Journal of Computer Networks, Architecture and High Performance Computing
Not a member yet
473 research outputs found
Sort by
Comparative Analysis of Earthquake Prediction with SVM, Naïve Bayes, and K-Means Models: Comparative Analysis of Earthquake Prediction with SVM, Naïve Bayes, and K-Means Models
No full textEarthquakes are natural disasters with significant impacts on people and the environment, so effective methods for prediction are needed to improve preparedness and risk mitigation. This study analyzes the performance of three algorithms Support Vector Machine (SVM), Naïve Bayes, and K-Means in predicting earthquakes in Indonesia using a dataset containing 4,645 historical data from BMKG processed through preprocessing, data separation, analysis, and performance evaluation with RapidMiner tools. The results show that SVM has the best performance with 99.87% accuracy, 99.83% precision, and 95.61% recall, making it highly relevant for earthquake prediction. Naïve Bayes achieved 90.31% accuracy and 95.08% recall, but the low precision (57.24%) shows the limitations of this model. K-Means successfully clusters earthquakes into two categories: small (3,661 data) and large (55 data) earthquakes, with a Davies-Bouldin Index value of 0.579, reflecting good clustering quality. Based on these results, SVM is recommended as a superior earthquake prediction model, while Naïve Bayes and K-Means are more suitable for additional analysis. This approach confirms the potential of machine learning algorithms in supporting future earthquake risk mitigation
Implementation of WSN and IoT to Monitor and Control Villa Electronic Equipment in Blankspot Areas
Full text linkMaintaining a remote villa in a blank spot area presents challenges in ensuring optimal environmental conditions without the direct presence of the owner. This study aims to develop an Internet of Things (IoT)-based Wireless Sensor Network (WSN) system using the XBee S2C module with the Zigbee remote monitoring and control protocol. This system utilizes temperature, humidity, lighting, and water level sensors connected to electronic device controls such as lights, fans, and water pumps. Sensor Nodes are placed in the villa to collect data, while Coordinator Nodes are located in areas with internet access to upload data to the Thingspeak platform. Data is visualized through an interactive web interface that allows for remote control up to 1.03 km. The test results show a data transmission success rate of 100% with an average control response time of 6.5 and 9 seconds. This system offers the best solution for managing a villa in a blank spot area, making it easy for owners to monitor and control electronic equipment in real-time. This research contributes to developing WSN and IoT technologies, especially for applications in remote areas with website platform
CRYPTOGRAPHY OF CHACHA20 and RSA ALGORITHMS for TEXT SECURITY
Full text linkThe purpose of this study is to apply the ChaCha20 and RSA cryptographic algorithms to enhance text security and safeguard data from unauthorized access, data breaches, and cyberattacks such as man-in-the-middle or replay attacks. ChaCha20, a symmetric encryption algorithm, is employed for generating efficient and secure keystreams, while RSA, an asymmetric algorithm, is used for encrypting numeric keys or messages. The integration of these two algorithms ensures robust data protection from various digital threats. The choice of this title stems from the growing urgency to prioritize data security in the digital era, especially given the increasing incidents of data leaks that often lead to significant consequences. This research focuses on analyzing the implementation of both algorithms in encryption and decryption processes, as well as evaluating their effectiveness in preserving data confidentiality and integrity. The findings of this study demonstrate that the ChaCha20 and RSA implementations effectively secure data, with the encryption and decryption processes functioning as intended. To further validate the system’s robustness, simulated attacks were conducted, and the results confirmed the system's ability to prevent unauthorized access. This research not only contributes to the development of reliable data security solutions but also highlights opportunities for future improvements. Enhancing algorithm efficiency and optimizing encryption runtime are potential areas for further exploration. By addressing these challenges, the study aims to pave the way for more robust and efficient cryptographic solutions in the evolving landscape of digital security
Wireless Network Quality Analysis Using RMA and RSSI Methods at BPKAD Berau District
