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

Enhancing resource management in fog-cloud internet of things systems with deep learning-based task allocation

10.11591/ijece.v14i6.pp7244-7253
Vijayalakshmi Venkatesan , Saravanan Murugan
A fog-cloud internet of things (IoT) system integrates fog computing with cloud infrastructure to efficiently manage processing data closer to the source, reducing latency and bandwidth usage. Efficient task scheduling in fog-cloud system is crucial for optimizing resource utilization and minimizing energy consumption. Even though many authors proposed energy efficient algorithms, failed to provide efficient method to decide the task placement between fog nodes and cloud nodes. The proposed hybrid approach is used to distinguish the task placement between fog and cloud nodes. The hybrid approach comprises the parametric task categorization algorithm (PTCA) for task categorization and the multi metric forecasting model (MMFM) based on deep deterministic policy gradient (DDPG) recurrent neural networks for scheduling decisions. PTCA classifies tasks based on priority, quality of service (QoS) demands, and computational needs, facilitating informed decisions on task execution locations. MMFM enhances scheduling by optimizing energy efficiency and task completion time. The experimental evaluation outperforms the existing models, including random forest (RF), support vector machine (SVM), and k-nearest neighbors (KNN). The proposed result shows an accuracy rate of 89%, and energy is consumed 50% lesser than the existing models. The proposed research advances energy-efficient task scheduling, enabling intelligent resource management in fog-cloud IoT environments.
Volume: 14
Issue: 6
Page: 7244-7253
Publish at: 2024-12-01

Global Leadership Initiative on Malnutrition criteria for predicting surgical site infection in elective laparotomy patients

10.11591/ijphs.v13i4.24175
Pauline Octaviani , Yohannessa Wulandari , Febiansyah Ibrahim , Diyah Eka Andayani
Laparotomy surgery patients are at risk for complication including surgical site infections (SSI) which are associated with high morbidity and mortality. Malnutrition has been identified as a risk factor for the occurrence of SSI but preoperative malnutrition identification remains low. The Global Leadership Initiative on Malnutrition (GLIM) has published a new, practical, and easily applicable definition of malnutrition. This study aims to evaluate whether malnutrition according to GLIM criteria is a predictor of SSI in elective laparotomy patients. This prospective cohort study involved 123 subjects aged 18-65 years undergoing elective laparotomy, without diabetes history. Their malnutrition status was assessed using GLIM criteria with bioelectrical impedance analysis (BIA) to evaluate muscle mass. A total 62 subjects were categorized into the malnutrition group and the remaining into nonmalnutrition group and then monitored for the presence of SSI up to 10 days postoperatively. SSI occurred in 13.8% of the subjects. The analysis showed a strong association between malnutrition and SSI in elective post laparotomy (RR 4.6; 95%CI 1.4-15.1; p=0.005). Malnutrition according to GLIM criteria is a significant predictor of SSI in elective post laparotomy patients.
Volume: 13
Issue: 4
Page: 1895-1902
Publish at: 2024-12-01

Assessment of heavy metals concentration of Mapanuepe Lake, Zambales, Philippines

10.11591/ijaas.v13.i4.pp854-863
Ma. Shiela G. Mendoza , Danilo V. Rogayan Jr.
Despite the absence of recent research, Mapanuepe Lake in the Philippines has been a significant environmental concern due to potential heavy metal contamination. Hence, the study assessed the heavy metal concentration of water and surface sediments and identified the other physicochemical properties of Mapanuepe Lake in San Marcelino, Zambales, Philippines. This descriptive research employed physical profiling and physicochemical characterization of water and surface sediments of the lake. Six sampling stations in the lake were selected based on their current land use and nearness to the point source of heavy metal pollution. The study found that the Mapanuepe Lake is a thriving place for algae and zooplankton. The heavy metal concentration of the lake water and sediment sample is within the standard limit. The water conductivity is considered to be within the standards. In terms of pH level, the sampling sites obtained a pH level within the acceptable limit. The concentration of heavy metals in the lake water and sediments is generally within the standard limit. Other physicochemical properties are also in the acceptable range. The community people and local government must collaborate to implement the crafted strategic environmental sustainability plan, which includes biodiversity conservation and ecotourism promotion. Likewise, the study provides updated and comprehensive data on the status of the lake's heavy metal concentration for policy formulation and further research.
Volume: 13
Issue: 4
Page: 854-863
Publish at: 2024-12-01

