cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Frieyadie
Contact Email
jurnal.inti@nusamandiri.ac.id
Phone
-
Journal Mail Official
jurnal.inti@nusamandiri.ac.id
Editorial Address
-
Location
Kota adm. jakarta pusat,
Dki jakarta
INDONESIA
INTI Nusa Mandiri
Published by PPPM Nusa Mandiri
ISSN : 02166933     EISSN : 2685807X     DOI : -
Core Subject : Science,
Computer Science & IT
The INTI Nusa Mandiri Journal is intended as a media for scientific studies on the results of research, thought and analysis-critical studies on the issues of Computer Science, Information Systems and Information Technology, both nationally and internationally. The scientific article in question is in the form of theoretical review and empirical studies of related sciences, which can be accounted for and disseminated nationally and internationally.
Arjuna Subject : -
Articles 13 Documents
 1   2 
Search results for , issue "Vol 18 No 1 (2023): INTI Periode Agustus 2023" : 13 Documents clear
ENSEMBLE STACKING DALAM ANALISA SENTIMEN REAKSI VETERAN MILITER AS TERHADAP PENGAMBILALIHAN AFGHANISTAN OLEH TALIBAN Henny Leidiyana
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4175

Abstract

Abstrak— Sentiment analysis can be used to glean information about user opinions and identify social or political trends. There have been many studies on sentiment analysis using machine learning or lexicon-based methods that have been quite impressive. However, machine learning models often have difficulty generalizing to new data due to various reasons, such as overfitting and limited training data. These models are also prone to bias and variance, which negatively affect the accuracy of their predictions. This study discusses the application of the ensemble stacking method in sentiment analysis with the topic of the takeover of Afghanistan by the Taliban. By monitoring social media, the author uses a dataset in the form of comments on YouTube news channels related to the topic raised. Several studies have shown how the ensemble stacking method predicts better than the single model. The research was carried out by creating a sentiment classification model with logistic regression machine learning algorithms, SVM, KNN, and CART then the ensemble stacking classifier formed by the base learner of the four algorithms. As a result, for a single classifier, the highest average accuracy is the logistic regression algorithm of 74.6 percent. The four algorithms are compiled and predicted by logistic regression, and the stacking ensemble classifier that is applied produces better accuracy than the stand-alone classifier, which is 75.3 percent
PROTOTYPE SISTEM PENDAFTARAN RAWAT JALAN PADA RSUD LARANTUKA NUSA TENGGARA TIMUR BERBASIS MOBILE Irwan Herliawan; Ignasius Geryanto Saon; Yuri Yuliani; Kukuh Panggalih
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4218

Abstract

Abstract—The role of the hospital is very helpful in efforts to improve the quality of public health, for this reason the need for fast and appropriate services so that human resources are maintained for their survival. At dr. Hospital Hendrikus Fernandez Larantuka East Nusa Tenggara, the registration service still uses the intranet system or local network and system errors often occur so that the patient registration process is hampered. In addition, the system created on the intranet network also has drawbacks, one of which is that it can only be accessed by people who are connected to the building's network. With these problems, there is a need for a mobile-based application that can be accessed directly by the public in real time from anywhere and any time. The purpose of this study is to create a mobile-based application design that is capable of processing inpatient registration services at hospitals with an attractive and user-friendly appearance. The method used in this study is the prototyping method. This method is a software development model by creating a prototype or model to provide an overview to the user by going through 5 stages, namely communications, quick plan, quick design model, prototype construct, and development delivery and feedback. The tool used in making this prototype is the Figma application. The results of this study are that there is an application prototype that can be used as reference material for RSUD dr. Hendrikus Fernandez Larantuka, East Nusa Tenggara, in developing his system so that the inpatient registration process can be carried out by the community anytime and anywhere. Likewise, information from the hospital can be received in real time by the public through the mobile-based hospital inpatient application.
SENTIMEN ANALISIS CHATGPT DENGAN ALGORITMA NAÏVE BAYES DAN OPTIMASI PSO Lestari Yusuf; Siti Masripah
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4230

Abstract

Abstract— ChatGPT which is an OpenAI technology that responds to conversations between humans and machines. enabling users of all ages and backgrounds to communicate naturally in multiple languages ​​without having prior knowledge or experience in programming or the computer world. However, a technology will always be at odds and has flaws on the human side, various assumptions about chatGPT are formed from many sides, such as in the world of education, chatGPT creates parallels for teachers and lecturers. When giving assignments, students/students can use chatGPT as material in answering assignments from teachers/lecturers. And that results in students/students not carefully reading the answers to these assignments, if that continues to happen, students/students will find it too easy to get something and then will lose interest in solving problems with their own efforts. This article aims to analyze sentiment analysis whose data is taken from Twitter using the keyword "CahtGPT OpenAI". With 2,000 data calculated using the naive Bayes algorithm and optimized using PSO, it is found that sentiment analysis for chatGPT itself has an accuracy of 69.23% with a positive class of 0.503 and a negative of 0.497 and obtains an AUC curve value of 0.68 +/- 0.55..
MODEL RAPID APPLICATION DEVELOPMENT UNTUK RANCANG BANGUN SISTEM PENGELOLAAN TRANSAKSI PERDAGANGAN INDOSURRATI SUKSES MAKMUR Sismadi Sismadi; Sopiyan Dalis; Syamsul Bahri; Diki Setiawan
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4241

