Journal of Computer Networks, Architecture and High Performance Computing
Not a member yet
473 research outputs found
Sort by
Naive Bayes and Simple Additive Weighting (SAW) Method for Whey Protein Product Selection in Fitness
Get PDFFitness is one of the most popular muscle-building sports for people of all ages. Meeting the body's protein needs can be through real food (daily food) such as meat, fish, nuts. However, it is not easy to meet daily protein through daily food alone, so with the existence of whey protein products everyone can meet their daily protein needs without having to add more food portions. The number of whey protein products on the market causes confusion among users in choosing the right product for their daily protein needs. The purpose of the research conducted by the author is to classify the types of whey protein products using the Naïve Bayes method and make recommendations for the best whey protein products based on their type using the Simple Additive Weighting (SAW) method. The results showed that in the classification of whey protein product types using the Naïve Bayes method, the Naïve Bayes method can classify well. The accuracy value obtained by the Naïve Bayes method in this study is 66.67%. This value is obtained because there are two products whose classification does not match the predetermined label. Things like this are natural because the probabilities used between products have a range that is not far away. The Simple Additive Weighting method succeeded in ranking the best whey protein products based on the Simple Additive Weighting method where the first rank was occupied by Optimum Nutrition Whey Gold Standard (WGS) with a value of 82.5 and the product with the lowest value was BSN Syntha 6 Ultra Premium Protein Matrix with a value of 22.5
Design And Build A Mobile-Based Calligraphy And Inscription Order Customize Application With The Waterfall Method Using Fabric JS
Get PDFMobile-based apps have become one of the most important aspects of daily life and even for spiritual and aesthetic purposes such as ordering calligraphy and inscriptions. This also had an impact on the Inscription Blessing Shop. In recent years, the demand for personalized calligraphy and inscriptions has increased significantly. However, this store experienced problems in the ordering process. The process of ordering calligraphy and inscriptions is often still done conventionally, where consumers have to come to the store to place an order which may take a long time and is inefficient. To overcome these obstacles, an effective and efficient system is needed by designing and building a mobile-based booking application. This application will be designed using the waterfall development method by utilizing Fabric JS technology as an interface design. The results of this study were obtained that a mobile-based application called the Blessing Inscription Application was formed which can order inscriptions and other carvings anywhere and anytime. The app can allow users to select different types of calligraphy fonts, set layouts, and add decorative elements. This research is expected to make a significant contribution in facilitating users' creativity and enriching their experience in designing and sharing calligraphy works and digital inscriptions
Implementation of Dart Programming Language in Mobile-Based DRs Snack Sales Application Design
Get PDFDRs Snack has been making and selling snacks in the vicinity. However, they face problems in manually recording sales and generating accurate reports. Therefore, this project aims to design and implement a mobile-based sales system application that will help DRs Snack in managing sales and recording reports more efficiently. The main objective of this project is to design and develop a mobile-based sales system application with Dart programming language and Flutter framework that can help dRs Snack in recording sales transactions in real-time, generate sales and financial reports quickly and accurately, improve operational efficiency and decision making. The method used for system development is Extreme Programing, where this method has a development target through the determination of unclear needs or changes to the needs very quickly and through a small to medium-sized team. The results of this study can manage menus and orders that have been proven to increase operational efficiency. The implementation of this system is able to reduce the time required for order processing and improve the accuracy of data related to stock and revenue. With an integrated system, customer service can be improved and reduce human error in summarizing total payments and ensure accuracy in payments. The system enables better data analysis, especially in monitoring order history and sales recap to improve sales reports. Suggestions from researchers to maximize the features of existing features and add features to complement the features that are already running
Implementation of Data Mining for Speech Recognition Classification of Sundanese Dialect Using KNN Method with MFCC Feature Extraction
Get PDFThe importance of preservation and development of speech recognition technology for regional languages such as Sundanese, which have unique phonetic characteristics. Regional language speech recognition can assist in the development of local, educational, and cultural preservation applications to implement and evaluate the effectiveness of the combination of MFCC and KNN methods in classifying Sundanese dialect speech recognition. Methods used include trait extraction with MFCC, which converts voice data into numerical representations based on frequency characteristics, and classification with KNN, which groups data based on similarity to train data. The Dataset used consisted of speech recordings of Western and Southern Sundanese dialects. The results showed that the k-Nearest Neighbors (KNN) method can classify Sundanese dialect speech recognition with an accuracy of 80.00%, showing good ability in distinguishing "Western" and "southern" dialects. Mel-Frequency Cepstral Coefficients (MFCC) proved to be very effective in extracting sound features, helping KNN achieve low error rates. The combination of MFCC and KNN proved effective for speech recognition classification of Sundanese dialects, providing satisfactory results with high accuracy
Customer Relationship Management Strategy in Mobile-Based E-Commerce Platform Development to Increase Purchase Interest
Get PDFThe demands of technological developments trigger every company to be able to increase competitive advantages in order to create a smooth business process. Customer satisfaction in comparing expectations before making a transaction with the service directly felt by a customer is one of the elements that affect how succesful. Therefore, this study develops and implements a mobile-based e-commerce system equipped with a customer relationship management feature that aims to increase the involvement of interest and product purchases at the Tarigan Clothing Store so that it can provide very significant additional value in a product marketing process. This mobile-based e-commerce information system application also utilizes javascript technology as its interface design. The use of javascript is considered to facilitate access to the latest features in the e-commerce application that is built because of the high existence of javascript which continues to develop according to technological advances. This mobile-based e-commerce application is expected to provide wider reach, convenience and become a more effective marketing tool for customers and Tarigan Clothing Store so that it can provide significant benefits for both parties and create a more comfortable and efficient shopping process
