Smart City Applications Research Articles

Data-driven decarbonization: Optimizing P+R in Istanbul with machine learning energy modeling and ITS

Due to the rapidly developing technologies, fast and practical solutions are offered to the problems encountered in daily life. Metropolitan cities are greatly affected by the ever-increasing population and migrations to big cities, the increase in production with the economy and job opportunities. At this point, with the introduction of smart transportation systems, fast and effortless solutions can be produced by saving time and space. City life can be facilitated by applying more efficient and rational solutions with smart transportation systems. In this study, it is aimed to investigate information about the Intelligent Transportation Systems and one of its applications, park and ride, which has created a significant agenda within the scope of transportation engineering in the recent past, and to provide information about the investments made by examining the application for Istanbul along with its various applications in the world. Some suggestions will be made by emphasizing the importance of the park and Ride smart city application for Istanbul. In conclusion, predictions of P + R application and energy consumption in periods of 1–24 months were made through machine learning. By obtaining energy consumption data thanks to machine learning, carbon gas emissions and its effects on greenhouse gases were also examined. It can be thought that by obtaining energy consumption data for the long term thanks to machine learning, it can make significant contributions to future investments, green environment-green world, and climate change studies.

The Role of 6G Technologies in Advancing Smart City Applications: Opportunities and Challenges

The Role of 6G Technologies in Advancing Smart City Applications: Opportunities and Challenges

5G enabled smart cities: A real-world evaluation and analysis of 5G using a pilot smart city application

Ubiquitous sensing in smart cities is expected to be one of the key beneficiaries of the high bandwidth and low latency capabilities of 5G. However, current 5G deployments still have low population coverage, and are unlikely to reach global coverage of above 80% before 2028. This means that new smart city applications are likely to experience a combination of 4G and 5G, limiting their data-intensive capabilities. Thus, it is necessary to assess the ability of current 5G deployments to support emerging smart city applications, and how they perform in 5G environments. Existing performance evaluations focus either on the 5G core or use instantaneous speed tests, which do not effectively assess the suitability of 5G deployments for smart city applications. In this paper, we present a comprehensive evaluation and analysis of real-world 5G network performance observed through the outcomes of a pilot smart city application, an innovative mobile 5G Internet of Things (IoT) solution to automatically identify and report road assets requiring maintenance. The pilot smart city application was deployed on 11 waste collection service trucks over a 6 month period (June 2022–Dec 2022). We undertook both application-specific and application independent network performance evaluation to assess the ability of the 5G deployment to support uninterrupted smart city services. Our analysis shows that while 5G is capable of supporting mobile video streaming applications, there are significant variations in network performance, which may make it unsuitable for applications that require higher data intensive or near real-time responsiveness.

Application and Development of Smart City in Guangdong, Hong Kong and Macao Greater Bay Area

With the acceleration of the global urbanization process, all countries and regions pay more and more attention to the sustainable development of cities. As of October 2021, 132 countries and regions have upgraded the goal of "carbon peak and carbon neutral" to a national strategy, and have proposed a vision of a zero-carbon future. The construction of a smart city has become an important factor in sustainable urban development. The special geographical location of Guangdong Hong Kong and Macao Greater Bay Area (hereinafter referred to as GBA) determines its development flexibility, and this region is bound to become one of the important development strategic regions in China. This paper selects the three core cities of GBA, Hong Kong, Guangzhou, and Shenzhen, as the research objectives, and to integrate, compare, and analyze the achievements of these cities in terms of smart cities. The research results can provide a reference for the construction direction of smart cities in other cities.

Innovative Application of Intelligent Internet of Things in Smart Cities

The Internet of Things, as an important component of the new generation of information technology system, regards the Internet as the main carrier of information, enabling all ordinary physical objects that can be independently addressed to achieve interconnectivity. This is the key to promoting urban modernization and building smart cities. This paper analyzes and studies the application of Internet of Things technology in smart cities. Based on the understanding of relevant concepts, it aims to understand the relationship between IoT technologies and smart city construction, clarify the role of Internet of Things in smart city construction, and the challenges currently faced by IoT technologies in smart city application. Therefore, taking the smart community as the starting point, the application of the smart Internet of Things in the smart community is completed through eight steps: demand analysis, planning and design, sensor and device deployment, data collection, data storage, data analysis, control and scheduling, and user application development. The experiment results show that after establishing a smart community control platform based on smart IoT technologies, the failure rate of the comprehensive information sending end, receiving end, output system, and hardware system is low, the user experience satisfaction is high, and the platform performance is strong.

