Publication Search

Work accidents are one of the problems that often occur in companies/agencies where accidents happen to employees/workers and cause serious physical injuries. BPJS Employment is an insurance program that is trusted by agencies/companies by claiming Work Accident Insurance (JKK) which can help in easing the financial burden on families as well as initial efforts to handle cases of work accidents that occur. The main aim of this research is to assist companies in handling work accident cases that occur. The data used in this research includes work accident reports collected from the Bpjs Ketenagakerjaan Stabat office. The method used is the clustering method with the K-means algorithm, which was chosen because of its ability to group fairly large amounts of data with fast and efficient computing time. By using the clustering method that has been used to process work accident case data at Bpjs Ketenagakerjaan in Stabat, we can produce new information from the 672 data that have been tested. From 672 work accident case data at Bpjs Employment in Stabat, 3 clusters were obtained with the results of Cluster 1 having 2 work accident case data, Cluster 2 having 9 work accident case data and Cluster 3 having 9 work accident case data.

The development of quantum computing presents new challenges to the security of data stored and processed by today's computer systems. Quantum computers have the ability to perform calculations at very high speeds, which could threaten the security of currently used encryption algorithms. Therefore, steps are needed to design and implement an operating system that is able to protect data from quantum computing threats. Ubuntu Linux version 22.04, as one of the leading open source Linux distributions, offers high-level security features. To face the era of quantum computing, it is necessary to carry out special development and implementation of this operating system. This research aims to improve the security of the Ubuntu Linux operating system version 22.04 so that it can withstand quantum computing attacks by designing and implementing a quantum-resistant cryptography protocol and testing the security and performance of the resulting system. This research method uses a qualitative approach and research and development (R&D) with literature studies. The research results show that the integration between Liboqs and OpenSSL on Linux Ubuntu 22.04 successfully implements a cryptographic algorithm that is resistant to quantum computing. Although there is a slight performance increase due to the additional overhead of the quantum algorithm, the security of the system in protecting data from quantum computing attacks is proven to be well maintained.    

Fingerprint recognition is a popular biometric technology due to its unique properties and high accuracy rate. Fingerprint recognition systems generally use fingerprint image representations, such as grayscale images, phase images, skeleton images, and minutiae. In this research, fingerprint image pre-processing is performed using Gaussian Blur, Median Blur, Thresholding, Otsu Thresholding, Thinning with Guo-Hall algorithm, and Minutiae Detection. Minutiae detection produces 426 termination points and 459 bifurcation points. The results of the pre-processing and minutiae detection were then used for minutiae matching on 5 different images. Minutiae matching produces varying degrees of similarity with a high level of accuracy, reaching an average accuracy of 88.80%.

To compete with other stores, store owners need to design various strategies, one of which is understanding customer purchase patterns. This article examines the Squeezer algorithm and compares the performance of the Apriori and FP-Growth algorithms in forming customer purchase association patterns that can be used as a reference for store owners in planning sales strategies. The data mining process was carried out using Association Rules and Clustering methods. A total of 1256 sales transaction data samples were analyzed to understand the association patterns produced by each method. Based on the test results with a minimum support of 0.2 and a confidence of 0.6, the Apriori algorithm produced 194 association rules with a total rule strength of 1.16. Meanwhile, the FP-Growth algorithm produced 52 association rules with the same total rule strength of 1.16. The Clustering Method resulted in 7 clusters with a similarity value of 0.06322. After comparison, the FP-Growth algorithm proved to have better performance in generating association rules compared to the Apriori algorithm.

This research aims to predict customer churn in a telecommunications company using Logistic Regression (LR) and Gradient Boosting Classifier (GBC) algorithms. Customer churn poses a significant challenge as acquiring new customers is costlier than retaining existing ones. The dataset from Kaggle comprises 7043 records and 21 attributes. The process includes data pre-processing, cleaning, transformation, and normalization using a Min-Max Scaler. The data is split into features (X) and target (y), then divided into training and testing sets with an 80:20 ratio. Both models were trained and evaluated using a confusion matrix. Results show that the GBC model outperforms the LR model, with an accuracy of 83% compared to LR's 81%. This study demonstrates the effectiveness of GBC in predicting customer churn.

