Internet of Things and Artificial Intelligence Journal
Internet of Things and Artificial Intelligence Journal (IOTA) is a journal that is officially under the auspices of the Association for Scientific Computing, Electronics, and Engineering (ASCEE), Internet of Things and Artificial Intelligence Journal is a journal that focuses on the Internet of Things (IoT), ISSN 2774-4353, publishing the latest papers in the IoT field and Artificial Intelligence (AI) i.e., Machine Learning (ML), and Deep Learning (DL)., etc., Topics can be included in this journal : IoT for various applications ( medical, sport, agriculture, smart city, smart home, smart environment, etc.) IoT communication and networking protocols ( LoRa, WiFi, Bluetooth Low Energy, etc.) IoT enabling technologies IoT system architecture IoT with a Recently Sensors Technology IoT with Wireless Sensor Network (WSNs) Technology Cloud-based IoT IoT data analytics IoT Security IoT Management Services IoT with Low Power and Energy Harvesting Future technologies for IoT Future Internet design for IoT Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL) Drone or UAV, and IoT Analyzes IoT with a Financial Technology (FINTECH) Managemen approach IoT for Education Technology IoT for Industry Computers & Security :: computer security, audit, control and data integrity in all sectors - industry, commerce and academia Computer application for Economy, Finance, Business, Micro, Small & Medium Enterprises (MSMEs), Accounting, Management, and other sectors Review articles on international & national legal rules in the use of computer software, internet of things, frequency usage, etc. Internet of Things and Artificial Intelligence Journal has a frequency of being published 4 times a year or 4 issues every year (February, May, August, and November) with the Peer review process.
Articles
174 Documents
<![CDATA[Machine Learning Approach to Analyze the Relationship Between State Defense Index and Human Development to Strengthen National Defense ]]>
<![CDATA[Qotrunada, Farah]]>;
<![CDATA[Budiyanto, Setiyo]]>;
<![CDATA[Wajdi , Achmad Farid]]>
<![CDATA[ Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February] ]]>
Publisher : <![CDATA[Association for Scientific Computing, Electronics, and Engineering (ASCEE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/iota.v5i1.869
<![CDATA[In efforts to strengthen national defense, it is important to understand how factors in human development, such as education, health, and economic welfare, can influence public awareness of national defense. This study aims to analyze the relationship between the National Defense Index (IBN) and the Human Development Index (IPM) in Indonesia using a Machine learning approach. To strengthen national defense, it is essential to understand how factors in human development, such as education, health, and economic welfare, can affect public awareness of national defense. Machine learning methods are applied to analyze the significant relationship between IBN and IPM, which is expected to provide insights for the development of more data-driven national defense policies. The results show that the Machine learning model can predict IBN values with high accuracy, supported by a Mean Squared Error (MSE) of 0.000638 and an R-squared value of 0.9026. This indicates that 90.26% of the variability in IBN values can be explained by the model, suggesting accurate predictions that are relevant for data-driven policies. Collaboration with various stakeholders is expected to enhance the application of these findings in further studies and the formulation of national defense policies. ]]>
<![CDATA[PCOS Disease Classification Using XGBoost Algorithm and Genetic Algorithm for Feature Selection ]]>
<![CDATA[Atika, Enda Putri]]>;
<![CDATA[Nadzirullah, Muh. Ilham]]>;
<![CDATA[Arindika, Alti]]>
<![CDATA[ Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February] ]]>
Publisher : <![CDATA[Association for Scientific Computing, Electronics, and Engineering (ASCEE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/iota.v5i1.874
<![CDATA[Polycystic Ovary Syndrome (PCOS) is an endocrine disorder that often occurs in women of reproductive age, with a global prevalence of 10-16%. The diagnosis of PCOS is still a challenge due to the uncertainty of the cause, which can worsen the patient's condition due to delayed detection. This study aims to develop a classification model to detect PCOS using a combination of SMOTE algorithm, genetic algorithm, and XGBoost. The dataset used is a public dataset from Kaggle entitled "Diet, Exercise, and PCOS Insights". A genetic algorithm was used to select the best 15 features, while SMOTE was applied to handle data imbalances. XGBoost is used for classification with a model accuracy of 82.86% and an F1-score of 88% for the PCOS negative class and 70% for the PCOS positive class. The results show that combining these algorithms can improve the accuracy of predictions and offer more efficient diagnosis solutions. This research is expected to contribute to developing early diagnosis methods for PCOS.]]>
