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

Arowana cultivation water quality forecasting with multivariate fuzzy timeseries and internet of things

10.11591/csit.v6i2.p136-146
Alauddin Maulana Hirzan , April Firman Daru , Lenny Margaretta Huizen
Water quality plays a crucial role in the growth and survival of arowana fish, with imbalances in key parameters (pH, temperature, turbidity, dissolved oxygen, and conductivity) leading to increased mortality rates. While previous studies have introduced various monitoring models using Arduino IDE and intrinsic approaches, they lack predictive capabilities, leaving cultivators unable to take proactive measures. To address this gap, this study develops a predictive model integrating the internet of things (IoT) with a fuzzy time series (FTS) algorithm. Through rigorous evaluation and validation, the proposed FTS-multivariate T2 model demonstrated superior performance, achieving an exceptionally low error rate of 0.01704%, outperforming decision tree (0.13410%), FTS-multivariate T1 (0.88397%), and linear regression (20.91791%). These findings confirm that FTS-multivariate T2 not only accurately predicts water quality but also significantly reduces the mean absolute percentage error, providing a robust solution for sustainable arowana aquaculture.
Volume: 6
Issue: 2
Page: 136-146
Publish at: 2025-07-01

Enhanced fault detection in photovoltaic systems using an ensemble machine learning approach

10.11591/ijres.v14.i2.pp507-517
Mohammed Salah Ibrahim , Hussein k. Almulla , Anas D. Sallibi , Ahmed Adil Nafea , Aythem Khairi Kareem , Khattab M. Ali Alheeti
Malfunctioning of photovoltaic (PV) systems is a main issue affecting solar panels and other related components. Detecting such issues early leads to efficient energy production with low maintenance costs and high system performance consistency. This paper proposed an ensemble model (EM) for fault detection (FD) in PV systems. The proposed model utilized advanced machine learning algorithms containing random forest (RF), k-nearest neighbors (KNN), and gradient boosting (GB). Traditional approaches often do not handle the several situations that PV systems can have. Our EM leveraged the power of GB’s algorithm in handling complex data patterns through iterative boosting, KNN’s capability in capturing local data structures, and RF’s strength in handling overfitting and noise through its tree structure randomness. Combining these models enhanced fault detection capabilities, providing excellent accuracy compared to individual models. To evaluate the performance of our EM, different experiments were conducted. The results demonstrated substantial improvements in detection fault, achieving an accuracy rate of 95%. This accuracy rate considered high underscores the model’s capability to handle fault detection of PV systems, posing a consistent solution for instant fault detection and maintenance scheduling.
Volume: 14
Issue: 2
Page: 507-517
Publish at: 2025-07-01

Enhancing intrusion detection systems with hybrid HHO-WOA optimization and gradient boosting machine classifier

10.11591/ijres.v14.i2.pp518-526
Mosleh M. Abualhaj , Ahmad Adel Abu-Shareha , Roqia Rateb
In this paper, we propose a hybrid intrusion detection system (IDS) that leverages Harris Hawks optimization (HHO) and whale optimization algorithm (WOA) for feature selection to enhance the detection of cyberattacks. The hybrid approach reduces the dimensionality of the NSL KDD dataset, allowing the IDS to operate more efficiently. The reduced feature set is then classified using logistic regression (LR) and gradient boosting machine (GBM) classifiers. Performance evaluation demonstrates that the GBM-HHO/WOA combination outperforms the LR-HHO/WOA approach, achieving an accuracy of 97.68%. These results indicate that integrating HHO and WOA significantly improves the IDS's ability to identify intrusions while maintaining high computational efficiency. This research highlights the potential of advanced optimization techniques to strengthen network security against evolving threats.
Volume: 14
Issue: 2
Page: 518-526
Publish at: 2025-07-01

An approximate model SpMV on FPGA assisting HLS optimizations for low power and high performance