Grouping is a process or activity to develop a system that is more organized and easy to understand, making it easier to analyze, identify or manage data and can also be used to explore information so that it becomes new knowledge for anyone who wants to obtain it. and in this case the information we want to explore is about MSME data in Binjai City. Namely, it is difficult to know how to identify existing business development patterns, whether they are not yet developed, less developed, already developed, and very developed. Offline and online promotions have not been optimal in increasing the growth and change of a business from time to time. And most MSMEs still don't understand how to market their products and services effectively and efficiently. MSMEs are one of the most numerous community business groups in Binjai City. To obtain this information, one solution that can be implemented is by utilizing data mining using input data in the form of Binjai City MSME data. This data will be processed using the clustering method with the k-means algorithm using MSME business type variables, sales type variables and development pattern variables. .Based on the results of grouping Binjai City MSMEs using the K-Means Clustering Method from 20 grouped data, 3 clusters and 2 iterations were obtained where cluster 1 contained 4 data and was located in the MSME business type group, namely the businesses included in this cluster were businesses in the field of Fashion, for the sales type group, uses online and offline types, and for business development patterns, it has a development pattern that has developed. cluster 2 has 11 and is located in the MSME business type group, namely the businesses included in this cluster are businesses in the culinary sector, for the sales type group the offline type is used, and for the business development pattern it has a development pattern that has developed. and cluster 3 has 5 data and is located in the MSME business type group, namely the businesses included in this cluster are businesses in the culinary sector, for the sales type group it is using the offline type, and for the business development pattern it has a less developed development pattern. so it can be concluded that the pattern of business development of Binjai City MSMEs produces relevant data so as to produce designs that can be used for this research.

This research aims to analyze the performance of various CPU scheduling algorithms in increasing the responsiveness of the Android operating system. Using algorithms such as First Come First Served (FCFS), Shortest Job First (SJF), Shortest Remaining Time First (SRTF), and Round Robin, this study evaluates the advantages and disadvantages of each in terms of average waiting time, throughput, and power consumption. Research methods include literature study, algorithm selection and implementation, as well as data testing and analysis. The research results show that choosing the right scheduling algorithm can increase system efficiency and responsiveness, as well as provide recommendations for Android operating system developers and the application developer community. It is hoped that these findings will help in determining the optimal solution for improving the performance of the Android operating system.

This study compares the performance of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) algorithms in detecting and classifying smoking activities. Using an image dataset containing two classes, Smoking and Non-Smoking, this research implements transfer learning using the InceptionResNetV2 model for CNN and the SVM method. Evaluation results show that CNN has higher accuracy compared to SVM in detecting smoking activities. This research contributes to the development of surveillance systems for smoke-free areas in smart cities.

Zakat fitrah is an obligation for every capable Muslim to purify oneself and one's wealth. Determining the priority of zakat fitrah recipients often becomes a challenge due to various factors that must be considered. This research aims to use the Fuzzy Simple Additive Weighting (F-SAW) algorithm as a decision support tool in determining the priority for distributing zakat fitrah. By using the F-SAW method, it is hoped that the prioritization process can be more objective and efficient..

Cats (Felis catus) are a type of carnivorous mammal from the Felidae family that was domesticated and has been one of the animals that has mingled with humans since time immemorial. Domestic cats are broadly divided into 2 types, namely village cats and purebred cats. Purebred cats have quite a varied number of types. Therefore, confusion often occurs in determining the type or breed of cat. Meanwhile, in practice, each race does not have the same treatment (especially in the aspect of care). In digital image processing, Machine Learning and Deep Learning are the main aspects in the process of applying technology that can overcome this problem, so research related to this problem was designed. This research was conducted to add insight for further research in a more sophisticated and effective image recognition process. In the experiments carried out in this research, the SVM, KNN, and CNN methods were tested with the Xception and EfficientNet-B1 architectures. Based on the final results obtained from this test, the CNN method with the Xception architecture is the best model. By using fine-tuning and a learning-rate of 1e-5, this method produces a micro average value of 0.974, on a cat breed image dataset of 13 classes and 7800 images. Meanwhile, the method that produces the fastest ETA Training and Testing is obtained by the KNN method, with an ETA Training time of 0.194 seconds, and an ETA Testing time of 1.782 seconds.      