<![CDATA[Optimization of Temperature Sensor Selection for Incubators: Real-Time Accuracy Analysis of DHT22, LM35, and DS18B20 in Controlled Environment Simulations ]]>
<![CDATA[siswoyo, agus]]>
<![CDATA[ Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February] ]]>
Publisher : <![CDATA[Association for Scientific Computing, Electronics, and Engineering (ASCEE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/iota.v5i1.877
<![CDATA[Temperature measurement accuracy is a critical factor in incubator systems, especially for medical and biological applications that require high precision. This study aims to analyze the performance of three popular temperature sensors (DHT22, LM35, and DS18B20) in the context of an incubator through controlled environment simulations, to determine the optimal sensor based on real-time accuracy, response time, and stability. The experimental method was carried out by replicating the operational conditions of the incubator using a climate chamber set at a temperature range of 30–40°C and a humidity of 60–80% RH. The sensor accuracy data was compared with a medical-grade reference thermometer (Fluke 1551A), while the response time was measured through a simulation of dynamic temperature changes (±5°C). The results showed that the DS18B20 recorded the highest accuracy with an average deviation of ±0.3°C and a response time of 2–3 seconds, supported by an interference-resistant 1-Wire digital interface. The LM35 exhibits good linearity (±0.5°C) but is susceptible to electrical noise without shielding, while the DHT22 has lower accuracy (±0.8°C) due to the influence of internal humidity on the measurement system. This study also reveals the need for regular calibration of the LM35 and a closed enclosure design for the DHT22 to minimize environmental errors. The study's conclusions recommend the DS18B20 as the optimal choice for high-precision medical incubators, with the inclusion of digital filters for signal optimization. These findings provide practical guidance for developers in selecting temperature sensors according to incubator design needs, whether for healthcare, biotechnology, or precision agriculture applications.]]>
<![CDATA[Conceptualizing Artificial Intelligence in the Indonesian Education Systems and Reciprocity with AI-Based Curriculum ]]>
<![CDATA[Alamsyah, Nurwahyu]]>;
<![CDATA[Neal, Dale]]>
<![CDATA[ Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February] ]]>
Publisher : <![CDATA[Association for Scientific Computing, Electronics, and Engineering (ASCEE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/iota.v5i1.878
<![CDATA[This study employs a Systematic Literature Review (SLR) to analyze the curriculum challenges in Indonesia and explore the potential AI-driven solutions to improve the education systems. The findings reveal that conventional teaching methods, lack of project-based learning (PBL), limited technology integration, and rigid learning approaches are among the most critical issues, leading to low student engagement and an imbalance between hard and soft skills. To address these challenges, AI technologies such as adaptive learning, formative assessments, and AI-powered virtual classrooms can be integrated to enhance personalized and competency-based learning. The findings suggest that by adopting AI-driven strategies, Indonesia can modernize its curriculum, enhance educational effectiveness, and align with global standards. This study contributes to evidence-based policymaking by offering insights into AI adoption in education and proposing a roadmap for a technology-integrated, student-centered learning system.]]>
<![CDATA[Clean Energy Innovation in Campus Environment with Small-Scale Wind Power Plants Integrated with IoT ]]>
<![CDATA[artanto, dian]]>;
<![CDATA[sutyasadi, petrus]]>;
<![CDATA[Lukiyanto, Yohanes Baptista]]>;
<![CDATA[Subanar, Gregorius Budi]]>;
<![CDATA[Anurogo, Baskoro Latu]]>;
<![CDATA[Halim, Enrico]]>;
<![CDATA[Indratma, Samuel]]>
<![CDATA[ Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February] ]]>
Publisher : <![CDATA[Association for Scientific Computing, Electronics, and Engineering (ASCEE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/iota.v5i1.881