10.11591/ijres.v14.i2.pp375-387
Alden C. Shaji , Zainab Aizaz , Kavita Khare
High performance computing (HPC) in embedded systems is particularly relevant with the rise of artificial intelligence (AI) and machine learning at the edge. Deep learning models require substantial computational power, and running these models on embedded systems with limited resources poses significant challenges. The energy-efficient nature of field-programmable gate arrays (FPGAs), coupled with their adaptability, positions them as compelling choices for optimizing the performance of sparse matrix-vector multiplication (SpMV), which plays a significant role in various computational tasks within these fields. This article initially did analysis to find a power and delay efficient SpMV model kernel using high level synthesis (HLS) optimizations which incorporates loop pipelining, varied memory access patterns, and data partitioning strategies, all of this exert influence on the underlying hardware architecture. After identifying the minimum resource utilization model, we propose an approximate model algorithm on SpMV kernel to reduce the execution time in Xilinx Zynq-7000 FPGA. The experimental results shows that the FPGA power consumption was reduced by 50% when compared to a previously implemented streaming dataflow engine (SDE) flow, and the proposed approximate model improved performance by 2× times compared to that of original compressed sparse row (CSR) sparse matrix.
Volume: 14
Issue: 2
Page: 375-387
Publish at: 2025-07-01

Design and structural modelling of patient-specific 3D-printed knee femur and tibia implants

10.11591/ijres.v14.i2.pp575-586
Bolugoddu Sandeep , Saravanan Dhanushkodi , Sudhakar Kumarasamy
Arthritis is a degenerative joint condition that progressively damages the knee, leading to pain, stiffness, and limited mobility. To alleviate these symptoms and restore joint functionality, total knee arthroplasty (TKA) is performed. This procedure becomes necessary due to either sudden trauma to the knee or gradual wear and tear of the meniscus and cartilage. TKA involves meticulous planning, precise bone cutting, and the placement of prosthetic components made from high-density polyethylene and metal alloys. However, traditional methods creating customized knee implants are expensive and time-intensive. This study explores the challenges in manufacturing personalized knee implants for TKA and evaluates the potential of three-dimensional (3D) printing technology in this process. Variations in knee joint anatomy across populations complicate surgery, as optimal outcomes rely on precise alignment and implant dimensions. A preoperative computed tomography (CT) scan identifies the region of interest (ROI), such as the knee joint. The scan data is then processed using computer-aided design (CAD) software to generate a printable file. The patient’s CT scan data is converted into a standard triangulation language (STL) file and CAD models of the knee joint. Errors such as overlapping triangles or open loops in the STL file are corrected, and unwanted geometries near the ROI are removed. Resection techniques are applied to create CAD models tailored to the patient’s bone morphology. Fused deposition modeling (FDM) is then used to produce prototypes of the knee joint and implants. Despite visible layer lines in the printed prototypes, challenges encountered during the process were effectively resolved.
Volume: 14
Issue: 2
Page: 575-586
Publish at: 2025-07-01

Different methods of antenna reconfiguration by switches: a review

10.11591/ijres.v14.i2.pp301-310
Reji Valsalam , Perumal Ramani , Pandian Sharmila
The rapid advancement of wireless communication technology has focused researcher's attention on reconfigurable antennas with multiple input and output (MIMO) and cognitive radio operation in high-data-rate modern wireless applications. Reconfigurable antennas perform various functions in terms of operating frequency, radiation pattern, and polarization. Electronic, mechanical, physical, and optical switches are used in reconfigurable antennas as control elements to adjust the switching mechanism and accomplish dynamic tuning. Electronic switches are the most widely used component in reconfigurable antennas because of their effectiveness, dependability, and simplicity in integrating with microwave circuitry. In this paper, a review of various kinds of efficient implementation methods for electrically controlled frequency reconfigurable antennas are proposed. More electrical switches are being used for reconfiguration such as micro electromechanical systems (MEMS), P-type, intrinsic, N-type (PIN), and varactor diodes. Even though PIN diodes are more frequently employed for reconfiguration due to their stability and constant variation in internal inductor and capacitor values. This study provides a deep analysis of the PIN diode usage in reconfigurable antennas and how to reduce the diodes in different microstrip reconfigurable antenna structures.
Volume: 14
Issue: 2
Page: 301-310
Publish at: 2025-07-01

