Garuda - Garba Rujukan Digital

Innovation In Project Management Utilizing Machine Learning Technology Joseph Teguh Santoso; Budi Raharjo
Journal of Technology Informatics and Engineering Vol 2 No 3 (2023): December : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v2i3.163

The successful adoption of programmable machines for complex tasks opens up opportunities for productivity and more efficient communication, but also poses serious challenges in IT project management. This study aims to tackle the issue of high project failure rates caused by inadequate planning. It aims to assist project managers in enhancing their project planning by implementing real-time solutions through the utilization of machine learning (ML) algorithms and a user-friendly graphical interface. This research is divided into two key phases. The initial phase involves an examination of existing literature in the field of machine learning to identify relevant concepts applicable to project management. In the subsequent stage, two distinct types of ML algorithms, namely example-based learning and regression modeling, will be integrated into a user-friendly platform. This research develops a system that utilizes machine learning algorithms to assist project managers in real-time or near real-time through a user-friendly graphical interface, with a focus on improving project planning and risk mitigation. This research shows that machine learning algorithms provide positive results in overcoming human factors and preventing risks based on the experience of project managers.

PENGGUNAAN ASSOSIATION RULE MINING DALAM PENETAPAN HARGA PROMOSI, STOK, DAN PENATAAN PRODUK PADA ETALASE Budi Raharjo
E-Bisnis : Jurnal Ilmiah Ekonomi dan Bisnis Vol 13 No 1 (2020): Jurnal Ilmiah Ekonomi dan Bisnis
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/e-bisnis.v13i1.282

In the first quarter of 2017, retail in Indonesia recorded a growth of 2.5%, while in 2018 the growth was only in the range of 1% -1.5%. The cause of the slow growth is the change in the consumption pattern of the people and it will continue at the beginning of 2018. In addition, the decreasing productivity of the community at the lower middle level. As a retailer, Anterah store also faces the same thing, so anticipating a decline in sales requires an analysis of the best-selling products and how to find out the relationship between the products purchased by consumers. The association relationship between these products will be used as the basis for product arrangement, so that the frequency of products that consumers often buy can be arranged closely together so that consumers do not have to look for them longer. Market basket analysis to determine the relationship between products sold simultaneously is used to explore association rules (Association Rule Mining) which will produce products that are purchased simultaneously as a consideration for product arrangement in Anterah Retail storefront. Meanwhile, the best-selling products will be explored using the Frequent Pattern Growth method in order to obtain a ranking list of the most purchased products by consumers. This analysis is used as a basis for considering product promotion. The test results on the sales sample data obtained an average value of minimum support = 0.0025, minimum confidence = 0.610, LaPlace = 0.9985, Gain = -0.006, p-s = 0.003, Lift = 103.82, Convicting 2.5285 with a processing time of 41.456 seconds.

Characterization Of Composition Error Summary Using Machine Learning Techniques And Natural Language Processing Mars Caroline Wibowo; Budi Raharjo
Pixel :Jurnal Ilmiah Komputer Grafis Vol 16 No 1 (2023): Vol 16 No 1 (2023): Jurnal Ilmiah Komputer Grafis
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/pixel.v16i1.1885

As software technology becomes more complex, software maintenance costs become more expensive. In connection with this, the development of software engineering makes the software system has many Composition choices that can be adjusted to the needs of the user. Error fixing involves analyzing Error Summary and modifying code. If bug-fixing steps are made as efficiently and effectively as possible then maintenance costs can be minimal. The purpose of this research is to establish a tool of machine learning for identifying Composition Error Summary and to find out the types of special Composition choices that can be used to save costs, time, and effort. In this study, the T-test was applied to appraise the analytical implication of conduct metrics when the “F-test” was taken to the Variance’s test. Classifiers used in this study are “All words” or “AW”, “Highly Informative Words” or “H-IW”, and “Highly Informative Words plus Bigram” or “H-WB”. Identical validation and Vexed validation techniques were used to calculate the effectiveness of machine learning tools. The results of this research denote that the instrument is competent for definitive Composition Error Summary and other Composition choices for definite Error Summary. This research determines the practicality of machine learning techniques in corrective issues relevant to Error summary. The result of this study also explained that Composition/non-Composition Error Summaries have contrasting aspects that can be accomplished by machine learning devices. The advanced tool could be upgraded in some areas to create it more powerful. The array identification section of the current study has limitations, an array with different words and Composition recognition tools tend to prefer Compositions with more words, so improvements to this could implicate consideration of the semantics of Error Summary, equivalent, and use of n-grams. Also, in using the technology of machine learning and Natural Language processing some advancements to be made to the present characterization structure so for future research it is highly recommended to clear up the first’s Error Summary before operating several operations in the present study.Composition Error Summary

