cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Indah Purnama Sari
Contact Email
indahpurnama@umsu.ac.id
Phone
+6282276837886
Journal Mail Official
ibctsabitjournal@gmail.com
Editorial Address
Jl. Batang Kuis - Lubuk Pakam Gg. Cempaka Dusun III No. 3, Tanjung Sari, Batang Kuis, Kab. Deli Serdang Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
Tsabit
Published by Ilmu Bersama Center
ISSN : -     EISSN : 30628504     DOI : https://doi.org/10.56211/tsabit
Core Subject : Science,
Computer Science & IT
Tsabit Journal of Computer Science is open to researchers and experts in the field of Computer Science. This journal functions as a forum for disclosing research results both conceptually and technically related to computer science. Tsabit journal of computer science is published twice a year, namely in June and December. Submitted manuscripts will be accepted by the editor and then checked for similarities with the Turnitin application. The review process is carried out using Double Blind Peer Review. Manuscripts received are expected to relate to new technologies and current issues. Please read the Guidelines and Template for this journal carefully. Authors who wish to send their manuscripts to the Tsabit Journal of Computer Science editorial team must comply with the writing guidelines. Tsabit Journal of Computer Science accepts manuscripts on the topics Software Engineering, Media, Game and Mobile Technologies, Data Mining, Information Security, Image Processing and Pattern Recognition, Natural Language Processing, Smart City, Expert System, Decision Support System, Cloud Computing, Digital Forensics , Artificial Intelligence, Machine Learning, Computational Intelligence, Computer Networking and other study topics relevant to Computer Science.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 35 Documents
 1   2   3   4 
Implementation of the C4.5 Decision Tree Algorithm for the Analysis and Diagnosis of Laptop Damage at Mitra Kreasi Computer Medan Taufik Rizky Pasaribu; Khairuddin Nasution; Mhd. Zulfansyuri Siambaton
Tsabit Journal of Computer Science Vol. 3 No. 1 (2026): June Edition
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/tsabit102

Abstract

A laptop is a portable computing device that is widely relied upon because of the mobility it offers, particularly for users who spend much of their time outside a fixed office. Frequent and intensive use, however, raises the risk of damage to both hardware and supporting components. At present, the diagnosis of laptop damage is still largely performed manually by technicians based on experience, a practice that is prone to misdiagnosis and tends to take a relatively long time. This research therefore aims to implement the C4.5 Decision Tree algorithm to analyze and diagnose laptop damage based on the symptoms that appear. The data used in this study consist of laptop service history records comprising several damage-symptom attributes, such as whether the laptop powers on, the condition of the screen display, the charging indicator, fan noise, and overheating condition. The C4.5 algorithm was used to build a decision tree by calculating entropy, information gain, and gain ratio values in order to determine the best attribute for the classification process. Calculations on the training data produced a total entropy value of 2.75, with Attribute 1 (the laptop turning off immediately when the charger is unplugged) and Attribute 3 (a BSOD with a MEMORY_MANAGEMENT code) sharing the highest information gain of 0.81125, making either eligible to serve as the root node; this research adopted Attribute 1 as the root. The resulting decision tree was then implemented into a web-based diagnostic application built with PHP and MySQL, and black box testing confirmed that the login, data management, C4.5 modeling, and damage-classification features all functioned as expected. The system is expected to help technicians and customers at Mitra Kreasi Computer Medan obtain faster, more structured, and more objective damage diagnoses.
Implementation of Seasonal ARIMA (SARIMA) for Sales Prediction of Pet Food Products: A Case Study of Abadi Petshop Fikri Haikal Harahap; Antoni; Darjat Saripurna
Tsabit Journal of Computer Science Vol. 3 No. 1 (2026): June Edition
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/tsabit104

Abstract

The rapid growth of pet ownership in Indonesia has driven a steady increase in demand for pet food products, which typically follows a recurring seasonal pattern across the year. Abadi Petshop, a local pet supply store, has so far relied on manual recording and the owner's intuition to estimate future sales, an approach that does not systematically account for historical sales patterns and frequently leads to inaccurate stock planning, resulting in either overstock or stockouts. This study aims to design and implement a web-based sales prediction system for pet food products using the Seasonal Autoregressive Integrated Moving Average (SARIMA) method, applied to monthly sales data of a Whiskas cat food product collected from January 2023 to December 2024 (24 observations). Non-seasonal differencing (d = 1) and seasonal differencing (D = 1, s = 12) were applied to achieve stationarity, and the Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF) plots were used to identify the model order, resulting in a SARIMA(1,1,1)(1,1,0)12 model with parameters φ = 0.6, Φ = 0.3, and θ = 0.4. The system was developed using the Laravel framework with a MySQL database, following the Unified Software Development Process (USDP), and functional black-box testing confirmed that all core features — including login, sales data input, prediction processing, forecast visualization, and result export — operated successfully. The resulting forecast for the twelve months following the training period projected a gradual upward trend, starting at 140.20 kg in the first month and reaching 175.50 kg by the twelfth month, consistent with the increasing trend and annual seasonal pattern observed in the historical data. These findings indicate that the SARIMA method is capable of automatically modeling trend and seasonal components in pet food sales data and can support Abadi Petshop in making more accurate, data-driven decisions regarding inventory planning and sales strategy.
Implementation of the Discrete Wavelet Transform (DWT) Algorithm for Video File Security Dea Sintia; Mhd. Zulfansyuri Siambaton; Rachmat Aulia
Tsabit Journal of Computer Science Vol. 3 No. 1 (2026): June Edition
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/tsabit105

