cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Rudy Herteno
Contact Email
rudy.herteno@ulm.ac.id
Phone
+6282250380732
Journal Mail Official
rudy.herteno@ulm.ac.id
Editorial Address
Jalan Ahmad Yani KM. 36, Kalimantan Selatan
Location
Kota banjarmasin,
Kalimantan selatan
INDONESIA
Journal of Data Science and Software Engineering
Published by Universitas Lambung Mangkurat
ISSN : 27755320     EISSN : 27755487     DOI : https://doi.org/10.20527/jdsse.v1i01.13
Core Subject : Science,
Computer Science & IT
Journal of Data Science and Software Engineering adalah jurnal yang dikelola oleh program studi Ilmu Komputer Universitas Lambung Mangkurat untuk mempublikasikan artikel ilmiah mahasiswa tugas akhir. Terbit tiga kali dalam setahun.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 46 Documents
 1   2   3   4   5 
IMPLEMENTASI TRANSFER LEARNING CONVOLUTIONAL NEURAL NETWORK UNTUK DETEKSI LUBANG JALAN PADA VIDEO DRONE Miftahul Muhaemen; Mohammad Reza Faisal; Dodon Turianto Nugrahadi; Andi Farmadi; Rudy Herteno
Journal of Data Science and Software Engineering Vol 1 No 01 (2020)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (448.61 KB) | DOI: 10.20527/jdsse.v1i01.3

Abstract

Pothole is one of the problems that can cause harm to a person or a lot of people and can even cost lives. So a lot of research has been done to detect potholes, especially image-based. This research uses Unmanned Aerial Vehicle (UAV) to get aerial video dataset and train Convolutional Neural Network (CNN) with the dataset. However, instead of doing learning from the beginning, transfer learning can be used to train CNN to recognize the object of a pothole and measure the value of its performance and what the optimal frame rate is. Then the results of this study indicate that the CNN model, ssd_resnet_50_fpn_coco gets an average performance value of 48.90 mAP. And the optimal frame rate with the average highest performance value at a frame rate of 30FPS with a value of 49.43 mAP, followed by 1FPS with a value of 48.36 mAP . Keywords: Performance, Transfer Learning, Convolutional Neural Network, Pothole Detection, Aerial Video.
IMPLEMENTASI ALGORITMA ENKRIPSI RSA PADA APLIKASI INSTANT MESSAGING Ardiansyah Sukma Wijaya; Dodon T. Nugrahadi; Muhammad Itqan Mazdadi; Andi Farmadi; Ahmad Rusadi
Journal of Data Science and Software Engineering Vol 1 No 01 (2020)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (428.136 KB) | DOI: 10.20527/jdsse.v1i01.4

Abstract

At this time the use of instant messaging applications is increasingly used compared to the use of SMS or other media because of its use which is more practical and faster. From the other side, the message information sent certainly requires confidentiality so that the message is not spread and known by others. For this reason mechanisms are needed, one of which is encryption to maintain message security. This research will implement the RSA (Rivest Shamir Adleman) encryption algorithm in the instant messaging application. This study uses a key length scenario of RSA 1024, 2048, 4096, and 6144 bits and a message length of 125, 250, 500, and 1000 characters implemented on 3 different devices. The results of testing on time and speed are the shorter the key used, the process will be shorter and faster. Keywords : RSA, Processing Time, Processing Speed
PENGARUH SOFTWARE METRIK PADA KINERJA KLASIFIKASI CACAT SOFTWARE DENGAN ANN Achmad Zainudin Nur; Mohammad Reza Faisal; Friska Abadi; Irwan Budiman; Rudy Herteno
Journal of Data Science and Software Engineering Vol 1 No 01 (2020)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (180.324 KB) | DOI: 10.20527/jdsse.v1i01.5

Abstract

Software Defect Prediction has an important role in quality software. This study uses 12 D datasets from NASA MDP which then features a selection of metrics categories software. Feature selection is performed to find out metrics software which are influential in predicting defects software. After the feature selection of the metric software category, classification will be performed using the algorithm Artificial Neural Network and validated with 5-Fold Cross Validation. Then conducted an evaluation with Area Under Curve (AUC), From datasets D” 12 NASA MDP that were evaluated with AUC, PC4, PC1 and PC3 datasets obtained the best AUC performance values. Each value is 0.915, 0.828, and 0.826 using the algorithm Artificial Neural Network.
Penyeleksian Calon Karyawan Menggunakan Metode Pembobotan Shannon Entropy dan Metode ARAS Halimah; Dwi Kartini; Friska Abadi; Irwan Budiman; Muliadi
Journal of Data Science and Software Engineering Vol 1 No 01 (2020)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (220.092 KB) | DOI: 10.20527/jdsse.v1i01.7