Abstract

The problem of manual recording is one of the problems that is often experienced by small and medium-scale businesses such as MSMEs, this occurs along with the increasing quantity of transactions, a large number of items of goods, and the growth and development of businesses, including PT. Surrati Sukses Makmur is engaged in the retail sale of perfume products. This problem can have negative impacts, such as difficulties in monitoring stock so that discrepancies easily occur, transactions not recorded so that data is lost, preparation of reports taking more time, fraud, and the need for a place to store documents. To overcome this problem, it is necessary to analyze and design a digital-based sales information system that can help the process of recording sales to be more efficient, accurate, safe, and easy. By using a digital information system, there is no need for a special place for document storage, loss of transaction data can be minimized so that it has an impact, PT. Surrati Sukses Makmur can improve performance and quality of service to customers, as well as operational costs can be reduced and inventory management can be easier. The design of this system uses the Rapid application Development (RAD) model with the aim that applications can be completed immediately and reduce the cost of making application systems so that reports can be made in a comprehensive and effective and efficient manner, , as well as with the black-box testing method in testing the application can be used more effectively and efficiently, and as a whole is in accordance with system requirements
KLASIFIKASI TIPE BERAT TUBUH MENGGUNAKAN METODE SUPPORT VECTOR MACHINE Taufik Hidayatulloh; Lestari Yusuf
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4254

Abstract

Abstract—The news of the death of a man in Indonesia is in the public spotlight because doctors have difficulty treating his illness because being overweight or obese causes the organs in the body to fail to function properly. Overweight causes the body to experience several health problems, including heart defects, diabetes, and several other diseases that can attack vital organs in the body. According to data on deaths caused by obesity, there are as many as 60 per 100,000 Indonesian population, and are a very feared killer. Faster handling of recognizing our body weight is important for each individual’s health. Classification can also help overweight in a person known more quickly. In this study, the classification algorithm that will be used is the Support vector machine (SVM). With 252 data, this study will use the SVM algorithm and look for the level of accuracy of the two classification classes, namely normal and overweight. This study produces an accuracy rate of 92.11% with a ROC curve value of 0.990 which means that the classification in this study is very good.
METODE VECTOR SPACE MODEL UNTUK WEB SCRAPING PADA WEBSITE FREELANCE Andi Nurkholis; Yusra Fernando; Faris Arkans Ans
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4266

Abstract

Abstract— In digitalization era, internet is at the center of all lines of community activity, just like the field of work. Currently, many platforms provide job vacancies, especially for freelancers. To obtain this information, users usually need to open several websites to find information about suitable job vacancies. Web scraping offers solution to overcome these problems. Based on research that has been done, the BeautifulSoup and Selenium libraries will be used to collect data. To search for data, vector space model method is used to find the level of data similarity between the query and the document. In exploring data, the average near-perfect recall value is 98%, while the average precision value is 56%. This is because data search uses three parameters, so the possibility of retrieving irrelevant data is more significant if the document contains a word in the user's query, even though the context does not match. Utilizing the Streamlit framework in Python can display the data processing results and help users navigate the web scraping process, data processing, and data search. This study aims to implement the web scraping method to retrieve data from freelance websites: Freelance, Project, and Sribulancer. By applying the vector space model method, users can search data from several websites without opening freelance websites one by one. Using data visualization in the form of a web application using the Streamlit framework, the web scraping results can also be processed to be presented in a more helpful form and save the user's time
KLASIFIKASI KONDISI BAN KENDARAAN MENGGUNAKAN ARSITEKTUR VGG16 ahmad fudolizaenun nazhirin; Muhammad Rafi Muttaqin; Teguh Iman Hermanto
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4270

Abstract

Tyres are the main component that a vehicle needs to work with reducing vibration due to uneven road surfaces, protecting the wheels from wear to provide stability between the vehicle and the ground helping to improve acceleration to facilitate travel while driving. Wear ensures stability between the vehicle and the ground helps improve acceleration for easy movement and driving. Caused including components that are often used, tires can experience damage such as the appearance of cracks in the tires. Cracks in tires can be triggered by factors such as age or the cause of the road that has been exceeded. Detection of tire cracks at this time is still carried out conventionally, where users see directly the state of the tire whether the tire is in good condition or cracked. Conventional methods are important because they maintain tire quality and rider safety. The Conventional Method certainly has weaknesses because vehicle users must have good vision and the ability to distinguish normal tires or cracked tires, but this method is considered less effective because it still uses human labor, causing the risk of human error (human negligence) which can hinder the process of identifying tire cracks. Based on this problem, this study will develop a deep learning model that can classify cracked tires using the VGG16 architecture. In this study, the model was created using 8 scenarios by changing the value of epochs, to get the best parameters in making the model. The results of the 8 scenarios carried out in this study are the best scenario obtained in scenarios 1,3,4 which get 98% accuracy in model testing
OPTIMASI NAIVE BAYES BERBASIS PSO UNTUK ANALISA SENTIMEN PERKEMBANGAN ARTIFICIAL INTELLIGENCE DI TWITTER Elly Indrayuni; Acmad Nurhadi
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4282

