Garuda - Garba Rujukan Digital

Penggunaan Model Deep Learning Untuk Meningkatkan Efisiensi Dalam Aplikasi Machine Learning Siswanto Siswanto; Maya Utami Dewi; Siti Kholifah; Greget Widhiati; Widya Aryani
JURNAL PENELITIAN SISTEM INFORMASI (JPSI) Vol. 1 No. 4 (2023): NOVEMBER : JURNAL PENELITIAN SISTEM INFORMASI
Publisher : Institut Teknologi dan Bisnis (ITB) Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54066/jpsi.v1i4.1619

The use of deep learning models has become a major focus in optimizing the efficiency of machine learning applications. This research discusses various deep learning models that can be applied to improve efficiency in the context of machine learning applications. These models are designed to handle the complexity of machine learning tasks with a high level of accuracy while still considering aspects of computational efficiency. This article involves an in-depth look at several deep learning models that have proven effective in various application domains. Discussion includes the use of convolutional neural network (CNNs) models for image processing, recurrent neural networks (RNNs) for sequential data, and transformer-based models for natural language processing tasks. In addition, deep learning model tuning and optimization strategies, such as pruning and quantization, are also discussed to improve the efficient use of computing resources. This research identifies challenges and opportunities in integrating these deep learning models into machine learning applications with maximum efficiency. By considering the need for accuracy and limited computational resources, this research provides a holistic view of the approaches that can be applied to deal with complexity in diverse machine learning scenarios. The results are expected to provide a significant contribution to the development of efficient and effective machine learning applications.

ANALYSIS RENDEZVOUS-BASED TECHNIQUES RELATE TO POWER CONSERVATION Agus Waryanto; Antonius Juniadhi Soekendar; Ely Andra Widharta; Greget Widhiati; Irdha Yunianto
Journal of Technology Informatics and Engineering Vol 1 No 2 (2022): August: 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.v1i2.138

Power conservation is a vibrant area of research on wireless sensor networks. Several research papers have shown that using mobile sync in the sensor field, which collects data from sensor nodes via single or multi-hop communication, can save significant energy. However, sinks move slowly, which increases sensor network delays, especially in delay-sensitive applications. To address this issue, various rendezvous-based techniques are described in which a subset of sensor nodes are selected from the field as rendezvous points (RPs). The remaining nodes transfer the captured data to the next RP, where the data is buffered. The RP is then used to build a path for the mobile sink to tour and collect the buffered data. This article describes various rendezvous-based techniques and analyzes their strengths and weaknesses in terms of energy savings.

PENGARUH HUBUNGAN ANTARA DISIPLIN BELAJAR DAN PRESTASI BELAJAR SISWA SD NEGERI DI DESA KALIWUNGU, KECAMATAN KALIWUNGU PADA SEMESTER I TAHUN PELAJARAN 2022/2023 Greget Widhiati; Suwardi Suwardi
E-Bisnis : Jurnal Ilmiah Ekonomi dan Bisnis Vol 15 No 2 (2022): Jurnal Ilmiah Ekonomi dan Bisnis
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/e-bisnis.v15i2.903

Discipline is defined as an effort to control oneself and the mental attitude of the individual or society in developing obedience and obedience to the rules and regulations based on encouragement and awareness that arises from the heart. If it is associated with learning, the discipline of learning is more related to the mental attitude of the individual in his obedience to carrying out learning activities The research was conducted at SD Negeri Kaliwungu 01 and SD Negeri 02 in Kaliwungu Village, Kaliwungu District. The research sample was taken by purposive sampling. The variable of this research is learning discipline as the independent variable, which is measured by two sub-variables, namely learning discipline in the school environment and family environment. The second variable is learning achievement as the dependent variable. The results showed that there was a relationship between the sub-variables of learning discipline in the school environment and learning achievement, but its contribution was very weak. This can be seen from the value of the correlation coefficient is 0.064 with a significance value on both sides of 0.491>0.05. While the sub-variable of learning discipline in the family environment also has a relationship with learning achievement with the value of the correlation coefficient is 0.183 with a significance value on both sides of 0.043 <0.05. In addition, the two sub-variables are interrelated which shows the correlation coefficient value of 0.366 with a 2-sided significance = 0.000 <0.05. Overall, the results of this study also show that there is a relationship between learning discipline variables (both school and family environments) with student achievement at SDN Kaliwungu 01 and 02. This relationship is known by the Kendall concordance test with a correlation coefficient of 0.539 and Asymp. Sig. =0.000<0.05. These results indicate that there is a relationship between learning discipline and learning achievement. In addition, the magnitude of the effect on achievement is 53.9%.

