Claim Missing Document
Check
Articles

Found 16 Documents
Search
Journal : Computer

IMPLEMENTASI MANAJEMEN BANDWIDTH MENGGUNAKAN METODE PEER CONNECTION QUEUE PADA MIKROTIK Mariyanto, Mariyanto; Maslan, Andi
Computer Science and Industrial Engineering Vol 9 No 3 (2023): Comasie
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v9i3.7697

Abstract

A hotspot consists of one or more WLAN or Wireless LAN Access Points of standard 802.11a/b/g that provide a restricted area in which users can freely join Access Points with WLAN-enabled mobile devices. With advances in technology, a router is a device that is used to perform the routing process. However, since routers are expensive, there are hardware alternatives such as Mikrotik. Mikrotik RouterOS is an operating system that can turn a computer into a router, or often called a PC Router. solutions to take advantage of bandwidth management and use Mikrotik router boards as a tool to divide bandwidth evenly. Because excessive use will cause a long load when accessing the internet or limited bandwidth. To distribute the load and manage the client connection path to a service on the server, the PCQ (Peer Connection Queue) method is used. The way to do PCQ is to upload with type pcq-dpwnload-phd, set the queue size and total queue size, and check the classification list for different addresses. In addition, to implement bandwidth management with PCQ for uploads, you must create the type pcq-upload-pd, set the queue size and total queue size, and check the classifier list for the source address. For setting upload and download targets on the proxy, you must point to the network address 192.168.100.0/24, with a maximum upload speed of 10 MBPS and 30 MBPS download. The results of this study indicate that the use of a PCQ-based proxy network can be applied properly for Pizza Hut delivery in Batam City.
ANALISIS KLASIFIKASI EMAIL SPAM MENGGUNAKAN ALGORITMA NAÏVE BAYES Rahman, Azan; Maslan, Andi
Computer Science and Industrial Engineering Vol 12 No 3 (2025): Comasie Vol 12 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v12i3.9792

Abstract

Spam emails pose a significant challenge in digital communication, requiring effective classification methods to enhance cybersecurity. This study evaluates the performance of the Naïve Bayes algorithm in detecting spam emails, focusing on accuracy, precision, and recall. The dataset consists of pre-labeled emails processed using TF-IDF for feature extraction. The results indicate that the algorithm achieved an accuracy of 90% before addressing class imbalance. After applying SMOTE, the final accuracy improved to 98%. These findings demonstrate that Naïve Bayes is an effective method for spam email classification, with SMOTE enhancing its performance in handling class imbalance.
ANALISIS SERVICE QUALITY BANDARA HANG NADIM BATAM MELALUI MODEL SERVQUAL Ghazali, Ihwan; Maslan, Andi
Computer Science and Industrial Engineering Vol 12 No 3 (2025): Comasie Vol 12 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v12i3.9837

Abstract

Hang Nadim, located in Batam City, Riau Island Regency, is one of Indonesia's international airports. Due to its size and reputation as an international airport, Hang Nadim Airport has a policy that restricts access to each sector. The use and assignment of airport PAS cards are typically subject to restrictions for airport staff. The airport region is off-limits to cargo workers, airline employees, shopkeepers, and renters. The state is in charge of ensuring airport safety and security in order to protect travelers. Without authorization from the airport, it is forbidden for anybody to be in specific areas of the airport, erect impediments, or engage in any other activity that could jeopardize flight security and safety
ANALISIS PERFORMA INTRUSION DETECTION SYSTEM SNORT DAN SURICATA TERHADAP SERANGAN SQL INJECTION Ramot Argenta Pasaribu, Fabian; Maslan, Andi
Computer Science and Industrial Engineering Vol 13 No 2 (2025): Comasie Vol 13 No 2
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i2.10403

Abstract

Web application security is becoming increasingly important due to the rise of threats such as SQL Injection, which exploits vulnerabilities to access sensitive data. As one of the most severe types of attacks, SQL Injection compromises the confidentiality, integrity, and access control of a system. Intrusion Detection Systems such as Snort and Suricata are used to detect and mitigate this. This study compares the effectiveness of Snort and Suricata in detecting SQL Injection using an experimental setup. The vulnerable web application (DVWA) was installed on Ubuntu, while attacks were launched from Kali Linux. Both IDS tools were configured to monitor network traffic and detect intrusions based on predefined rules. Performance was evaluated using accuracy, precision, recall, and F1 score. Suricata outperformed Snort in all metrics, Suricata also demonstrated faster detection. These results indicate that Suricata is more accurate and efficient at detecting SQL injection attacks in the test environment.
DETEKSI SERANGAN MALWARE MENGGUNAKAN METODE SUPPORT VECTOR MACHINE Simbolon, Hery Sanjaya; Maslan, Andi
Computer Science and Industrial Engineering Vol 13 No 2 (2025): Comasie Vol 13 No 2
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i2.10478

Abstract

The rapid development of information technology has increased the potential for threats to system security, one of which is malware attacks. Malware is malicious software that has the ability to disrupt, damage, or steal computer system data without user knowledge. To prevent further damage to the system, malware activity detection is very important. The purpose of this study is to create a classification model that can identify malware attacks based on the behavior of operating system processes when using the Support Vector Machine (SVM) method. The dataset used has 100,000 data entries that have 33 attributes that indicate process activity such as CPU usage, memory, and context shifts. Data is divided into training data and test data, exploratory data analysis (EDA) to understand data characteristics, data preprocessing to clean and standardize attributes, feature selection based on correlation to reduce model complexity, and development and training of a classification model using SVM with a linear kernel. Using a confusion matrix and evaluation metrics such as accuracy, precision, recall, and F1 score, the model is evaluated. Test results show that the developed SVM model performed very well, with an accuracy of 99.57%, a precision of 99.76%, a recall of 99.38%, and an F1 score of 99.57%. This model also distinguished malware processes from normal processes with a very small number of misclassifications. The results indicate that SVM can perform malware detection based on the behavior of system processes quite well. This research can contribute to the development of automated security systems that can detect threats in real time and help strengthen system defenses against cyberattacks.
PENERAPAN FUZZY LOGIC UNTUK MEMPREDIKSI PENJUALAN MAKANAN DI USAHA SHAKEEL KEBAB MENGGUNAKAN METODE MAMDANI Nasaruddin, Andira; Maslan, Andi
Computer Science and Industrial Engineering Vol 13 No 4 (2025): Comasie Vol 13 No 4
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i4.10581

Abstract

Particularly in the food industry, like Shakeel Kebab MSME, sales are a crucial performance metric. The lack of a data-driven method to predict future sales trends is one of the main issues. Using historical sales data from 2022 to 2024, this analysis predicts food sales using the Mamdani fuzzy logic method. Fuzzification, rule formation, inference, and defuzzification are all steps in the research process, and MATLAB software is used for implementation. The outcomes show that the fuzzy system can correctly identify sales trends. For example, the system generated a defuzzification value of 91.67 in September 2024, and consistently 80 in November and December. These outcomes demonstrate that the Mamdani fuzzy method is effective in supporting predictive decision-making for food sales, especially for small business owners.