The Indonesian Journal of Computer Science
The Indonesian Journal of Computer Science (IJCS) is a bimonthly peer-reviewed journal published by AI Society and STMIK Indonesia. IJCS editions will be published at the end of February, April, June, August, October and December. The scope of IJCS includes general computer science, information system, information technology, artificial intelligence, big data, industrial revolution 4.0, and general engineering. The articles will be published in English and Bahasa Indonesia.
Articles
1,170 Documents
<![CDATA[Karakteristik Pembatalan Reservasi Kamar Hotel Pada Online Travel Agent Menggunakan Algoritma C4.5 ]]>
<![CDATA[Zhafira Zafitri]]>;
<![CDATA[Muhammad Ihsan Jambak]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3268
<![CDATA[Sistem reservasi hotel konvensional yang digunakan di masa lalu digantikan oleh perusahaan teknologi inovatif yang disebut dengan Online Travel Agent (OTA) seperti Traveloka, Tiket.com dan lainnya. Namun, adanya sistem reservasi online ini munculnya suatu permasalahan dimana tingginya tingkat pembatalan reservasi. Penelitian ini bertujuan menganalisis data dengan menggunakan aplikasi RapidMiner dan algoritma C4.5, penggunaan algoritma tersebut pada penelitian ini dapat membantu pihak OTA untuk memahami karakteristik customer yang cenderung membatalkan reservasi mereka dan memperkirakan peluang pembatalan reservasi di masa depan, serta mengatasinya. Data yang digunakan pada penelitian ini berasal dari situs kaggle dengan jumlah atribut/fitur sebanyak 28 fitur/atribut (27 atribut reguler dan 1 atribut sebagai label) dan terdiri dari 56.474 baris. Dari hasil modeling dan pengujian didapatkan rule dan pohon keputusan yang dapat dijadikan aturan dalam menentukan customer yang membatalkan reservasi. Hasil pohon keputusan menunjukan bahwa terdapat 10 fitur/atribut yang memiliki pengaruh besar terhadap pembatalan reservasi kamar hotel oleh customer dan atribut previous_cancellations merupakan atribut pertama yang dipertimbangkan untuk memahami karakteristik pembatalan tersebut. Pengujian model menggunakan K-Fold Cross Validation pada penelitian ini menghasilkan nilai akurasi sebesar 72.68% .]]>
<![CDATA[Refining Web-Based Job Search through Goal-Directed Design Improvement ]]>
<![CDATA[Buana, I Gusti Agung Ayu Made Bidari Bening]]>;
<![CDATA[Oetama, Raymond]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3269
<![CDATA[This study aims to improve a job search web application that not only addressed usability problems but also surpassed user expectations. A recently released job search web application was found to have usability problems during interviews with the Information Technology division. To measure the usability of the application and provide recommendations for improvement, the study uses the Goal-Directed Design framework, Performance Measurement method, and System Usability Scale measurement method. The evaluation was conducted twice, with the first assessment identifying problems and the second evaluation measuring the effectiveness of the recommendations made. The website prototype was developed and passed all test scenarios with an A+ grade. The modifications make important level of effectiveness, achieving an A+ grade with an 85% effectiveness rate. Furthermore, the website received exceptional user satisfaction, with an A+ rating and a score of 85.5 in usability satisfaction.]]>
<![CDATA[Identification of Maize Leaf Diseases Based On AlexNet and ResNet50 Convolutional Neural Networks ]]>
<![CDATA[Micheni, Maurice]]>;
<![CDATA[Birithia, Rael]]>;
<![CDATA[Mugambi, Cyrus]]>;
<![CDATA[Too, Boaz]]>;
<![CDATA[Kinyua, Margaret]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3270
<![CDATA[Maize crop protection is crucial for global food security, requiring accurate disease identification. In Kenya, farmers rely on subjective visual analysis of symptomatic leaves, which is time-consuming and prone to errors. Computer vision technologies, like deep learning and machine learning, offer promising solutions for disease identification. This study applies Convolutional Neural Networks (CNNs), specifically AlexNet and ResNet-50, to automatically learn image features and enhance speed and accuracy in maize leaf disease identification. A dataset of 3200 digital maize leaf disease images from Embu County is used for training and testing. AlexNet achieved the highest average accuracy of 98.3%, followed by ResNet-50 at 96.6%. The machine learning, support vector machine (SVM) exhibited the lowest average accuracy of 85.5%. These findings highlight the significance of utilizing AlexNet and ResNet-50 in maize leaf disease identification and classification.]]>
<![CDATA[Perbandingan Algoritma Support Vector Machine dan Neural Network untuk Klasifikasi Penyakit Hati ]]>
<![CDATA[Nurrokhman, Ma'mur Zaky]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3274