Abstract

This study discusses the selection of prospective employees using the Shannon Entropy weighting method and the Additive Ratio Assessment (ARAS) method which aims to determine the accuracy of the results obtained from the method. The Shannon Entropy method is a weighting method that assigns criteria weights based on the calculation of alternative employee selection data and the Additive Ratio Assessment (ARAS) method is a ranking method that has a utility function. Testing the data in this study using the Mean Absolute Error (MAE) method to get system accuracy results. Based on testing conducted using 6 criteria and 56 alternative data for prospective employees, the accuracy of the method used was 85.34%.
SENSITIVITY TEST FUZZY TOPSIS AND FUZZY TOPSIS ROC METHODS FOR THE SELECTION OF THE SASIRANGAN BANJAR FABRIC MOTIFS Nafis Satul Khasanah; Andi Farmadi; Dodon Turianto Nugrahadi; Muliadi; Rudy Herteno
Journal of Data Science and Software Engineering Vol 1 No 01 (2020)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (145.762 KB) | DOI: 10.20527/jdsse.v1i01.11

Abstract

Decision making is one of problem that we often find in society, as well as choosing the fabric of the motif of Sasirangan Banjar that currently there are many kinds of it. So, to find out the ideal solution need the various of considerations that will make hesitation. And it will influence in time of accuracy of decision-making. Multi Atribut Decision Making (MADM) is a part of decision-making with various criteria that have a weight. The objective is to find out and ideal solution that can be optimal in implementation. The used Fuzzy TOPSIS and Fuzzy TOPSIS ROC methods an important to make an assesment with a simple system and calculation of priority weights to produces various motives. The result of two methods that have been test sensitivity are the best decision with the result 7,16% for weight Rank Order Centroid (ROC) and 0,6% for weight TOPSIS. So, Fuzzy TOPSIS ROC is better in values weight because it has a higher sensitivity than the Fuzzy TOPSIS.
IMPLEMENTASI TEKNIK PENDEKATAN LEVEL DATA UNTUK MENYELESAIKAN KASUS DATA TIDAK SEIMBANG PADA KLASIFIKASI CACAT SOFTWARE Hanif Rahardian; Mohammad Reza Faisal; Friska Abadi; Radityo Adi Nugroho; Rudy Herteno
Journal of Data Science and Software Engineering Vol 1 No 01 (2020)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (275.168 KB) | DOI: 10.20527/jdsse.v1i01.13

Abstract

Defects can cause significant software rework, delays, and high costs, to prevent disability it must be predictable the possibility of defects. To predict the disability the metrics software dataset is used. NASA MDP is one of the popular software metrics used to predict software defects by having 13 datasets and is generally unbalanced. The reward in the dataset can reduce the prediction of software defects because more unbalanced data produces a majority class. Data imbalance can be handled with 2 approaches, namely the data level approach technique and the algorithm level approach technique. The data level approach technique aims to improve class distribution by using resampling and data synthesis techniques. This research proposes a data level approach using resampling techniques, namely Random Oversampling (ROS), Random Undersampling (RUS), Synthetic Minority Oversampling Technique (SMOTE), Tomek Link (TL) and One-Sided Selection (OSS) which are classified with Naïve Bayes was also validated using 10 Fold Cross-Validation, then evaluated with the Area Under ROC Curve (AUC). Prediction results based on the dataset obtained the best AUC value on MC2 with a value of 0.7277 using the Synthetic Minority Oversampling Technique (SMOTE). Prediction results based on the data level approach technique obtained the best average AUC value using Tomek Link (TL) with a value of 0.62587. Prediction results based on the dataset obtained the best AUC value on MC2 with a value of 0.7277 using the Synthetic Minority Oversampling Technique (SMOTE). Prediction results based on the data level approach technique obtained the best average AUC value using Tomek Link (TL) with a value of 0.62587. Prediction results based on the dataset obtained the best AUC value on MC2 with a value of 0.7277 using the Synthetic Minority Oversampling Technique (SMOTE). Prediction results based on the data level approach technique obtained the best average AUC value using Tomek Link (TL) with a value of 0.62587.
PERFORMANCE ANALYSIS OF CLASSIFIER ON FACEBOOK DATA USING UNIGRAM & BIGRAM COMBINATIONS Yudha Sulistiyo Wibowo; Mohammad Reza Faisal; Ahmad Rusadi; Dodon T Nugrahadi; Muhammad Itqan Mazdadi
Journal of Data Science and Software Engineering Vol 1 No 02 (2020)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (240.626 KB)

