Garuda - Garba Rujukan Digital

Article Per Year (5 Year)

All

IJISCS (International Journal of Information System and Computer Science)

ijiscs
Website

Published by Institut Bakti Nusantara

ISSN : 25980793 EISSN : 2598246X DOI : -

Core Subject : Science, Engineering,

Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

The IJISCS (International Journal of Information System and Computer Science) is a publication for researchers and developers to share ideas and results of software engineering and technologies. These journal publish some types of papers such as research papers reporting original research results, technology trend surveys reviewing an area of research in software engineering and technologies, survey articles surveying a broad area in software engineering and technologies. The scope covers all areas of software engineering methods and practices, object-oriented systems, rapid prototyping, software reuse, cleanroom software engineering, stepwise refinement/enhancement, ambiguity in software development, impact of CASE on software development life cycle, knowledge engineering methods and practices, formal methods of specification, deductive database systems,logic programming, reverse engineering in software design, expert systems, knowledge-based systems, distributed knowledge-based systems, knowledge representations, knowledge-based systems in language translation & processing, software and knowledge-ware maintenance, Software Specification and Modeling, Embedded and Real-time Software (ERTS), and applications in various domains of interest.

Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi

Articles 121 Documents

5 6 7 8 9

COMPARISON OF K-NEAREST NEIGHBOR AND NAÏVE BAYES FOR BREAST CANCER CLASSIFICATION USING PYTHON Irma Handayani; Ikrimach Ikrimach
IJISCS (International Journal of Information System and Computer Science) Vol 5, No 1 (2021): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v5i1.953

Classification is widely used to determine decisions according to new knowledge gained from processing past data using algorithms. The number of attributes can affect the performance of an algorithm. Several data mining methods that are widely used for classification include the K-Nearest Neighbor and naïve Bayes algorithm. The best algorithm for one data type is not necessarily good for another data type. It is even possible that a good algorithm will be horrendous for other data types. To overcome this issue, this study will analyze the accuracy of the K-Nearest Neighbor and Naïve Bayes algorithms for the classification of breast cancer. So that patients with existing parameters can be predicted which are malignant and benign breast cancer. This pattern can be used as a diagnostic measure so that the cancer can be detected earlier and is expected to reduce the mortality rate from breast cancer.

THE EFFECTS OF FEATURE SELECTION METHODS ON THE CLASSIFICATIONS OF IMBALANCED DATASETS Femi Dwi Astuti; Indra Yatini Buryadi
IJISCS (International Journal of Information System and Computer Science) Vol 6, No 3 (2022): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v6i3.1279

imbalanced data often results in less than optimal classification. Also, datasets with a large number of attributes tends to make the classification results not too good, and in order get better classification accuracy results, one thing that could be done is to perform pre-processing to select the features to be used in the classification. This research uses information gain and gain ratio feature selection algorithms for the pre-processing stage prior to classification, and Naïve Bayes algorithm for the classification. The test is performed to determine the values of accuracy, precision, recall from the classification process without feature selection; accuracy value with information gain feature selection; accuracy value with gain ratio; and accuracy value with CBFS feature selection. The results are then compared to determine which feature selection algorithm gives the best results when applied to data with imbalanced classes. The results showed that the classification accuracy on the default of credit card client dataset using Nave Bayes algorithm was 64.27%. The information gain feature selection was able to increase the accuracy by 5.27% (from 64.27% to 69.54%), while the gain ratio feature selection was able to increase the accuracy by 14.19% (from 64.27% to 78.46%). In this case, the gain ratio is more suitable for data with greatly varied attribute values.