Full text linkWireless networks are now essential in supporting government operations, including at the BPKAD office in the Berau district. However, problems like unstable connections and slow speeds often arise as obstacles. This study aims to evaluate the quality of the wireless network in the BPKAD asset room of the Berau district by applying the Reliability, Maintainability, and Availability (RMA) and Received Signal Strength Indication (RSSI). Quantitative research method. The research population is all wireless access points (Wi-Fi) spread across the BPKAD office. The research sample is the asset field room. Data collection methods through observation, RMA measurement, and RSSI measurement. The data that has been collected will be analyzed using the RMA (Reliability, Maintainability, and Availability) and RSSI (Received Signal Strength Indication) methods. The results obtained show that most of the measurement days recorded network availability (availability) of 100%. However, there was a decrease on August 26, 2024 (99.58%) and September 3, 2024 (97.05%) due to the increased frequency of system failures. The analysis of RSSI showed that the signal quality fell into the excellent category with an average of -36.6 dBm. However, a decrease was recorded on August 30, 2024, with a value of -44 dBm. The results of this study underscore the importance of regular maintenance and upgrades to the network infrastructure in anticipation of possible deterioration. Recommendations include improving security systems, hardware updates, and technical training for IT staff to strengthen the network's support of activities at the BPKAD Office of Berau Regency
Islamic Sound Recognition Using MFCC and SVM: Case Study on Takbir and Sholawat
Full text linkThis study aims to develop an identification model for Islamic religious sounds, specifically Takbir and Sholawat pronunciations, using audio signal processing and machine learning techniques. With the increasing need for intelligent systems capable of recognizing speech patterns in religious contexts, the implementation of reliable audio classification methods becomes essential. This research utilizes Mel-Frequency Cepstral Coefficients (MFCC) to extract relevant spectral features from audio samples, representing the unique characteristics of Takbir and Sholawat utterances. The dataset consists of 300 audio recordings, evenly distributed between the two classes. Each audio file is preprocessed and converted into a fixed-length MFCC feature vector, which is then labeled accordingly. The feature vectors are split into training and testing sets using an 70:30 ratio. A Support Vector Machine (SVM) classifier is trained using the training data to recognize the distinction between Takbir and Sholawat patterns based on their acoustic signatures. Performance evaluation is carried out using accuracy, precision, recall, and F1-score metrics. The dataset used consists of 300 audio recordings with a division of 200 takbir recordings and 100 sholawat recordings. The MFCC feature extraction process uses 13 coefficients with optimized parameters to capture discriminative spectral characteristics. As a baseline, a Support Vector Machine (SVM) implementation with Radial Basis Function (RBF) kernel was performed for performance comparison
Optimization of the K-Means Method and Davies-Bouldin Index (DBI) Technique in Mapping Spotify's Most Popular Songs Based on Mood
Full text linkSpotify is a leading music streaming platform that offers a wide variety of songs with audio characteristics capable of influencing listeners' moods. This study aims to optimize the K-Means method to cluster popular songs based on users’ moods, with the support of the Davies-Bouldin Index (DBI) technique to determine the optimal number of clusters. The dataset was obtained from Kaggle, utilizing audio features such as danceability, valence, energy, and others as the basis for clustering. The results show that the implementation of K-Means optimized with DBI produces more accurate clustering, as indicated by lower DBI values. This approach has the potential to enhance mood-based music recommendation systems, enriching the user experience
User Experience Analysis of Employee Attendance List on Talent Application with Heuristic Evaluation Method
Full text linkThe development of digital technology has influenced human resource management systems, particularly in the management of employee attendance records. One of the most widely used applications in Indonesia is Mekari Talenta, a cloud-based HRIS platform with features ranging from online attendance, leave, overtime, to payroll integration. Despite its high rating on the Google Play Store, there are still a number of complaints regarding user experience, such as confusing navigation, an unintuitive interface, and difficulty in accessing certain features. This study aims to analyze the user experience on the Talenta application using the Heuristic Evaluation method based on Nielsen's 10 principles. Data collection was conducted through questionnaires and processed using SPSS for validity, reliability, and descriptive percentage analysis. The results of the study show that most of the Heuristic Evaluation principles scored in the "Good" category, especially in terms of visibility of system status, consistency and standards, and aesthetic and minimalist design. However, there are still weaknesses in terms of help and documentation as well as error prevention that need improvement. These findings recommend that developers improve the interface display, clarify the help documentation, and optimize the error prevention feature so that the application can provide a more optimal user experience. Further research is recommended using other evaluation methods, such as the User Experience Questionnaire (UEQ) or in-depth interviews, to obtain a more comprehensive picture