Evaluation of the operational efficiency of 3 MWp photovoltaic power plant situated in the Sahara Desert of Algeria

10.11591/ijpeds.v15.i4.pp2618-2630
Messaouda Chaib , Abdeldjalil Dahbi , Ali Benatiallah
The primary aim of this study is to examine the behaviour of the photovoltaic plant installed in Kabertene, Algeria, under desert climate conditions. Simulations and modeling have been carried out for the photovoltaic cell, panel, and array under standard test conditions as well as a range of different operating conditions. Furthermore, the photovoltaic (PV) plant has been simulated using measured data, PVsyst, and MATLAB Simulink. The aim was to assess the solar energy potential within the examined geographic area and evaluate the performance of the PV plant. The performance of the obtained results was compared in different cases. The real results closely match those of PVsyst and MATLAB software when using real data and the real performance ratio, because it takes into consideration the cleanliness state of the PV panels. The results indicate that environmental factors, especially solar radiation and temperature, exert a considerable effect on the operational capacity of the PV system. This leads to variations in the electrical energy output and the performance ratio of the system. The total yearly energy injected into the grid was 5028.21625 MWh. The annual average daily PV system performance ratio is 67%. Finally, the research concludes that the area has substantial solar potential, encouraging the development of new PV plants.
Volume: 15
Issue: 4
Page: 2618-2630
Publish at: 2024-12-01

Enhanced U-Net models with encoder and augmentation for phytoplankton segmentation

10.11591/ijaas.v13.i4.pp1013-1022
Ovide Decroly Wisnu Ardhi , Tri Retnaningsih Soeprobowati , Kusworo Adi , Esa Prakasa , Arief Rachman
This study comprehensively analyzes U-Net models for semantic segmentation in phytoplankton image recognition, leveraging encoders such as EfficientNet-B5, MobileNetV2, ResNet50, and ResNeXt50 and employing the Adam optimizer. The research highlights the U-Net MobileNetV2 model with optical distortion, which achieves notable test scores with 93.69% Dice, 88.14% intersection over union (IoU), 99.89% Precision, and 100% Recall, underscoring the efficacy of the applied augmentation strategies, including geometric and distortion transforms, and color and blur techniques. The U-Net ResNet50 model with mix transform consistently demonstrates high accuracy in critical metrics, outperforming others, while EfficientNet-B5 with blur suggests increased model sensitivity with improved recall. These results underscore the crucial role of encoder-augmentation synergy in model performance. Training and testing times across models have remained under 250 seconds, reflecting methodological efficiency. Overall, these results demonstrate the model's excellent performance for the semantic segmentation task.
Volume: 13
Issue: 4
Page: 1013-1022
Publish at: 2024-12-01

A novel eight-switch nine-level modified ANPC inverter topology and its optimal modulation strategy

10.11591/ijpeds.v15.i4.pp2234-2242
Adnane El-Alami , Radouane Majdoul , Abdelhafid Ait Elmahjoub
An eight-switch nine-level modified ANPC inverter (8S-9L-MANPC) is designed and simulated in this paper. With this topology, only one DC voltage source and eight active semiconductor switches are required, significantly reducing system size, weight, and cost. The structure consists of a five-level ANPC inverter cascaded with a two-level leg converter. This arrangement extends the 5L-ANPC structure to a 9L configuration without requiring the use of additional capacitors. To maintain the balancing of the flying capacitor (FC), a modulation strategy using a switching state redundancy-based control method is employed. Recent 9L inverters incorporating flying capacitors and based on a hybrid structure have been compared with the proposed structure. By conducting this comparison, we can highlight the potential improvements offered by the proposed structure over the recent 9L inverters in terms of reduced component count, simplified design, and cost savings. The proposed 8S-9L-MANPC inverter is tested under various operating situations in MATLAB/Simulink simulation.
Volume: 15
Issue: 4
Page: 2234-2242
Publish at: 2024-12-01

