation. The research sample used 44 class IX students at MTS Rahmatullah. According to students, aspects of teaching materials, aspects of content, and difficulty of teaching materials at school are inadequate at 84.25%, 80% and 82.5%. Student interest in environmentally friendly technology practicum guidebooks was 84.25%. The higher the light intensity, the higher the current, power, and voltage. Expert validation shows; the prototype of an automatic garden lighting system based on solar cells and a practical guidebook on environmentally friendly technology are very suitable for use (89.14% and 90.75%). The use of environmentally friendly technology practicum guidebooks increased students' critical thinking skills in the high category (N-Gain = 0.7937) and received responses from teachers and students in the "almost all" category (91.50% and 89.9%).
Volume: 16
Issue: 3
Page: 1457-1471
Publish at: 2025-09-01

Bibliometric visualization of metal-air battery research trends

10.11591/ijpeds.v16.i3.pp1865-1880
Satria Pinandita , Rustam Asnawi , Mochamad Syamsiro
Metal-air batteries are rechargeable secondary batteries with high energy density, typically using carbon electrodes. However, carbon waste poses environmental risks. Fly ash, a byproduct of coal combustion, offers a sustainable alternative due to its high electrical conductivity. This study analyzes research trends on metal-air batteries and fly ash from 2019 to 2023 using bibliometric visualization of Scopus-indexed publications. The keyword search was refined from 'Battery' to 'Air Battery' and, finally, 'Air Battery' with 'Fly Ash,' yielding 60 relevant articles. Using the VOSviewer, research patterns, key focus areas, and collaboration networks were identified. The results indicate a 14.87% increase in publications from 2019 to 2023, with significant growth from 2019 to 2021 before declining after 2022. This fluctuation suggests shift in research interests toward other battery technologies. Fly ash demonstrates potential as a carbon substitute for air batteries, promoting sustainability. However, further research is needed to optimize its application and address technical challenges. Bibliometric visualization highlights a growing interest in fly ash for environmentally friendly battery development due to its abundance and sustainability.
Volume: 16
Issue: 3
Page: 1865-1880
Publish at: 2025-09-01

Structural behavior of reinforced soil walls under seismic loads

10.11591/ijaas.v14.i3.pp711-723
Reynaldo Melquiades Reyes Roque , Lincoln Jimmy Fernández Menacho , Brayanm Reynaldo Reyes Huerta , Fabrizio del Carpio Delgado
One of the main engineering challenges has been to design an economical soil retaining structure with high seismic resistance. From this perspective, reinforced soil walls have been developed with a focus on flexibility, in order to efficiently resist the effects of similar historical events in the event of a significant earthquake. The overall objective of this study was to compare the structural behavior of a geogrid-reinforced soil wall (Terramesh® system) under static and pseudo-static loads, and in a seismic environment simulated using the finite element method, in a shopping center in Trujillo, Peru. A case study was conducted using a mixed methodology, both applied and analytical-comparative in scope. Furthermore, the finite element methodology, material constitutive modeling, and dynamic time-history analysis of modal structures were chosen. It was determined that seismic loading can produce a 53.33% increase in deformations compared to the static state; Likewise, the overall safety factor under dynamic conditions tends to decrease by 27.85% compared to the static case. This study demonstrated the scope of geogrid reinforcement (Terramesh® system) through a practical case of a reinforced soil wall, using Plaxis 2D software to compare, estimate, and compare structural behavior in static, dynamic, and simulated environments.
Volume: 14
Issue: 3
Page: 711-723
Publish at: 2025-09-01

Deep learning for image classification of submersible pump impeller

10.11591/ijaas.v14.i3.pp838-848
Phan Nguyen Ky Phuc , Doan Huu Chanh , Trong Hieu Luu
This study presented a deep learning-based model in the submersible pump impellers quality inspection process. The proposed method aimed to relieve worker workload, automate the system, as well as increase the accuracy in defect detection and classification. The proposed approach aims to be implemented on systems with low investment cost and limited resources, i.e., small single-board computers, enabling flexible deployment in industrial environments. The model consisted of three convolutional neural network (CNN) models, i.e., visual geometry group 16 (VGG16), ResNet50, and a custom model. The outputs of three networks were either synthesized later through an ensemble stage or used separately. A graphical user interface (GUI) was also developed for real-time inspection and user-friendly interaction. The approach achieved up to 99.8% accuracy in identifying defects, including surface scratches, corrosion, and geometric irregularities. The proposed method improved the quality assurance process by reducing manual inspection efforts. Future research could explore advanced techniques like anomaly detection to further enhance system performance and versatility.
Volume: 14
Issue: 3
Page: 838-848
Publish at: 2025-09-01

When studying applied physics: what problems are there, and do pre-service physics teachers need?

