Jurnal Indonesia : Manajemen Informatika dan Komunikasi

Sistem Kendali Mikroklimat Greenhouse Cerdas Berbasis Hybrid GA-LSTM dan Fuzzy Logic Controller

Rainer Maghma Royali — 2026-05-10

Controlling temperature and humidity in greenhouses is a complex challenge due to its non-linear nature and dependence on external weather conditions. Conventional control methods often experience energy inefficiency and delayed responses to drastic changes. This study proposes a hybrid approach by combining Long Short-Term Memory (LSTM) optimized using Genetic Algorithm (GA) for temperature prediction, and Fuzzy Logic Controller (FLC) for actuator decision-making. Genetic Algorithm is employed to find optimal hyperparameters (number of neurons and batch size) in the LSTM architecture. Experimental results demonstrate the GA-LSTM model's capability in predicting temperature with high accuracy, yielding an R² score of 0.9881 and Root Mean Square Error (RMSE) of 1.1273°C. These accurate predictions are subsequently used as input to the FLC to regulate exhaust fan speed and mist pump status. Simulations demonstrate the system's capability in making energy-efficient decisions—activating actuators only when conditions are predicted to deviate from ideal values—while remaining responsive to extreme temperature anomalies.

Strategi Komunikasi Efektif Pengelolaan Arsip Digital untuk Mendukung Layanan Inklusif bagi Disabilitas Tuli di PT KAI Tahun 2025

Hasbi Ridla Ilahi — 2026-05-10

Effective communication is a pivotal component in the provision of inclusive digital archive services, particularly for individuals who are Deaf and depend on visual communication and Indonesian Sign Language (Bisindo). The objective of this study is threefold: first, to analyze the communication process in the management of digital archives at PT Kereta Api Indonesia (Persero); second, to identify communication barriers experienced by Deaf individuals; and third, to formulate strategies for developing inclusive digital archive services. The research employs a descriptive qualitative approach with participatory observation, interviews, and documentation studies at the Section of Asset Ownership Document and Files (USDA) of PT KAI. Participatory observation was conducted to directly observe the steps in using the Rail Document System (RDS), the workflow of digital archive services, and the interactions between Deaf and hearing staff members. Over two months, in-depth data were collected through observation, interviews, and documentation involving seven informants, both internal and external. The results indicate that the management of PT KAI's digital archives has been technically well-executed; however, it does not fully accommodate the needs of Deaf users. The study proposes several recommendations, including the integration of Indonesian Sign Language (Bisindo) into the digital archive system, the provision of content or features accompanied by visual guides, the implementation of sign language training for PT KAI employees, and the reinforcement of internal company policies and regulations. These recommendations aim to ensure the provision of equitable and inclusive digital archive services at PT KAI

Representasi Unsur Jawa dalam Film Ketika Cinta Bertasbih 1 (Analisis Semiotika Charles Sanders Peirce)

Ido Afriadi — 2026-05-10

This study examines Javanese cultural values found in the religious theatrical film Ketika Cinta Bertasbih 1. The research question addressed is what signs and meanings represent Javanese cultural values in the film. The approach used is semiotic analysis, focusing on symbolic meaning as the object of study. The research method applied is descriptive qualitative, which prioritizes depth of meaning over generalization of results. The data in this study consist of verbal and non-verbal texts. Verbal texts include spoken and written language, while non-verbal texts take the form of images and setting backgrounds contained in the film. Data were collected through an observation and note-taking technique, comprising: (1) watching the film, (2) recording relevant information, (3) collecting data through screenshots, (4) sorting the data, and (5) analyzing the data to draw conclusions. This study employs the semiotic framework of Charles Sanders Peirce, focusing on symbolic meaning as the unit of analysis. The findings reveal 4 images and narratives carrying symbolic meanings related to Javanese cultural elements, particularly through the use of Javanese vocabulary and settings located in Central Java.

Analisis Teori Keputusan Pembelian Kotler & Keller: Peran Influencer dalam Membentuk Perilaku Fast Moving Skincare pada Generasi Z melalui Media Sosial Instagram

Aisyah Putri Balqis — 2026-05-10

This research examines the role of influencers in shaping Fast Moving Skincare consumption behavior among Generation Z on Instagram, against the backdrop of rapid beauty product proliferation that drives trend-responsive purchasing patterns. Drawing on Kotler and Keller's (2009) consumer decision-making theory, this study employs a descriptive qualitative approach through in-depth interviews with four informants — beauty community members and active skincare users. The findings reveal that influencer impact is not uniform across all stages of the decision-making process. At the problem recognition stage, Generation Z relies primarily on personal experience and close social circles rather than influencer content. Influencers become relevant at the information search stage, functioning as visual and interactive reference points, though audiences apply active filtering throughout. At the alternative evaluation stage, peer influence from close social circles outweighs influencer recommendations. This finding points to an additional stage not accounted for in the original Kotler and Keller model: the influence of close social environments immediately before the purchase decision. Generation Z's purchasing behavior, taken as a whole, remains selective and is not straightforwardly driven by digital trends.

Pengaruh Konten Media Sosial Instagram pada Akun @selatan.florist terhadap Minat Beli Followers: Pendekatan Elaboration Likelihood Model

Retno Wulandari — 2026-05-10

The rapid advancement of technology has pushed business actors to rely on social media as their primary promotional channel. On the @selatan.florist account, several obstacles were identified in content production — particularly in feeds, stories, and reels — concerning visual appeal, upload consistency, and the depth of informative value delivered to the audience. This study examines the extent to which social media content produced by @selatan.florist affects followers' purchase intention. The Elaboration Likelihood Model (ELM) serves as the theoretical lens, explaining how individuals process persuasive messages and form attitudes in response. A quantitative methodology was applied, with a structured questionnaire distributed to 152 respondents who follow the @selatan.florist account. Simple linear regression analysis reveals a statistically significant influence of social media content on purchase intention. The R² value of 66.3% indicates that visual aesthetics and informational depth in the account's content are decisive factors in converting audience attention into purchasing behavior.

Sistem IoT Berbasis Edge untuk Pemantauan Kualitas Udara Perkotaan Real-Time

I Putu Arich Arthawan — 2026-05-10

Air pollution in urban areas has become a serious issue due to rapid urbanization, industrial activities, and the increasing number of motor vehicles, which directly impact human health and the environment. Conventional monitoring systems that rely on cloud-based processing often face challenges such as high latency and limitations in providing real-time information. This study aims to develop an Internet of Things (IoT)-based air quality monitoring system integrated with edge computing to improve data processing efficiency and reduce latency. The proposed system utilizes sensors for PM2.5, carbon monoxide (CO), temperature, and humidity, which are connected to an edge device to perform local data processing before being transmitted to the cloud. The research methodology includes system architecture design, hardware and software implementation, and performance evaluation based on latency, data accuracy, and system responsiveness. The results indicate that the edge-based approach significantly reduces latency compared to cloud-based systems while maintaining high data accuracy. In addition, the system is capable of providing real-time data visualization through a dashboard, enabling faster and more effective decision-making. Therefore, the integration of IoT and edge computing offers an efficient, scalable, and promising solution for urban air quality monitoring and supports the development of smart city applications.