Claim Missing Document
Check
Articles

Found 34 Documents
Search

Transforming Agriculture: An Insight into Decision Support Systems in Precision Farming Yi, Ding; Jun, Luo; Haodic, Gao; Xing, Zhang; Lie, Ye; Maidin, Siti Sarah; Ishak, Wan Hussain Wan; Wider, Walton
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.274

Abstract

Precision agriculture seamlessly incorporates advanced technologies and data analysis to improve farming efficiency and sustainability through immediate resource allocation. Therefore, this study aims to synthesize research findings related to agriculture, Decision Support Systems, and precision agriculture through a systematic literature review conducted in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The search was performed on the Scopus database, specifically focusing on publications published in English between the years 2017 and 2023. Out of 126 periodicals, a rigorous process was used to determine which publications met the specific criteria for inclusion and exclusion. As a result, only 8 relevant studies were chosen. The review emphasizes the substantial capacity of Decision Support Systems in precision agriculture, demonstrating that DSS has the capability to enhance crop yields by 15% and decrease water consumption by 20%. Through the utilization of big data, machine learning, and advanced technologies, Decision Support Systems has the potential to transform the agricultural industry by enhancing productivity, optimizing resource allocation, and enabling early identification of pests and diseases. The utilization of real-time data from Decision Support Systems empowers farmers to make well-informed choices, effectively managing production while upholding environmental sustainability. This, in turn, plays a crucial role in ensuring the economic viability of farms and enhancing global food security. However, addressing challenges like data privacy concerns, enhancing user-friendly interfaces, establishing robust data administration infrastructure, and providing adequate training and support for end-users is imperative for the successful implementation of data-driven Decision Support Systems in precision agriculture.
CS-based Lung Covid-Affected X-Ray Image Disorders Classification using Convolutional Neural Network Triasari, Biyantika Emili; Budiman, Gelar; Maidin, Siti Sarah; Jaya, M. Izham; Hariyani, Yuli Sun; Irawati, Indrarini Dyah; Zhao, Zhong
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.371

Abstract

Lung diseases, such as pneumonia, significantly affect the respiratory system, especially the lungs. This condition causes various degrees of lung damage in patients of all age groups, including the elderly, adults, and children. Even after treatment and recovery, diagnosing lung damage remains important, which can be done using rapid tests, clinical evaluations, CT scans, or X-rays. This study focuses on the classification of X-ray images of lungs affected by pneumonia and normal lungs, using the Convolutional Neural Network method based on Compressive Sensing (CS) simulated using MatLab. The purpose of the study is to determine the performance by calculating the confusion matrix value. The number of datasets used for normal lungs and those affected by pneumonia is 300 X-ray images from several different sources, with 60% training data, 30% validation, and 10% testing. The addition of the compression process causes a decrease in image quality, expressed in PSNR, as well as a decrease in classification parameters such as accuracy. Compared with previous research, the system without compression produces the highest accuracy. The results of the study can help classify lungs affected by pneumonia.
Intelligent Transportation System's Machine Learning-Based Traffic Prediction Govindaraju, S; Indirani, M; Maidin, Siti Sarah; Wei, Jingchuan
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.364

Abstract

The aim of this study is to develop an accurate and timely traffic flow prediction tool that considers various factors influencing road conditions, such as road repairs, rallies, traffic signals, and other everyday events that can impact traffic movement. By providing drivers with near real-time predictive insights, they can make more informed decisions, enhancing traffic management and potentially supporting future autonomous vehicle technologies. Given the exponential growth in traffic data, this research applies big data principles to the transportation domain, where existing traffic prediction models struggle to handle real-world applications effectively. In this study, we implemented machine learning, genetic algorithms, soft computing, and deep learning techniques, achieving a traffic flow prediction accuracy of 93.5%. The results demonstrate a significant improvement in prediction accuracy compared to conventional models, which typically average around 85%. Additionally, image processing algorithms for traffic sign identification are integrated, achieving 90% accuracy in identifying key traffic signs, further aiding in the training of autonomous vehicles. The proposed approach addresses the challenges posed by large-scale transportation data, offering a solution with improved predictive accuracy and practical utility.
Trust Aware Congestion Control Mechanism for Wireless Sensor Network Priscilla, G. Maria; Kumar, B.L. Shiva; Maidin, Siti Sarah; Attarbashi, Zainab S.
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.564