Implementation of the Internal Control System in Increasing the Accountability of the Financial Reports Budi Raharjo; Aris Sarjito; Editha Praditya Duarte
Formosa Journal of Social Sciences (FJSS) Vol. 3 No. 4 (2024): December 2024
Publisher : PT FORMOSA CENDEKIA GLOBAL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55927/fjss.v3i4.12924

his study aims to describe the implementation of the internal control system in increasing the accountability of the financial statements of the Ministry of Defense of the Republic of Indonesia. This research uses a qualitative method with a descriptive analysis approach. Data was collected by interview method based on the maturity assessment of the integrated Government Internal Control System. The results of this study indicate that the Ministry of Defense has implemented an adequate internal control system. In line with this, there is also an increase in the accountability of its financial statements

5G NETWORK TRAFFIC FORECASTING USING MACHINE LEARNING Budi Raharjo; Mars Caroline Wibowo
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol. 13 No. 2 (2022): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v13i2.850

The idea of network chunks being described as virtual subsets of the physical resources of 5G infrastructure is used in standards for 5G communications. The efficiency of ML predictors for traffic prediction in 5G networks has been established in recent research so that it becomes to assess the capability demands of each network slice and to see how it progresses as a large number of network slices are deployed over a 5G network over time to be very important. The main objective of this research is to establish the model that has the potential to help network management and resource allocation in 5G networks with machine learning performance analysis in predicting network traffic on high-dimensional spatial-temporal cellular data, in addition to investigating the effectiveness of various neural network models in traffic prediction from univariate and multivariate perspectives. The research method used is a quantitative research method using correlation analysis, statistical analysis, and distribution analysis on the temporal and spatiotemporal frameworks developed to predict traffic from a univariate and multivariate perspective. To predict 24-hour mobile traffic requires combining spatial and temporal dependencies. The univariate analysis will be carried out by applying a temporal framework that includes FCSN, 1DCNN, SSLSTM and ARLSTM to capture temporal dependencies. The results of various experiments in this study show that the proposed spatiotemporal model outperforms the temporal model and other techniques in the mobile traffic forecasting literature including internet, SMS, and calls.

PERFORMANCE EVALUATION OF PENETRATION TESTING TOOLS IN DIVERSE COMPUTER SYSTEM SECURITY SCENARIOS Joseph Teguh Santoso; Budi Raharjo
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol. 13 No. 2 (2022): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v13i2.851

This study aims to scrutinize various tools and techniques employed in vulnerability assessment, to furnish a comprehensive guide regarding the efficacy of computer system penetration testing tools, and to offer a post-exploitation analysis approach to aid security professionals in selecting security tools. The increasing interconnectivity and complexity of computer systems in this ever-evolving digital age have led to the growing sophistication of cyber threats such as hacking, malware, and data theft. To counter these threats, penetration testing has become the primary method for securing computer systems. However, in diverse environments, efficient and adaptive penetration testing tools are needed. The selection of the right tools, with a focus on their efficiency in detecting vulnerabilities and providing mitigation solutions, is a paramount and highly crucial consideration. Additionally, post-exploitation analysis to develop more effective protection strategies after a successful attack is also becoming increasingly important. This research contributes to the fields of Communication Networks and System Security, offering insights into the challenges of selecting the right tools for penetration testers and underscoring the importance of vulnerability assessment in securing computer systems. The research approach employed comprises static analysis and manual analysis, encompassing techniques such as fingerprinting, vulnerability scanning, fuzzing, Nmap scanning, and the utilization of a database search tool called search-sploit. The results of this study indicate that the tools and techniques employed in this research can assist in identifying and mitigating vulnerabilities in computer systems. However, due to certain limitations, the research findings may not apply to diverse scenarios.