Abstract

Penelitian ini pada analisis sentimen menggunakan metode random forest sebagai klasifikasi. TF-IDF adalah fitur berbobot dan fitur kombinasi dari N-Grams adalah unigram dan bigram sebagai kata fitur. Dalam penelitian ini TF-IDF digunakan untuk fitur ekstraksi, tes ini menggunakan data Komentar Facebook tentang Berita Olahraga. Dalam studi ini, dataset digunakan sebanyak 1000 data terbagi menjadi 2, yaitu data pengujian dan pelatihan data. Mencapai kinerja akurasi tinggi hasil dalam fitur unigram dengan akurasi 83,67% dari 2757 fitur, Bigram menghasilkan 58% dengan fitur sebanyak 8457.
Penerapan Long Short Term Memory RNN untuk Prediksi Transaksi Penjualan Minimarket Patrick Ringkuangan; Fatma Indriani; Muhammad Itqan Mazdadi; Irwan Budiman; Andi Farmadi
Journal of Data Science and Software Engineering Vol 1 No 02 (2020)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (475.488 KB)

Abstract

This study aims to determine whether it can build a prediction of sales of goods at the Lapan-Lapan Mart by using the Long Short Term Memory Recurrent Neural Network method that can be used to predict the sale of goods. In this study, the data was taken from the Lapan-Lapan Mart, together with data on 10 different items sold every day. The data is then compiled for the level of sales to be weekly and a total of 52 data is obtained for each item so that the total data is amounted to 520. To get the weight in the LSTM calculation, there are two processes, namely forward and backward . the weight will be used to make predictions using the basic formula of the LSTM.Based on the research that has been done, it is known that the highest accuracy of using MAD (Mean Absolute Deviation) is 91 gr (11.61803507) indomie goods and 1.8kg of lemon daia (2.077000464) for the lowest MAD
IMPLEMENTASI ALGORITMA C5.0 UNTUK MEMBENTUK POLA POHON KEPUTUSAN DIAGNOSA PENYAKIT DIABETES MELLITUS Muhammad Latief Saputra; Irwan Budiman; Radityo Adi Nugroho; Dwi Kartini; Muliadi
Journal of Data Science and Software Engineering Vol 1 No 02 (2020)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (464.45 KB)

Abstract

This study applies the C5.0 algorithm to form a decision tree pattern for diagnosing diabetes mellitus. C5.0 algorithm is a decision tree based classification algorithm. This algorithm focuses on the acquisition of information gain on all attributes. The data used is a diabetes mellitus dataset obtained from the Kaggle database website. Data preprocessing is done and data sharing is done 4 times with the distribution of training data 60% 70% 80% and 90%. Data sharing uses stratafied random sampling methods so that the distribution of training and testing data is in accordance with its portion. Calculation of accuracy performance using confusion matrix. Classification performance using C5.0 algorithm. With 90% training data get 72.73% accuracy of rules generated as many as 70 rules. With 80% training data the accuracy value is 74.03%. The rule is 64 rules. With 70% training data get an accuracy value of 76.52% of the rules generated 59 rules. With 60% training data get an accuracy value of 74.59% of the rules generated as many as 53 rules. From all the experiments that have been done, the best accuracy is found in experiments with 70% training data.
IMPLEMENTASI METODE CONVOLUTIONAL NEURAL NETWORK UNTUK PREDIKSI HARGA SAHAM LQ45 Aris Pratama; Dwi Kartini; Akhmad Yusuf; Andi Farmadi; Irwan Budiman
Journal of Data Science and Software Engineering Vol 1 No 02 (2020)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (195.714 KB)

Abstract

Stock are securities of ownership of a company. Investments in the stock market on average can produce a return rate of 10-30% per year, this amount is about two to three times higher than the rate of return on deposits or savings in banks which are only 5-10 % every year. One problem is the stock price is fluctuating or changing due to certain factors. This study compares several window size data with different amounts of data, aiming to find window size data with a more accurate amount of data for stock price predictions. Convolutional neural network algorithm with window size data of 7 days, 14 days, 21 days and 28 days in the amount of data 1 year and 2 years for stock price predictions. The results of this study are the convolutional neural network algorithm with a data window size of 7 days at the amount of data 2 years is more accurate than the window size data and the amount of other data. Because the smallest error result is 0.000201587.

Page 1 of 5 | Total Record : 46

 1   2   3   4   5 

Filter by Year

2020 2022


Reset
Filter By Issues
All Issue Vol 3 No 03 (2022) Vol 3 No 02 (2022) Vol 3 No 01 (2022) Vol 2 No 03 (2021) Vol 2 No 02 (2021) Vol 2 No 01 (2021) Vol 1 No 02 (2020) Vol 1 No 01 (2020)