cover
Contact Name
Muhammad Sidik
Contact Email
jtik@provisi.ac.id
Phone
+6289671418611
Journal Mail Official
muhsidik@provisi.ac.id
Editorial Address
Jl. Majapahit No.304, Pedurungan Kidul, Kec. Pedurungan, Kota Semarang, Jawa Tengah 50192 Telp: (024) 6723456 E-mail : lppm@provisi.ac.id
Location
Kota semarang,
Jawa tengah
INDONESIA
Jurnal Teknologi Informasi dan Komunikasi
ISSN : 20870868     EISSN : 25989707     DOI : https://doi.org/10.51903/jtikp.v13i1
JTIK :Jurnal Teknologi Informasi dan Komunikasi merupakan Jurnal yang diterbitkan oleh LP2M Sekolah Tinggi Manajemen Informatika dan Komputer Provisi Semarang. Jurnal ini terbit 2 kali dalam setahun yaitu pada bulan April dan September. Misi dari Jurnal JTIK adalah untuk menyebarluaskan, mengembangkan dan menfasilitasi hasil penelitian inter-disiplin di bidang Teknologi Informasi dan Komunikasi, sistem komputer, informatika dan komunikasi sebagai media bagi para dosen, guru, peneliti dan para praktisi dalam bidang Teknologi Informasi dan Komunikasi, sistem komputer, informatika dan komunikasidari seluruh Indonesia, dalam melakukan pertukaran informasi tentang hasil-hasil penelitian terbaru yang telah dilakukan.
Articles 278 Documents
DESAIN SISTEM KENDALI SUHU RUANG PEMANAS DENGAN METODE ULTIMATE CYCLE Muhammad Amiruddin; Imadudin Harjanto; Bambang Hadi Kunaryo
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol 15 No 2 (2024): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v15i2.895

Abstract

A room heating device equipped with a temperature control system that will be used to regulate the room temperature so that it is stable at a certain value. Before designing the hardware and setting the control methods that will be used, to simplify the design, a system response simulation is first carried out. In order to simulate the response of the temperature control system in the heating room, a mathematical model of the heating room and the temperature control system used is needed. Therefore, an approach using the FOPDT method is used to determine the mathematical model of the heating space. After obtaining a suitable mathematical model for the heating room in this research case, it is continued by providing a control gain (P-I-D) so that the performance of the heating room control system meets the requirements. To get the gain value (P-I-D), tuning is carried out using the ultimate cycle method. Providing Kp=0.06 to this temperature control system provides a steady state error performance of 5°C, rise time of 247 seconds and overshoot of 10°C. The addition of 1/Ti = 0.00133 and the change in Kp = 0.027 resulting from ultimate cycle tuning, have the effect of eliminating the steady state error but increasing the rise time to 530 seconds. The addition of Td = 112.5 and changes in 1/Ti = 0.0022 and Kp = 0.036 resulting from ultimate cycle tuning, have the effect of reducing the rise time to 380 seconds, but increasing the overshoot to 18°C
OPTIMASI MODEL DEEP LEARNING UNTUK RASPBERRY MENGGUNAKAN PRUNING DAN KUANTISASI Harjanto, Imadudin; Amiruddin, Muhammad; Kunaryo, Bambang Hadi
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol 15 No 2 (2024): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v15i2.898

Abstract

Artificial intelligence with deep learning. Has been widely used at many field especially in computer vision technology. It can be found in many purpose and variety of device for it’s deplayment. Deep learning is a neural network that is arranged in very deep layers in order to extract information in more detail. However, with the high level of performance can be achieved, in other hand, another problem arises; the need for very large computing resources in the process. This study has objective to find method and strategies for optimizing edge device in order to continue implementing deep learning with good performance even with limited computing resources. This study uses pruning and quantization methods. After the conventional training process, additional treatment is carried out by reducing the layers and quantizing the weights to reduce the fractional numbers on each weight. At the final step, the conversion of the optimized model into a format suitable for Raspberry Pi 4 is carried out. The results of these experiment showed a significant increase in prediction latency of 2.8x faster and a decrease in file size to 13.74% smaller. This is very beneficial in the implementation of deep learning on Raspberry Pi which has minimal memory and computing capacity.
PENGARUH BRAND AMBASSADOR TERHADAP MINAT BELI PRODUK MOM UUNG Anggraeni, Diana; Muctar, Shanon Riesva Natasya; Ahmad, Rosmalia
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol 15 No 2 (2024): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v15i2.899