Abstract

Congestion in wireless sensor networks (WSNs) can occur from various factors, including resource limitations and the transmission of packets surpassing the capacity of receiving nodes. This congestion may arise from natural causes or be exacerbated by self-serving nodes. Furthermore, malicious sensor nodes within WSNs have the capability to instigate congestion-like scenarios by either flooding the network with redundant fake packets or maliciously discarding genuine data packets. Relying solely on conventional congestion control techniques proves inadequate for ensuring fair delivery, necessitating a proactive approach to prevent such adversities by segregating these nodes from the network. Existing congestion control strategies often make the unrealistic assumption that all nodes are authentic and behave appropriately. To address these challenges, a proposed Genetic Algorithm based Trust-Aware Congestion Control (GA-TACC) not only manages congestion under natural circumstances but also considers scenarios where hostile nodes deliberately improve packet delivery. The GA evaluates the credibility score (CS), contributing to enhanced performance, and GA-TACC demonstrates superiority over existing state-of-the-art techniques for wireless sensor network.
An Exploration into Hybrid Agile Development Approach Maidin, Siti Sarah; Yahya, Norzariyah
International Journal of Advanced Science and Computer Applications Vol. 2 No. 2: September 2023
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47679/ijasca.v2i2.32

Abstract

The aim of this paper is to provide a review of the different hybrid agile models. This study raised the question “what are the types of hybrid agile models and their features”? The systematic review was done using Preferred Reporting Items for Systematic Reviews and Meta-Analyses Model for comprehensive searching. Scopus is used as the database for searching articles. A total of 131 papers related to agile and hybrid agile models were retrieved and finally after screening and filtering, only 26 papers were included in the study. This paper probes into the features of agile and hybrid agile models and thus recommends hybrid agile models as one of the best-suited models in software development due to several reasons. Some of the reasons are due to its comprehensiveness in managing a large-scale project with good documentation and developing better methods for business analysis. This paper concludes by providing insight into the different types of hybrid agile models in software development. This paper starts with an Introduction section, followed by a Materials and Method section, continued with a Results and Discussion section, and finally concludes the research in the Conclusion section.
Unveiling Hybrid Model with Naive Bayes, Deep Learning, Logistic Regression for Predicting Customer Churn and Boost Retention Subramanian, Devibala; Ajitha, Ajitha; Maidin, Siti Sarah
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.675

Abstract

The telecommunications sector is rapidly evolving but is increasingly challenged by customer churn, where subscribers switch to competing service providers. This study introduces a hybrid model for churn prediction and customer retention by combining machine learning methods—Naive Bayes, Deep Learning, and Logistic Regression—with sentiment analysis on user-generated content (UGC). Data was gathered through two primary sources: survey responses and 352 social media comments from users aged 20–35. The survey data was enriched with features such as gender, age, subscription period, complaints, and retention efforts. The preprocessing steps included handling missing values, scaling features, and encoding categorical variables to ensure model robustness. Experimental results demonstrated that Logistic Regression achieved the highest accuracy (88.45%) and sensitivity (91.33%) in detecting potential churners. The PCA-based approach followed closely with an accuracy of 86.77% and a balanced sensitivity-specificity profile (89.95% and 83.58%, respectively), effectively capturing key churn indicators. Random Forest and Decision Tree classifiers yielded lower sensitivity but remained strong in specificity, indicating their suitability for identifying loyal customers. Attribute weight analysis across models revealed that subscription plan, age, and retention effort were consistently influential in churn prediction. Furthermore, the integration of sentiment analysis provided emotional context to churn behavior, with negative comments triggering alerts for proactive engagement. The study highlights the predictive strength of combining structured survey data and unstructured UGC through machine learning and sentiment analytics. It underscores the importance of personalized retention strategies based on model interpretability and correlation weight findings. This hybrid approach equips telecom companies with actionable insights to minimize churn and sustain customer loyalty in a competitive market.
Dynamic Replica Management Strategy Based-on Data Accessing Popularity for Load Balancing and Optimizing Network Performance in Cloud Storage Thavamani, S.; Maidin, Siti Sarah; Varun, S. T.
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.674