Implications of artificial intelligence chatbot models in higher education

10.11591/ijai.v13.i4.pp3808-3813
Hissan Khandakar , Syed Ali Fazal , Kazi Fattah Afnan , Khandakar Kamrul Hasan
Artificial intelligence (AI) is becoming increasingly influential in the academic sector, which is why it is important to explore the ethical dilemmas and concerns surrounding AI chatbots’ design, development, and deployment in educational contexts. Conducted as a thematic literature review, this paper explores existing research on AI in education, AI chatbots, and their integration with higher education to gather evidence and insights that discuss ethical implications and challenges. The study has analyzed several articles on AI chatbots and their integration into academic fields. Significant gaps have been identified, such as the need for more practical implications and the recognition of AI chatbots as a collaborative tool for academic purposes. More AI chatbots should be explicitly trained on data relevant to the learners’ study to examine their usefulness properly. The paper discusses the ethical dilemmas and concerns about the design, development, and deployment of AI chatbots in higher education. It seeks to provide insights and recommendations to ensure the ethical use of AI chatbots in higher education by identifying significant gaps in the existing literature and providing scenarios to expect in the development of AI in education.
Volume: 13
Issue: 4
Page: 3808-3813
Publish at: 2024-12-01

A novel deep anomaly detection approach for intrusion detection in futurisitic network

10.11591/ijai.v13.i4.pp4895-4905
Sai Krishna Lakshminarayana , Prabhugoud I. Basarkod
In an era where networks are increasingly heterogeneous and multi-domain, establishing robust security models to protect data and network infrastructure is becoming ever more complex. Traditional intrusion detection systems (IDS) often struggle with novel or variant attacks that fall outside predefined rule sets, resulting in significant detection challenges. This paper proposes a methodologically refined approach leveraging data-driven insights and statistically robust feature selection to enhance the training dataset. The study presents a long short-term memory-autoencoder (LSTM-AE) based learning model designed for multi-class anomaly detection. The model's novelty lies in its application of distance metrics to define distinct thresholds for varied attack classifications, a strategy that significantly amplifies detection precision. Experimental results validate the superior performance of the proposed system, achieving 94.82% accuracy rate, outperforming similar existing works. The study also proactively addresses common issues of class imbalance and skewed data representation in benchmark datasets by strategically training the model on normal traffic, enhancing its capability to generalize and identify anomalies effectively.
Volume: 13
Issue: 4
Page: 4895-4905
Publish at: 2024-12-01

Evaluating metaverse platforms for educational purposes: a heuristic evaluation study

10.11591/ijaas.v13.i4.pp1023-1031
Cadelina Cassandra , Mohamad Noorman Masrek , Fadhilah Aman
This research's primary objective is to investigate the educational potential by investigating the metaverse website, emphasizing from users' perspectives. It is critical to examine the functionality to identify any potential faults in the learning experience because of the complexities of metaverse apps, which include 3D virtual environments and complex interactions. This study uses heuristic evaluation, which is a useful method for analyzing application success by utilizing well-established design principles and best practices in user interface and user experience design. To conduct this study, a panel of five experts, each with outstanding competence in the topic, was assembled to test the metaverse website in an educational setting. The evaluation was built on the ten heuristic evaluation standards, which served as a solid framework for measuring its usability and functionality. According to the findings of this examination, the average severity number of heuristic issues is one. This result indicates that the website is under "cosmetic problems only." While this implies that specific areas need to be addressed to improve overall quality, it also means that these difficulties do not take precedence over other vital ones. As a result, the website has significant promise as a metaverse instructional platform, and changes can be made to further improve its efficiency.
Volume: 13
Issue: 4
Page: 1023-1031
Publish at: 2024-12-01

