Search

Data science is a science that is currently very popular and can be applied in various industries. Of course, the need for proficient people in this field is growing in demand by many businesses, including large corporations. Data science is a science that combines expertise in a particular field of science with programming, mathematics, and statistics skills. The goal is to extract knowledge or information from data. The problem that usually occurs in the data science process is at the data modeling stage, namely the accuracy of the mathematical model that will be used to obtain the estimated parameter values. To overcome this problem, this research was conducted to test the correctness of analytic derivatives in mathematical models and conduct data modeling using analytic derivatives that have been tested to obtain the estimated value of each parameter. The validation process is carried out using an analytic and numeric gradient comparison. If the comparison of the two values is close to zero, then the analytical derivatives used are correct. The parameter estimation method used is the Maximum Likelihood Estimation. In this research, it was concluded that the value of the analytic gradient is the same or close to the numeric gradient value for each parameter so that the analytic derivatives are correct and can be used for the next stage. With the results of this research, the expected implication is to get more accurate data modeling so that the conclusions obtained are more precise. [ABSTRACT FROM AUTHOR]

The waste problem is a problem that, until now, is quite challenging to overcome, especially with the amount of waste increasing daily. Data in 2019 shows that there are 175,000 tons of waste, of which 14% is plastic waste. The amount of waste indeed continues to grow over time. For this reason, it is necessary to take steps to overcome these problems. One of the steps that can be done is to take advantage of technology. In this research, it was explained how to develop a mobile-based application that is useful for educating and answering problems about waste. This application serves to pick up the waste and will later be managed to be used as a more useful form. This research also explained the results of the application feasibility test involving several respondents using the System Usability Scale (SUS) mechanism, where the results indicated that the application was running well. [ABSTRACT FROM AUTHOR]

In order to be able to develop a website with ease, a tool or software called a framework could be really useful in many ways. Django is one of the many frameworks that are able to provide a backend solution to develop a fully working website. In this paper, the writer compared Keyword Driven Testing, Unit Testing, and Data-Driven Testing to determine which one is the most efficient and easy to do to develop a fully working website. The test result found that Data Driven Testing is the most effective and efficient method to do. It is because Django is mostly used to develop a website that requires a database system, which already fulfills the main requirements to condone Data Driven Testing, primarily using data as its primary resources. [ABSTRACT FROM AUTHOR]

A COVID-19 pandemic is a worldwide event that affects all sectors. One of which is mental health problems. Mental health problems can come in any form. The most common form is depression. Depression is very common worldwide and is increasing due to COVID-19. Depression can be helped with many forms of coping mechanisms. One method is using books. Reading a book that provides supporting life will help fight spirit. In the social distancing condition, people are not freely allowed to go shopping outside. This means that getting things that are not primary needs, such as books, is not easily done. Meanwhile, simultaneously, the growth of the internet evolution has helped humanity for a long time. The modern era of online shopping is one of them. Website that provides primary human needs has been very common in this decade. In this study, we aim to solve problems related to people who need to treat their souls without going out from home in the pandemic condition, that wants to buy a book motivation particular for cure mental using web-based intermediary prototype apps. [ABSTRACT FROM AUTHOR]

The problem of the Covid-19 pandemic is one of the most significant factors that has shaken the tourism sector in Indonesia. Just imagine that there has not been one year, and many sectors have been affected, one of which is tourism. The number of tourist visits in Indonesia has decreased drastically from previous years. Of course, this must be a severe consideration to the government and the tourism owner. In order to overcome this problem, the writers created a project using internet technology, an application, and a website to develop our business called 2Gather. 2Gather is an online social-travel application/platform that connects an individual user with another particular user, allowing them to be able to make friends while also having fun traveling across the continent. [ABSTRACT FROM AUTHOR]

This paper explains the training process of the ResNet-50 architecture Convolutional Neural Network (CNN) model from the Keras application and the implementation of the model in the attendance system prototype. This project aims to find the best optimizer function for the face recognition model configuration and evaluate the model with an attendance system prototype. Dataset used in this project is the authors' institution's employees' face image dataset. Six classes with seven images each are collected as a training dataset. Trial-and-error experiments with different model configurations are done to get the best model. The best result is implemented in the attendance system prototype. The model was trained with 500 epochs at the beginning of an experiment and more than 50 epochs if the result is not satisfying, and re-configure learning rate, batch size, and the optimizer function if there is no accuracy improvement after epochs addition. This project concluded that the best optimizer function is Adam, and modification of the CNN model configuration significantly improves accuracy. As a result, in the 4th experiment, ResNet-50 reached 95% accuracy on testing and 100% on training with Adam optimizer function, Softmax activation function as output layer, 16 as the batch size value, and 0.001 as the learning rate value. The accuracy is not stable even until 700 epochs. However, this result achieves better accuracy than the previous project, a face recognition system using Linear Binary Pattern Histogram (LBPH) algorithm done by Sarwar and a face recognition-based attendance system using custom CNN architecture by M. K. Rusia. [ABSTRACT FROM AUTHOR]