A Secure and Reliable Framework for Explainable Artificial Intelligence (XAI) in Smart City Applications

A Secure and Reliable Framework for Explainable Artificial Intelligence (XAI) in Smart City Applications

A comprehensive survey on an IoT-based smart public street lighting system application for smart cities

The swift advancement and updating of urban lighting systems, along with the incorporation of smart and Internet of Things (IoT) infrastructure, have opened up numerous opportunities for technological progress across various facets of life. This paper offers a comprehensive overview on the development of smart public street lighting infrastructure tailored for IoT applications in smart cities. Initially, the focus lies on transitioning from conventional lighting to Light-Emitting Diodes (LEDs) technology in street lighting. Complementing this transition, the incorporation of the wireless networked sensors and controllers ensures dynamic brightness control in operational zones, envisioning substantial energy savings. Furthermore, the notion characterizing smart cities denotes incorporating modern digital infrastructures to develop innovative functionalities and connect various application, following the IoT paradigm. The key findings from the proposed study have enhanced knowledge regarding smart public street lighting application. This system integrates smart poles equipped with LEDs lamps technology, smart sensors, communication network and monitoring unit, leveraging current technological advancements in IoT applications. The implementation of IoT-based smart public street lighting systems presents several challenges, including integrating diverse sensors and actuators ensuring robust device communication, secure data management, and effective system scaling and maintenance. Despite these challenges, this system significantly advances smart city infrastructure by enhancing energy efficiency, safety, and sustainability. However, addressing their high initial costs, data privacy and security concerns, and ongoing maintenance are crucial in future studies to realize their full potential in smart cities.

YOLO-GTWDNet: a lightweight YOLOv8 network with GhostNet backbone and transformer neck to detect handheld weapons for smart city applications

YOLO-GTWDNet: a lightweight YOLOv8 network with GhostNet backbone and transformer neck to detect handheld weapons for smart city applications

Digital Twin and federated learning enabled cyberthreat detection system for IoT networks

The widespread deployment of Internet of Things (IoT) devices across various smart city applications presents significant security challenges, increased by the rapidly evolving landscape of cyber threats. Traditional security solutions, including those using Federated Learning with federated averaging, suffer from inefficiencies due to random node selection and partial data sampling, which can hinder the detection of comprehensive network-wide attacks. This paper introduces a novel Cyberthreat Detection System for IoT networks that leverages Digital Twin technology and an optimized Federated Learning approach. Our hypothesis implies integrating Digital Twin models within an IoT security framework to improve real-time cyberthreat detection capabilities. We implement a 'Adaptive Thresholding with Early Stopping method' based methodology in Federated Learning to systematically train and aggregate local models based on predefined training rounds, thereby ensuring that all local models contribute to the global model until a target accuracy is achieved. This method significantly improves the detection of zero-day attacks by reducing dependency on random selections and partial data. The system architecture features Digital Twins of IoT medical infrastructure components—such as radiology, intensive care, and outpatient care—positioned at the network edge to minimize latency and bandwidth usage. Comparative evaluations of our model against traditional federated averaging methods demonstrate superior performance, with enhancements in model aggregation efficiency evidenced by higher F1 scores and reduced CPU usage. Specifically, our distributed digital twin environment at the edge layer shows 14% and 33% latency reductions compared to fog and cloud-based implementations, respectively. This study highlights the potential of Digital Twin and advanced Federated Learning methodologies to secure IoT networks against evolving and growing cyber threats.

Decomposition and reconstruction algorithms for IoT reliability analysis utilizing 5G technology for smart cities

Internet of Things (IoT) and 5G communication technologies in smart cities deliver promising services for heterogeneous applications. The application reliability banks on uninterrupted and seamless services experienced by the users. However, the increasing smart city application demands influence the experience reliability through augmented wait times. This article therefore introduces a Coherent Reliability Service Broadcasting Technique (CRSBT) for sustaining constructive application services. This technique incorporates linear regressive and digressive learning for application service improvements and restrictions. Based on the demand, the regressive process verifies the wait time and with the reducing demands, the service broadcast ratio is verified. These two factors are verified post the demand and response through 5G resource allocations and IoT computations. Both the service-oriented features are validated for regressive service broadcast and either of the one is used for digressive response. The coherence between the computations (IoT) and resources (5G) is verified on-demand and linearly. Therefore, the proposed technique is reliable in sustaining service broadcast, less wait time, and maximum flexibility.