Abstract

The importance of maternal and child health issues is the focus of sustainable development goals. In an effort to maintain the quality of mother's breast milk through booster products, Mom Uung will provide healthy babies. To reach it, you need the role of a brand ambassador so that breastfeeding mothers are interested in buying and using it. The aim of this research is to determine the influence of brand ambassador level on the level of buying interest of breastfeeding mothers who follow Mom Uung's Instagram account for products. This research uses the AIDA model, purchase intention, and brand ambassadorship as a basis for viewing the phenomenon from a theoretical and conceptual perspective. The research methodology uses a positivism paradigm with a quantitative approach. Meanwhile, this type of research is explanatory in nature to see the influence of brand ambassadors on interest in buying Mom Uung products by breastfeeding mothers as the unit of analysis. The sampling technique was purposive by attaching several criteria to respondents, in this case 100 breastfeeding mothers, obtained using the Slovin formula. Simple linear regression analysis is used as a data analysis technique. Research findings show that Nagita Slavina as the brand ambassador for Mom Uung products has a significant influence on the buying interest of breastfeeding mothers. In conclusion, there is an influence of brand ambassadors on purchasing interest. Therefore, it can be concluded that brand ambassadors influence consumer buying interest (breastfeeding mothers).
PEMETAAN JALAN DENGAN METODE AHP-SMART DI KISARAN TIMUR BERBASIS WEBGIS Ulan, Tri Ulandari; Triase, Triase; Harahap, Aninda Muliani
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol 15 No 2 (2024): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v15i2.902

Abstract

Kerusakan jalan merupakan masalah yang sering dihadapi oleh masyarakat. Kerusakan jalan dapat menyebabkan gangguan dalam mobilitas masyarakat, meningkatkan risiko kecelakaan, meningkatkan resiko kemacetan, dan mempengaruhi kegiatan ekonomi di wilayah tersebut, sehingga diperlukan solusi yang efisien untuk rekomendasi perbaikan jalan. Oleh karena itu dalam penelitian ini dibangunlah sebuah sistem informasi geografis rekomendasi perbaikan jalan dengan metode AHP-SMART yang kemudian hasilnya dipetakan menjadi pemetaan kerusakan jalan. Pada penelitian ini metode pengumpulan data yang digunakan peneliti yaitu Research and Development (R&D). Serta metode RAD sebagai metode pengembangan sistem.
SISTEM PENDUKUNG KEPUTUSAN PENERIMAAN BEASISWA BERPRESTASI DENGAN METODE SIMPLE ADDITIVE WEIGHTING (SAW) (Studi Kasus Di SMKN 1 Bawen) Putri, Sherly Pradipta Arshyindi; Andika, Robby; Priyadi, Priyadi
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol. 16 No. 2 (2025): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v16i2.1009

Abstract

The selection of scholarship candidates at SMK N 1 Bawen is still carried out manually using computers, making it vulnerable to data input errors and inconsistencies in the calculation of criteria scores. Furthermore, the lack of a fair and scientific assessment method often leads to social jealousy among students and their guardians. Manual management of selection information also makes it difficult to manage user access rights as needed. This study aims to develop a web-based information management system that applies the Simple Additive Weighting (SAW) method to improve the accuracy of calculating criteria scores for scholarship candidates automatically and fairly. This system is designed to be able to manage user access rights easily and securely. The research methodology used includes needs analysis, system design, implementation, and testing. The results show that the developed system can reduce data input errors, improve calculation consistency, and provide more transparent and systematic decisions. The implementation of this system is expected to assist schools in managing scholarship recipient selection more effectively and efficiently.
ANALISIS SENTIMEN ULASAN KONSUMEN MENGGUNAKAN ALGORITMA TF-ID UNTUK MENGETAHUI TINGKAT KEPUASAN PELANGGAN(STUDI KASUS : GUNTHEM PREMIUM COFFEE) Widyastuti, Fransisca Sonia; Mailoa, Evangs
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol. 16 No. 2 (2025): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v16i2.1010

Abstract

In today’s digital era, customer review shared across online platforms are regarded as key indicators for evaluating customer satisfaction and shaping the reputation of s business, including coffee shops. In this study, sentiment analysis was conducted on customer reviews of Gunthem Premium Coffee using the TF-IDF (Term Frequency – Inverse Documen Frequency) method. A total of 46 review entries were collected from Google Maps and GoFood and were manually labeled as either positive or negative. The analysis was carried out in several stages, including text pre-processing, manual labeling, and feature extraction using TF-IDF. Irrelevant word were removed, and important terms were identified based on their weight across the dataset. The result showed that most reviews expressed positive sentiments, with words such as “delicious”, “coffee”, “comfortable”, and “clean” found to have the highest TF-IDF weights. A wordcloud visualization was also created to support the analytical findings. Therefore, the TF-IDF method was proven effective in identifying customer opinions and can serve as a foundation for formulating strategies to enchance service quality and customer satisfaction in the coffee shop industry..
MARKET BASKET ANALYSIS MENGGUNAKAN ALGORITMA APRIORI UNTUK MENDUKUNG STRATEGI PROMOSI PRODUK Bintang Samasto, Revo; Mailoa, Evangs
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol. 16 No. 2 (2025): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v16i2.1011