Abstract

At present the development of Artificial Intelligence technology is progressing rapidly. There are many new artificial intelligence technologies available in various fields. Artificial Intelligence is an artificial intelligence program that can study data, perform processes of thinking and acting like humans. The presence of Artificial Intelligence technology has many positive impacts, especially in increasing work effectiveness and efficiency. However, AI is also a threat to human resources because slowly human work is being replaced by Artificial Intelligence. Various opinions about the development of Artificial Intelligence are widely discussed on social media such as Twitter. Sentiment analysis is a computational study to automatically categorize opinions into positive or negative categories. In this study, the Naive Bayes algorithm was used to analyze sentiment or public opinion regarding the development of Artificial Intelligence for Twitter users. The data collection method used is crawling data on Twitter. The results of the sentiment classification test for the development of Artificial Intelligence using Naive Bayes yield an accuracy value of 86.42%. Meanwhile, the results of the sentiment classification test using Naive Bayes based on Particle Swarm Optimization (PSO) increased with an accuracy value of 87.55%. Based on the results of this study, the use of PSO as an optimization technique for the Naive Bayes algorithm is proven to be the best algorithm model in sentiment analysis for the development of Artificial Intelligence for English text.
PENENTUAN KELAYAKAN BANGUNAN CAGAR BUDAYA MENGGUNAKAN METODE SIMPLE MULTI ATTRIBUTE RATING TECHNIQUE (SMART) Hesti Ratna Setyaningrum; Muhammad Rafi Muttaqin; Mochzen Gito Resmi
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4286

Abstract

Abstract— Nowadays, awareness of the importance of cultural heritage is decreasing among the public, especially among youth who will become leaders and inherit the culture of their region. Law Number 11 of 2010 stipulates the importance of protecting and preserving cultural heritage because it has significant value in history, science, education, religion and culture. Therefore, the existence of cultural heritage must be considered and maintained properly according to applicable regulations. There are several criteria for assessing buildings that will be used as cultural heritage according to Law number 11 of 2010 in Chapter III, article 5, cultural heritage criteria, namely the age of the building, historical value, cultural value and architectural value. This study aims to create a system that can determine the feasibility of a building as a cultural heritage in a precise and accurate way (case study DISPORAPARBUD Purwakarta). In this study, the Simple Multi Attribute Rating Technique (SMART) method was used in the Decision Support System (SPK). The results of this study are to produce recommendations for buildings that are worthy of being cultural heritage in accordance with predetermined criteria, namely the Normal School building with a value of 1 by occupying the first rank, which will then be recommended to the Purwakarta DISPORAPARBUD
KOMPARASI FUNGSI AKTIVASI NEURAL NETWORK PADA DATA TIME SERIES Ibnu Akil
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4288

Abstract

Abstract— The sophistication and success of machine learning in solving problems in various fields of artificial intelligence cannot be separated from the neural networks that form the basis of its algorithms. Meanwhile, the essence of a neural network lies in its activation function. However because so many activation function which are merged lately, it’s needed to search for proper activation function according to the model and it’s dataset used. In this study, the activation functions commonly used in machine learning models will be tested, namely; ReLU, GELU and SELU, for time series data in the form of stock prices. These activation functions are implemented in python and use the TensorFlow library, as well as a model developed based on the Convolutional Neural Network (CNN). From the results of this implementation, the results obtained with the CNN model, that the GELU activation function for time series data has the smallest loss value

Page 1 of 2 | Total Record : 13

 1   2 

Filter by Year

2023 2023


Reset
Filter By Issues
All Issue Vol. 20 No. 2 (2026): INTI Periode Februari 2026 Vol. 20 No. 1 (2025): INTI Periode Agustus 2025 Vol. 19 No. 2 (2025): INTI Periode Februari 2025 Vol. 19 No. 1 (2024): INTI Periode Agustus 2024 Vol. 18 No. 2 (2024): INTI Periode Februari 2024 Vol 18 No 1 (2023): INTI Periode Agustus 2023 Vol 17 No 2 (2023): INTI Periode Februari 2023 Vol 17 No 1 (2022): INTI Periode Agustus 2022 Vol 16 No 2 (2022): INTI Periode Februari 2022 Vol 16 No 1 (2021): INTI Periode Agustus 2021 Vol 15 No 2 (2021): INTI Periode Februari 2021 Vol 15 No 1 (2020): INTI Periode Agustus 2020 Vol 14 No 2 (2020): INTI Periode Februari 2020 Vol 14 No 1 (2019): INTI Periode Agustus 2019 Vol 13 No 2 (2019): INTI Periode Februari 2019 Vol 13 No 1 (2018): INTI Periode Agustus 2018 Vol 12 No 2 (2018): INTI Periode Februari 2018 Vol 12 No 1 (2017): INTI Periode Agustus 2017 Vol 11 No 2 (2017): INTI Periode Februari 2017 More Issue