International Journal of Smart Systems

A Review: Application of AIOT in Smart Cities in Industry 4.0 and Society 5.0

Saluky — 2023-02-14

This review paper explores the application of Artificial Intelligence of Things (AIOT) in smart cities under the contexts of Industry 4.0 and Society 5.0. The main objective of the paper is to analyze and evaluate the latest developments and implementations of AIOT in smart cities, and to provide insights on the potential benefits, challenges, and future research directions. The study uses a systematic literature review approach and synthesizes relevant literature from various sources. The results indicate that AIOT has immense potential to revolutionize the way smart cities operate by enhancing the efficiency, sustainability, and livability of urban spaces. However, the adoption of AIOT also poses several challenges such as security, privacy, and ethical concerns. The paper concludes that a more collaborative and interdisciplinary approach is needed to fully realize the potential of AIOT in smart cities and address the challenges that come with it. The findings of this review provide useful insights for policymakers, practitioners, and researchers interested in the development and implementation of AIOT in smart cities.

Implementation of Algorithm C4.5 in Predicting Learning Readiness

Kosal Dharany — 2023-02-14

This paper discusses the implementation of the C4.5 algorithm in predicting learning readiness. Algorithm C4.5 is a machine learning technique that is often used to generate decision tree-based classification models. This study aims to develop a predictive model of learning readiness using the C4.5 algorithm. The data used in this study is secondary data obtained from the results of filling out the questionnaire by students. The stages in model development include data processing, making decision trees, and model evaluation. The results of the study show that the model developed using the C4.5 algorithm can predict learning readiness with fairly high accuracy. It is hoped that the results of this research can become a reference for the development of decision support systems in the education sector.

Reasoning Adaptive Ability in Solving Questions Mathematics Logic Based on Learning Creativity

Annis Sholiha Suhanda — 2023-02-14

The purpose of this study was to analyze the adaptive reasoning skills by students' creativity in solving mathematical logic. This study uses a qualitative descriptive research method. The subject of the research was a 3rd grade student of IAIN Syekh Nurjati who was chosen by one of the students with high learning creativity, medium learning creativity, and low learning creativity. Use sampling techniques aimed at selecting subjects. The data collection techniques used were written tests, indirect communication techniques and interviews, while the tools in this study were adaptive reasoning tests, learning creativity questionnaires and interview guidelines. Use triangulation techniques to test the validity of the data. Data analysis was carried out through data simplification, data presentation and conclusion drawing. The results showed that students with high learning creativity met four indicators, namely, guessing, giving reasons for the truth of the statement, drawing conclusions from the statement, and testing the validity of the argument but did not meet the indicators of getting a model from mathematical symptoms, students with moderate learning creativity only met two indicators, namely submitting allegations and verifying the validity of arguments; students with low learning creativity only meet one indicator, namely providing reasons or evidence for statements.

Algorithm Implementation With Ensemble Learning On Weather Forecast

Ira Ramadhaniyati — 2023-02-14

Weather conditions are vital in the continuation of human life. Knowing weather conditions became crucial because almost all human life is connected to it. From agriculture, plantations, even to human activities. Therefore, the method of a weather forecast is required for information on today's weather conditions as well as in the future. The purpose of these weather forecasts is simply so that people can use this for survival. Normally we can tell weather conditions from rainfall, temperature and wind speed. The issue, however, is how to determine accurate weather predictions and can be easily used by the general public. In the study, selecting learning ensemble to calculate existing data groups by involving multiple algorithms to find average accuracy and determine which methods work most optimally. As for research results it is expected to be the basis for building weather forecast applications. Accuracy results at 81.21% and mse 18.79%.

A Review: Application of Deep Learning in Smart City Analysis

Phuong Dong — 2023-02-14

The rapid development of smart cities has led to the increasing demand for advanced technologies that can effectively manage the vast amount of data generated by various sources. Deep learning, a subset of machine learning, has been successfully applied in various domains and has shown remarkable performance in analyzing large-scale and complex data. This review paper presents a comprehensive analysis of the recent advancements and applications of deep learning in smart city analysis. The paper covers the different use cases of deep learning in the smart city domain, such as transportation, energy, healthcare, security, and public services. The review also highlights the challenges and opportunities of applying deep learning in the smart city domain and suggests potential research directions for future work. The analysis demonstrates the effectiveness of deep learning in smart city analysis and its potential to contribute to the development of smarter and more sustainable cities.

Enhancing Citizen Engagement in Smart Cities with Chatbot

Chung Huang — 2023-03-31

Smart cities rely on the engagement and participation of their citizens to achieve their goals of improving quality of life, sustainability, and efficiency. However, traditional communication channels between citizens and smart city services can be limited, leading to reduced engagement and participation. In this paper, we propose the integration of a chatbot to enhance citizen engagement in smart cities. The chatbot is designed to understand natural language queries and provide quick and accurate responses about smart city services such as public transportation, waste management, and emergency services. The chatbot is integrated with the smart city services through APIs, allowing for real-time information updates. A user study is conducted to evaluate the effectiveness of the chatbot in enhancing citizen engagement. The study measures metrics such as user satisfaction, response time, and accuracy of the chatbot's responses. The results indicate that the chatbot is effective in improving citizen engagement by providing quick and accurate information about smart city services. The integration of a chatbot has the potential to enhance citizen engagement in smart cities, leading to improved quality of life, sustainability, and efficiency. The chatbot provides a convenient and accessible communication channel for citizens to interact with smart city services, improving overall citizen experience in the city. Future work may involve expanding the chatbot's capabilities to include more smart city services and improving the chatbot's performance through machine learning algorithms.

Anomaly Detection in Surveillance Videos through Object-Oriented Analysis

Auni Khadijah — 2023-04-01

Detecting and pinpointing irregularities in surveillance videos has remained a persistent challenge. The current approaches, which are based on patches or trajectories, do not have a semantic understanding of the scenes and may split the targets into fragments. To address this issue, this research proposes a new and efficient algorithm that combines deep object detection and tracking, while fully leveraging spatial and temporal information. A dynamic image is introduced by integrating both appearance and motion information and then fed into an object detection network, which accurately detects and classifies objects, even in crowded and poorly lit scenes. Based on the detected objects, an effective and scale-insensitive feature, named Histogram Variance of Optical Flow Angle (HVOFA), is developed together with motion energy to identify abnormal motion patterns. To further detect missing anomalies and reduce false detections, a post-processing step is carried out with abnormal object tracking. This algorithm outperforms existing methods on established benchmarks.