Rotating Kernel CNN Optimization for Efficient IoT Surveillance on Low-Power Devices

This study presents an innovative method to optimize convolutional neural networks (CNNs) tailored for the prevalent low-power platforms in IoT and embedded devices, which are integral to smart city infrastructures. Our approach introduces a novel “Rotating Convolutional Kernel” technique, designed to significantly reduce the computational load of CNNs while maintaining high accuracy, an essential feature for the constrained processing capabilities of devices produced by Hisilicon, MediaTek, and Novatek, among others. By leveraging the intelligent video engine (IVE) capabilities inherent in low-end CPUs, our optimized YOLOv3-Tiny model, with fewer than 100 K parameters and specifically fine-tuned for pedestrian and vehicle detection, demonstrates impressive processing speeds of 52 ms/frame on the HI3516EV200 chip and 66 ms/frame on the MSC313E chip, with minimal accuracy compromise. Despite a substantial reduction in parameter count compared to that in MobileNetV2, our model’s top-1 accuracy only slightly decreases by 2.6%, showcasing the effectiveness of our optimization technique. Our findings highlight the potential and applicability of our method in enhancing the performance and utility of IoT and embedded devices within smart cities. By achieving an optimal balance between computational efficiency and detection accuracy, our approach offers a promising avenue for advancing the capabilities of low-power devices in urban surveillance, traffic management, and other smart city applications, thereby contributing to the development of more intelligent, efficient, and responsive urban environments.

Distributed neuro-fuzzy routing for energy-efficient IoT smart city applications in WSN

Distributed neuro-fuzzy routing for energy-efficient IoT smart city applications in WSN

Additively Manufactured, Flexible 5G Electronics for MIMO, IoT, Digital Twins, and Smart Cities Applications

This review encompasses additive manufacturing techniques for crafting 5G electronics, showcasing how these methods innovate device creation with novel examples. A wearable phased array device on commonplace 3D printed material is described, with integrated microfluidic cooling channels used for thermal regulation of integrated circuit bulk components. Mechanical and electrical tunability are exemplified in an origami-inspired phased array structure. A 3D printed IoT cube structure shows the flexibility in the number of geometries additively manufactured 5G devices can adhere to. Finally, integrating 3D optical lenses with 5G electronics is shown.

Adopting security practices in software development process: Security testing framework for sustainable smart cities

The dependence on smart city applications has expanded in recent years. Consequently, the number of cyberattack attempts to exploit smart application vulnerabilities significantly increases. Therefore, improving smart application security during the software development process is mandatory to ensure sustainable smart cities. But the challenge is how to adopt security practices in the software development process. There are Several established and mature security testing frameworks exist that consider security requirements and testing during Several already established and mature security testing frameworks exist that consider security requirements and testing during Software Development Life Cycle (SDLC), but there is a unique challenges posed by smart city applications and the need for a comprehensive approach to address the evolving threat landscape in this context. This paper proposed a framework that adopts security testing practices in all phases of the software development process. The proposed framework identifies several security activities and steps that can be applied in each phase of the software development process.

Human‐centered Smart Cities: An evaluation of a small community using the Smart Cities Initiative framework

AbstractIn September 2023, the INCOSE Smart Cities Initiative released a framework to evaluate and define smart city systems. The framework includes a human‐centered definition of a smart city and offers metrics of a smart city. The definition, metrics, and framework are based on a systematic process that allows consistent evaluation of city that focuses on providing for fundamental human needs.Many smart city applications still focus on technology, regardless of whether that technology provides a clear benefit to the stakeholders of the city. Systems engineering tools and practices offer potential for improving smart city implementations by improving the alignment of needs and solutions. Unfortunately, in new domains, such as the plethora domains involved with smart cities, systems engineering can be viewed as unnecessary overhead. Therefore, the usefulness of the systems engineering concepts that underlie the INCOSE Smart Cities framework could be overlooked unless it can provide immediate value. As a demonstration of how the new framework could be used by someone interested in engaging INCOSE Smart Cities concepts, a high‐level application of the definitions and framework was performed.The analysis demonstrated that a simple review of the city system, using the perspectives of the INCOSE Smart Cities initiative, could reveal strengths and weaknesses of a smart city and identify potential next steps for improvement. This paper is a case study of how to use qualitative analysis to apply the human‐centered definition and framework to evaluate a Smart City. The case study provides an opportunity to evaluate the strengths and weaknesses of the new INCOSE framework.

