JURNAL SISTEM DAN TEKNOLOGI INFORMASI

A Literature Study on Deep Learning Approaches for Face Mask Detection in Air Pollution Mitigation

Nabila Putri Shalehah lala — 2025-09-29

Air pollution ranks among the most significant environmental health issues, especially in cities with elevated pollution levels. Face masks act as an easy but effective way to limit the intake of harmful pollutants like particulate matter (PM2.5), carbon monoxide, and various atmospheric substances. Nonetheless, the efficacy of maks is significantly infuluced by regular use among the public. In this scenario, progeress in deep learning and computer vision creates a change to create automated systems for detecting face maks. This study analyzes current literature on deep learning techniques for mask detection, emphasizing their significance in minimizing air pollution. The method uses a systematic literature review through databases such as Scopus, IEEE Xplore, MDPI, and ScienceDirect, encompassing works from 2020 to 2025. Articles ware examined according to architecture, datasets, and perfomace outcomes. Results indicate that YOLOv3 and MobileNetV2 models based on CNN achieve high precision (95-99%) in detecting masks, although the majority of studies concentrate on COVID-19 scenarios. Research gaps consist of the lack of specific datasets for pollution, restricted outdoor evaluations, absence of lightweight models for edge devices, and poor integration with air quality monitoring. This research emphasizes innovation by transitioning from pandemic sotuations to enduring air pollution, palceing Al-based mask detection as a viable public health approach.

THE EFFECT OF GADGET USE DURATION ON PROGRAMMING ABILITIES AND COMPUTER COURSE GRADES

Arry Avorizano — 2025-12-10

This study aims to analyze the relationship between gadget usage duration and programming skills and computer course grades. Data was collected through questionnaires from 56 respondents aged 10–20 years. The methods used include descriptive statistics, Pearson correlation, t-test, and Chi-Square test. Results indicate no significant relationship between gadget usage duration and programming skills (r = 0.0557; t = 0.4098 < 2.00) or computer course grades (r = 0.196; t = 1.384 < 2.01). The Chi-Square test (χ2 calculated = 11.074 < χ2 table = 12.592) also confirmed no significant relationship between gadget duration and computer grades. The conclusion of this study is that the duration of gadget usage does not significantly affect programming skills and computer course grades in the respondents.

Design of a High Availability Infrastructure Based on Microservices Using an Infrastructure as Code (IaC) Approach with Terraform and Kubernetes

Nasywaa Putricia Ananda — 2025-12-15

The development of modern software architecture has shown a significant shift from monolithic approaches to microservices architecture in order to support scalability and flexibility of information systems (Newman, 2021). However, the adoption of microservices increases the complexity of infrastructure management due to the distributed nature of the components, thereby requiring automation and guarantees of service availability, commonly referred to as High Availability (Burns et al., 2019). Without proper management, this complexity can lead to single points of failure and configuration drift. This study aims to theoretically examine the design of High Availability infrastructure using the Infrastructure as Code (IaC) approach with Terraform and container orchestration using Kubernetes (HashiCorp, 2024; Kubernetes Authors, 2024). The research method employed is a systematic literature study with a descriptive-analytical approach, based on scientific publications, official documentation, and relevant reference books. The findings indicate that the combination of Terraform and Kubernetes conceptually supports configuration consistency through immutability principles, automated infrastructure provisioning across multi-availability zones, and precise self-healing mechanisms (Morris, 2021). Therefore, the IaC approach in microservices architecture has the potential to provide a reliable, efficient, and resilient infrastructure solution capable of meeting high service availability requirements (above 99.9%).

Keywords: High Availability, Microservices, Infrastructure as Code, Terraform, Kubernetes, DevOps.