PENGARUH HUBUNGAN ANTARA DISIPLIN BELAJAR DAN PRESTASI BELAJAR SISWA SD NEGERI DI DESA KALIWUNGU, KECAMATAN KALIWUNGU PADA SEMESTER I TAHUN PELAJARAN 2022/2023 Greget Widhiati; Suwardi Suwardi
E-Bisnis : Jurnal Ilmiah Ekonomi dan Bisnis Vol 15 No 2 (2022): Jurnal Ilmiah Ekonomi dan Bisnis
Publisher : LPPM Universitas Sains dan Teknologi Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/e-bisnis.v15i2.903

Discipline is defined as an effort to control oneself and the mental attitude of the individual or society in developing obedience and obedience to the rules and regulations based on encouragement and awareness that arises from the heart. If it is associated with learning, the discipline of learning is more related to the mental attitude of the individual in his obedience to carrying out learning activities The research was conducted at SD Negeri Kaliwungu 01 and SD Negeri 02 in Kaliwungu Village, Kaliwungu District. The research sample was taken by purposive sampling. The variable of this research is learning discipline as the independent variable, which is measured by two sub-variables, namely learning discipline in the school environment and family environment. The second variable is learning achievement as the dependent variable. The results showed that there was a relationship between the sub-variables of learning discipline in the school environment and learning achievement, but its contribution was very weak. This can be seen from the value of the correlation coefficient is 0.064 with a significance value on both sides of 0.491>0.05. While the sub-variable of learning discipline in the family environment also has a relationship with learning achievement with the value of the correlation coefficient is 0.183 with a significance value on both sides of 0.043 <0.05. In addition, the two sub-variables are interrelated which shows the correlation coefficient value of 0.366 with a 2-sided significance = 0.000 <0.05. Overall, the results of this study also show that there is a relationship between learning discipline variables (both school and family environments) with student achievement at SDN Kaliwungu 01 and 02. This relationship is known by the Kendall concordance test with a correlation coefficient of 0.539 and Asymp. Sig. =0.000<0.05. These results indicate that there is a relationship between learning discipline and learning achievement. In addition, the magnitude of the effect on achievement is 53.9%.

A Systematic Literature Review on the Application of the Philosophy of Science in Addressing Online Gambling Threats : Cybersecurity and Ethical Technology Integration Danang Danang; Siswanto Siswanto; Greget Widhiati
Jurnal Sains dan Ilmu Terapan Vol. 7 No. 2 (2024): Jurnal Sains dan Ilmu Terapan
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jsit.v7i2.920

This study aims to explore the application of the philosophy of science in developing an ethical, effective, and inclusive cybersecurity model to address the growing threat of online gambling. Using the Systematic Literature Review (SLR) method, 54 articles from reputable databases such as Scopus, IEEE Xplore, SpringerLink, and ScienceDirect were analyzed in-depth. The analysis focused on methodological validity, thematic relevance, contributions to security model development, source credibility, data accessibility, and quality of presented analysis. The results reveal that online gambling platforms leverage technologies such as blockchain, artificial intelligence (AI), and encryption to obscure illegal activities, complicating detection and prevention efforts. As a response, the philosophy of science provides a theoretical foundation to integrate ethical values such as privacy, transparency, and fairness into the development of cybersecurity technologies. Technologies like zero-trust architecture, federated learning, and big data analytics were identified as key tools for building proactive security systems. Furthermore, multistakeholder collaboration among governments, industries, academia, and society is recommended to establish adaptive regulations that foster robust digital security.

Peran Majelis Gereja dalam Meningkatkan Kesejahteraan Sosial Ekonomi Umat Kristen melalui Pelayanan Diakonia Widya Ariyani; Greget Widhiati
Jurnal Filsafat dan Teologi Katolik Vol. 7 No. 2 (2024): Jurnal Filsafat dan Teologi Katolik
Publisher : STIKAS Santo Yohanes Salib Kalimantan Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58919/juftek.v7i2.217