Development of Medical Record System Posyandu Taman Salak with Waterfall Method
Full text linkOne form of ICT utilization in the health sector is a digital-based health application. Health applications are included in the National Health System (SKN). Posyandu is a form of health service effort that is managed by, for and from the community with the aim of facilitating access to basic health services for mothers and children. Posyandu Taman Salak is one of the health facilities available in Madiun City. The process of recording and processing data on all Posyandu Taman Salak activities is still done by handwriting in a report book. This causes cadres to have difficulty monitoring children's growth and development and are overwhelmed in preparing reports to the integrated health post supervisors. Based on the description of the problems at the Taman Salak Posyandu, it is necessary to develop a Posyandu medical record system to make it easier for Posyandu cadres to process Posyandu data, monitor child growth and development and make reports. The purpose of this study is to design and build a Posyandu Taman Salak medical record system using the Waterfall system development modeling. The design stages use DFD and ERD. The system has been completed based on the website and has conducted functional system testing with the result that all system functions can be ru
INFLATION RATE ESTIMATION USING HYBRID ARIMA-ADAPTIVE NEURO FUZZY INFERENCE SYSTEM METHOD
Full text linkInflation is an important issue that affects the economic stability of a country or region. Unstable inflation will have a negative impact on society, especially on commodity prices including food and energy. Inflation is classified as a time series and will usually recur over time, five years later, or ten years later. , the problem of inflation needs to be studied and analyzed using existing approaches in time series. This research focuses on the application of Hybrid ARIMA-Adaptive Neuro Fuzzy Inference System method for inflation estimation, which is expected to provide a more accurate picture of the price fluctuations of basic needs in North Sumatra. Overall, the results show that the ability of the Hybrid ARIMA-Adaptive Neuro Fuzzy Inference System method in estimating inflation values is quite good with the results tending to be stable and not experiencing many sharp fluctuations. The inflation value is in the range of around -2.69 to -2.73 throughout the predicted period. However, a continuous negative number indicates a price decline or economic pressure, so further analysis or development is needed to understand the cause. The estimation results may help to maintain stability or make desired changes in the future
Application of Data Mining with C5.0 Algorithm to Recommend Prosperous Family Card (KKS) Recipients
No full textPoverty is a social problem that still often occurs in various regions in Indonesia, including in Silau Laut District which consists of several villages such as Bangun Sari, Silo Bonto, Silo Lama, Lubuk Palas, and Silo Baru. Although the area is quite large, there are still many families who are classified as poor and unable to meet their basic needs. To overcome this, the government launched the Prosperous Family Card (KKS) program as a form of social assistance. However, the process of determining prospective KKS recipients still faces various obstacles, such as a random selection method based on data sent by each village to the central government. This raises concerns about the inaccuracy of the target in the distribution of aid, so that the aid is not received by families who really need it. In addition, a lot of data has not been utilized optimally in the selection process. Therefore, this study aims to design a website-based information system that can help Silau Laut District in providing recommendations for prospective KKS assistance recipients by utilizing data mining techniques. The algorithm used is C5.0, because it is able to produce a decision tree with high accuracy, while the system development method used is Rapid Application Development (RAD) to accelerate the system development process. The result of this research is an information system that can process community data and provide recommendations for prospective KKS assistance recipients in a more objective and targeted manner in the next period