Optimization of Energy Consumption in IoT Devices Using Reinforcement Learning Algorithms

Eflan ananda pujito — 2025-12-16

The proliferation of Internet of Things (IoT) devices was systematically investigated, revealing pervasive energy
constraints that critically limit operational reliability, sustainability, and scalability across billions of predominantly battery
powered deployments projected to exceed 18.8 billion connected units by 2024. Conventional energy optimization
techniques—including static duty-cycling protocols, fixed transmission power configurations, and rule-based heuristics—
were determined inadequate for adapting to real-time variations in traffic loads, channel quality fluctuations, interference
patterns, and heterogeneous quality of service (QoS) requirements characteristic of diverse applications ranging from
real-time healthcare monitoring to periodic environmental sensing, resulting in excessive energy expenditure,
accelerated battery depletion, elevated packet loss rates, increased end-to-end latency, and overall network
performance degradation. Q-learning reinforcement learning was implemented within a comprehensive simulated
wireless sensor network environment comprising 10-100 battery-constrained nodes periodically transmitting
environmental data to a central gateway, with the optimization problem rigorously formulated as a Markov Decision
Process (MDP). Autonomous RL agents were enabled to optimize critical operational parameters including transmission
power levels (0-20 dBm), dynamic sampling frequencies (1-10 Hz), and adaptive sleep-wake intervals (10 seconds to 5
minutes) through comprehensive state representations encompassing residual battery capacity (1000-5000 mAh),
current traffic density, channel quality indicators (SNR, packet error rate), and application-specific QoS constraints.
Extensive simulations were conducted using established NS-3 network simulator and Python-based reinforcement
learning frameworks (Gym, Stable Baselines3) across diverse operational scenarios varying node density, traffic
patterns, and environmental conditions, executing 10,000 episodes per configuration with optimized hyperparameters
(learning rate α=0.1, discount factor γ=0.95, ε-greedy exploration decay). Results demonstrated statistically significant
superiority over fixed 30% duty-cycling and static power baselines: 35.7-42.3% reductions in total energy consumption
(721-892 mJ/node), 68% extension of network lifetime (239 hours until 20% node failure), packet delivery ratios
exceeding 91%, and marked improvements in energy-per-bit efficiency, validated through rigorous statistical analysis
(t-test/ANOVA, p<0.001). Action attribution analysis identified sleep-wake optimization (41% contribution), dynamic
power control (37%), and sampling rate adjustments (22%) as primary efficiency drivers, positioning reinforcement
learning as a transformative paradigm for sustainable large-scale IoT ecosystems while highlighting needs for lightweight
Deep RL variants and edge deployment optimizations to address training computational overhead.

THE IMPACT OF THE Syva CHATBOT ON CUSTOMER SATISFACTION AND SHARIA COMPLIANCE IN KB BANK SYARIAH DIGITAL SERVICES

Nurul Izzah Ahlam — 2025-12-19

This study aims to analyze the impact of implementing the Syva chatbot on customer satisfaction and sharia compliance in digital services at KB Bank Syariah. Using a descriptive quantitative approach, data were collected through questionnaires and interviews with customers and customer service staff. The results show that chatbot features (AI capability, NLP, and responsiveness) have a significant effect on service quality, including reliability, ease of use, and sharia compliance. High service quality subsequently increases customer satisfaction. This study also identifies a literature gap by integrating User Experience (UX) and sharia compliance aspects in the context of digital Islamic banking and provides recommendations for KB Bank Syariah to optimize the Syva chatbot service.

Keywords: Chatbot, Customer Satisfaction, Sharia Compliance, Digital Services, KB Bank Syariah, User Experience (UX)

DESIGN AND UI/UX EVALUATION OF A WEB-BASED ZAKAT FITRAH INFORMATION SYSTEM AT AL MUJAHIDIN MOSQUE

Muhammad Faris Syauqy Syauqy — 2026-01-05

Zakat fitrah is a mandatory obligation for Muslims that must be managed properly to ensure accurate distribution
and transparency. However, the management of zakat fitrah at Al Mujahidin Mosque is still conducted manually,
which may lead to data recording errors, inefficiencies, and delays in reporting. This study aims to design and
implement a web-based Zakat Fitrah Information System to support the management of muzakki data, mustahik
data, zakat receipt, zakat distribution, and reporting processes. The scope of this research is limited to the
administrative management of zakat fitrah at Al Mujahidin Mosque. The system development methodology
applied in this research is the Software Development Life Cycle (SDLC) using the Waterfall model, which consists
of requirement analysis, system design, implementation, testing, and maintenance stages.The system was
developed using HTML and CSS for the user interface, JavaScript for system interaction and validation, and
MySQL as the database management system. Functional testing was conducted using Black Box Testing to ensure
that all system features operate as expected. In addition, a User Experience (UX) evaluation was performed using
a Likert-scale questionnaire involving 10 respondents who are directly involved in zakat management activities.
The UX evaluation results show an average score of 4.32 out of 5, indicating that the system is easy to use, well
structured, and meets user needs.Based on the implementation and testing results, it can be concluded that the
proposed system is capable of improving the accuracy of data recording, efficiency of zakat management, and
transparency of zakat distribution and reporting. Therefore, the developed system can be utilized as an effective
solution to support zakat fitrah management at Al Mujahidin Mosque.