GOOGLE PLAY STORE USERS COMMENT REVIEW CLASSIFICATION USING SVM CLASSIFIER AND RANDOM FOREST Hadiyasa, Muhammad Rafi; Isa, Sani Muhamad
IJISCS (International Journal of Information System and Computer Science) Vol 7, No 3 (2023): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v7i3.1584

In today's digital age, social media stands as a dynamic arena where individuals freely express their thoughts and opinions, from succinct tweets on Twitter to expansive narratives on platforms like Facebook and Instagram. However, amidst this vast sea of user-generated content, a glaring void persists a definitive rating system capable of distilling the nuanced sentiments embedded within these diverse commentaries. This study thus emerges as a pioneering endeavor, poised to bridge this crucial gap in sentiment analysis. Leveraging the transformative potential of the Word2vec methodology in the preprocessing phase, researchers embark on a comprehensive journey to classify comments on a meticulous 1-5 rating scale, thereby unraveling the multifaceted spectrum of sentiments encapsulated within them. Complementing this groundbreaking approach, the Random Forest classification model is harnessed to bolster the analytical prowess of the study. The resultant accuracy score of 60.4% stands as a testament to the study's significant strides towards achieving a deeper understanding of comment sentiment in the realm of social media. However, this is merely the inception of a promising trajectory; the study's findings hold the promise of not only refining sentiment analysis techniques but also revolutionizing diverse sectors, from market research to product development. With this study, the narrative of sentiment analysis transcends the confines of academia, beckoning forth a new era of nuanced comprehension and meaningful engagement within the sphere of social media commentary. As the study concludes, it leaves behind a compelling call to action, inviting further exploration and innovation in this dynamic field.

ANDROID-BASED LECTURE ROOM SCHEDULING APPLICATION (CASE STUDY : STMIK PRINGSEWU CAMPUS) Dela Jemirnia; Angger Purno Nugroho; Sucipto Sucipto
IJISCS (International Journal of Information System and Computer Science) Vol 2, No 3 (2018): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v2i3.707

Technological developments are increasingly rapid and fast, especially and communication technology. For all fields, starting the fields of buying and selling, education, health, and others. The communication and information technology very helpful in various ways from the word of lecturers, campus staff, and students. STMIK Pringsewu still use manual, student still have to see schedule of waiting room of STMIK Pringsewu. Application development using php script. The method used to develop this system is by System Development Life Cycle approach with stages and design using Data Flow Diagram modelling. Based on the results of system testing, Application and Scheduling Applications are designed in accordance with the expected, it can be concluded that the application design courses and lecture room based on Android is work and function.

ACCURACY OPTIMIZATION OF KWH HIGH VOLTAGE CONSUMER TRANSACTIONS WITH SELECTION OF CURRENT TRANSFORMER (CT) RATIO IN ACCORDANCE WITH CONTRACTED POWER Soetjipto Soewono; Nanang Hadi
IJISCS (International Journal of Information System and Computer Science) Vol 4, No 3 (2020): IJISCS (International Journal Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v4i3.930

The greater growth of electricity consumption, especially for high voltage consumers, it is important for PLN to know the effect of the current transformer (CT) error ratio in the accuracy of the kwh of electricity transactions, by researching the error ratio of CT 400/1 and 800/1 R, S, and T phase. When the contracted power of 120 MVA can be used CT class 0.2s ratio 400/1 and 800/1 ratio, when using CT class 0.2s ratio 400/1 then the kwh meter can be set according to the CT ratio that is the ratio 400/1 because CT ratio 400/1 has a negative error ratio at loads below 73.59%, and positive error ratio at loads over 73.59% up to 100% load, and` when using CT class 0.2s ratio 800/1 then the kwh meter can set a CT ratio of 800 / 0.98 because CT ratio 800/1 has a positive error ratio of 0.02% from 1% load to 100% load, so that it does not harm the customer as a positive CT ratio error tolerance . This needs to be done in order to create justice between PLN and high voltage consumers in the calculation of kwh transactions.The greater growth of electricity consumption, especially for high voltage consumers, it is important for PLN to know the effect of the current transformer (CT) error ratio in the accuracy of the kwh of electricity transactions, by researching the error ratio of CT 400/1 and 800/1 R, S, and T phase. When the contracted power of 120 MVA can be used CT class 0.2s ratio 400/1 and 800/1 ratio, when using CT class 0.2s ratio 400/1 then the kwh meter can be set according to the CT ratio that is the ratio 400/1 because CT ratio 400/1 has a negative error ratio at loads below 73.59%, and positive error ratio at loads over 73.59% up to 100% load, and` when using CT class 0.2s ratio 800/1 then the kwh meter can set a CT ratio of 800 / 0.98 because CT ratio 800/1 has a positive error ratio of 0.02% from 1% load to 100% load, so that it does not harm the customer as a positive CT ratio error tolerance . This needs to be done in order to create justice between PLN and high voltage consumers in the calculation of kwh transactions.

