Garuda - Garba Rujukan Digital

Cluster Analysis for Performance Evaluation of Outsourcing Engineers in the Telecommunication Industry Hasibuan, M. Rivai; Kusrini, K; Muhammad, Alva Hendi
IJISTECH (International Journal of Information System and Technology) Vol 7, No 1 (2023): The June edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v7i1.301

The telecommunications industry relies significantly on the knowledge and contributions of engineers, who play a crucial role in designing, enhancing, and supervising diverse communication infrastructure systems. As engineers gain experience, they frequently advance to supervisory or consulting positions in which they provide expert guidance. Many businesses have delegated their recruitment processes to contract workers to optimize operational costs and boost productivity. It is essential to evaluate the performance of outsourced employees in order to determine the value they add to the organization. Performance evaluations play a vital role in evaluating factors such as attendance, skill level, burden management, and job performance. These evaluations aid in contract renewal decision-making. Various metrics emphasizing factors such as effective skills, well-defined objectives, and regular status updates can be used to determine the success of outsourced employees. This permits a comprehensive evaluation and the identification of improvement areas. In this paper, the investigation concentrates on using cluster analysis techniques, specifically partition-based algorithms such as K-means, to classify outsourced workers according to their individual skills and characteristics. Then, we compare the provided insights with the density-based algorithm DBSCAN to comprehend them. Cluster analysis is a potent method for analyzing large datasets, allowing for swift and confident conclusions. By utilizing cluster analysis, organizations can gain insight into the diverse skill sets and characteristics of their outsourced workforce, thereby improving resource allocation, task assignment, and management as a whole

Sistem Inventaris Stok Obat Menggunakan Metode Exponential Moving Average Sukaria, Petra Nugra; Muzakki, Mohammad Haris; Adhani, Muhammad Azmi; Kusrini, K; Agastya, I Made Artha
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 9, No 2 (2024): Edisi Agustus
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v9i2.828

The management of drug inventory in hospitals is a crucial aspect that affects the quality of healthcare services and patient safety. Uncertain drug demand can lead to overstock, resulting in wastage due to expiration, or understock, endangering patient safety. This study aims to develop a drug inventory system using the Exponential Moving Average (EMA) method to forecast drug sales. Historical sales and purchase data from Betang Pambelum Hospital, Palangka Raya, were used for forecasting. The implementation of the EMA method proved to provide accurate forecasting results, with the Mean Absolute Percentage Error (MAPE) falling into good to very accurate categories. This system not only reduces the risks of drug overstock and understock but also helps hospitals in more efficient inventory management. The adoption of this system is expected to enhance the quality of healthcare services through better drug inventory management

Metode Support Vector Machine pada Klasifikasi Pengaduan Masyarakat Anggraini, Resti Kusuma; Kusrini, K; Fatta, Hanif Al
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 8, No 1 (2023): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v8i1.547

Public complaint service is a very important service in a government agency. Service 112 is a public complaint service that is connected directly to the 112 call center that has been appointed by the local government. The government of the city of Samarinda through the Office of Communication and Informatics also has a call center service 112 which is commonly called by Samarinda City residents, namely the Samarinda Siaga Service 112. Various kinds of complaints from the public make operators have to be more careful in categorizing every complaint that comes in, and not infrequently the community convey it using the regional language which can make it difficult for operators to categorize the complaint. Text mining is one of the methods used in the classification process. In this study, the text mining process was used to classify public complaints using the Support Vector Machine method. The results of the research that has been carried out using as many as 120 public complaint data, which are then divided into 2, namely as training data as much as 96 data and data testing as much as 24 data using the Support Vector Machine method using the RBF kernel get an accuracy result of 79%, a precision of 56%, recall of 100%, f1-score of 71% and support 5.