Nowadays, the web platform is famously used to deliver information and to support trade activity in the marketplace online. Increasing internet users can be an opportunity for business people, especially for sellers that sell used cell phones. Unfortunately, the traditional market still conventionally sells their phone, which has shortcomings, i.e., the product cannot be promoted extensively to prospective customers. To overcome this problem, this study proposes the business idea of web-based platform technology that can use by sellers to promote their used cell phones in the online market. The business idea can also give detailed information related to the product so buyers' perspectives can get more trust from the seller, and the product can be accessed from anywhere through internet media. The system that we propose also provides information service to maintenance of mobile phone, so when the customers have problem with their phone can fix with the vendor provided on the website. [ABSTRACT FROM AUTHOR]

Smartphones are an object that is always carried everywhere and cannot be separated from everyday life. Smartphones were created with various purposes and features present in terms of education, entertainment, information, communication, and others. Besides these positive things, smartphones also trigger negative impacts such as wasting time interacting with screens, reducing academic achievement, and even decreasing muscle mass due to lack of movement. The next level is to make people become addicted to smartphones. For early adolescent children, smartphone addictions cause insomnia, social behavior, low self-esteem, and even anxiety. The complexity of anxiety symptoms in children is difficult for adults to understand. So, a way to predict smartphone addiction in early adolescence was initiated with a machine learning method, namely the SVM algorithm. The experiment in this paper is the SVM kernel testing. The best performance of SVM is while using a linear kernel; the accuracy reaches 96.4467%. [ABSTRACT FROM AUTHOR]

User Experience (UX) is gaining popularity as an essential success factor in many sectors and industries, including educational institutions. The problem in this study is how we, as VERGA application developers, can measure the level of user experience by measuring it using the User Experience Questionnaire method in the hope that when we get feedback from users, we can improve the performance of the VERGA application in terms of User Experience. It is the result of the interaction of users and systems. Researchers can produce and measure UX, whether essential or not because the purpose of making and owning a product is to answer existing problems and provide good service. The purpose of this paper is to measure and explain how the user experience in using the Verga application in various aspects of the Verga application. one method of testing user experience is the User Experience Questionnaire (UEQ) where this method has six scales or attributes to be measured namely: attractiveness, perspicuity, efficiency, dependability, stimulation, and novelty with twenty-six (26) items in total. The benefit of this paper is that the development team can redevelop the application to support user satisfaction and experience, and we hope that the user experience can be improved in this test. [ABSTRACT FROM AUTHOR]

Technology in this era is beginning to develop day by day. This makes all sectors help, such as the financial sector. Many innovations have emerged, such as Quick Response Code Indonesian Standard (QRIS), online payments, and others. Money withdrawals are also making progress, such as cardless withdrawals. However, some people often feel the length of the queue and the absence of time to go to the Automatic Teller Machine (ATM). The Easy Take Money (ETM) application, an innovation in taking money modernly, can help people in need. However, providing a complete experience to users requires an honest assessment from potential customers. The User Experience Questionnaire (UEQ) method can help the development of Easy Take Money applications to get the quality value of a product or application based on impressions from users when using a product or application. UEQ has six research scales comprising 26 items, including Attractiveness, Perspicuity, Efficiency, Dependability, Stimulation, and Novelty. In this study, respondents had different backgrounds from the age range from 18 years to 25 years who already had experience in using applications. From the analysis using UEQ, it is known that ETM applications have a high value in the aspect of Perspicuity. [ABSTRACT FROM AUTHOR]

Wadul is a whistleblowing protocol to report entities that are assumed to be rule-breaking ones or create injustice behavior in a vast, broad community. Today this system is advantageous to almost every government in the world, as it increases the concern of people to improve their government's empathy towards people. There are many kinds of systems that have similar functions in each governmental institution. Even so, this system grew up independently of each institution and was not integrated because each institution had its way of facing down the public reports. This paper explores the supporting features of creating a responsive and interactive website and mobile platform application. Data were collected by analyzing several consistent sources and interviewing representatives of government institutions, including developers' relatives. The result of this work is the result of user satisfaction with the Wadul application, which is achieved through the UEQ survey. From 25 respondents obtained an average value of 5 to 7, with the results included in the excellent category. Of the six categories of rating scales, the highest mean value lies in the perspicuity category, with a mean value of 1.84. This work also aimed for the government institution to create a higher concern about people's conditions and concerns. Based on the UEQ results, it can be concluded that the majority of potential users, especially on a few aspects of the scale, such as attractiveness, perspicuity, and efficiency, are quite good. [ABSTRACT FROM AUTHOR]