Ferry Astika Saputra

Fraud in healthcare claims represents a critical challenge that undermines the efficiency and sustainability of Indonesia's National Health Insurance (JKN) system. This study contributes a large-scale comparative evaluation of five machine learning algorithms for classifying potential fraud in BPJS Kesehatan claims, namely Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest (RF), XGBoost + SMOTE, and Logistic Regression (LR). A novelty of this study lies in applying the SMOTE technique in conjunction with XGBoost to address class imbalance in fraud datasets. The dataset consists of over 200,000 claim entries, which have undergone data cleaning, normalization, and feature selection. Performance was assessed using precision, recall on fraud class (positive), f1-score, accuracy, and confusion matrix visualizations to capture classification error distribution. Results demonstrate that ANN and XGBoost + SMOTE are superior in detecting fraudulent claims with high recall, while SVM achieves the most balanced performance in terms of precision and sensitivity. Random Forest and Logistic Regression serve as moderate baselines but are less effective in identifying complex fraud patterns. This study contributes to the development of a more adaptive and efficient fraud detection system based on machine learning, with practical implications for strengthening the automatic verification system used by BPJS Kesehatan.

Digitalization is an important step in improving the efficiency of public services, particularly in managing queues in government institutions such as sub-district offices. Kelurahan Gebang Putih Surabaya faces significant challenges in managing its manual queue system, which often results in discomfort for the public due to long waiting times, exceeding 5 minutes. This reduces public satisfaction and causes inefficiencies in the queue process. To address this issue, this study aims to develop and implement a digital queue system that can be accessed both online and on-site, using the User-Centered Design (UCD) approach. This approach ensures that every aspect of the system's design and development focuses on user needs through an iterative process, where the design is adjusted based on direct feedback from users. The proposed solution in this study includes the creation of a mobile and website-based queue system, allowing the public to easily take a queue number online and also enabling quick on-site queueing with a wait time of less than 10 seconds. Another advantage of this system is its automated reporting feature, which facilitates documentation and queue reports, thereby accelerating administration and monitoring to the city government. The results show that the implementation of this system significantly reduces the queue-taking time from over 5 minutes to less than 10 seconds, successfully transforming the manual system into a more efficient digital system, and streamlining the reporting process to the government, which in turn improves the quality and satisfaction of public services.

Tajwid is an important science that regulates the way of reading the verses of the Al-Qur’an properly. Learning Tajwid means knowing the meaning that corresponds to the correct recitation. Learning to read the Al-Qur’an tends to be done traditionally in a place of learning or by calling a teacher to the house. Learning in this way has some drawbacks, such as the limited availability of trained and competent teachers because not all areas have sufficient access to these teachers. Dependence on schedules and locations can be a constraint for students with limited mobility or busy schedules. The role of the teacher is still important in learning tajwid, especially in providing effective explanations, guidance, and feedback. However, to overcome these shortcomings, integration with independent and technology-based learning methods can help improve the accessibility, flexibility, and quality of tajwid learning. The classification of tajwid laws using image processing allows users to see the results of inputting images of verses of the Al-Qur’an into the type of detected nun sukun tajwid and how to recite it. The initial stage of this system in detecting tajwid laws from uploaded images is the input of images by users, which can be done in two ways, namely by directly taking pictures using a smartphone camera or uploading images from the gallery. This is followed by the OCR process to detect the Arabic text contained in the image and provide diacritics for that Arabic text. Finally, letter classification is carried out after nun sukun and classification of tajwid laws contained in accordance with the detected letters after nun sukun. This system has an accuracy rate of 92.18% from the classification results that have been carried out.

Handling Missing Value dengan Pendekatan Regresi pada Dataset Akuakultur Berukuran Kecil

Snort is a well-known, signature-based network intrusion detection system (NIDS). The Snort sensor must be placed within the same physical network, and the defense centers in the typical NIDS architecture offer limited network coverage, especially for remote networks with a restricted bandwidth and network policy. Additionally, the growing number of sensor instances, followed by a quick increase in log data volume, has caused the present system to face big data challenges. This research paper proposes a novel design for a cloud-based Snort NIDS using containers and implementing big data in the defense center to overcome these problems. Our design consists of Docker as the sensor’s platform, Apache Kafka, as the distributed messaging system, and big data technology orchestrated on lambda architecture. We conducted experiments to measure sensor deployment, optimum message delivery from the sensors to the defense center, aggregation speed, and efficiency in the data-processing performance of the defense center. We successfully developed a cloud-based Snort NIDS and found the optimum method for message-delivery from the sensor to the defense center. We also succeeded in developing the dashboard and attack maps to display the attack statistics and visualize the attacks. Our first design is reported to implement the big data architecture, namely, lambda architecture, as the defense center and utilize rapid deployment of Snort NIDS using Docker technology as the network security monitoring platform.

Internet attacks are a frequent occurrence and the incidence is always increasing every year, therefore Matagaruda project is built to monitor and analyze internet attacks using IDS (Intrusion Detection System). Unfortunately, the Matagaruda project has lacked in the absence of trend analysis and spatiotemporal analysis. It causes difficulties to get information about the usual seasonal attacks, then which sector is the most attacked and also the country or territory where the internet attack originated. Due to the number of unknown clusters, this paper proposes a new method of automatic bisecting K-means with the average of SSE is 93 percents better than K-means and bisecting K-means. The usage of big spark data is highly scalable for processing massive data attack.

Smart home is a concept in which all electronic equipment in a home can be monitored and controlled remotely. The main problem in the implementation of a smart home is a relatively expensive cost, the lack of centralized control system so that most nodes in a smart home will work independently and connectivity to the internet must always be there to activate a smart home because each node connected to the server on the internet. In this paper, we will present a smart home system using Arduino as node and raspberry pi as controller (local server) for smart home node, in this system also enable smart home can be accessed locally (intranet) and internet.

To date, malware caused by botnet activities is one of the most serious cybersecurity threats faced by internet communities. Researchers have proposed data-mining-based IDS as an alternative solution to misuse-based IDS and anomaly-based IDS to detect botnet activities. In this paper, we propose a new method that improves IDS performance to detect botnets. Our method combines two statistical methods, namely low variance filter and Pearson correlation filter, in the feature-selection process. To prove our method can increase the performance of a data-mining-based IDS, we use accuracy and computational time as parameters. A benchmark intrusion dataset (ISCX2017) is used to evaluate our work. Thus, our method reduces the number of features to be processed by the IDS from 77 to 15. Although the number of features decreases, it does not significantly change the accuracy. The computational time is decreased from 71 seconds to 5.6 seconds.

TOR (The Onion Router) TOR (The Onion Router) has been a very popular anonymous proxy service. Since its first usage, TOR has been improved and become a very big network consisting more than 7000 relays. Beside used by journalist, activist, and writer as a tool for their freedom of speech, its highly anonymous service is also used by bot-nets, malware, distributed denial of service attacks, hidden services that sells illegal things, spams, and many more. This paper will explain about a TOR usage detection system by using deep packet inspection to extract and analyze its network traffic. The result of the analysis will be used as a parameter for a proxy server to block TOR traffic in the network. Using this network, detection, and blocking design, we can block the Onion Router Traffic originated from TOR browser.