Diaconal ministry is one form of church service that embodies the love of Christ in serving others. However, in practice, this ministry is often carried out in a charitable manner and has yet to fully address comprehensive and sustainable empowerment of the congregation. This study is driven by the urgent need to develop a diaconal service that not only provides temporary assistance but also effectively enhances the socio-economic independence of the congregation, particularly within the context of Gereja Isa Almasih Pringgading, where some Christian members face economic challenges due to limited access, resources, and institutional church support. The objective of this study is to analyze and describe the role of the Church Council in developing reformative and sustainable empowerment-based diaconal ministry. A qualitative descriptive method was employed, with data collected through in-depth interviews with Church Council members and service recipients, direct observations of diaconal activities, and documentation of church archives and social service reports. Data were analyzed thematically to identify patterns of service, empowerment strategies, and socio-economic impacts on the congregation. The study's findings reveal that the Church Council plays a strategic role in transforming diaconal ministry from mere charitable assistance into a structured empowerment program. Successfully implemented programs include entrepreneurial skills training, micro-business mentoring for congregation members, internal church cooperative development, and the establishment of local economic partnership networks. The impacts of these programs are reflected in increased household incomes, improved economic independence for some members, and strengthened social solidarity within the congregation. This study produces a conceptual model of empowerment-based diaconal ministry that can be replicated by other local churches to sustainably enhance congregational welfare.

PEMBERDAYAAN UKM DALAM PROMOSI WISATA EDUKASI: PENGEMBANGAN BROSUR INTERAKTIF DI DESA SUGIHAN KABUPATEN SEMARANG Zusrony, Edwin; Edy Jogatama Purhita; Endang Kustami; Agustinus Budi Santoso; Indra Ava Dianta; Widya Ariyani; Greget Widhiati; Jarot Dian Susatyono; Ida Hendriyani; Siti Kholifah; Haryo Kusumo
BUDIMAS : JURNAL PENGABDIAN MASYARAKAT Vol. 7 No. 2 (2025): BUDIMAS : Jurnal Pengabdian Masyarakat
Publisher : LPPM ITB AAS Indonesia Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29040/budimas.v7i2.17645

This community service activity aims to empower Small and Medium Enterprises (SMEs) in Sugihan Village, Tengaran District, Semarang Regency, through training in making digital brochures to promote educational tourism using the Canva application. This program was implemented in response to the lack of digital literacy and dependence on conventional promotions that limit the reach of the educational tourism market in Sugihan Village. The implementation method includes five stages: (1) analysis of the needs of SMEs and educational tourism, (2) preparation of digital brochure materials and designs, (3) training in making digital brochures, (4) implementation and mentoring, and (5) evaluation and continuous development. Participants were taught visual design techniques, persuasive content preparation, and distribution strategies through social media. The evaluation results showed a significant increase in the abilities of 25 participants: 75% were able to make independent digital brochures. It is hoped that after this training activity, it will have an impact on increasing tourist visits to Sugihan Village, Semarang Regency. Collaboration between academics from the University of Computer Science and Technology Lecturer team and the SME community also strengthens the sustainability of the program, with the formation of a digital working group to update promotional content regularly.

Federated Hybrid CNN GRU and COBCO Optimized Elman Neural Network for Real Time DDoS Detection in Cloud Edge Environments Danang Danang; Maya Utami Dewi; Greget Widhiati
International Journal of Electrical Engineering, Mathematics and Computer Science Vol. 2 No. 2 (2025): International Journal of Electrical Engineering, Mathematics and Computer Scien
Publisher : Asosiasi Riset Teknik Elektro dan Infomatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/ijeemcs.v2i2.293

Improvement amount Distributed Denial of Service (DDoS) attacks in cloud infrastructure and edge computing demands solution adaptive, distributed, and efficient detection in a way computing. Research This propose an optimized Federated Learning (FL) based DDoS detection model using Centroid Opposition-Based Bacterial Colony Optimization (COBCO) to training the Elman Neural Network (ENN). The proposed architecture consists of of two components Main: on the edge node side, a hybrid Convolutional Neural Network–Gated Recurrent Unit (CNN–GRU) model is used to extraction feature local from traffic data network, while on the server side, model parameters from each node are collected and used for training an optimized ENN with COBCO. Approach This aim increase accuracy detection at a time maintain efficiency local data communication and privacy. In progress experimental, model tested use three benchmark datasets: NSL-KDD, CICIDS2017, and CICDDoS2019. The preprocessing process includes feature encoding categorical, normalization numeric, class balancing using SMOTE, as well as validation cross (k-fold). Initial results show that combination of FL, CNN–GRU, and COBCO–ENN produces improvement significant in accuracy and time convergence compared to approach conventional such as PSO, GA, and non- federative models. In addition, the proposed model capable maintain performance detection tall although executed in edge environment with limitations source Power. Study This give contribution important in development system scalable, privacy-preserving, and adaptive intelligent DDoS detection to dynamics Then cross modern network. Integration of FL and COBCO in ENN training shows potential big for used in implementation real in cloud-edge infrastructure. In addition, the proposed model demonstrates strong scalability and adaptability, making it highly suitable for dynamic and evolving network environments.

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search