Abstract

The intense business competition requires companies to deeply understand consumer behavior in order to design effective marketing strategies. This study was conducted to analyze customer purchasing patterns using the market basket analysis method with the Apriori algorithm. This was done because previously the company carried out promotional strategies conventionally without utilizing data analysis or understanding consumer purchasing patterns, resulting in less optimal promotional outcomes. The data used consists of 103 briquette sales transactions during the period from March 2024 to March 2025, which were then processed to find frequent itemsets and association rules. The analysis results show that the combination of Hexagonal With Hole (non-premium) briquettes and Rectangle (non-premium) briquettes is the most frequently purchased together, with a support value of 39.81%, a confidence value of 91.11%, and a lift value of 1.42. These findings provide strategic insights that companies can use to design promotions through bundling and cross-selling.
PENGELOMPOKAN GAYA BELAJAR SISWA UNTUK MENDUKUNG EFEKTIFITAS PEMBELAJARAN DENGAN K-MEANS Krisna Setiawan; Mailoa, Evangs
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol. 16 No. 2 (2025): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v16i2.1013

Abstract

Many schools use learning styles that are not aligned with students' preferences, which can hinder the effectiveness of learning. This study aims to cluster students based on their learning style preferences to support more effective teaching. Data were collected from 27 students using a questionnaire covering four learning styles: Visual, Auditory, Reading/Writing, and Kinesthetic. The K-Means algorithm was used to cluster the data, resulting in three optimal clusters with the highest Silhouette Score of 0.340. The clustering results show three student groups: Visual, Auditory-Reading, and Kinesthetic, with the highest average academic scores in the Auditory-Reading cluster. This study demonstrates that clustering based on learning styles can improve academic achievement, and it is recommended to implement personalized teaching strategies according to students' learning style clusters to enhance learning effectiveness.
PREDIKSI KELULUSAN MAHASISWA MENGGUNAKAN MACHINE LEARNING Hasbullah, M.Imam; Verdi Yasin
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol. 16 No. 2 (2025): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v16i2.1025

Abstract

Predicting student graduation is an essential component in academic management within higher education institutions. The growing issue of delayed graduations and dropouts (DO) has raised significant concerns in the educational field. By utilizing machine learning methods, predictions regarding student graduation can be made with high accuracy, based on historical data such as academic performance, attendance, background, and social factors. This paper aims to explore various machine learning methods applied in previous studies for predicting student graduation, including Decision Tree, Random Forest, SVM, and Neural Networks. The findings of these studies suggest that models like Random Forest and XGBoost tend to provide the highest accuracy in predicting student outcomes. This review is intended to serve as a foundational reference for the development of data-driven systems for predicting graduation rates in academic environments.  
PENGELOLAAN INFORMASI DIGITAL DALAM MENANGANI PERJUDIAN ONLINE DI INDONESIA Muhajir, Muhammad Zaenal Muhajir; Yulyana, Eka; Aryani, Lina
JURNAL TEKNOLOGI INFORMASI DAN KOMUNIKASI Vol. 16 No. 2 (2025): September
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtikp.v16i2.1053

Abstract

Online gambling has become a serious problem in Indonesia, with an increase in gambling content reaching 5,128,871 pieces in the 2017-2024 period, of which 67.4% was addressed by 2024. This study aims to evaluate and analyze digital information management strategies used to address the problem of online gambling in Indonesia. This study applies a qualitative methodology through a single case study approach at the Directorate of Informatics Application Control (APTIKA) of the Ministry of Communication and Digital. Data collection was carried out through four main methods: observation, in-depth interviews, documentation, and literature study. Data analysis uses the Miles and Huberman model with the Defense In Depth information security theory from Coole & Brooks (2011) which consists of four aspects: governance, people, process, and technology. The results show that digital information management has been implemented with a strong operational structure through the implementation of regulations from the ITE Law, the PDP Law, and the PP PSTE, human resource capacity development through continuous training, the implementation of comprehensive SOPs with encryption technology and strict access control, and the use of advanced technology for monitoring and detection. Furthermore, there are still significant obstacles, particularly significant gaps in public communication and accessibility of information to the public, limited prevention education programs, and challenges in dealing with technological developments used by cybercriminals.