A custom reduced instruction set computer-V based architecture for real-time electrocardiogram feature extraction

10.11591/ijres.v14.i2.pp412-427
Vinayak Vikram Shinde , Sheetal Umesh Bhandari , Deepti Snehal Khurge , Satyashil Dasharath Nagarale , Ujwal Ramesh Shirode
The growing demand for energy-efficient and real-time biomedical signal processing in wearable devices has necessitated the development of application-specific and reconfigurable embedded hardware architectures. This paper presents the register transfer level (RTL) design and simulation of a custom reduced instruction set computer-V (RISC-V) based hardware architecture tailored for real-time electrocardiogram (ECG) feature extraction, focusing on R-peak detection and heart rate (HR) calculation. The proposed system combines ECG-specific functional blocks including a specialized ECG arithmetic logic unit and a finite state machine-based ECG control unit with a compact 16-bit RISC-V control core. Hardware optimized algorithms are used to carry out pre-processing activities such high-pass and low-pass filtering as well as feature extraction processes including moving average filtering, derivative calculation, and threshold based peak identification. Designed to reduce memory footprint and control complexity, a custom instruction set architecture supports modular reconfigurability. Functional validation is carried out by Xilinx Vivado simulating RTL components described in very high speed integrated circuit (VHSIC) hardware description language (VHDL). The present work shows successful simulation of important architectural components, complete system-level integration and custom ECG data validation. This work provides the basis for an application-specific, reconfigurable, power efficient hardware solution for embedded health-monitoring devices.
Volume: 14
Issue: 2
Page: 412-427
Publish at: 2025-07-01

Optimizing social media analytics with the data quality enhancement and analytics framework for superior data quality

10.11591/ijres.v14.i2.pp472-480
B. Karthick , T. Meyyappan
his paper introduces the data quality enhancement and analytics (DQEA) framework to enhance data quality in social media analytics through machine learning (ML) algorithms. The efficacy of the framework is validated through features tested against human coders on Amazon Mechanical Turk, achieving an inter-coder reliability score of 0.85, indicating high agreement. Furthermore, two case studies with a large social media dataset from Tumblr were conducted to demonstrate the effectiveness of the proposed content features. In the first case study, the DQEA framework reduced data noise by 30% and bias by 25%, while increasing completeness by 20%. In the second case study, the framework improved data consistency by 35% and overall data quality score by 28%. Comparative analysis with state-of-the-art models, including random forest and support vector machines (SVM), showed significant improvements in data reliability and decision-making accuracy. Specifically, the DQEA framework outperformed the random forest model by 15% in accuracy and 20% in true positive rate, and the SVM model by 10% in error rate reduction and 18% in reliability. The results underscore the potential of advanced data analytics tools in transforming social media data into a valuable asset for organizations, highlighting the practical implications and future research directions in this domain.
Volume: 14
Issue: 2
Page: 472-480
Publish at: 2025-07-01

Enhancing TV program success prediction using machine learning by integrating people meter audience metrics with digital engagement metrics

10.11591/ijeecs.v39.i1.pp353-363
Khalid El Fayq , Said Tkatek , Lahcen Idouglid
With the emergence of numerous media services on the internet, television (TV) remains a highly demanded medium in terms of reliability and innovation, despite intense competition that compels us to devise strategies for maintaining audience engagement. A key indicator of a TV channel’s success is its reach, representing the percentage of the target audience that views the broadcasts. To aid TV channel managers, the industry is exploring new methods to predict TV reach with greater accuracy. This paper investigates the potential of advanced machine learning models in predicting TV program success by integrating people meter audience metrics with digital engagement metrics. Our approach combines convolutional neural networks (CNNs) for processing digital engagement data, long short-term memory (LSTM) networks for capturing temporal dependencies, and gaussian processes (GPs) for modeling uncertainties. Our results demonstrate that the best-performing hybrid model achieves a prediction accuracy of 95%. This study contributes to the field by addressing manual scheduling errors, financial losses, and decreased viewership, providing a more comprehensive understanding of audience behavior and enhancing predictive accuracy through the integration of diverse data sources and advanced machine learning techniques.
Volume: 39
Issue: 1
Page: 353-363
Publish at: 2025-07-01

