Garuda - Garba Rujukan Digital

Penerapan Algoritma Cerdas Bidirectional Encoder Refresentations From Transformers Dalam Menganalisis Opini Publik Terhadap Produk Yang Mengalami Boikot Sulaeman, Asep Surahman; Sujjada, Alun; Kharisma, Ivana Lucia
Jurnal Inovtek Polbeng Seri Informatika Vol 9, No 1 (2024)
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/isi.v9i1.4252

Social media, particularly Instagram, has become a primary platform for expressing opinions and participating in public discussions on various social, economic, and political issues. One of the prominent issues on social media is product boycotting. Boycotting a product can significantly impact the brand's image and sales. Famous brands such as McDonald’s, KFC, Starbucks, Burger King, and Pizza Hut are the main targets in boycott actions. This study uses a dataset of 1,750 comments from Instagram accounts on related products. The data is divided into two labels, positive and negative, based on automatic labeling from transformers and manual labeling. Sentiment analysis results show that McDonald’s has 41.43% positive sentiment and 58.57% negative sentiment, KFC has 85.14% positive and 14.86% negative, Starbucks has 97.71% positive and 2.29% negative, Burger King has 50% positive and negative, and Pizza Hut has 80.57% positive and 19.43% negative. Modeling results using the pre-trained Bidirectional Encoder Representation From Transformers (BERT) from Bert-Base-Uncased show accuracy results for McDonald’s products at 84.14%, KFC products at 95%, Starbucks products at 94.16%, Burger King products at 91.42%, and Pizza Hut products at 93.80%.

Construction Of Railway Door Automation Prototypes Using Arduino, Servo Motors and Ultrasonic Sensors : Konstruksi Prototipe Otomatisasi Pintu Kereta Api Menggunakan Arduino, Motor Servo, dan Sensor Ultrasonik Kharisma, Ivana Lucia; Kamdan; Firdaus, Asep Rizki; Prayoga , Rizki Haddi; Yasin, Fakhriyal Riyandi; Tresna Ati, Mutiara Annisa
Digital Zone: Jurnal Teknologi Informasi dan Komunikasi Vol. 14 No. 1 (2023): Digital Zone: Jurnal Teknologi Informasi dan Komunikasi
Publisher : Publisher: Fakultas Ilmu Komputer, Institution: Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/digitalzone.v14i1.13584

The Indonesian railway system is currently experiencing a lot of developments in terms of technology. The Indonesian railway system has been integrated with technology 4.0, where all transaction processes, whether payment, ordering tickets or monitoring trains, can be monitored via electronic media. Of course, this technology must be supported by adequate infrastructure, one of which is the railroad crossing. In Indonesia, several railroad lines have been constructed, and many portal or crossbar railroads have also been constructed. The railroad gate is part of the railway system which has a very important role, especially in regulating the safety of train travel. The rail gateway has been a problem and a source of accidents in recent years. This is because there are no security facilities at any rail portals, causing drivers to continue to break traffic laws. The making of this automatic railroad doorstop uses the Prototype method, namely a simulation that uses Arduino UNO R3, servo motors, HC-SR04 ultrasonic sensors and other components that can support the manufacture of this railroad doorstop prototype. The prototype of this automatic train doorstop is equipped with many sensors that works automatically according to what is ordered, so that its use can be easily controlled and implemented in real life. This automatic railroad crossing system is expected to optimize the task of the railroad crossing guard by providing automation for the process of opening and closing the railway door and providing additional warning information for the community around the railway door location so as to reduce the potential for accidents caused by drivers or people who break traffic laws.

Perbandingan Naїve Bayes Classifier Dan Support Vector Machine Dalam Mengklasifikasikan Tingkat Pengangguran Terbuka Di Indonesia Dewi, Dhita Diana; Kharisma, Ivana Lucia; Bila, Nida Aulia Salsa
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 9, No 2 (2024): Edisi Agustus
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v9i2.811

Unemployment is one of the factors of problems in the economic field, this will have an impact on the balance of the economy. A person can be said to be unemployed if the person does not meet the requirements as a workforce. Open unemployment is a workforce that does not actually have a job. Therefore, this study will classify the Open Unemployment Rate (TPT) in Indonesia in the 2020-2023 period. This study will use the Naїve Bayes Classifier (NBC) and Support Vector Machine (SVM) algorithms. In the SVM algorithm method, for the negative class consists of a precision value of 62%, a recall of 80%, an F1 Score of 70%. While for the positive class consists of a precision value of 87%, a recall of 72%, an F1 Score of 79%. In the NBC algorithm method, for the negative class consists of a precision value of 71%, a recall of 50%, an F1 Score of 59%. While for the positive class consists of a precision value of 76%, a recall of 89%, an F1 Score of 82%. Based on these calculations, the accuracy value of each algorithm has the same accuracy value, which is 75%.