THREAT ATTRIBUTES HANGING IN THE WILD ANDROID Irda Yunianto; Mars Caroline Wibowo; Budi Raharjo
Journal of Technology Informatics and Engineering Vol. 1 No. 3 (2022): December: Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v1i3.150

Android is a complicated system that applications and component are usable and support for multiple work together, giving rise to highly complex interdependence relationships. Meanwhile, the Android environment is notable for being greatlty disparate and decentralized: different Operation System version is personalized and re-personalized by different parties about fast and used by whoever that can develop an application for that version. Android secure its explanation sources over an app sandbox and permissions model, where each application execution in this part can entrance only suspectible overall assets and another application component (value providers, services, activities, publication receivers) by the appropriate liscense. This study uses Harehunter measurement to automatically detect Hare vulnerabilities in Android system applications. Harehunter and HareGuard performance evaluations were carried out in this study, both of which proved to be highly effective. The approach used here is divergent investigation, by searching all quoted, decompiled script, and obvious data for targeted attribute determination as an initial step, and running an XML parser. The outcome of this research show that the impact of Hares is very significant. The application of HareGuard in this study proved to be effective in detecting all attack applications that were made. Further evaluation of the performance impact on the minimum system host. For future research, to make Harehunter more effective, it is suggested to use a more qualified analyzer. So that this direction can be explored in more depth.

Innovation In Project Management Utilizing Machine Learning Technology Joseph Teguh Santoso; Budi Raharjo
Journal of Technology Informatics and Engineering Vol. 2 No. 3 (2023): December : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v2i3.163

The successful adoption of programmable machines for complex tasks opens up opportunities for productivity and more efficient communication, but also poses serious challenges in IT project management. This study aims to tackle the issue of high project failure rates caused by inadequate planning. It aims to assist project managers in enhancing their project planning by implementing real-time solutions through the utilization of machine learning (ML) algorithms and a user-friendly graphical interface. This research is divided into two key phases. The initial phase involves an examination of existing literature in the field of machine learning to identify relevant concepts applicable to project management. In the subsequent stage, two distinct types of ML algorithms, namely example-based learning and regression modeling, will be integrated into a user-friendly platform. This research develops a system that utilizes machine learning algorithms to assist project managers in real-time or near real-time through a user-friendly graphical interface, with a focus on improving project planning and risk mitigation. This research shows that machine learning algorithms provide positive results in overcoming human factors and preventing risks based on the experience of project managers.

PENERAPAN MODEL PEMBELAJARAN KOOPERATIF TEKNIK MAKE A MATCH UNTUK MENINGKATKAN HASIL BELAJAR SISWA PADA PEMBELAJARAN KEWAJIBAN DAN HAKKU KELAS III DI SDN PENGARADAN 01 Budi Raharjo
JGuruku: Jurnal Penelitian Guru Vol 2 No 1 (2024)
Publisher : Fakultas Keguruan dan Ilmu Pendidikan Universitas Kuningan