<![CDATA[Universities as innovation centers have a strategic role in driving the clean energy transition through the implementation of small-scale wind power plants integrated with IoT. This article analyzes the potential of wind power technology in campus environments, which have an average low wind speed (3–5 m/s) through Savonius-type vertical axis turbines equipped with IoT modules for real-time monitoring of wind speed, wind direction, electrical energy production, and battery status. The results show that this technology is capable of producing 100–200 W of power with a wind energy conversion efficiency to electrical energy of up to 20-30%. The implementation of this technology not only increases energy independence but also becomes a renewable energy education platform for students. Multidisciplinary collaboration between the fields of electrical engineering, mechanical engineering, and informatics engineering is the key to system optimization, while green campus policies can accelerate the adoption of this technology nationally.]]>
<![CDATA[NLP-Semantic Machine Learning-Based System for Intelligent Classification of Professional Skill-Sets for Efficient Human Resource Management Process ]]>
<![CDATA[Umoren, Imeh]]>;
<![CDATA[Akwang, Nse]]>;
<![CDATA[Inyang, Saviour]]>;
<![CDATA[Afolorunso, Adenrele]]>;
<![CDATA[James, Gabriel]]>
<![CDATA[ Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February] ]]>
Publisher : <![CDATA[Association for Scientific Computing, Electronics, and Engineering (ASCEE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/iota.v5i1.882
<![CDATA[Skill sets can improve individual professional proficiency and enable individuals to perform better at work. Professional skill sets create opportunities to aid in advancement in job classification of individual skill advantage resulting in good human resource management to efficiently present employers with adequate and qualified candidates for a given job offer. Classifying the right people for the right skills is a common task in human resource management. This research work presents a mechanism for classifying individual extracted Summary page texts of Curriculum Vitae (CV) through the application of the Semantic Machine Learning Model. First, data was gathered by mining different summary page curriculum vitae both online and offline. Second, preprocessing of datasets, by undergoing data cleaning, text normalization, and feature extraction and splitting data sets into training and test sets in the ratio of 80:20% for train and test set. Thirdly, exploratory data analysis was carried out to visualize different variables to determine how each metrics (parameter) interact with each other regarding Skill Sets classification based on the five topics concerns (Goal Oriented, Emotional Intelligence, Good Communication Skills, Problem Solving, and Leadership skills). Fourthly, Using an Artificial Neural Network for the classification of the text vectors, ANN gave an accuracy of 94% on the 10-epoch used in the model. Performance evaluation on the model was carried out and results show a precision of 82%, 76%, 40%, 66%, and 57 % respectively for Goal Oriented, Emotional Intelligence, Good Communication Skills, Problem Solving, and Leadership skills classifications. The proposed system served as an efficient Human resource management process.]]>
<![CDATA[Design and User Analysis of a Learning Management System: Student Competency-Based Learning ]]>
<![CDATA[Pratisto, Eko Harry]]>;
<![CDATA[Danoetirta, Daffa Raszya]]>
<![CDATA[ Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February] ]]>
Publisher : <![CDATA[Association for Scientific Computing, Electronics, and Engineering (ASCEE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/iota.v5i1.883
<![CDATA[The rapid evolution of digital technology in education has highlighted the need for robust platforms that support student competency-based learning, wherein each learner progresses at an individualized pace and demonstrates mastery of specific competencies. Building on evidence that personalized instruction improves engagement and learning outcomes, this study aims to develop a Learning Management System (LMS) capable of enhancing both formative and summative assessments. The primary objectives are to facilitate the uploading of learning materials, manage user roles (teachers, students, administrators), and provide flexible assignment distribution—all while promoting self-directed, sustainable learning. An Agile methodology was adopted to ensure iterative development and close collaboration with stakeholders, allowing for quick adaptations to evolving requirements. System architecture was designed using UML, focusing on role-based workflows and clear user interfaces. Throughout the process, regular sprints were conducted, incorporating continuous testing and feedback loops to refine functionality. The LMS was then evaluated through usability testing using the System Usability Scale (SUS). Findings from 80 student participants yielded an average SUS score of 81.75, which falls into the “very good” category, suggesting high user acceptance and ease of use. These results affirm the system’s effectiveness in supporting competency-based learning, as students can monitor individual progress in real-time and receive timely feedback from teachers. Moreover, teachers benefit from streamlined assessment processes, enabling them to devote more attention to pedagogical improvements. Although this research was conducted in a single school environment and over a relatively short period, the encouraging results indicate strong potential for broader implementation. Future development may integrate features such as learning analytics, gamification, and personalized content recommendations, thereby further enhancing adaptive learning experiences across diverse educational contexts.]]>