Abstract

Network performance plays a vital role in organizational efficiency, where large volumes of data, fast transmission, and low latency significantly enhance productivity and reduce downtime. Cloud storage offers a service model that enables remote data management and efficient content distribution. In such systems, data replication is widely used to improve availability, reliability, fault tolerance, and throughput. However, static replication policies often allocate replicas during system initialization, failing to adapt to the dynamic and heterogeneous nature of cloud environments. These environments are susceptible to challenges such as data loss, node failures, and fluctuating demand, which can degrade service quality. To address this, we propose a dynamic replica management strategy that considers data popularity, active peer participation, and peer capacity. Virtual peers are grouped into strong, medium, and weak clusters based on their weight values, which are derived from bandwidth, CPU speed, memory size, and access delay. Content is categorized into Class I, II, and III based on access frequency. Highly popular data (Class I) is replicated in strong clusters, while less frequently accessed data is placed in medium and weak clusters. A hierarchical routing mechanism ensures that queries are directed to the appropriate cluster. The proposed system was implemented and evaluated through simulations. Results show up to 25% improvement in throughput, 20% reduction in packet drops, 97% query efficiency, and decreased bandwidth utilization under high load. By maintaining optimal replica counts without compromising availability, the system supports cloud SLA compliance while minimizing overhead. This solution is aligned with the ninth UN Sustainable Development Goal: Industry, Innovation, and Infrastructure.
Intelligent Solar Panel Monitoring Using Machine Learning and Cloud-Based Predictive Analytics Dhilipan, J.; Vijayalakshmi, N.; Shanmugam, D.B.; Maidin, Siti Sarah; Shing, Wong Ling
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.720

Abstract

The increasing global energy demand necessitates reliable and sustainable solutions, with solar photovoltaic (PV) technology emerging as a key carbon-neutral option. However, optimizing solar energy systems requires advanced monitoring and predictive analytics to enhance efficiency and ensure long-term performance. This study introduces an Internet of Things (IoT)-based solar energy monitoring system, integrating machine learning algorithms and cloud computing to enhance real-time performance assessment. The proposed system employs K-Means Clustering for condition classification, Support Vector Machine (SVM) for fault detection, Long Short-Term Memory (LSTM) for energy forecasting, Prophet for time-series predictions, and Isolation Forest for anomaly detection. The system was validated using a 125-watt photovoltaic module, monitoring temperature, solar radiation, voltage, and current. A Wi-Fi-enabled microcontroller collects data, which is processed through a cloud-based platform and visualized via the Blynk application. Experimental results demonstrate 94.2% energy prediction accuracy using LSTM, 89.7% fault classification accuracy with SVM, and 88.5% anomaly detection accuracy with Isolation Forest, confirming high reliability. The system's wireless tracking mechanism minimizes resource consumption, ensuring scalability and adaptability for commercial and industrial applications. The integration of IoT, machine learning, and cloud analytics provides a cost-effective and scalable approach for solar PV optimization. Future enhancements include deep learning models and reinforcement learning algorithms to improve energy forecasting, fault detection, and adaptive optimization, ensuring greater efficiency, resilience, and sustainability in solar energy management.
Implementation of Machine Learning Algorithms for Detecting Bot and Fraudulent Accounts on Instagram Based on Public Profile Characteristics Maidin, Siti Sarah; Xing, Zhang; Lie, Ye
International Journal for Applied Information Management Vol. 4 No. 4 (2024): Regular Issue: December 2024
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/ijaim.v4i4.94

Abstract

The rapid growth of Instagram as a social media platform has led to increased challenges related to fake accounts, including bots, spam, and scam profiles, which threaten the integrity and trustworthiness of online information. This study implements machine learning algorithms, particularly the Random Forest classifier, to detect and classify Instagram accounts into four categories: Real, Bot, Spam, and Scam, based on publicly available profile characteristics. A dataset of 15,000 Instagram profiles was collected and preprocessed, extracting features such as follower count, following count, posting frequency, and presence of profile information. The Random Forest model was trained and evaluated, achieving an accuracy of 97% with high precision and recall across all categories. Behavioral analysis revealed distinct patterns in following/follower ratios, posting activity, and mutual friends that differentiate genuine users from fake accounts. Feature importance ranking highlighted follower count as the most influential attribute for classification. The model demonstrated strong robustness through ROC and Precision-Recall curves, underscoring its effectiveness in a multiclass classification task. This approach not only enhances automated detection and moderation of malicious accounts but also contributes to maintaining a safer social media environment by mitigating misinformation and fraud. Future work could improve detection by incorporating temporal activity data, linguistic analysis, and real-time monitoring to adapt to evolving deceptive behaviors. Taken together, this study confirms the viability of machine learning methods in addressing the growing issue of fake accounts on Instagram, offering scalable and interpretable solutions for social media security.
Lora Communication System for Early Detection and Monitoring of Water Toxicity in Floating Net Cages Rahmafadilla, Rahmafadilla; Irawati, Indrarini Dyah; Rizal, Mochammad Fahru; Maidin, Siti Sarah
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.787