10.11591/ijaas.v14.i3.pp650-661
Renol Afrizon , Lilia Ellany Mohtar , Mohd Syahriman Mohd Azmi , Hidayati Hidayati
Applied physics courses are essential for pre-service physics teachers (PsPTs), but they often encounter challenges in pursuing this educational pathway. This study aims to identify the problems and learning elements that PsPTs need in applied physics learning using the McKillip discrepancy model. The data were collected using questionnaires and bibliometric techniques. A total of 23 PsPTs participated in the study. Additionally, 1,000 articles were consulted as a data source. The data analysis uses descriptive statistics and the VOSviewer software. The first finding is primary issues identified in applied physics learning e.g., the difficulty of locating suitable learning resources, the dearth of in-depth physics comprehension, the absence of visualization like augmented reality (AR), the failure to undertake empirical activities in the laboratory, and global warming and climate change topic were pertinent at the high school level, entailed intricate issues, and were abstract. The second finding is a learning module that is integrated with science, technology, engineering, and mathematics (STEM), and AR is needed by PsPTs. Finally, this need has been paramount over the past decade to meet PsPTs' needs. Thus, the needs analysis results serve as an initial reference point for decision-makers to identify elements and develop integrated STEM and AR applied physics learning modules.
Volume: 14
Issue: 3
Page: 650-661
Publish at: 2025-09-01

Wireless charging Class-E inverter for zero-voltage switching over coupling coefficient range

10.11591/ijpeds.v16.i3.pp1752-1764
Anon Namin , Chuchat Donloei , Ekkachai Chaidee
A novel and practical methodology is presented in this study for designing contactless wireless energy systems using resonant-mode Class-E converters, aiming to sustain efficient soft-transition switching under various levels of magnetic coupling, even under coil misalignment. The approach integrates the wireless power transfer (WPT) circuit with the inverter’s series resonant network and analytically derives the relationship between the coupling coefficient and impedance phase angle to identify zero voltage switching (ZVS) conditions. A key contribution is the use of the maximum expected coupling coefficient as a critical design point to ensure ZVS across practical variations. A complete step-by-step design procedure is provided. Simulation and experimental results confirm that the inverter achieves and maintains ZVS for coupling values in the range 0 < k ≤ kdesigned, with efficiencies reaching up to 95%. This work supports the advancement of soft-switching inverter design to enable robust and efficient WPT systems under practical misalignment conditions.
Volume: 16
Issue: 3
Page: 1752-1764
Publish at: 2025-09-01

A hybrid features based malevolent domain detection in cyberspace using machine learning

10.11591/ijaas.v14.i3.pp916-927
Saleem Raja Abdul Samad , Pradeepa Ganesan , Amna Salim Rashid Al-Kaabi , Justin Rajasekaran , Murugan Singaravelan , Peerbasha Shebbeer Basha
The rise of social media has changed modern communication, placing information at our fingertips. While these developments have made our lives easier, they have also increased cybercrime. Cyberspace has become a refuge for modern cybercriminals to conduct destructive actions. Most cyberattacks are carried out through malicious links shared on social media platforms, emails, or messaging services. These attacks can have serious consequences for individuals and organizations, including financial losses, sensitive data breaches, and damage to reputation. Early identification and blocking of such links are crucial to protecting internet users and securing cyberspace. Current research uses machine learning (ML) algorithms to detect malicious hyperlinks based on observed patterns in uniform resource locators (URLs) or web content. However, cyberattack tactics are constantly changing. To address this challenge, this paper introduces a robust method that performs a fine-grained analysis of URLs for classification. Lexical and n-gram features are examined separately, with URL n-grams represented using Word2Vec embeddings. The results from hybrid feature sets are combined using a logistic regression (LR) model to increase overall classification accuracy. This robust method allows the system to use both the structural components of the URL and the fine-grained patterns obtained by the n-grams.
Volume: 14
Issue: 3
Page: 916-927
Publish at: 2025-09-01

Dissolved organic matter released from paper trash in water during ultraviolet irradiation: impacts on trihalomethane formation

