Journal of Computer Networks, Architecture and High Performance Computing
Not a member yet
473 research outputs found
Sort by
Simple Additive Weighting to Determine The Best Employee in a Freight Forwarding and Logistics Company
Get PDFThe problem is that there is no method used to determine the best employee in the company based on the criteria set by the company. The purpose of this research is to propose simple additive weighting as a method for finding the best employees according to the weighting carried out. To make decisions, there are several criteria and criteria weights that are needed as a measuring tool to assess employees who will be promoted, attendance, QSM, Quiz, leading. Period of work and team work. The weight value of each criterion is attendance 0.20, QSM 0.25, Quiz 0.15, leading 0.20, tenure 0.10 and team work 0.10. Quality service management (QSM) if sub criteria < 200 QSM value 1, sub criteria 201 - 300 QSM value 2, sub criteria 301 - 400 QSM value 3, sub criteria 401 - 500 QSM value 4, sub criteria 501 - 600 QSM value 5. The results of the analysis with the saw method obtained two employees who got the highest score who had the right to be promoted for promotion with a value of 84.25 and 82.25. the conclusion is that the SAW method is influential in supporting and facilitating decision making to determine promoted employees
Design of Mask Detection Application Using Tensorflow Lite based on Android Mobile
Get PDFA mask is a type of personal protective equipment (PPE) that is essential for protecting the nose and mouth from contamination by droplets or airborne particles. The use of masks became highly popular during the Covid-19 pandemic, which began in December 2019 in China and peaked in Indonesia in 2020. Despite the pandemic subsiding and vaccinations increasing immunity, some companies still require masks to prevent the spread of illnesses such as colds and flu, especially in work processes that produce smoke, such as soldering and welding. To ensure employees comply with mask usage, effective supervision is necessary. Manual supervision is less efficient, thus a digital detection method is needed. This study developed a mask detection application using deep learning algorithms and the TensorFlow Lite framework on an Android platform. The application can detect mask usage with 100% accuracy at a distance of 1 to 5 meters. The system was tested under various lighting conditions and environments to ensure reliability. Additionally, the implementation of this technology can be extended to other public areas to ensure compliance with health protocols. This tool helps companies easily monitor and enforce mask-wearing discipline among employees, thereby enhancing workplace safety and health. Future work could explore the integration of this system with other health monitoring tools to create a comprehensive safety solution
Comparison of Automation Testing On Card Printer Project Using Playwright And Selenium Tools
Get PDFThe quality of the software is greatly determined by the testing phase, which involves various test cases that can be conducted through manual testing and automation testing. Manual testing is performed manually without using automation scripts, whereas automation testing is conducted using automation scripts. ABC is a company that operates globally in the field of access control, with the Card Printer being one of the menus used in access control. In the development process of this software, both manual and automation testing phases are carried out. The automation testing process employs the Selenium tool, which has proven to be time-consuming and poses challenges when running numerous test cases. This research aims to develop automation testing using Playwright to address the long execution time issue encountered with Selenium. The research utilizes the Card Printer project in the development of automation testing and adopts the Agile methodology. The result of developing automation testing using Playwright was successfully applied to 12 test cases. Additionally, the time analysis between Playwright and Selenium showed that Playwright has a total execution time of 4.9 minutes, which is faster compared to Selenium's total execution time of 8.3 minutes. With faster execution times, Playwright can be considered a tool in the development of automation testing
Cybersecurity Integration in Enterprise Architecture for IoT Infrastructure in Steel Manufacturing