Optimizing battery energy storage sizing in microgrids using manta ray foraging optimization algorithm

10.11591/ijpeds.v15.i4.pp2535-2544
Yazhar Yatim , Mohammad Faridun Naim Tajuddin , Shahril Irwan Sulaiman , Azralmukmin Azmi , Shahrin Md Ayob , Tole Sutikno
The integration of renewable energy sources (RES) into microgrids (MGs) is becoming increasingly important as the world strives to transition towards more sustainable and eco-friendly energy systems. Unfortunately, integrating RES such as solar and wind power into MGs poses challenges due to their intermittent nature. The batteries need to be integrated into the MG system to overcome these challenges and ensure a stable and reliable power supply. However, the size of the battery presents another challenge as it affects the total operation cost of the MG system. Manta ray foraging optimization (MRFO) is used as an optimization technique to minimize the total operation cost of the MG system while ensuring optimum battery capacity. This algorithm is compared with the particle swarm optimization (PSO), differential evolution (DE), and the sine cosine algorithm (SCA). As a result, the proposed technique achieved a better solution than the existing algorithms.
Volume: 15
Issue: 4
Page: 2535-2544
Publish at: 2024-12-01

A study of Tobacco use and mortality by data mining

10.11591/ijece.v14i6.pp6861-6873
Laberiano Andrade Arenas , Inoc Rubio Paucar , Cesar Yactayo-Arias
The use of data mining to address the issue of people who consume tobacco and other harmful substances for their health has led to a significant dependence among smokers, which over time causes illnesses that may result in the addict's death. As a result, the research's goal is to apply a data mining study whose findings showed that the confidence intervals are less than 0.355. However, the lift and conviction in the last three rules are also lower, making it unlikely that these rules will be followed. On the other hand, the knowledge discovery in data bases method was used. It consists of the following stages: data selection, preparation, data mining, and evaluation and interpretation of the results. To that end, comparisons of agile data mining methodologies like crisp-dm, knowledge discovery in data, and Semma are also done. As a result, using specific criteria, dimensions are segmented to allow for the differentiation of these methodologies. As a result, a comparison graph of models such as naive Bayes, decision trees, and rule induction is used. To sum up, it can be said that the rules of association apply to men, the number of admissions, and the cancers that can be brought on by smoking. Also, the percentage of male patients admitted with cancers that can be brought on by smoking Last but not least, the number of admissions and cancers that can be brought on by smoking
Volume: 14
Issue: 6
Page: 6846-6860
Publish at: 2024-12-01

Indonesian sentiment towards global economic recession in 2023 using optimized hyperparameters of support vector machine kernels

10.11591/ijai.v13.i4.pp4948-4956
Dairatul Maarif , Adinda Aulia Hafizha , Andi Kurniawan
The potential for the 2023 global recession has troubled people worldwide, particularly in light of the COVID-19 pandemic. This study employs a sentiment analysis approach to examine how the Indonesian internet community, particularly on Twitter, perceives the topics related to the global economic recession. We collected 11,017 uploaded tweets that were analyzed using support vector machine classifier with linear, radial basis function (RBF), sigmoid, and polynomial kernel schemes. Furthermore, we optimized the classifiers with C, Gamma, and degree hyperparameters. Empirical evidence indicates a lack of preparedness to face a global recession, evidenced by most responses towards 2023 global recession exhibiting concerns about high inflation and economic instability. The finding also suggests that the optimized RBF is a superior modeling kernel relative to others. Collectively, these results provide insights with significant implications for sentiment analysis, natural language processing, and the study of behavioural economics.
Volume: 13
Issue: 4
Page: 4948-4956
Publish at: 2024-12-01

A comparative study of long short-term memory based long-term electrical load forecasting techniques with hyperparameter optimization