<![CDATA[Design of NLP-based chatbot media as a mental health consultation media with Depression Anxiety Stress approach ]]>
<![CDATA[Hadi, Abd]]>
<![CDATA[ Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February] ]]>
Publisher : <![CDATA[Association for Scientific Computing, Electronics, and Engineering (ASCEE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/iota.v5i1.888
<![CDATA[The development of technology has increased rapidly, this is in line with the increasing consumption of data and information. Getting information for all users has become easier with the development of artificial intelligence, Chatbot is partly an example of artificial intelligence technology that allows machines to think and make decisions independently, Depression Anxiety Stress Scales (DASS) is a commonly used tool for measuring mental health conditions, consisting of a series of questions used to measure a person's level of depression, anxiety, and stress. DASS helps provide a better picture of a person's psychological condition, which can help further diagnosis and intervention. In this study, we conducted a chatbot design using the NLP approach using DASS data as many as 3 categories of anxiety, stress, and depression. From the test results obtained by the chatbot from 41 questions, there were 85% percent accurate answers.]]>
<![CDATA[Design and Control of IoT Based Automatic Watering Devices for Vegetable Plants ]]>
<![CDATA[Iriyanti, Aldarisma]]>;
<![CDATA[Agung, Muhammad]]>;
<![CDATA[Wahid, Abdul]]>
<![CDATA[ Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February] ]]>
Publisher : <![CDATA[Association for Scientific Computing, Electronics, and Engineering (ASCEE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/iota.v5i1.890
<![CDATA[This research aims to design and develop an Internet of Things (IoT)--based automatic watering device for vegetable crops, especially water spinach and bok choy. The IoT technology used allows users to monitor and control the watering process remotely through an Android-based mobile application. The device is equipped with a soil moisture and temperature sensor (DHT22), which automatically controls the water pump and fan according to the needs of the plants. System testing was conducted to ensure the functionality of the sensors and that the automatic watering system operates effectively. The test results show that the device works efficiently in maintaining soil moisture and plant temperature, thereby improving the maintenance of vegetable crops. With this system, watering is done promptly and according to the needs of the plants, thereby reducing water and energy wastage. This research offers a practical solution for farmers or plant enthusiasts to monitor and care for plants automatically and efficiently.]]>
<![CDATA[Career Prediction of Informatics Engineering Alumni Using Naïve Bayes Algorithm ]]>
<![CDATA[Nurkholis, Nurkholis]]>;
<![CDATA[Am, Andri Nofiar.]]>
<![CDATA[ Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February] ]]>
Publisher : <![CDATA[Association for Scientific Computing, Electronics, and Engineering (ASCEE) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/iota.v5i1.897
<![CDATA[Alumni are an important part of education, especially in higher education where alumni can be a reference for the quality of the majors, the more alumni graduates who can get jobs in accordance with their majors, the better the teaching and learning process in the majors, but if the opposite happens, the university needs to evaluate the teaching and learning process so that the students produced can keep up with the times, during the process of finding work in accordance with the alumni's majors. Uin Suska Riau informatics engineering alumni are no exception where analyzing alumni careers is important to be able to improve the quality of Uin Suska Riau in producing alumni who are able to compete in the future. The Naïve Bayes algorithm is a branch of machine learning that can make predictions using classification techniques in predicting the career data of informatics engineering alumni. In the study there was alumni data to carry out the prediction process on career suitability with majors using 275 data and divided into training data and testing data resulting in an accuracy of 75%.]]>
