Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Empowering Malaysian micro agri-entrepreneurs: the role of key success factors in e-agribusiness adoption
Get PDFProgress in the agricultural sector is one of the most imperative tools to enhance the productivity of agribusiness. This study identified the key success factors required for the adoption of e-agribusiness platforms in the Malaysian agriculture sector. The study analyzed potential key factors from the prior studies and contextually adjusted using a pilot study. These factors are categorized in various categories such as financial imperative, technological imperative, knowledge imperative, risk and trust factors, governance and public policy, and challenging business environment. The study has collected data from 302 micro agri-entrepreneurs within Malaysia through a questionnaire for quantitative analysis. The exploratory factor analysis (EFA) is used to see the impact of critical success factors (CSFs) that help to increase technological adoption thereby enhancing communication, advertisement, and overall sales of agri-products on the e-business platform. The study has a significant impact on key success factors (financial imperative, technological imperative, knowledge imperative, risk and trust factors, governance and public policy, and challenging business environment) on the adoption of e-agribusiness platforms. The findings provide guidelines to micro agri-entrepreneurs and policymakers that how to use key success factors to improve business performance by utilizing e-agribusiness platforms
Improved feature extraction method and K-means clustering for soil fertility identification based on soil image
Get PDFThis research is conducting analysis of digital land images using digital image processing techniques. The main purpose of the research is to classify soil fertility based on two-dimensional RGB colored digital soil images. The research is done by extracting features and shapes from the soil image. The research uses methods of segmentation, extraction, and identification against digital soil images. This research is carried out in three stages. The first phase of this research is image pre-processing which begins with the conversion of RGB color image to Grayscale then color conversion to binary which subsequently performs noise reduction with the method Three-layer median filter. The second stage is a process that is divided into the first two stages, namely the process of segmentation by grouping RGB color images into L*a*b which is continued by clustering using the K-means clustering method. The second is the extraction of characteristics of the soil image which is characteristic of shape and texture. The final stage is the identification of soil images that are clustered into two types: fertile soils and unfertile soil. The study achieved an accuracy of 85% which could accurately identify 20 images while inaccurately classifying 5 images out of a total of 25 input images
Novel intelligent trust computation for securing internet-of-things using probability based artificial intelligence
Get PDFWith rising demands of smart appliances with normal locations transforming themselves in smart cities, internet-of-things (IoT) encounters various evolving security challenges. The frequently adopted encryption-based approaches have its own limitation of identifying dynamic threats while artificial intelligence (AI) based methodologies are found to address this gap and yet they too have shortcomings. This manuscript presents an intelligent trust computational scheme by harnessing probability-based modelling and AI-scheme for monitoring the dynamic malicious behavior of an unknown adversaries. The study contributes towards a novel AI-model using reinforcement learning towards leveraging decision making for confirming the presence of unknown adversaries. The benchmarked study shows that proposed system offers significant improvement when compared to existing AI-models and other cryptographic schemes with respect to delay, throughput, detection accuracy, execution duration
Boosting stroke prediction with ensemble learning on imbalanced healthcare data
Get PDFDetecting strokes at the early day is crucial for preventing health issues and potentially saving lives. Predicting strokes accurately can be challenging, especially when working with unbalanced healthcare datasets. In this article, we suggest a thorough method combining machine learning (ML) algorithms and ensemble learning techniques to improve the accuracy of predicting strokes. Our approach includes using preprocessing methods for tackling imbalanced data, feature engineering for extracting key information, and utilizing different ML algorithms such as random forests (RF), decision trees (DT), and gradient boosting (GBoost) classifiers. Through the utilization of ensemble learning, we amalgamate the advantages of various models in order to generate stronger and more reliable predictions. By conducting thorough tests and assessments on a variety of datasets, we demonstrate the efficacy of our approach in addressing the imbalanced stroke datasets and greatly enhances prediction accuracy. We conducted comprehensive testing and validation to ensure the reliability and applicability of our method, improving the accuracy of stroke prediction and supporting healthcare planning and resource allocation strategies
An efficient segmentation using adaptive radial basis function neural network for tomato and mango plant leaf images
Get PDFAgriculture has become simply to feed ever-growing populations. The tomato is arguably the most well-known vegetable in agricultural areas and plays a significant role in the growth of vegetables in our daily lives. However, because this tomato has multiple diseases, image segmentation of the diseased leaf shows a key role in classifying the disease by the leaf's symptoms. Therefore, in this paper, an efficient plant disease segmentation using an adaptive radial basis function neural network (ARBFNN) classifier. The proposed radial basis function (RBF) neural network is enhanced by using the flower pollination algorithm (FPA). Firstly, the noise is detached by an adaptive median filter and histogram equalization. Then, from every leaf image, different kind of color features is extracted. After the extraction of features, those are fed to the segmentation phase to section the disease serving from the input image. The efficiency of the suggested method is analyzed based on various metrics and our technique attained a better accuracy of 97.58%
User acceptance model questionnaire generator for information system applications