This research aims to classify news headlines into clickbait and non-clickbait using the Multinomial Naive Bayes method. The data used comes from the dataset CLICK-ID: A Novel Dataset for Indonesian Clickbait Headlines. The research process involves stages of data collection, preprocessing, feature extraction, model training, model evaluation, and result analysis. The test results show that the Multinomial Naive Bayes algorithm consistently produces an accuracy rate of around 78%. Optimization using Grid Search did not result in an accuracy improvement. However, there was an improvement in the recall value for the non-clickbait class from 76% to 80%. The best parameter found was an alpha of 0.15. Therefore, the Multinomial Naive Bayes algorithm can be effectively used to address the problem of classifying clickbait news headlines, with the potential to contribute to clickbait prevention efforts in the future.

This paper explores the Time-Based One-Time Password (TOTP) authentication mechanism enhanced with lightweight cryptographic algorithms, presenting it as an advanced solution to the limitations of traditional OTP systems. There are a lot of applications and systems where this mechanism is applied. For example, bank applications, e-commerce websites, access control system, healthcare system, etc. TOTP generates dynamic, time-sensitive passwords using the current time and a secret key processed through a cryptographic hash function, significantly improving security by reducing vulnerabilities to code reused and interception. The adoption of lightweight algorithms ensures that TOTP can be efficiently implemented on resource-constrained devices, such as those on the Internet of Things (IoT) ecosystem. Despite its benefits, TOTP faces challenges including synchronization issues between client devices and servers, and a trade-off between computational efficiency and security strength. This paper discusses the implications of these challenges and evaluates how TOTP, with appropriate design considerations, can provide a robust, secure, and efficient authentication method suitable for various applications, from digital banking to IoT environments.

With the rapid expansion of the Industrial Internet of Things (IIoT), integrating devices, machines, and systems to optimize operations and enable data-driven decision-making, ensuring robust security measures is essential. While blockchain has shown the potential to upgrade traditional authentication methods in IIoT environments, vulnerabilities persist. This paper introduces two innovative methods to enhance blockchain-based authentication in IIoT: first, integrating AI-driven anomaly and threat detection into the blockchain authentication scheme; second, implementing Ethereum smart contracts for enhanced authentication with a two-factor authentication (2FA) system and GFE algorithms. By combining AI for anomaly detection with decentralized smart contracts and blockchain-based 2FA, and leveraging GFE algorithms to enhance blockchain capabilities, the proposed scheme aims to significantly fortify security measures. This integration offers a resilient defense against evolving threats, ensuring transparency, adaptability, and heightened security in IIoT applications.

Adequate provision of drinking water in quantity, quality, and continuity is needed to realize a healthy and productive society. A well-managed Drinking Water Supply System (SPAM) is essential to meet this need. Based on Government Regulation Number 122 of 2015, the implementation of SPAM involves the development and management of drinking water which is the responsibility of the local government and PUDAM as the implementer. The main challenges faced by PUDAM include the high level of water loss or Non-Revenue Water (NRW), which reaches 40% in Indonesia. One of the efforts to reduce the NRW level at PUDAM Banyuwangi Regency in the Kalipuro District area is to detect abnormal consumption in customer drinking water consumption. This study uses the Deep Q Network and Local Outlier Factor algorithms to detect anomalies in drinking water consumption, with the aim of comparing the performance of the two algorithms in identifying abnormal consumption patterns at PUDAM Banyuwangi Regency. The results of the study indicate that the Local Outlier Factor algorithm is more suitable for anomaly detection as evidenced by the absence of detection errors and an F1-Score value of 36%.

This thesis examines the critical role of education in societal transformation, drawing on Werner Jaeger's assertion that the state is the primary agent of education and cultural evolution. In "Paideia," Jaeger emphasizes the state's role in shaping individual development and humanity's essence through educational systems. The thesis introduces the concept of a Ministry of Generosity, a state initiative aimed at fostering a Culture of Generosity as a formal measure of societal happiness. This ministry would integrate the Pedagogy of Generosity into education, promoting prosperity and compassion across economic and educational spheres. The thesis explores the General Theory of Generosity and its practical application in social and educational technology, highlighting the pioneering work of Dr. hc Vicente Pironti, founder of Humaniza. It examines how these technologies can drive cultural transformation and set a global standard for education and societal well-being. Additionally, the thesis addresses the development of humanized algorithms within the Artificial Intelligence Universe, incorporating ethical parameters and compassion for humans, sentient beings, and the environment. These humanized algorithms are presented as a crucial element in realizing the new Culture of Generosity.  