Get PDFAs a result of the widespread adoption of Internet of Things technology in the steel manufacturing industry, there is an urgent requirement for the implementation of robust cybersecurity measures. The proliferation of IoT devices has caused a data explosion, which in turn has increased the risk of cyberattacks. The purpose of this research is to develop an enterprise architecture model that is capable of effectively managing cybersecurity risks on Internet of Things infrastructure in the steel manufacturing industry. This is a response to the urgent challenge that has been presented. The methodology utilized in this study is a rigorous qualitative approach, which involves the collection and analysis of data through interviews and literature reviews related to the topic. Following an in-depth analysis of the findings of the research, several important goals have been established. These goals include the identification of potential dangers, the reduction of potential risks, and the effective implementation of security controls. Within the context of the steel manufacturing industry, this research makes a significant contribution to the improvement of cybersecurity in Internet of Things infrastructure. In addition to identifying potential dangers and mitigating risks, the architecture model that has been proposed is about more than that. It offers a comprehensive and well-coordinated safety strategy, which guarantees a strong defense against cyber threats
Predictive Modeling of Preeclampsia Risk Using Random Forest Algorithm within a Machine Learning Framework
Get PDFPreeclampsia is a serious pregnancy complication characterized by high blood pressure, potentially leading to organ damage, making early risk prediction crucial to reducing maternal morbidity and mortality. This study aims to develop a preeclampsia risk prediction model using medical and clinical data from 80 patients at Rumah Bersalin Sadan. The data include demographic profiles, blood pressure, weight, maternal age, preeclampsia history, body mass index, number of previous pregnancies, as well as genetic and environmental factors. The dependent variable is the risk of preeclampsia, either as a binary outcome (yes/no) or as a continuous risk score. The predictive model was built using multivariate linear regression and the Random Forest algorithm. The results showed that the Random Forest model achieved an accuracy of 65.22%, with an F-statistic of 7.345 and a very small p-value (1.908e-06), indicating that the model effectively explains data variability. However, the low Kappa value suggests room for improvement through feature refinement, hyperparameter tuning, or exploring other algorithms. Although these findings suggest that Random Forest is a promising method, further evaluation and model optimization are needed to enhance predictive performance and determine whether this method is the most suitable for the dataset used
Analysis of Drug Sales Patterns in the Belawan Naval Hospital Pharmacy Using Apriori Algorithm
Get PDFHospital pharmacy plays an important role in ensuring drug availability and effective stock management. With the increasing number of drug redemptions, manual data management becomes inefficient and can lead to understocking or overstocking. Therefore, a method is needed that is able to automatically analyze drug sales patterns to improve stock management efficiency. One approach that can be used is the Apriori algorithm, an effective data mining technique for finding patterns in drug redemptions. This study aims to analyze drug redemption patterns at the Belawan Navy Hospital Pharmacy using the Apriori algorithm. The data used is drug redemption data. The Apriori algorithm is applied to find relationships between drug items that are often purchased together, so that it can provide useful insights in drug stock management. The results of the study showed that the Apriori algorithm successfully identified several significant drug redemption patterns. These patterns can be used to improve the efficiency of drug stock management and ensure timely drug availability, as well as reduce the risk of understocking or overstocking. The results of the study used logistic regression to predict discrete (binary) values from a column based on values from other columns and the accuracy obtained was 1.0 or 100%. This study concludes that the application of data mining with the Apriori algorithm can provide significant benefits in optimizing the management of drug stock redemption in hospital pharmacies
Utilizing Convolutional Neural Network for Learning Web-Based Braille Letter Classification System
Get PDFThis paper aims to facilitate prospective teachers and people who want to learn braille letters. The system designed is a website that will classify braille letters using the convolutional neural network (CNN) method with the activation functions used, namely ReLU and Softmax. In this research, the input is an image of braille letters with grayscale elements. The output of the data is a regular alphabet letter. Most of this research data consists of training and testing data, which is 2,722 pieces. The accuracy results obtained in the data training process using Max Pooling and epoch 30 for data is 92.15%, epoch 50 is 94.58%, and for training data with epoch 100 is 96.64%. The test results using the system produce an accuracy value of all braille letter image data of 92.30%. Furthermore, for better system development, it is recommended to use hyperparameter tuning to minimize classification uncertainty in braille letter images
Implementation Convolutional Neural Network for Visually Based Detection of Waste Types