10.11591/ijece.v14i6.pp7080-7089
Geetha Mani , Suresh Seetharaman , Jothinathan Kandasamy , Lekshmy Premachandran Ladha , Anish John Paul Mohandas , Swamy Sivasubramoniam , Valarmathi Iyappan Renugadevi
Long-term load forecasting (LTLF) is crucial for reliable electricity supply, infrastructure planning, and informed energy policies, ensuring grid stability and efficient resource allocation. Traditional methods, like statistical models and expert judgment, rely on historical data but may struggle with dynamic changes in technology, regulations, and consumer behavior. Addressing challenges such as economic uncertainties, seasonal variations, data quality, and integrating renewable energy requires advanced forecasting models and adaptive strategies. This research aims to develop an efficient LTLF model for the Coimbatore region in Tamil Nadu, India, using long short-term memory (LSTM) networks. While LSTM has limitations in capturing long- term dependencies and requires high data quality and complex management, optimizing hyperparameters, including through the opposition-based hunter- prey optimization (OHPO) technique, is explored to enhance its predictive performance. The results show that the proposed OHPO-configured LSTM model for LTLF achieves superior performance compared to other techniques, with a mean square error (MSE) of 0.25, root mean square error (RMSE) of 0.5 and mean absolute percentage error (MAPE) of 0.27. This research underscores the significance of improving LTLF precision for informed decision-making in infrastructure planning and energy policy formulation.
Volume: 14
Issue: 6
Page: 7080-7089
Publish at: 2024-12-01

Optimal cell-to-cell active balancing using fuzzy type-2 BEC implemented zeta and quasi-resonant buck converters on Li-ion based battery pack

10.11591/ijpeds.v15.i4.pp2275-2286
Indhana Sudiharto , Farid Dwi Murdianto , Vena Chika Widyasavitta
Many motorized vehicles use non-environmentally friendly fuels causing more pollution. To tackle this, electric vehicles with battery technology are becoming popular. Many electric cars use Li-ion battery packs. However, these battery packs can have differences between individual batteries, affecting their performance. When electric cars accelerate, the batteries can get imbalanced, which shortens their lifespan. To prevent this, a balancing circuit is needed to make sure each battery cell stays equal. To get the balancing current according to the needs of each battery cell and switching network components. As a result, this research creates a cell-to-cell active balancing using the quasi-resonant buck converter that can reduce ripple from zeta converter output. Fuzzy type-2-BEC adjusts the duty cycle zeta converter circuits. The output is set equal to the average cell voltage. Four pieces of Li-ion are connected in the series at 14.4 V/3 Ah. To test the balancers, two variations were used to determine the system's reliability. From the test result, variation one can balance all cells at the 60 s, and variation two can balance all cells at the 150 s.
Volume: 15
Issue: 4
Page: 2275-2286
Publish at: 2024-12-01

Self-adaptability parallel active filter to load variations study

10.11591/ijpeds.v15.i4.pp2435-2442
Ahmed Derrouazin , Mohamed Ali Moussa , Bachir Mokhtari
Due to the increasing use of power electronics equipment, the quality of energy in the electrical network is deteriorating sharply. Indeed, this equipment consumes non-sinusoidal currents, even if they are powered by a sinusoidal voltage, and behaves like generators of harmonic currents. To "clean up" the network, there are several means, among them; the parallel active filter (PAF) which is the most used means because it has proven its effectiveness for the elimination of harmonics caused by a non-linear load. However, this PAF must prove its effectiveness constantly, because the unexpected variation of the loads supplied by the electrical network can call into question its effectiveness. The main objective of this work is to confirming that PAF is a permanent filter and adapts automatically and instantaneously to any load. For this, several simulation tests were carried out under MATLAB/Simulink. The results obtained are very satisfactory, as they confirmed the robustness and self-adaptability of the filter with respect to the sudden variation in loads, the tests carried out on the PAF also show us that the response of the filter is done almost in real time.
Volume: 15
Issue: 4
Page: 2435-2442
Publish at: 2024-12-01
1 2 3
...
2097 2098
Show 397 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