<![CDATA[Pada penelitian ini dilakukan perbandingan dua algoritma untuk klasifikasi penyakit hati, yaitu algoritma Support Vector Machine (SVM) dan Neural Network berjenis Multi Layer Perceptron (MLP). Pelatihan model dilakukan dengan bantuan Grid Search Cross Validation (GridSearchCV). Tujuan dari penelitian ini yaitu untuk mengetahui model machine learning dengan performa terbaik yang dihasilkan dari kedua algoritma tersebut. Dataset yang digunakan diambil dari situs UCI Machine Learning Repository dengan nama dataset yaitu Indian Liver Patient Dataset. Hasil penelitian menunjukkan bahwa model klasifikasi penyakit hati dengan algoritma SVM memiliki kinerja yang lebih baik dan akurasi yang lebih tinggi yaitu 87,65%. Kinerja yang baik ini juga ditandai dengan hasil pada Confusion Matrix yang menunjukkan bahwa model tidak memprediksi penderita penyakit hati sebagai bukan penderita penyakit hati sehingga tidak membahayakan penderita penyakit hati.]]>
<![CDATA[Performance Analysis of CT-Scan Covid-19 Classification Using VGG16-SVM ]]>
<![CDATA[Buana, Rifqi Genta]]>;
<![CDATA[Abdulloh, Ferian Fauzi]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3275
<![CDATA[The world was shaken by the emergence of a deadly virus variant called Severe Acute Respiratory Distress Syndrome CoronaVirus 2 which causes COVID-19 disease. This phenomenon started at the end of 2019 which later became an outbreak that caused a deadly pandemic. A significant number of people lose their lives because of this outbreak. A fast and precise diagnosis is needed so that the patients can be treated immediately. This study is intended to overcome these problems by utilizing machine learning to classify lung CT-Scan images. This study propose to use the Convolutional Neural Network (CNN) based on Visual Geometry Group (VGG) 16 layers architecture and Support Vector Machine (SVM) as its classifier. The classification results of the proposed method achieve 89% and 96% accuracy on the two different datasets. This study results can help overcome problems related to the COVID-19 diagnosis and the lack of resources to classify images. The world was shaken by the emergence of a deadly virus variant called Severe Acute Respiratory Distress Syndrome CoronaVirus 2 which causes COVID-19 disease. This phenomenon started at the end of 2019 which later became an outbreak that caused a deadly pandemic. A significant number of people lose their lives because of this outbreak. A fast and precise diagnosis is needed so that the patients can be treated immediately. This study is intended to overcome these problems by utilizing machine learning to classify lung CT-Scan images. This study propose to use the Convolutional Neural Network (CNN) based on Visual Geometry Group (VGG) 16 layers architecture and Support Vector Machine (SVM) as its classifier. The classification results of the proposed method achieve 89% and 96% accuracy on the two different datasets. This study results can help overcome problems related to the COVID-19 diagnosis and the lack of resources to classify images.]]>
<![CDATA[Child drowning prevention: GPS and LoRa based emergency alert system ]]>
<![CDATA[Enam, Md. Rayef]]>;
<![CDATA[Ghosh, Subhasish]]>;
<![CDATA[Sarker, Dr. M. Mesbahuddin]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3277
<![CDATA[UNICEF recently published in the "Country Office Report 2021" about the mortality of children in Bangladesh, "Every day, 30 children die from drowning – Bangladesh's second leading cause of under-five mortality. Drowning is preventable, and most cases occur within a child's home community." Bangladesh is a country of rivers, which means Bangladesh called a riverine country located in South Asia. The Center for Injury Prevention and Research conducted a survey, Around 19000 people of (all types of ages) drown every year in Bangladesh. Among them, 14500 which mean 77% are children. In our research, the emergency alert system is designed to be cost-effective and user-friendly for village communities in Bangladesh. The system is divided into two components: the kid is equipped with the transmitter, and the receiver is placed at home. The transmitter and receiver both use a LoRa transmission module that can communicate accurately within a 300-meter range (coverage up to 10 Kilometers) and can transmit 256 bytes of data. The transmitter collects geolocation data using a GPS module and sends the data to the receiver using the LoRa module. The receiver module is configured by setting up the geolocation of risky places. The receiver will send SMS or buzzing the receiver to alert the parents when the transmitter or kid is nearby risky places. The Equirectangular approximation method calculates the distance between children's positions from risky areas. Additionally, the transmitter and receiver may communicate encrypted messages using AES 128-bit symmetric encryption technology compatible with Arduino Nano controller. Thus, our emergency alert system can save children from drowning in the home environment.]]>
<![CDATA[The Role of Artificial Intelligence and Machine Learning in Smart and Precision Agriculture ]]>