Implementasi Chatbot dengan pendekatan Natural Language Processing dan Naïve Bayes dalam meningkatkan layanan perusahaan Sebayang, Alvin Christoper; Kharisma, Ivana Lucia; Sujjada, Alun; Kamdan, K
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 3 (2024): Edisi Juli
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i3.434

The development of information technology has influenced how organizations provide services to users. Customer service is an activity aimed at ensuring customer satisfaction through the assistance provided by an individual in addressing issues and meeting their needs. However, in certain conditions, customer service may not be able to handle or serve customers, such as outside working hours and recurring general inquiries from users. In this context, Chatbots have become a promising solution to enhance service quality. This study aims to implement a Chatbot with a Natural Language Processing (NLP) approach and Naive Bayes classification method to improve the performance of the Mangcoding web service or PT Anugrah Kreasi Digital. The system development method in this study includes user needs analysis, Chatbot architecture design, NLP model development, and integration with existing web service platforms. The use of NLP methods is expected to improve accuracy so that the Chatbot can understand the users' natural language and provide relevant responses according to their requests. This study uses a qualitative approach to evaluate the performance of the Chatbot in enhancing web services. The results of this study are expected to improve the efficiency of web services through the implementation of a Chatbot with an NLP approach and Naive Bayes classification method, enabling the Chatbot to provide accurate answers. Additionally, it is expected to provide guidance for organizations in utilizing Chatbot technology to improve interactions with users in the context of web-based services.

Analisis Keamanan Dan Eksploitasi Kernel Android 13 Menggunakan Metasploit Reverse_Tcp Alhidamkara, Salman; Somantri, S; Kharisma, Ivana Lucia
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 3 (2024): Edisi Juli
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i3.410

The development of information technology, especially in the mobile field, has changed the way we interact with devices substantially. Android, as the most dominant mobile operating system used worldwide, attracts significant attention to its security aspects. Despite improvements in the security of Android devices, exploitation attempts continue to be made by security researchers and hackers using various methods, including exploitation via Reverse_TCP with tools such as Metasploit. This research aims to analyze the security of Android 13 devices using the Reverse_TCP method via Metasploit. The methods used involve exploitation by sending backdoor applications, opening Meterpreter sessions, and stealing data such as SMS and call logs. The results showed that Google Play Protect detected malicious applications, but the applications could still be installed and run, indicating a weakness in the security detection system. Reverse_TCP exploits can lead to unauthorized access to personal data and full control of the device, posing significant risks to users. Proposed preventive measures include using the Mobile Security Framework (MobSF), enabling Google Play Protect, and disabling unnecessary app permissions. This study suggests further research to overcome limitations and explore further the security aspects of Android

Penerapan Algoritma Random Forest untuk Menganalisis Ulasan Aplikasi Spotify pada Google Play Insany, Gina Purnama; Kharisma, Ivana Lucia; Rosmawati, Rosmawati
Jurnal Pendidikan Informatika (EDUMATIC) Vol 8 No 2 (2024): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v8i2.26394

The development of internet technology and mobile devices has played an important role in transforming the music industry and driving the emergence of music streaming services, such as Spotify. This research aims to understand Spotify users' preferences and expectations through sentiment analysis of user reviews. The review data was retrieved from Google Play Store using web scraping technique, including rivew and rating of 1000 Indonesian and 1000 English reviews. Random Forest algorithm was used to model the sentiment of the reviews, with the analysis process including data collection, labeling, preprocessing, Term Frequency-Inverse Document Frequency (TF-IDF) weighting, oversampling, modeling, and evaluation with confusion matrix. Algorithm testing was conducted using 70% training data and 30% test data. The classification evaluation results of the Random Forest algorithm showed a model accuracy of 88.4% for Indonesian reviews and 93.6% for English reviews. These findings show that the Random Forest algorithm is effective for sentiment analysis in a multilingual context and can help app developers improve service quality based on user sentiment. This research was also deployed using Streamlit, enabling access and usage by users for fast and interactive sentiment analysis.