High voltage deviation, State of charge (SOCs) divergence, and inappropriate load/power sharing are some challenges that DC microgrids face. These problems can be rectified easily if the control algorithm is designed based on the other units' data. However, utilization of communication links has some disadvantages which make them improper in many cases. Regarding that, in this paper, a novel communication-free control method is presented. In this method, the droop gain is divided into two parts. The first part of the droop gain is selected according to the line resistance in such a way, that the effect of line resistance on current sharing is omitted, while the second part is considered for balancing SOCs. Regarding that, it is defined as a function of SOC such that the higher SOC unit injects more and absorbs less current. Comparing the simulation results of the proposed method with other methods proves that the proposed method can balance SOCs and reduce the DC bus voltage deviation like the SOC-based method. Besides, it can share current properly like the virtual resistance method.

The business of selling coffee in the world is growing more easily and quickly with the provision of a place which is usually called a cafe or shop. One of them is the Titik Hitam Nalar cafe in Jakarta, but the ordering process with customers takes longer to wait for orders and customer payments that are not neatly arranged create conditions that’s are not conducive, resulting in continuous negative criticism. Therefore, an application is needed that helps employees work in every part, both in terms of ordering, manufacturing, and payments, using the FIFO algorithm which focuses on which services are prioritized first in order to reduce negative sentiment from customers. The Android-based application was created by involving every design phase, making it easier for customers and employees to provide a service facility that works well and is suitable for use.  

The insurance business within an insurance company offers insurance products owned by the insurance company. In every insurance product there is a premium payment and the premium is the income of an insurance company at the rate of the amount insured. The problem that PT BNI Life Insurance has is that there are many stops in premium payments such as policy redemptions due to errors in the benefits received or incorrect selection of the insurance product, this can reduce the achievement of targets for an insurance company. The aim of this research is to find out the best classification algorithm compared between K-Nearest Neighbor and Naive Bayes to predict the type of insurance product that customers will choose. In this research, data mining methods are applied to compare two different methods, namely the K-Nearest Neighbor method and the Naïve Bayes method. The level of accuracy results for the K-Nearest Neighbor method is 80% and the Naïve Bayes method is 70.53%, which means that the K-Nearest Neighbor method is the best method to apply to an insurance product classification system based on the demographics of prospective customers.

The Industrial Internet of Things (IIoT) has revolutionized industrial processes, offering automation and data-driven decision-making. However, this interconnectedness brings new security challenges, especially in crucial infrastructure sectors. Traditional security measures are inadequate, leading to the exploration of innovative solutions. Blockchain technology has emerged as a promising solution due to its decentralized and immutable nature. This paper proposes a Hybrid Blockchain-Based Authentication Mechanism for IIoT, combining Delegated Proof of Stake (DPoS) and Elliptic Curve Cryptography (ECC). The hybrid architecture utilizes public and private blockchains to ensure scalability, efficiency, and security. Lightweight consensus algorithms, DPoS, are incorporated to optimize performance, while ECC provides efficient cryptographic techniques suitable for IIoT environments. An interoperable framework facilitates seamless integration with existing infrastructure, ensuring regulatory compliance and compatibility. Decentralized identity management further enhances security and privacy. Results and analysis demonstrate the effectiveness of the proposed solution, positioning hybrid blockchain architecture as the most suitable approach for enhancing security in IIoT environments.

This research analyzes the use of the Prim Algorithm in determining priority routes for package delivery by express service couriers. Through case studies, this research evaluates the efficiency of package delivery by considering delivery priority and the distance the courier will travel. The research results show that the Prim Algorithm is effective in minimizing delivery loads by connecting priority delivery points with minimal travel distance. This research method uses the Prim Algorithm to create a delivery route graph that connects all priority delivery points with a minimum travel distance, with data including the location of the delivery point, priority and distance between locations. The results show that the Prim Algorithm is effective in minimizing delivery load by generating optimal routes, allowing couriers to prioritize package delivery efficiently. This proves the important role of the Prim Algorithm in package delivery strategies for express service couriers.