UX Analysis on SpeedID Application Using Usability Testing Method and System Usability Scale

The SpeedID application is a smart city application developed by a subsidiary of PT Bamboomedia Cipta Persada, namely PT Inovasi Solusi Nusantara since 5 years ago. The SpeedID application wants to present a solution to the city's problems to become a new digital identity for the smart city community. Because it was only developed 5 years ago, the SpeedID application is classified as a new application and has never been analyzed for usability before. Usability analysis is carried out to improve user experience, so that the SpeedID application can be accepted and used more easily by users. This research uses Usability Testing method with Performance Measurement and Retrospective Think Aloud (RTA) techniques and System Usability Scale (SUS). The results obtained are the SpeedID application has a quality that cannot be said to be effective, efficient and meet user satisfaction. In addition, the average score of the System Usability Scale (SUS) Questionnaire is 70.33. The score is rated "C" with an adjective rating of "Good" with the acceptance range included in the "Marginal" category, and finally the net promotion score (NPS) is included in the "Passive" category, which explains that the use of the SpeedID application gets an assessment that is still marginalized by its users. This shows that the SpeedID application still urgently needs correction to improve quality to its users and design improvements also need to be made so that the SpeedID application is even better at meeting user expectations in the future.

Addressing Data Distribution Shifts in Online Machine Learning Powered Smart City Applications Using Augmented Test-Time Adaptation

Addressing Data Distribution Shifts in Online Machine Learning Powered Smart City Applications Using Augmented Test-Time Adaptation

Smart City Solution “A Full Stack Solution For Smart Cities”

Abstract —In the landscape of smart cities, Smart City Connect emerges as a pivotal solution, seamlessly integrating essential services like healthcare, dining, lodging, maintenance, fitness, and accommodation. This research paper explores how Smart City Connect optimizes urban living by ensuring convenient access to top-tier hospitals, diverse restaurants, and comfortable accommodation options. The platform fosters efficiency through reliable repair services and promotes well being with state-of-the-art fitness facilities. By prioritizing accessibility, efficiency, and sustainability, Smart City Connect redefines the urban experience, shaping vibrant and inclusive communities for residents and visitors alike. Index Terms – Web-Based Application, Smart City Application.

Deep Smart Cities: A Review of Smart Cities Applications-Based an Inference of Deep Learning Upon IoT Devices

Recent years have witnessed an increase in the use of IoT devices in Smart Cities (SC). With the remarkable success of integrating deep learning (DL) in various fields of SC such as smart environment, smart agriculture, and more. There is an emerging field to deploy DL into IoT devices to meet the requirement of SC applications as real-time applications and lightweight computation. However, the limited resource of IoT devices poses a challenge to fulfilling the DL models that demand large storage and massive computation. The aim of this paper is focused on the integration of DL with IoT in SC and conducts up-to-date state-of-the-art studies on the SC applications. First, a present overview of SC, IoT and DL. Second, we review studies that integrate DL and IoT into four SC applications (smart environment, smart transportation, smart agriculture, and smart home). It covers a series of crucial applications in SC such as Air pollution, water pollution, autonomous driving, activity recognition and detection, indoor localization, and more. Third, present the main challenges once integrate DL on IoT devices in SC. Lastly, we introduced open issues for the future direction obtained when integrate DL models with IoT devices in SC applications to inspire further research in this area.

Indonesia's Digital Push to Combat Literacy Crisis

This study investigates the government's role in improving literacy rates in Sidoarjo, Indonesia, where reading interest is the lowest in ASEAN. Using a descriptive qualitative method, interviews with library officials revealed that innovative programs and digital media are key to enhancing public engagement. The research highlights the Sidoarjo government's implementation of smart city applications and digital resources to support education and public services. Results indicate that practical information and effective use of digital tools are essential for increasing literacy. This study underscores the importance of government initiatives in addressing literacy challenges and improving educational outcomes. Highlights: Government Initiatives: Smart city applications and digital tools boost literacy in Sidoarjo. Low Literacy Rates: Indonesia's lowest reading interest in ASEAN needs urgent intervention. Innovative Programs: Digital media and practical information enhance public engagement and literacy. Keywords: Literacy, Government Role, Digital Media, Education, Sidoarjo