CLOUD COMPUTING INFRASTRUCTURE DESIGN TO OPTIMIZE DIGITAL UMKM BUSINESSES

Faridz Adiansyah — 2026-01-07

Advances in digital technology enable Micro, Small, and Medium Enterprises (MSMEs) to adapt to the digital environment to improve competitiveness and business sustainability. However, limited information technology infrastructure, high investment costs, and low technical readiness are major obstacles in the digital transformation process of MSMEs. Cloud computing offers a solution through the provision of flexible, efficient, and affordable technology services. This study aims to design a simple cloud computing infrastructure that suits the needs of digital MSMEs. Theoretical and literature reviews are used to identify the benefits, challenges, and relevant cloud service models for MSMEs. The research method used is a descriptive and design approach, with data mining through literature studies and analysis of MSME needs. The results show that the implementation of cloud computing, particularly through SaaS-based services, can improve cost efficiency, operational flexibility, and data security for MSMEs. The proposed infrastructure design emphasizes ease of use, scalability, and the utilization of built-in security features. The conclusion of this study confirms that appropriate cloud computing design can be a strategic solution in supporting the sustainable digital transformation of MSMEs.

DESIGNING A CLOUD-BASED IT INFRASTRUCTURE TO SUPPORT NEIGHBORHOOD ADMINISTRATION WEB APPLICATIONS

Muhammad Rizqy Zufarrel — 2026-01-10

Administrative management at the neighborhood level (Rukun Tetangga/RT) in Indonesia is still largely handled manually, often leading to data inaccuracies and delayed services. While a dedicated website offers a solution for digitalization, its effectiveness relies heavily on a robust underlying technology infrastructure. This research aims to design a cloud-based IT infrastructure specifically tailored for small-scale administrative needs with limited budgets. Adopting the Network Development Life Cycle (NDLC) methodology, the study analyzes technical requirements ranging from Virtual Private Server (VPS) selection and secure data storage to automated backup schemes. The findings indicate that cloud infrastructure not only ensures higher uptime compared to local physical servers but also offers significant cost efficiency. This proposed design is intended to serve as a practical guide for local community leaders in establishing reliable, transparent, and affordable information systems.

DESIGNING INFORMATION TECHNOLOGY INFRASTRUCTURE BASED ON ZERO TRUST ARCHITECTURE TO IMPROVE CAMPUS DATA SECURITYM

Naufal Aditya Putra M.Fitroh — 2026-01-10

Virtual transformation in better education has accelerated establishments' dependence on facts technology infrastructure in dealing with instructional statistics, management, and research. This condition is observed via an growth in cyber threat risks due to machine complexity, person mobility, and the use of more than one gadgets. traditional perimeter security is considered ineffective in handling the dynamics of modern cyber threats on campus. This have a look at ambitions to design an trouble-based totally generation infrastructure the usage of zero trust structure with a view to enhance campus data safety. The technique used is design science studies the usage of a structured literature look at approach to cybersecurity standards, specially NIST unique publication 800-207, and relevant previous studies. The consequences of this take a look at are a conceptual layout of a 0 agree with structure that consists of identity and get entry to control, network segmentation, endpoint protection, and centralized safety monitoring. The proposed layout is wanted to minimize the chance of illegal access, boom safety visibility, and support access flexibility in the contemporary campus surroundings. This research affords conceptual contributions to the implementation of 0 believe structure as an adaptive and sustainable information security tactic for better education establishments.