Get PDFWaste detection plays an essential role in ensuring efficient waste management. Convolutional Neural Networks are used in visual waste detection to improve waste management. This study uses a data set that covers various categories of waste, such as plastic, paper, metal, glass, trash, and cardboard. Convolutional Neural Networks are created and trained with refined architecture to achieve precise classification results. During the model development stage, the focus is on utilizing transfer learning techniques to implement Convolutional Neural Networks. Utilizing pre-trained models will speed up and improve the learning process by enriching the representation of waste features. By using the information embedded in the trained model, the Convolutional Neural Network can differentiate the specific attributes of various waste categories more accurately. Utilizing transfer learning allows models to adapt to real-world scenarios, thereby improving their ability to generalize and accurately identify waste that may exhibit significant variation in appearance. Combining these methodologies enhances the ability to identify waste in diverse environmental conditions, facilitates efficient waste management, and can be adapted to contemporary needs in environmental remediation. The model evaluation shows satisfactory performance, with a recognition accuracy of about 73%. Additionally, experiments are conducted under authentic circumstances to assess the reliability of the system under realistic circumstances. This study provides a valuable contribution to the advancement of waste detection systems that can be integrated into waste management with optimal efficiency
The Impact of Big Data on Enterprise Architectural Design: A Conceptual Review
Get PDFA conceptual analysis of the impact of big data on enterprise architecture design is provided in this article. Within the framework of expanding digitalization, big data has emerged as a pivotal component in delineating the strategy and framework of organizations. The objective of this study is to investigate the ways in which big data can impact and facilitate the growth of efficient enterprise architecture. Qualitative analysis is the method utilized by researchers to comprehend the intricacies of the interaction between enterprise architecture and big data. This article examines several facets by conducting an extensive review of the literature, including the ways in which big data can facilitate the enhancement of analytical capabilities, innovation in business processes, and strategic decision-making. Emerging challenges, including data security, privacy, and the necessity for IT infrastructure adaptation, are also considered in this study. The outcomes of the review indicate that the implementation of big data in enterprise architecture may substantially alter business strategies and operations. These encompass enhanced system adaptability, customized service provision, and predictive functionalities. Nonetheless, these modifications necessitate modifications to privacy policies, risk management, and data governance. This study presents novel findings regarding the influence of big data on enterprise architecture and provides researchers and practitioners with recommendations for developing and executing successful big data strategies. This research thereby enhances the current body of literature and offers practical guidance in the field
Analysis of Machine Learning Classifiers for Speaker Identification: A Study on SVM, Random Forest, KNN, and Decision Tree
Get PDFThis study investigates the performance of machine learning classifiers in the domain of speaker identification, a pivotal component of modern digital security systems. With the burgeoning integration of voice-activated interfaces in technology, the demand for accurate and reliable speaker identification is paramount. This research provides a comprehensive comparison of four widely used classifiers: Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), and Decision Tree (DT). Utilizing the LibriSpeech dataset, known for its diversity of speakers and recording conditions, we extracted Mel-frequency cepstral coefficients (MFCCs) to serve as features for training and evaluating the classifiers. Each model's performance was assessed based on precision, recall, F1-score, and accuracy. The results revealed that RF outperformed all other classifiers, achieving near-perfect metrics, indicative of its robustness and generalizability for speaker identification tasks. KNN also demonstrated high performance, suggesting its suitability for applications where rapid execution and interpretability are critical. Conversely, SVM and DT, while yielding moderate and lower performances respectively, highlighted the necessity for further optimization. These findings underscore the effectiveness of ensemble and distance-based classifiers in handling complex patterns for speaker differentiation. The study not only guides the selection of appropriate classifiers for speaker identification but also sets the stage for future research, which could explore hybrid models and the impact of dataset variability on performance. The insights from this analysis contribute significantly to the field, providing a benchmark for developing advanced speaker identification system