<![CDATA[Bezas, Konstantinos]]>;
<![CDATA[Foteini Filippidou]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3278
<![CDATA[In recent years, the agricultural sector has been undergoing a new "green revolution" characterized by the increasing use of information and communication technology (ICT) and the transition from traditional farming methods to smart agricultural practices, also known as Agriculture 4.0. Robotics, combined with the use of drones, the emerging field of the Internet of Things (IoT), machine learning, and artificial intelligence, are now being deployed in digital transformation services in agriculture, aiming to optimize crop performance and agricultural sustainability. According to research and international literature, the new trends are now oriented towards the development of global and state-of-the-art connected agricultural systems through digital management platforms, with the goal of facilitating the flow of data and information. Although many efforts are being made to implement smart agriculture, there are still challenges that require further research.]]>
<![CDATA[User Acceptance Research on The Legal Documentation and Information Network Platform in Majalengka Government ]]>
<![CDATA[Hudoarma, Fathurahman Ma'ruf]]>;
<![CDATA[Sensuse, Dana Indra]]>;
<![CDATA[Lusa, Sofian]]>;
<![CDATA[Putro, Prasetyo Adi Wibowo]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3279
<![CDATA[The evaluation of JDIH platform's user acceptance in accessing legal documentation and information has not been conducted, resulting in an average visitation rate of only 15%. The objective of this study is to identify the factors that influence user acceptance of the JDIH platform and provide recommendations for enhancing visitor traffic to the JDIH platform. This study was conducted using a mixed methods approach, incorporating the Technology Acceptance Model as its foundational theory and integrating the Innovation Diffusion Theory, DeLone & McLean IS Success Model, and Habit variables as its external constructs. The quantitative data processing method was conducted using the PLS-SEM method with the assistance of the SmartPLS application. The findings of this study reveal that the factors of relative advantage, habit, perceived benefits of use, and intention to use significantly influence user acceptance in utilizing the JDIH platform.]]>
<![CDATA[Perbandingan Kinerja LSTM, Bi-LSTM, dan GRU pada Klasifikasi Judul Berita Clickbait ]]>
<![CDATA[Anas Fikri Hanif]]>;
<![CDATA[Theopilus Bayu Sasongko]]>;
<![CDATA[Arif Dwi Laksito]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3281
<![CDATA[Maraknya penggunaan konsep clickbait menjadi tantangan bagi para pengguna media sosial. Sering kali mereka tertipu dengan judul sebuah artikel yang berbeda dengan isi artikelnya. Oleh karena itu diperlukan sebuah model yang mampu melakukan klasifikasi terhadap judul clickbait maupun non-clickbait. Meskipun beberapa penelitian sudah dilakukan untuk membuat sebuah model klasifikasi judul clickbait, akan tetapi analisa perbandingan sangat diperlukan untuk menentukan model terbaik yang dapat digunakan dalam klasifikasi judul clickbait. Oleh karenanya peneliti melakukan perbandingan terhadap tiga model deep learning yang berbeda (LSTM, Bi-LSTM, dan GRU) guna menemukan model terbaik yang dapat menyelesaikan kasus ini dengan memanfaatkan data publik dari penelitian sebelumnya. Hasilnya algoritma GRU merupakan algoritma terbaik yang berhasil mencapai akurasi 97,16%. Tidak hanya itu GRU juga memiliki nilai tinggi dalam beberapa metrik evaluasi lainnya, yaitu precision 96,63%, recall 97,66%, dan F1-score 97,14%. Selain menghasilkan metrik evaluasi yang baik, model GRU juga tergolong cepat dalam melakukan training dengan waktu 328 detik.]]>
<![CDATA[Analisa Perbandingan Algoritma CNN dan LSTM untuk Klasifikasi Pesan Cyberbullying pada Twitter ]]>
<![CDATA[Radjavani, Alifqi]]>;
<![CDATA[Bayu Sasongko, Theopilus]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v12i4.3287
<![CDATA[Dengan meningkatnya penggunaan sosial media, cyberbullying telahmencapai titik puncak sepanjang masa. Anonimitas pada internet membuatcyberbullying sangat merusak, dikarenakan korban akan merasa jika tiadajalan keluar dari pelecehan tersebut. Setiap individu harus selalu waspadaterhadap cyberbullying dan dihimbau untuk selalu melindungi diri sendiribeserta orang lain dari hal ini. Pada kasus ini, penulis membuat model yangsecara otomatis akan menandai tweet yang berpotensi membahayakan sertamemecah pola pesan kebencian tersebut. Dataset yang disediakan olehpenulis berisi sekitar 48.000 tweet yang telah dilabeli sesuai dengan jenis dandata-data tersebut telah diseimbangkan dan berisi sekitar 8000 data.Penelitian ini membandingkan algoritma Convolutional Neural Networkdengan Long Short-Term Memory untuk menentukan algoritma terbaik untukdataset pada penelitian ini. Berdasarkan hasil penelitian yang sudahdilakukan disimpulkan jika Long Short-Term Memory adalah algoritmaterbaik dengan f1-score 83.09%.]]>
