cover
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
juti.if@its.ac.id
Editorial Address
Gedung Teknik Informatika Lantai 2 Ruang IF-230, Jalan Teknik Kimia, Kampus ITS Sukolilo, Surabaya, 60111
Location
Kota surabaya,
Jawa timur
INDONESIA
JUTI: Jurnal Ilmiah Teknologi Informasi
ISSN : 24068535     EISSN : 14126389     DOI : http://dx.doi.org/10.12962/j24068535
JUTI (Jurnal Ilmiah Teknologi Informasi) is a scientific journal managed by Department of Informatics, ITS.
Arjuna Subject : -
Articles 5 Documents
Search results for , issue "Vol. 21, No. 2, July 2023" : 5 Documents clear
ELICITIATION OF INFORMATICS ENGINEERING INFOTECH WEBSITE NEEDS USING A USER PERSONA APPROACH Saleh, Abd.; Kusuma, Wahyu Andhyka
JUTI: Jurnal Ilmiah Teknologi Informasi Vol. 21, No. 2, July 2023
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v21i2.a1128

Abstract

Requirements elicitation is the most important activity in the software development process, because it has a direct impact on the success of the development process. The success of a software is determined from the involvement of a user persona at the design stage. The involvement of user personas in software design is critical in the requirements engineering process, because if the process is done incorrectly, the resulting software will also have poor quality. This study focuses on using the approach of the user persona in collecting information related to the needs of the informatics engineering infotech website at the University of Muhammadiyah Malang, so that the results obtained can be in accordance with the needs of the user. The final result that is expected in this research is a design of the plagiarism check feature for the practitioner's program automatically on the infotech website which is implemented in the form of use cases and prototypes. This feature will later make it easier for assistants in assessing program results collected by practitioners, so that the time needed to correct the program can be done faster.
SENTIMENT ANALYSIS ON E-LEARNING UNIVERSITY XYZ WITH NAÏVE BAYES CLASSIFIER METHOD Fernando, Jose; Fathoni, Fathoni
JUTI: Jurnal Ilmiah Teknologi Informasi Vol. 21, No. 2, July 2023
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v21i2.a1147

Abstract

The covid-19 pandemic forced students and lecturers to carry out teaching and learning from home. Therefore, XYZ    University focuses its students on using e-learning. E-learning that has been running and used by students must be evaluated, so that teaching and learning activities can run well. Evaluation can be done by collecting opinions based on the features of XYZ University E-learning on students through questionnaires. All opinions can be analyzed using classification method called Naïve Bayes and Support Vector Machine for comparison.  The research started by collecting data, preprocessing data, labeling using polarity, calculating the frequency that often from each e-learning feature, and calculating the accuracy of the Complement Naïve Bayes model and Support Vector Machine model. The research results conducted on 1995 dataset testing, in student opinions with 1289 positive values, 372 negative values, and 364 neutral values. Reinforced by the comparison result of Complement Naive Bayes and Support Vector Machine. When Complement Naïve Bayes model accuracy of 89%, recall 85,3%, and the f1-score 85%. While Support Vector Machine accuracy is lower 11,1% than Complement Naïve Bayes Model with only 74,4%. These results indicate that of the 12 features on XYZ University E-learning, 8 features have a good opinion, 2 features have a bad opinion, and 2 feature have a neutral opinion.
GEO-REPLICATION IN A REVIEW OF LATENCY AND COST-EFFECTIVENESS Putra, Taufiq Odhi Dwi; Ansyah, Adi S. S.; Arifin, Miftahol; Ijtihadie, Royyana M.
JUTI: Jurnal Ilmiah Teknologi Informasi Vol. 21, No. 2, July 2023
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v21i2.a1165

Abstract

Replication is a data distribution technique for synchronization between databases so that data remains consistent. Replication can overcome data loss problems and perform system recovery quickly if a problem occurs on one of the servers. One of the problems is when a natural disaster occurs at the server location. As a result, if you do not have data replication in different locations, it will cause the system to not run and possibly lose data. Then, geo-replication can reduce latency because the distance between the client and the data center is much closer. The application of geo-replication in general replicates data in all data centers. As a result, the cost of implementation is high because it requires a lot of resources. Because of the various advantages and disadvantages in its application, it is necessary to group geo-replication techniques to make it easier for researchers and technicians to adjust as needed. Therefore, this paper surveys the articles on Geo-replication techniques to implement cost-effectiveness and latency. The articles surveyed included a method for selecting replication sites, a method for reducing round trip time, a method according to data type, and selecting a leader to determine which server node to use. The results of the article survey show that implementing geo-replication for cost-effectiveness is more suitable for use in systems where all users do not need to access all data. Meanwhile, low latency is more suitable for systems used by various types of users. This paper can utilize the techniques that have been reviewed to overcome the problem of cost-effectiveness and latency in implementing Geo-replication.
MULTI-DOCUMENT SUMMARIZATION USING A COMBINATION OF FEATURES BASED ON CENTROID AND KEYWORD Ranggianto, Narandha Arya; Purwitasari, Diana; Fatichah, Chastine; Sholikah, Rizka Wakhidatus
JUTI: Jurnal Ilmiah Teknologi Informasi Vol. 21, No. 2, July 2023
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v21i2.a1195

Abstract

Summarizing text in multi-documents requires choosing important sentences which are more complex than in one document because there is different information which results in contradictions and redundancy of information. The process of selecting important sentences can be done by scoring sentences that consider the main information. The combination of features is carried out for the process of scoring sentences so that sentences with high scores become candidates for summary. The centroid approach provides an advantage in obtaining key information. However, the centroid approach is still limited to information close to the center point. The addition of positional features provides increased information on the importance of a sentence, but positional features only focus on the main position. Therefore, researchers use the keyword feature as a research contribution that can provide additional information on important words in the form of N-grams in a document. In this study, the centroid, position, and keyword features were combined for a scoring process which can provide increased performance for multi-document news data and reviews. The test results show that the addition of keyword features produces the highest value for news data DUC2004 ROUGE-1 of 35.44, ROUGE-2 of 7.64, ROUGE-L of 37.02, and BERTScore of 84.22. While the Amazon review data was obtained with ROUGE-1 of 32.24, ROUGE-2 of 6.14, ROUGE-L of 34.77, and BERTScore of 85.75. The ROUGE and BERScore values outperform the other unsupervised models.
DC-SAM: DILATED CONVOLUTION AND SPECTRAL ATTENTION MODULE FOR WHEAT SALT STRESS CLASSIFICATION AND INTERPRETATION Khotimah, Wijayanti Nurul
JUTI: Jurnal Ilmiah Teknologi Informasi Vol. 21, No. 2, July 2023
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v21i2.a1219

Abstract

Salt stress can impact wheat production significantly and is difficult to be managed when the condition is critical. Hence, detecting such stress whet it is at an early stage is important. This paper proposed a deep learning method called Dilated Convolution and Spectral Attention Module (DC-SAM), which exploits the difference in spectral responses of healthy and stressed wheat. The proposed DC-SAM method consists of two key modules: (i) a dilated convolution module to capture spectral features with large receptive field; (ii) a spectral attention module to adaptively fuse the spectral features based on their interrelationship. As the dilated convolution module has long receptive fields, it can capture short- and long dependency patterns that exist in hyperspectral data. Our experimental results with four datasets show that DC-SAM outperforms existing state-of-the-art methods. Also, the output of the proposed attention module reveals the most discriminative spectral bands for a given wheat stress classification task.

Page 1 of 1 | Total Record : 5