Patient Management System Using Fuzzy Multiple Attribute Decision Making Method with SAW at Noura Aesthetic Clinic
Get PDFThis study presents the development and implementation of a Patient Management System (PMS) at Noura Aesthetic Clinic using the Fuzzy Multiple Attribute Decision Making (FMADM) method with Simple Additive Weighting (SAW). The aim is to enhance the decision-making process for patient treatment prioritization and management. The PMS integrates various patient attributes, including medical history, treatment urgency, and resource availability, into a comprehensive decision-making framework. By employing the FMADM method, the system addresses the inherent uncertainties and subjectivities in patient data, ensuring more accurate and reliable prioritization. The SAW technique further refines this process by assigning weighted scores to each attribute, facilitating a straightforward and effective comparison. This combination allows for a balanced assessment of multiple factors, promoting optimal resource allocation and improving overall patient care. The implementation at Noura Aesthetic Clinic demonstrated significant improvements in operational efficiency and patient satisfaction. The system's adaptability to diverse clinical settings and its user-friendly interface make it a valuable tool for healthcare providers. This study underscores the potential of advanced decision-making methodologies in transforming patient management practices, paving the way for more informed and equitable healthcare delivery
Evaluation of Determining the Best Product Promotion Media Decisions for MSMEs with ROC Ranking Technique and SAW Ranking Method
Get PDFMicro, Small, and Medium Enterprises (MSMEs) face challenges in determining effective promotional media to increase sales of their products. This research aims to evaluate and determine the best promotional media for MSMEs using the ROC (Rank Order Centroid) ranking technique and the SAW (Simple Additive Weighting) method. The criteria used include Advertising Costs, Target Market, Promotion Time, and Brand Image. Based on the calculation of criteria weights with the ROC technique and evaluation of alternatives with the SAW method, Social Media was found to be the best promotional media, followed by Search Engines and Product Collaboration. Social Media has advantages in low cost, wide target market reach, and promotional flexibility and effectiveness. Search Engines and Product Collaboration also showed good results in reaching the target market and promotional flexibility. In contrast, Print Media ranked the lowest due to limited reach and high costs. This research provides guidance for MSMEs in choosing the right promotional media and optimizing resources for maximum promotional results
Naïve Bayes-based Student Graduation Prediction Model: Effectiveness and Implementation to Improve Timely Graduation
Get PDFStudies in an educational institution, when the lack of timely graduation of students in each batch and the number of students in each batch, causes an imbalance between incoming students and outgoing students and causes a decrease in accreditation from the campus, this should not continue to happen, the solution to dealing with this problem as an early detection of students who graduate on time is to predict the length of the student study period they have. Therefore, researchers will discuss the design of a prediction system for graduating on time using the Naïve Bayes method, to predict student graduation so that there is no imbalance of incoming and outgoing students. The construction of this system also uses the Naïve Bayes method and the CRISP-DM (Cross Industry Standard Process Data Mining) development method. In this case study, the Naïve Bayes method predicts data into 2, namely 1 (graduated on time) and 0 (did not graduate on time) by labeling the data used. In this model using 3247 data with the selection of features, namely semester achievement index 1 (ips1), ips2, ips3, ips4, ips5, semester credit units1 (credits1), credits2, credits3, credits4, credits5, semester credit units not passed 1 (skstidaklulus1), skstidaklulus2, skstidaklulus3, skstidaklulus4, skstidaklulus5 and labels. Using these feature variables results in model performance with 80% accuracy, with 80% accuracy it can be said that the model works well
Analysis Of Opinion Sentiment Towards Electric Vehicle Tax On Social Media X Using The Support Vector Machine (SVM) Method
Get PDFElectric vehicle tax is increasingly becoming an important issue related to environmental and fiscal policies. Electric vehicles are considered an environmentally friendly solution to reduce greenhouse gas emissions and dependence on fossil fuels. However, public perception of electric vehicle tax is still mixed. This study aims to analyze public sentiment about electric vehicle tax based on data from social media platform X, using the Support Vector Machine (SVM) method. The data used was taken through a crawling technique with a total of 1,014 valid data. The data was then classified into positive and negative classes with a transformer. In this analysis, the data was divided with a ratio of 8:2 between training data and test data. 811 were used as training data and 203 as test data. The research stages involved data preprocessing, sentiment labeling, data separation into training and test data, and weighting using TF-IDF. After that, SVM was applied to classify tweets into positive and negative sentiments. The test results showed that the SVM algorithm had an accuracy of 79%, precision of 85%, recall of 89%, and F1-score of 87%. Based on the results of this study, some people feel unsure about the government's policy regarding electric vehicle tax, because it is considered unfair to the lower middle class. Electric vehicles are considered more expensive than fuel-powered vehicles, so this policy is considered unprofitable
Android Based Sports Infrastructure E-Booking Application at Provincial Youth and Sports Office Using Waterfall Method
Get PDFBooking is an agreement process in the form of ordering goods or services. The Youth and Sports Service (DISPORASU) is a government agency under the auspices of the Governor of North Sumatra. DISPORASU provides sports infrastructure that can be used by the general public by rental method. In the rental process, DISPORASU still applies the direct rental method, by coming to the DISPORASU office in Medan City, so this results in a large number of tenants piling up at the same time. Therefore, a system is needed that helps tenants in carrying out the infrastructure rental process. The concept is an Android-based Sports Infrastructure E-Booking application. This application was built and designed using the waterfall model and UML (Unified Modeling Language) with several diagrams, namely Use Case Diagrams, Activity Diagrams and Class Diagrams. The programming language used is Dart, Flutter Framework and Firebase as the database. By building this sports infrastructure E-Booking application, it is hoped that it can help improve performance in future business processes and become a reference for employees/staff in this agency itself