Rancang Bangun Aplikasi Pendeteksi Tingkat Kepekatan Asap Hasil Pembakaran Berbasis Internet of Things Somantri, S; Kharisma, Ivana Lucia; Angelina, Nadila
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 2 (2023): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i2.680

The objective of this study is to develop and construct an Internet of Things (IoT) system(Internet of Things) application for detecting the concentration level of smoke resulting from combustion. The current advancement in technology has had a significant Significant influence across a range of domains, encompassing the realm of Internet of Things (IoT). The IoT network allows devices to interact and exchange information automatically, enhancing efficiency and security in various sectors. Early detection of smoke is crucial for preventing further damage and protecting human health. Therefore, this research utilizes MQ-135 and TGS 2600 sensors as smoke detection sensors. Through IoT, real-time measurement of smoke concentration can be achieved, enabling immediate actions in response to significant changes. The data collected through IoT can to enhance effectiveness, the information can be stored within a database and efficient research. By implementing this application, it is expected to provide a better solution for automatic detection and monitoring of smoke resulting from combustion, reducing air pollution risks, and enhancing human safety.

Rancang Bangun Aplikasi Pendeteksi Tingkat Kepekatan Asap Hasil Pembakaran Berbasis Internet of Things Somantri, S; Kharisma, Ivana Lucia; Angelina, Nadila
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 2 (2023): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i2.680

The objective of this study is to develop and construct an Internet of Things (IoT) system(Internet of Things) application for detecting the concentration level of smoke resulting from combustion. The current advancement in technology has had a significant Significant influence across a range of domains, encompassing the realm of Internet of Things (IoT). The IoT network allows devices to interact and exchange information automatically, enhancing efficiency and security in various sectors. Early detection of smoke is crucial for preventing further damage and protecting human health. Therefore, this research utilizes MQ-135 and TGS 2600 sensors as smoke detection sensors. Through IoT, real-time measurement of smoke concentration can be achieved, enabling immediate actions in response to significant changes. The data collected through IoT can to enhance effectiveness, the information can be stored within a database and efficient research. By implementing this application, it is expected to provide a better solution for automatic detection and monitoring of smoke resulting from combustion, reducing air pollution risks, and enhancing human safety.

MANFAAT SUSENAS (Survei Sosial Ekonomi Nasional) DALAM PEMBANGUNAN MASYARAKAT KABUPATEN SUKABUMI Apriliyanti, Silvi; Kharisma, Ivana Lucia
MAJU : Indonesian Journal of Community Empowerment Vol. 2 No. 1 (2025): MAJU : Indonesian Journal of Community Empowerment, Januari 2025
Publisher : Lembaga Pendidikan dan Penelitian Manggala Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62335/xemch822

Data collection on the social and economic conditions of the comummunity is an activity carried out by the government to deremine the percentage og the poor population, school participation rates, and household expenditures. The cental Bureau of Statistics (BPS) conducts a program twice a year called the National Socioeconomic Survey (Susenas). In its implementation, Susenas uses the Paper and Pencil Interviewing (PAPI) method where the BPS team directly visits selected households as respondents to be interviewed according to the provided question template. There are two questionnaires used: first,related to education and employment. Second, household expenditure and consumtion. The results of the implemented Susenas provide an overview of the the indicators of people’s welfare, which is expeted to make future development planning more targeted and more responsive to the needs of the general public, so that in turn, the quality of life of the people of Sukabumi Regency through government policies referring to the results of Susenas will continue to improve along with the development of the region.

Klasifikasi Tanaman Hias Philodendron Berdasarkan Citra Daun Menggunakan Metode Convolutional Neural Network Al-Basori, Muhamad Cepnur; Insany, Gina Purnama; Kharisma, Ivana Lucia
Journal Cerita: Creative Education of Research in Information Technology and Artificial Informatics Vol 10 No 2 (2024): Journal CERITA : Creative Education of Research in Information Technology and Ar
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/cerita.v10i2.3238

Philodendron ornamental plants have a unique and varied aesthetic beauty, making them sought after in the landscaping and decoration industry. However, accurate classification of the various Philodendron species is challenging due to their morphological similarities and complex variations. In this research, an approach using Convolutional Neural Networks (CNN) is introduced to classify Philodendron ornamental plants based on the image of their leaves. This method aims to automatically identify Philodendron species through the use of artificial neural networks trained on leaf images. A CNN architecture was developed which includes a convolution layer and a max-pooling layer to extract features from the input image hierarchically. Also applied are data augmentation techniques to increase the variety of training samples and reduce overfitting. Experimental results show that the proposed CNN method is able to classify Philodendron ornamental plants with good accuracy, reaching 95,00% on the test dataset. This research contributes to the development of an automatic system for identifying Philodendron ornamental plants, which can be used in planting, plant care and plant identification applications.

Title

Found 16 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 16 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 16 Documents
Search