A novel approach to transparent and accurate fuel dispensing for consumer protection

10.11591/ijres.v14.i2.pp353-364
Gayatri Phade , Sharada Narsingrao Ohatkar , Murugan Pushpavalli , Vidya Chitre , Vijaya Pawar , Omkar Suresh Vaidya , Harikrishnan Ramachandran
Consumer rights are exploited around the world and it is necessary for to protect consumer rights by means of safeguarding consumers from various unfair trade practices. Those most vulnerable to such exploitation must be shielded, and this is achieved through consumer protection measures. One such example of unethical behavior is fuel stealing at fuel stations. To overcome this critical issue, a low-cost fuel quantity sensing and monitoring system is proposed in this paper. A fuel detection system will ensure the exact quantity of fuel filled in fuel tank and will detect fuel theft, if any, at fuel pumps. An embedded system is developed for this purpose, consisting of sensors, display devices, communication devices and microcontroller. The quantity of fuel filled in the tank is transmitted to mobile phone of the consumer to avoid fuel theft. Performance of the system is validated by comparing the displayed amount of fuel dispensed and actual filled in the tank and achieve 99.95% accuracy. With this consumer right to get the value for amount paid for the petrol will be protected. This novel feature can be added in the fuel tank of the smart vehicle development and design as a future scope.
Volume: 14
Issue: 2
Page: 353-364
Publish at: 2025-07-01

An optimized simulated annealing memetic algorithm for power and wirelength minimization in VLSI circuit partitioning

10.11591/ijres.v14.i2.pp365-374
P. Rajeswari , Smitha Sasi
The development of physical architecture standards for very large scale integration (VLSI) single and multichip platforms is still in its early stages. To deal with the growing complexity of modern VLSI systems, it has become common practice to split large circuit architectures into smaller, easier-to-manage sub-circuits. Circuit partitioning improves parallel modeling, testing, and system performance by lowering chip size, number of components and interconnects, wire length (WL), and delays. VLSI partitioning's primary goal is to split a circuit into smaller blocks with as few connections as possible between them. This is frequently accomplished by recursive bi-partitioning until the required complexity level is reached. Thus, partitioning is a fundamental circuit design challenge. An efficient remedy that offers a heuristic method that explores the design space to iteratively enhance outcomes is evolutionary computation. In order to minimize WL, area, and interconnections, we provide an optimized simulated annealing memetic algorithm (OSAMA) that combines local search methods with evolutionary tactics. The efficiency of the method was evaluated using criteria like runtime, cost, delay, area, and WL. OSAMA's ability for effective partitioning is demonstrated by experimental results, which confirm that it dramatically lowers important design parameters in VLSI circuits.
Volume: 14
Issue: 2
Page: 365-374
Publish at: 2025-07-01

Blockchain technology for optimizing security and privacy in distributed systems

10.11591/csit.v6i2.p214-224
Wisnu Uriawan , Adrian Putra Pratama , Shafwan Mursyid
Blockchain technology is increasingly recognized as an effective solution for addressing security and privacy challenges in distributed systems. Blockchain ensures information security by validating data and defending against cyber threats, while guaranteeing data integrity through transaction validation and reliable storage. The research involves a literature study, problem identification, analysis of blockchain security and privacy, model development, testing, and analysis of trial results. Furthermore, blockchain enables user anonymity and fosters transparency by utilizing a distributed network, reducing the risk of fraudulent activities. Its decentralized nature ensures high reliability and accessibility, even in node failures. Blockchain enhances security and privacy by offering features like data immutability, provenance, and reduced reliance on trust. It decentralizes data storage, making tampering or deletion extremely challenging, and ensures the invalidation of subsequent blocks upon any changes. Blockchain finds applications in various domains, including supply chains, finance, healthcare, and government, enabling enhanced security by tracking data origin and ownership. Despite scalability and security challenges, the potential benefits of reduced costs, increased efficiency, and improved transparency position blockchain as a promising technology for the future. In summary, blockchain technology provides secure transaction recording and data storage, thus enhancing security, privacy, and the integrity of sensitive information in distributed systems.
Volume: 6
Issue: 2
Page: 214-224
Publish at: 2025-07-01