10.11591/ijaas.v14.i3.pp869-877
Teguh Budi Prijanto , Nia Yuniarti Hasan , Kahar Kahar , Muammar Qadafi , Wisnu Prayogo
When exposed to ultraviolet (UV) light, paper trash could release dissolved organic matter (DOM) as a disinfection byproduct (DBP) precursor in water. This study was undertaken to assess the regulated DBPs, trihalomethanes-4 (THM4) generation potential, and estimated cytotoxicity of paper trash soaked in water during UV radiation. The UV irradiation was carried out at 1, 6, 12, 24, and 48 hours. The released organic material was determined using ultraviolet-visible (UV-Vis) adsorption at wavelengths ranging from 200 to 700 nm. Chlorination was carried out for 24 hours to determine THM4 formation potentials. According to the research findings, the longer the radiation period, the more THM4 species are formed in plain paper samples. On the other hand, the production of trichloromethane (TCM) on paper samples containing writing decreased as the UV radiation period increased. THM4 levels reached 103.12 and 150.57 µg/L for plain and writing paper samples, respectively. UV absorbance at 272 nm (A272) shows a 92% association with THM4 production, making it suitable as an initial characterization approach. Paper trash pollution in water could form carcinogenic DBPs, THM4, if used as a water source in a water treatment plant using chlorine disinfection.
Volume: 14
Issue: 3
Page: 869-877
Publish at: 2025-09-01

Eco-friendly durable asphalt using maleic-modified rosin ester

10.11591/ijaas.v14.i3.pp793-803
Emma Savitri , Edy Purwanto , Restu Kartiko Wisi , Aloisiyus Yuli Widianto , Reyhan Sava Pratama , Yosafat Gary Tegar Harijono
Asphalt, a crucial component of transportation infrastructure, particularly in regions with high traffic loads and extreme climates, often lacks the necessary elasticity, strength, and durability. Various asphalt modifiers have been explored, but many struggle with cost, thermal stability, and environmental impact. This study, however, investigates maleic-modified rosin ester, a gum rosin derivative, as a sustainable and cost-effective asphalt modifier. The base asphalt was heated to 150-190 °C, sheared at 100 rpm, and combined with 4-20% maleic rosin ester and sulfur. The modified asphalt was subjected to tests, including penetration, softening point, ductility, density, kinematic viscosity, Fourier transform infrared (FTIR), and dynamic shear rheometer (DSR) tests. The results are promising, showing that maleic rosin ester enhances penetration resistance and softening points while maintaining ductility and viscosity within acceptable limits. Chemical analysis confirmed improved adhesion, crosslinking, and thermal stability, making the modified asphalt more deformation-resistant. This suggests that maleic-modified rosin ester is a viable alternative to synthetic polymers, offering improved durability and sustainability. The enhanced durability of the modified asphalt provides confidence in its long-term performance, making it a reliable choice for transportation infrastructure.
Volume: 14
Issue: 3
Page: 793-803
Publish at: 2025-09-01

Haystack-based Facebook’s data storage architecture: store, directory, and cache

10.11591/ijaas.v14.i3.pp671-681
Tole Sutikno , Ahmad Heryanto , Laksana Talenta Ahmad
Haystack is Facebook's unique way of managing large amounts of user-generated content like photos. The architecture prioritizes performance, reliability, and scalability to overcome network-attached storage system bottlenecks. Haystack speeds data access and ensures data integrity during hardware failures by using physical and logical volumes. This study examines the architecture of Facebook's Haystack data storage system and its effects on scalability and efficiency in handling large photo data. According to the study, the store, directory, and cache functions work together to reduce input/output (I/O) operations and improve metadata processing, which traditional network-attached storage systems cannot do. Haystack manages massive photo data storage and retrieval, solving network-attached storage (NAS) limitations. It balances throughput and latency by minimizing disk operations and optimizing metadata processing. Each store, directory, and cache contribute to this ecosystem. The Haystack architecture reduces disk operations and metadata processing bottlenecks with distributed caching. A cache allows instant access to frequently requested images and balances read and write operations across the system. We should study advanced storage system architectures based on Facebook's Haystack architecture. This could involve investigating faster metadata processing algorithms, using artificial intelligence (AI) to improve fault detection and repair systems, and assessing the economic impact of distributed caches.
Volume: 14
Issue: 3
Page: 671-681
Publish at: 2025-09-01
1 2 3
...
2097 2098
Show 224 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