Get PDFTo foresee users’ behavior, the technology acceptance model (TAM) and theories applied in different fields were evaluated to understand factors influencing IT adoption. This study analyzed TAMs used in various IT fields where information systems are being adopted and created an application to generate a user acceptance questionnaire for user acceptance studies. These are based on key variables targeted by acceptance models that have already proven effective. In developing the software, questions relating to each attribute are compiled into one database, tagging each attribute to the model so users can select and view which question corresponds to that attribute. Sample questions can now be generated and exported to a word processor. The user acceptance questionnaire generator was successfully developed based on variables and attributes from famous TAMs. The software also passed the test results conducted for every functional requirement. Considering the abovementioned observations, reluctance to embrace and utilize information systems may be minimized by doing a user acceptance study utilizing the questionnaires exported from the generator. For improvement, other researchers may integrate more acceptance models and other variables not covered and create a web app version for broader reach
Five-Tier BI architecture with tuned decision trees for e-commerce prediction
Get PDFIn recent times, remarkable performance has been shown by large language models (LLMs) in a range of natural language processing (NLP) such as questioning, responding, document production, and translating languages. In today's competitive business landscape, understanding consumer behaviour in online buying is crucial for the success of e-commerce platforms. The work proposes a novel Five-Tier service-oriented BI architecture (FSOBIA) that leverages advanced tuned decision tree (ATDT) techniques for predicting online buying behaviour. The proposed FSOBIA offers e-commerce platforms a scalable and adaptable solution for gaining insights into consumer preferences and making informed business decisions. The goal of FSOBIA's design and implementation is to meet the needs of evolving users and quicker service. Experimental evaluations on real-world datasets in FSOBIA achieved over 95% prediction accuracy, outperforming traditional models: Decision trees (82%), and XGBoost (91%), while offering better scalability and computational efficiency
Optimizing cloud tasks scheduling based on the hybridization of darts game hypothesis and beluga whale optimization technique
Get PDFThis paper presents the hybridization of two metaheuristic algorithms which belongs to different categories, for optimizing the tasks scheduling in cloud environment. Hybridization of a game-based metaheuristic algorithm namely, darts game optimizer (DGO), with a swarm-based metaheuristic algorithm namely, beluga whale optimization (BWO), yields to the evolution of a new algorithm known as “hybrid darts game hypothesis – beluga whale optimization” (hybrid DGH-BWO) algorithm. Task scheduling optimization in cloud environment is a critical process and is determined as a non-deterministic polynomial (NP)-hard problem. Metaheuristic techniques are high-level optimization algorithms, designed to solve a wide range of complex, optimization problems. In the hybridization of DGO and BWO metaheuristic algorithms, expedition and convergence capabilities of both algorithms are combined together, and this enhances the chances of finding the higher-quality solutions compared to using a single algorithm alone. Other benefits of the proposed algorithm: increased overall efficiency, as “hybrid DGH-BWO” algorithm can exploit the complementary strengths of both DGO and BWO algorithms to converge to optimal solutions more quickly. Wide range of diversity is also introduced in the search space and this helps in avoiding getting trapped in local optima
Technology in halal certification: a ten-year bibliometric study
Get PDFThis study explores the role of technology in halal certification using bibliometric analysis. Based on 88 articles from the Scopus database (2014–2024), the research employs tools like Publish or Perish (PoP), Microsoft Excel, and VOSviewer to reveal the intellectual framework of relevant literature. The finding indicates a steady increase in manuscript productivity from 2014-2024 despite a declining citation trend. Journal of Islamic Marketing, Mohd Zabiedy Mohd Sulaiman, Malaysia, and the National Defence of Malaysia emerged as most prolific journal, author, country, and institution that produce the most, respectively, in publishing on the topic. The paper that has influenced other research the most is Rejeb et al.’s integrating the IoT in the halal food supply chain: a systematic literature review and research agenda. Five significant keyword clusters that frequently show up in the 88 articles examined in this study are halal supply chain, consumer behavior towards halal foods, the role of blockchain in the halal industry, the role of information technology in halal cosmetics, and halal logo in food products. This study highlights the increasing integration of technology in halal certification, emphasizing the need for continuous innovation, interdisciplinary collaboration, and alignment with industry demands to maintain relevance. Additionally, it underscores Malaysia’s leadership in this field while noting the global expansion of halal research, the impact of emerging technologies like blockchain and IoT, and the need for stronger institutional collaboration to enhance transparency, traceability, and market growth
Enhancing solar radiation forecasting using machine learning algorithms
Get PDFWith the increasing amount of photovoltaic (PV) generation, accurate solar radiation forecasting is essential to the safe operation of power systems. This work examines many machines learning (ML) techniques that use both exogenous and endogenous inputs to forecast sun radiation. In order to find pertinent input parameters and their values based on previous observations, the forecasting models’ performance is assessed using metrics like mean absolute error (MAE), mean squared error (MSE), R-squared (R2), and root mean squared error (RMSE). Accurate power output forecasting is becoming more and more necessary as the need to switch to renewable energy sources (RES) like solar and wind power grows. There is a clear demand for more reliable solutions because current models frequently struggle with temporal complexity and noise. A revolutionary deep learning-based technique designed especially for green energy power forecasting was developed in response. The study uses time series smoothing and the autoregressive integrated moving average (ARIMA) model for casing in order to create a solid basis for analysis and modeling that is free of noise and outliers. The proposed method aims to address the limitations of existing forecasting methods and promote the creation of more accurate and reliable forecasts in the field of renewable energy