Show Abstract | Download Original | Original Source | Check in Google Scholar

ABSTRAK Tujuan penelitian ini adalah untuk meningkatkan hasil belajar Tema 4 Subtema 4 Kewajiban dan Hakku Sebagai Warga Negara melalui penerapan model pembelajaran kooperatif teknik make a match pada siswa kelas III SDN Pengaradan 01, Tanjung, Brebes tahun ajaran 2019/2020. Bentuk penelitian ini adalah penelitian tindakan kelas (PTK) yang dilaksanakan dalam tiga siklus. Tiap siklus terdiri dari 4 tahapan yaitu perencanaan, pelaksanaan tindakan, observasi, dan refleksi. Subjek penelitian ini adalah guru dan 28 siswa kelas III SDN Pengaradan 01, Tanjung, Brebes. Teknik pengumpulan data yang dilakukan adalah observasi, wawancara, tes, dan dokumentasi. Teknik analisis data yang digunakan adalah analisi model deskriptif komparatif yaitu dengan membandingkan hasil sebelum dilakukan penelitian dengan hasil pada akhir tiap siklus setelah penelitian. Uji validitas data pada penelitian ini menggunakan validitas isi. Peningkatan hasil belajar dapat dibuktikan dengan meningkatnya nilai siswa pada setiap siklus yaitu nilai rata-rata hasil belajar perpindahan kalor siswa sebelum tindakan hanya sebesar 59,8. Pada siklus I menjadi 67,6 dan pada siklus II menjadi 74,8, lalu pada siklus III meningkat lagi menjadi 83,5. Sebelum dilaksanakan tindakan, siswa yang memperoleh nilai di atas KKM (≥71) hanya sebanyak 9 siswa (32%), pada siklus I meningkat menjadi 14 siswa (50%), dan pada siklus II meningkat lagi menjadi 21 siswa (75%). Dan pada siklus III meningkat menjadi 28 siswa atau 100%. Berdasarkan hasil penelitian yang telah dilaksanakan dapat disimpulkan bahwa dengan menggunakan model pembelajaran kooperatif teknik make a match dapat meningkatkan hasil belajar Tema 4 Subtema 4 Kewajiban dan Hakku sebagai warga negara pada kelas III SDN Pengaradan 01, Tanjung, Brebes tahun ajaran 2019/2020. Kata kunci: Make a match, kewajiban dan hak. APPLICATION OF THE MAKE A MATCH TECHNIQUE COOPERATIVE LEARNING MODEL TO IMPROVE STUDENT LEARNING OUTCOMES IN LEARNING OBLIGATIONS AND RIGHTS CLASS III AT SDN PENGARADAN 01 ABSTRACT The aim of this research is to improve learning outcomes for Theme 4, Subtheme 4, My Obligations and Rights as a Citizen through the application of the cooperative learning model of the make a match technique for class III students at SDN Pengaradan 01, Tanjung, Brebes for the 2019/2020 academic year. The form of this research is classroom action research (PTK) which is carried out in three cycles. Each cycle consists of 4 stages, namely planning, implementing actions, observing and reflecting. The subjects of this research were teachers and 28 class III students at SDN Pengaradan 01, Tanjung, Brebes. The data collection techniques used were observation, interviews, tests and documentation. The data analysis technique used is comparative descriptive model analysis, namely by comparing the results before the research is carried out with the results at the end of each cycle after the research. Testing the validity of the data in this research uses content validity. The increase in learning outcomes can be proven by the increase in student scores in each cycle, namely the average score of students' heat transfer learning outcomes before the action was only 59.8. In cycle I it was 67.6 and in cycle II it was 74.8, then in cycle III it increased again to 83.5. Before the action was implemented, only 9 students (32%) got scores above the KKM (≥71), in the first cycle this increased to 14 students (50%), and in the second cycle it increased again to 21 students (75%). And in cycle III it increased to 28 students or 100%. Based on the results of the research that has been carried out, it can be concluded that using the cooperative learning model, the make a match technique, can improve learning outcomes for Theme 4 Subtheme 4 My Obligations and Rights as a Citizen in class III at SDN Pengaradan 01, Tanjung, Brebes for the 2019/2020 academic year. Keywords: Make a match, obligations and rights

Characterization Of Composition Error Summary Using Machine Learning Techniques And Natural Language Processing Mars Caroline Wibowo; Budi Raharjo
Pixel :Jurnal Ilmiah Komputer Grafis Vol. 16 No. 1 (2023): Vol 16 No 1 (2023): Jurnal Ilmiah Komputer Grafis
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/pixel.v16i1.1885

As software technology becomes more complex, software maintenance costs become more expensive. In connection with this, the development of software engineering makes the software system has many Composition choices that can be adjusted to the needs of the user. Error fixing involves analyzing Error Summary and modifying code. If bug-fixing steps are made as efficiently and effectively as possible then maintenance costs can be minimal. The purpose of this research is to establish a tool of machine learning for identifying Composition Error Summary and to find out the types of special Composition choices that can be used to save costs, time, and effort. In this study, the T-test was applied to appraise the analytical implication of conduct metrics when the “F-test” was taken to the Variance’s test. Classifiers used in this study are “All words” or “AW”, “Highly Informative Words” or “H-IW”, and “Highly Informative Words plus Bigram” or “H-WB”. Identical validation and Vexed validation techniques were used to calculate the effectiveness of machine learning tools. The results of this research denote that the instrument is competent for definitive Composition Error Summary and other Composition choices for definite Error Summary. This research determines the practicality of machine learning techniques in corrective issues relevant to Error summary. The result of this study also explained that Composition/non-Composition Error Summaries have contrasting aspects that can be accomplished by machine learning devices. The advanced tool could be upgraded in some areas to create it more powerful. The array identification section of the current study has limitations, an array with different words and Composition recognition tools tend to prefer Compositions with more words, so improvements to this could implicate consideration of the semantics of Error Summary, equivalent, and use of n-grams. Also, in using the technology of machine learning and Natural Language processing some advancements to be made to the present characterization structure so for future research it is highly recommended to clear up the first’s Error Summary before operating several operations in the present study.Composition Error Summary

Title

Found 35 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 35 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 35 Documents
Search