GOODS INVENTORY APPLICATION SYSTEM of "MEKAR JAYA" VILLAGE-OWNED ENTERPRISES (BUMDes) Ari Bowo; Maharani Panggestu; Muhamad Muslihudin
IJISCS (International Journal of Information System and Computer Science) Vol 6, No 2 (2022): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v6i2.1210

Village-Owned Enterprises are known to the public as BUMDes according to Government Regulation Number 4 of 2015 concerning the Establishment, Management, and Management of Village-Owned Enterprises to manage assets, services, and other businesses for the welfare of the village community. BUMDes is one of the agencies working in the economic and social fields as a provider of agents to the community, especially in the village business sector. The problem in this study is that the recording of goods sold often results in errors in the details of the number of goods sold and the stock of goods that are still available at BUMDes Mekar Jaya. As a result, it interferes with the business marketing process because the available goods data is less accurate. The research method used in this research is data collection method, information system development method of System Development Life Cycle (SDLC), and fishbone diagram research flow. The analysis result of this study is that the web-based inventory application system at BUMDes Mekar Jaya in Panjerejo Village, Gadingrejo District, Pringsewu Regency has explained that by making a web-based inventory application system at BUMDes Mekar Jaya can improve work performance more, precisely and accurately. So, it can make it easier to work on reports of incoming goods or outgoing goods. For the manufacture of the application system, the researcher uses the PHP programming language and the MySQL database which is supported by several related applications. In this study, researchers also conducted testing using black box testing. A black box is a way to perform tests such as the functions which exist in the application to make it easier for general users. With the application system, this inventory can be used simultaneously with the old system so that within a certain time the old system can be abandoned and the new system can be fully used effectively.

THE IMPLEMENTATION OF A SIMPLE LINIER REGRESSIVE ALGORITHM ON DATA FACTORY CASSAVA SINAR LAUT AT THE NORTH OF LAMPUNG Dwi Marisa Efendi
IJISCS (International Journal of Information System and Computer Science) Vol 2, No 1 (2018): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v2i1.549

Cassava is one type of plant that can be planted in tropical climates. Cassava commodity is one of the leading sub-sectors in the plantation area. Cassava plant is the main ingredient of sago flour which is now experiencing price decline. The condition of the abundant supply of sago or tapioca flour production is due to the increase of cassava planting in each farmer. With the increasing number of cassava planting in farmer's plantation cause the price of cassava received by farmer is not suitable. So for the need of making sago or tapioca flour often excess in buying raw material of cassava This resulted in a lot of rotten cassava and the factory bought cassava for a low price. Based on the problem, this research is done using data mining modeled with multiple linear regression algorithm which aim to estimate the amount of Sago or Tapioca flour that can be produced, so that the future can improve the balance between the amount of cassava supply and tapioca production. The variables used in linear regression analysis are dependent variable and independent variable . From the data obtained, the dependent variable is the number of Tapioca (kg) symbolized by Y while the independent variable is milled cassava symbolized by X. From the results obtained with an accuracy of 95% confidence level, then obtained coefficient of determination (R2) is 1.00. While the estimation results almost closer to the actual data value, with an average error of 0.00.

SERVICES CANCER DETECTION SYSTEM USING K-NEAREST NEIGHBOURS(K-NN) METHOD AND NAÏVE BAYES CLASSIFIER Sri Rezeki Candra Nursari; Nanda Mahya Barokatun Nisa
IJISCS (International Journal of Information System and Computer Science) Vol 4, No 1 (2020): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v4i1.893