Abstract

Floating Net Cages/ Keramba Jaring Apung (KJA) are at risk of polluting the air, which can affect fish farming. Therefore, an early monitoring system is needed that can measure air quality such as temperature, pH, and dissolved oxygen (DO) in real-time. This system utilizes the LoRa RFM95W module to wirelessly transmit environmental data from sensors installed on the cages, which continuously monitor water quality parameters such as temperature, pH, and DO in real-time. The data obtained is then processed to monitor changes in water toxicity in real-time, allowing early detection of potential threats to the ecosystem. Tests were conducted at distances of 50m, 180m, 300m, 340m, and 440m. The results showed that the system worked well up to a distance of 300m with RSSI values between -85 dBm to -120 dBm and SNR more than 2 dB. However, at distances of 340m and 440m, the signal decreased and the delay increased. At a depth of 340m, only one experiment was successful with RSSI -134 dBm and SNR -6 dB, while at a depth of 440m, only a few experiments were successful with RSSI between -122 dBm to -132 dBm and SNR between 1 dB to -6 dB. The prototype system successfully transmitted real-time air quality data to a web-based monitoring center. Data from the sensors were sent via the LoRa network to a central server for further monitoring.
Co-Authors Abbas, Elaf Sabah Abbas, Intesar Abdul Radhi, Rafah Hassan Abdul-Kareem, Bushra Jabbar Abdullah Abdullah Ahmed, Mohsen Ali Ahmed, Saif Saad Ajitha, Ajitha Al Hilfi, Thamer Kadum Yousif Al-Dosari, Ibraheem Hatem Mohammed Alfalahi, Saad.T.Y. Ali, Taghreed Alaa Mohammed Arthi, R. Attarbashi, Zainab S. Ayyasy, Yahya Bakar, Normi Sham Awang Abu Binti Abdul Rahim, Yusrina Dhilipan, J. Fallah, Dina Faraj, Lydia Naseer Fauzi, Muhammad Ashraf bin Fauri Ge, Wu Gelar Budiman Govindaraju, S Guangfa, Wu Hadi, Shahd Imad Hafedh, Milad Abdullah Hammad, Qudama Khamis Hamodi Aljanabi, Yaser Issam Hao Wu Haodic, Gao Hemalatha, M. Indirani, M Indrarini Dyah Irawati Ishak, Wan Hussain Wan Ismail, Laith S. Jafar, Qusay Mohammed Jaleel Maktoof, Mohammed Abdul Jamil, Abeer Salim Janan, Ola Jaya, M. Izham Jeyaboopathiraja, J. Jing Sun Khalil, Baker Mohammed Kowthalam, Vijay Rathnam Kumar, B.L. Shiva Lie, Ye Luo Jun Mahdi, Ammar Falih Mahdi, Mohammed Fadhil Mahendiran, N Majeed, Adil Abbas Mariajohn, Princess Mohammed, Doaa Thamer Murad, Nada Mohammed Nayef, Hamdi Abdullah Nazar, Mustafa Nivetha, N. Praneesh, M. Priscilla, G Maria Priscilla, G. Maria Rahmafadilla, Rahmafadilla Rizal, Mochammad Fahru Sajid, Wafaa Adnan Salman, Khdier Samson, A Sunil Selvaraj, Poovarasan Shaker, Alhamza Abdulsatar Shanmugam, D.B. Shing, Wong Ling Shivakumar, B L Shivakumar, B. L. Shnain, Saif Kamil Subramanian, Devibala Sumathi, N Sumathi, V. Taher, Nada Adnan Thavamani, S. Triasari, Biyantika Emili Varun, S. T. Vidhya, B. Vijayalakshmi, N. Wan Ishak, Wan Hussain Wei, Jingchuan Wider, Walton Yahya, Norzariyah Yamin, Fadhilah Yang, Qingxue Yi, Ding Yilin, Li Yousif Al Hilfi, Thamer Kadum YULI SUN HARIYANI Zhang Xing Zhao, Zhong Zhaoji, Fu