EMG-based hand gesture classification using Myo Armband with feedforward neural network

10.11591/ijeecs.v39.i1.pp159-166
Sofea Anastasia Mohd Said , Norashikin M. Thamrin , Megat Syahirul Amin Megat Ali , Mohamad Fahmi Hussin , Roslina Mohamad
This paper presents the development of an electromyography (EMG)-based hand gesture identification system for remote-controlled applications. Even though the Myo Armband is no longer commercially supported, the research discusses its use in EMG data collecting. Open-source libraries were utilized to capture EMG data from this device to solve this problem. Using the developed data acquisition platform, data was collected from 30 participants who performed three (3) gestures - a fist, an open hand, and a pinch. The energy spectral density (ESD) and power ratio (pRatio) were extracted to describe gesture-specific patterns. A feedforward neural network (FFNN) was implemented for classification, initially configured with 10 hidden neurons and later optimized to 40 neurons to improve the performance. The box plot analysis showed channels CH1, CH4, CH5, and CH7 as the most significant for enhancing classification accuracy. The optimized FFNN achieved 80% and 70% for the training and testing accuracies, respectively. However, the results suggest that implementing a systematic protocol during data acquisition to reduce signal overlap between movements could improve classification accuracy. In conclusion, the study successfully developed an open-source EMG data acquisition platform for MYO Armband and demonstrated acceptable hand gesture recognition using an optimized FFNN.
Volume: 39
Issue: 1
Page: 159-166
Publish at: 2025-07-01

Building a photonic neural network based on multi-operand multimode interference ring resonators

10.11591/ijres.v14.i2.pp311-319
Thanh Tien Do , Hai Yen Pham , Trung Thanh
Photonic neural networks (PNNs) offer significant potential for enhancing deep learning networks, providing high-speed processing and low energy consumption. In this paper, we present a novel PNN architecture that employs nonlinear optical neurons using multi-operand 4×4 multimode interference (MMI) multi-operand ring resonators (MORRs) to efficiently perform vector dot-product calculations. This design is integrated into a photonic convolutional neural network (PCNN) with two convolutional layers and one fully connected layer. Simulation experiments, conducted using Lumerical and Ansys tools, demonstrated that the model achieved a high test accuracy of 98.26% on the MNIST dataset, with test losses stabilizing at approximately 0.04%. The proposed model was evaluated, demonstrating high computation speed, improved accuracy, low signal loss, and scalability. These findings highlight the model’s potential for advancing deep learning applications with more efficient hardware implementations.
Volume: 14
Issue: 2
Page: 311-319
Publish at: 2025-07-01

Machine learning methods for energy sector in internet of things

10.11591/ijres.v14.i2.pp538-545
Reyhane Hafezifard , Soodeh Hosseini
This research paper focuses on exploring machine learning studies and conducting a comparative analysis of their advantages, disadvantages, implementation environments, and algorithms. A key aspect of the study involves evaluating the energy efficiency using machine learning algorithms to predict energy consumption. Additionally, a feature selection algorithm is employed to rank the features, with the highest-ranking feature identified as one of the most significant. The experimentation is conducted using the Weka tool, incorporating several machine learning algorithms such as linear regression, k-nearest neighbors, decision stump, radial basis function (RBF) network, and isotonic regression. The RBF algorithm, which relies on RBF, shares similarities with neural network algorithms. Results indicate a minimum error value of 1.546 for cooling load and 1.364 for heating load. The random forest algorithm emerges as the most suitable choice within the context of this study.
Volume: 14
Issue: 2
Page: 538-545
Publish at: 2025-07-01
1 2 3
...
2097 2098
Show 270 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