According to WHO (World Health Organization) data, every 2 minutes a woman dies. In Indonesia alone, 40 - 45 women are diagnosed with cervical cancer every day. Of those diagnosed, around 20-25 die from cervical cancer. About 95% more cervical cancer is caused by infection with the HPV virus or the human papilloma virus and an estimated death rate reaches 270,000 deaths each year. Cervical cancer occupies the third rank type of cancer in the world after breast and lung cancer, because the symptoms are not very visible at an early stage, so it is referred to as "Silent Killer". Based on the data and cases above, the latest technology that is able to detect cervical cancer in order to speed up the detection process for someone to be quickly treated is an artificial intelligence application that serves to detect whether someone should run 4 cervical cancer testing techniques, namely Hinselmann, Schiller, Citology, and biopsy with K-nearest neighbors algorithm and Naive Bayes classifier is one of the latest technologies that can facilitate the work of a doctor and speed up the process of detecting someone whether to run 4 testing techniques or not. The correct amount of data classified by the K-Nearest Neighbors method is 558 data from 858 data. The classification accuracy of the Naïve Bayes method is 84.7%. The correct amount of data classified by the Naïve Bayes method is 558 data from 858 data. The classification accuracy of the Naïve Bayes method is 84%.

STOCK MARKET FORECASTING: A REVIEW OF LITERATURE Srivatsa Maddodi; K. G. Nandha Kumar
IJISCS (International Journal of Information System and Computer Science) Vol 5, No 3 (2021): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v5i3.1064

Prediction of stock markets is a complex and challenging task due to price data generated is huge in volume, changes every second, sensitive to human emotions (fear), actions (Wars) and natural disasters (floods, famine, earthquake). Many Methods have been used to predict the stock price like Technical Analysis, Time Series, Fundamental analysis, etc. Prediction of stock price provides knowledgeable information about the status of the stock price and will also help in decision making for the investors. Much research has been carried out in prediction of stock prices using different approaches of Machine Learning techniques, Deep Learning, Sentiment Analysis etc. This paper explores and reviews some of the recent works carried out in predicting stock prices.

APPROXIMATE AND STABILITY SOLUTION FOR NON-LINEAR SYSTEM OF INTEGRODIFFERENTIAL EQUATIONS OF VOLTERRA TYPE WITH BOUNDARY CONDITIONS Butris, Raad Noori; Noori, Noori R
IJISCS (International Journal of Information System and Computer Science) Vol 7, No 2 (2023): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v7i2.1482

In this paper, we investigate the approximation and stability solutions of non-linear systems of integro-differential equations of Volterra type with boundary conditions, by using the numerical-analytic method which were introduced by Samoilenko. The study of such integro-differential equations leads to extend the results obtained by Butris for changing the system of non-linear integro- differential equations of Volterra type to the system of non-linear integro-differential equations of the Volterra type with boundary conditions. Theorems on a solutions are established under some necessary and sufficient conditions on compact spaces.

Page 7 of 13 | Total Record : 121

5 6 7 8 9

Filter by Year

2017 2025

Filter By Issues

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
Muhamad Muslihudin

Contact Email
ijiscs@ftikomibn.ac.id

Phone
+6272922240

Journal Mail Official
ijiscs@ftikomibn.ac.id

Editorial Address
Editor IJISCS (International Journal of Information System and Computer Science) Bakti Nusantara Institute Street Wisma Rini No.09 Pringsewu, Lampung Phone: 0729-22240

Location
Kab. pringsewu,

Lampung

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name Muhamad Muslihudin

Contact Email ijiscs@ftikomibn.ac.id

Phone +6272922240

Journal Mail Official ijiscs@ftikomibn.ac.id

Editorial Address Editor IJISCS (International Journal of Information System and Computer Science) Bakti Nusantara Institute Street Wisma Rini No.09 Pringsewu, Lampung Phone: 0729-22240

Location Kab. pringsewu, Lampung INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
Muhamad Muslihudin

Contact Email
ijiscs@ftikomibn.ac.id

Phone
+6272922240

Journal Mail Official
ijiscs@ftikomibn.ac.id

Editorial Address
Editor IJISCS (International Journal of Information System and Computer Science) Bakti Nusantara Institute Street Wisma Rini No.09 Pringsewu, Lampung Phone: 0729-22240

Location
Kab. pringsewu,

Lampung

INDONESIA