Cluster Analysis for Performance Evaluation of Outsourcing Engineers in the Telecommunication Industry Hasibuan, M. Rivai; Kusrini, K; Muhammad, Alva Hendi
IJISTECH (International Journal of Information System and Technology) Vol 7, No 1 (2023): The June edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v7i1.301

The telecommunications industry relies significantly on the knowledge and contributions of engineers, who play a crucial role in designing, enhancing, and supervising diverse communication infrastructure systems. As engineers gain experience, they frequently advance to supervisory or consulting positions in which they provide expert guidance. Many businesses have delegated their recruitment processes to contract workers to optimize operational costs and boost productivity. It is essential to evaluate the performance of outsourced employees in order to determine the value they add to the organization. Performance evaluations play a vital role in evaluating factors such as attendance, skill level, burden management, and job performance. These evaluations aid in contract renewal decision-making. Various metrics emphasizing factors such as effective skills, well-defined objectives, and regular status updates can be used to determine the success of outsourced employees. This permits a comprehensive evaluation and the identification of improvement areas. In this paper, the investigation concentrates on using cluster analysis techniques, specifically partition-based algorithms such as K-means, to classify outsourced workers according to their individual skills and characteristics. Then, we compare the provided insights with the density-based algorithm DBSCAN to comprehend them. Cluster analysis is a potent method for analyzing large datasets, allowing for swift and confident conclusions. By utilizing cluster analysis, organizations can gain insight into the diverse skill sets and characteristics of their outsourced workforce, thereby improving resource allocation, task assignment, and management as a whole

Evaluasi Tata Kelola dan Manajemen Risiko Unit Teknologi Informasi dan Pangkalan Data pada Perguruan Tinggi Keagamaan Islam Negeri XYZ dengan Menggunakan Framework COBIT 2019 Sulistiyono, Agus; Kusrini, K
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.512

The Information Technology and Data Base Unit (UTIPD) is one of the units at the XYZ State Islamic Religious College (PTKIN) which is tasked with managing and developing information system management, network and application maintenance, managing databases, and developing other information technology (IT). This research aims to evaluate governance and risk management at UTIPD at PTKIN XYZ. As a higher education institution that continues to develop, PTKIN XYZ relies heavily on information technology to support its operations, administration and academic activities. However, with the increasing complexity of information systems and associated risks, an in-depth evaluation of how IT governance and risk management is implemented is needed. The COBIT 2019 framework, which is an international standard framework for IT governance and management, is used in this research to assess IT governance and risk management capabilities at UTIPD. The primary focus of this evaluation is to determine the extent to which current IT governance practices meet expected standards, as well as to identify areas requiring improvement. This research includes an analysis of COBIT 2019 domains that are relevant to IT governance and risk management. The results of this research show that the APO07 domain and APO12 domain processes only obtained capability level 2 and obtained a gap value (GAP) of 1 each. In addition, this research also presents recommendations for improving IT governance and risk management at PTKIN XYZ, with the aim of Finally, to ensure that this university can utilize information technology optimally, reduce risks, and support the achievement of its strategic goals. It is hoped that the findings from this research can become a reference for PTKIN XYZ and other higher education institutions in strengthening IT governance and risk management.

Classification Of Mustard Leaf Diseases Using Convolutional Neural Network Architecture Hafidurrohman, M.; Kusrini, K
Journal of Electrical Engineering and Computer (JEECOM) Vol 7, No 1 (2025)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v7i1.10779

Diseases in mustard leaves can reduce productivity if not detected early. This study aims to develop and evaluate a disease classification system for mustard leaves using Convolutional Neural Network (CNN) architectures, specifically Xception and VGG19, while comparing their performance in terms of accuracy and computational efficiency. The mustard leaf image dataset undergoes preprocessing before being used for model training and testing. Experimental results show that Xception achieves the highest validation accuracy of 99% with better loss stability compared to VGG19, which attains 94.50% accuracy but exhibits greater fluctuation. In terms of time efficiency, VGG19 reaches optimal accuracy faster and completes the training process in 42 seconds, whereas Xception requires more epochs and a training time of 50 seconds. Therefore, Xception is recommended for classification tasks that demand high accuracy and stability, while VGG19 is more suitable for rapid detection with a slight trade-off in accuracy stability.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search