Abstract

The growing reliance on digital video across education, entertainment, communication, and security applications has made video one of the most widely used forms of multimedia data, yet this growth has also exposed video files to risks such as unauthorized access, data theft, content manipulation, and misuse of digital information. This study addresses these risks by implementing the Discrete Wavelet Transform (DWT) algorithm as a signal-processing-based method for securing video files. DWT decomposes each video frame from the time domain into the frequency domain, producing a visual representation that is difficult to recognize, while the Inverse Discrete Wavelet Transform (IDWT) reconstructs the video back to a form approximating the original. A security key was applied to the wavelet coefficients to prevent reconstruction without proper authorization. The system was built in Python using OpenCV for video processing, PyWavelets for the DWT/IDWT operations, NumPy for numerical computation, and CustomTkinter for the desktop interface, following a Research and Development approach with a Waterfall development model. Black box testing confirmed that the encryption and decryption functions operated correctly across the tested video files, and quality evaluation using Peak Signal to Noise Ratio (PSNR), Mean Squared Error (MSE), Signal to Noise Ratio (SNR), and entropy showed that the encrypted videos exhibited substantial visual distortion relative to the originals, with PSNR values around 10–11 dB, MSE values in the range of roughly 5,100–5,700, and an entropy of approximately 7.37, indicating that the visual structure of the video content was concealed effectively. These findings suggest that DWT can serve as a practical signal-transformation-based approach to video data security, although its protection level remains below that of dedicated cryptographic algorithms such as AES or RSA, leaving room for future work that combines DWT with stronger cryptographic techniques.
Implementation Of The Discrete Sine Transform (Dst) Algorithm For Video File Compression Muhammad Abdillah Nasution; Khairuddin Nasution; Mhd. Zulfansyuri Siambaton
Tsabit Journal of Computer Science Vol. 3 No. 1 (2026): June Edition
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/tsabit106

Abstract

Video is one of the multimedia data formats whose use continues to grow across fields such as education, entertainment, and digital communication, a trend that has increased the demand for storage capacity and bandwidth. A video is composed of a large collection of frames containing substantial amounts of pixel data, which results in comparatively large file sizes. This condition calls for a compression method capable of reducing file size without significantly degrading visual quality. This study implements the Discrete Sine Transform (DST) algorithm in the video file compression process and analyzes its effect on file size and video quality. DST is applied to transform data from the spatial domain into the frequency domain so that data redundancy can be reduced while important information is retained. The compression procedure divides each video into a series of frames and applies the DST transformation to optimize data efficiency. Testing was carried out on video files in MP4 and AVI formats, with compressed video quality evaluated using the Peak Signal to Noise Ratio (PSNR) parameter and compression efficiency measured by comparing file sizes before and after compression. The results show that the DST method is able to reduce video file size while maintaining visual quality. The AVI format achieved an average compression efficiency of 44.96%, while the MP4 format achieved 28.76%. In addition, the PSNR values for all tested videos remained above 37 dB, indicating that the compressed video quality can still be classified as good.
Anomaly Detection in Electrical Energy Consumption Using Long Short-Term Memory (LSTM) Andi Zulherry; Mhd. Basri; muhammad Gunawan
Tsabit Journal of Computer Science Vol. 3 No. 1 (2026): June Edition
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/tsabit123

Abstract

The increasing deployment of smart meters has generated large volumes of electrical energy consumption data, creating new opportunities for intelligent anomaly detection to reduce non-technical losses, equipment failures, and abnormal consumption patterns. Conventional statistical and rule-based approaches often struggle to capture complex temporal dependencies in sequential electricity usage data. This study proposes a Long Short-Term Memory (LSTM)-based anomaly detection model to identify abnormal electricity consumption patterns with high accuracy. A time-series dataset consisting of historical hourly electricity consumption records was collected from smart metering systems and preprocessed through missing-value imputation, normalization using Min-Max Scaling, and sequence windowing. The proposed LSTM model was trained to learn normal consumption behavior and detect anomalies based on prediction error using an adaptive threshold determined from reconstruction residuals. Model performance was evaluated using accuracy, precision, recall, F1-score, and Area Under the Receiver Operating Characteristic Curve (AUC), and compared with conventional Machine Learning methods, including Support Vector Machine (SVM) and Isolation Forest. Experimental results demonstrate that the proposed LSTM model achieved an accuracy of 97.3%, precision of 96.8%, recall of 97.9%, F1-score of 97.3%, and an AUC of 0.985, outperforming the baseline models in detecting anomalous electricity consumption patterns. The superior performance is attributed to the LSTM architecture's ability to model long-term temporal dependencies and nonlinear consumption behaviors. These findings indicate that LSTM provides an effective and reliable approach for real-time anomaly detection in smart energy systems, supporting intelligent energy management, reducing power losses, and improving the operational reliability of modern electrical distribution networks.

Page 4 of 4 | Total Record : 35

 1   2   3   4 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 3 No. 1 (2026): June Edition Vol. 2 No. 2 (2025): December Edition Vol. 2 No. 1 (2025): June Edition Vol. 1 No. 2 (2024): December Edition Vol. 1 No. 1 (2024): June Edition