ABSTRACT. A considerable percentage of accidents on the highway occur as a result of traffic congestion induced by driver distraction triggered by the sight of a prior incident. Secondary crashes are defined as crashes that occur as a result of an original crash, either at the crash scene or inside the traffic queue or backup in either direction. Highway agencies are highly interested in establishing safety measures to reduce these types of incidents. Enabling the flow of information among vehicles allows motorists to proactively take precautions and approach traffic queues and accident sites more cautiously. Emerging technologies, including connected and autonomous vehicle technologies, can improve safety during incidents by facilitating communication between vehicles over an ad-hoc wireless vehicular network. Therefore, the objective of this study is to assess the potential impact of vehicular communication technology in mitigating the likelihood of further crashes during an incident on a heavily traffic highway. Research was conducted based on the developed simulation modelling framework. Since crashes cannot be directly estimated from micro-simulation, we proposed a combination of the micro-simulation model VISSIM and the Surrogate Safety Assessment Model (SSAM) to capture vehicular conflicts. This approach allows us to measure vehicular conflicts as an indicator of the likelihood of secondary crashes. The results suggest that using connected vehicles (CVs) can be an effective method to reduce the probability of further accidents.

ABSTRACT. There are numerous challenges in the last mile of urban logistics operations related to efficiency, resource allocation, environmental sustainability, and delivery operations. Technological innovation in recent years is trying to fill these loopholes and bring out efficient, reliable, and sustainable last-mile delivery. This paper provides a summary of the current optimization approaches in last-mile delivery, covering traditional Linear Programming methods, sophisticated algorithmic techniques known as metaheuristic methods, Artificial Intelligence (AI) based approaches, experience-based methodologies, and energy conservation techniques. These sets of optimization techniques—derived from optimization theory and computational algorithms—are diverse in their strategies for route planning, resource allocation, and energy management and tailored to the complex nature of urban delivery networks. In this regard, promising future technologies have also been discussed to re-orient last-mile delivery. Autonomous delivery by drones is one such game-changing solution that can enable rapid and eco-friendly delivery capabilities. Smart delivery acceptance systems through extensive use of advanced sensor technologies and data analytics help simplify parcel reception processes and make them much more efficient and safer. In the context of changing customer preferences and the emergence of e-commerce, the optimization of the last mile is critical in satisfying increasing demand while ensuring environmental sustainability and operational efficiency. Such innovative technologies and optimization strategies will enable delivery providers to better manage urban logistics challenges to deliver better customer experience and achieve sustainable growth in the last mile of delivery.

ABSTRACT. This study delves into the widespread impact of the Internet of Things (IoT) on urban landscapes, with a primary focus on mitigating the prevalent challenges of traffic congestion and parking scarcity. Introducing innovative Smart Parking Systems (SPS), we harness the power of IoT, notably leveraging Raspberry Pi as a foundational platform. This SPS boasts a suite of advanced features including real-time parking spot detection and erroneous parking identification, complemented by a user-friendly mobile application offering intuitive guidance. The advanced camera infrastructure at entry points, which uses cutting-edge image processing techniques to enable the smooth recognition of permitted cars, is the central component of this system. The empirical results demonstrate how effective the SPS prototype is at easing parking-related problems; quick spot detection greatly reduces driver search times while also easing traffic congestion. Moreover, adding a mobile application improves user experience and increases SPS operational effectiveness. Considering the transformative potential of IoT, the research plays a pivotal role in alleviating congestion and parking challenges in urban environments. Furthermore, this SPS seamlessly integrates with existing payment infrastructure, enabling drivers to conveniently settle parking fees via debit/credit cards or by using the dedicated mobile application. A unique feature of this SPS is its enhanced functionality which guarantees adherence to designated parking spaces. Rigorous checks verify the proper vehicle positioning within allocated spaces, minimizing instances of haphazard parking, and optimizing space utilization within the SPS ecosystem.

ABSTRACT. Rapid urbanization has led to significant negative impact on transportation system behavior and quality of life. Thus, sustainability of transportation system is needed, and this could be achieved with the help of traffic simulation software. Traffic simulation software are used for modelling and simulation of different scenarios to evaluate their feasibility and implement the best solution. This paper aims to help readers with choosing the best software for the situation being modelled and simulated. The paper compared between ten software that are widely used. The comparison was based on traffic flow models (microscopic, mesoscopic, macroscopic, and hybrid), availability of software and price (open-source or commercial), operation system (Microsoft Windows, Linux, and/or MacOS), output visualization (2D, 3D, or both), objective, and most importantly, incorporation of intelligent transportation system (ITS), and autonomous and connected vehicles. The software selected are reliable and trusted in the field, hence, no software is better than the other in general. However, when it comes to incorporation of ITS, and connected and autonomous vehicles, the level of incorporation varies between the software, and some have no incorporation. Vissim, Aimsun, and TransModeler have the best incorporation of ITS, and connected and autonomous vehicles.

ABSTRACT. This paper explores the development of Natural Language Processing (NLP) systems designed to fact-check speech and text through a distributed architecture. The integration of various Question-Answering (QA) systems to improve question diversity, coverage, and adapt modular frameworks to dynamic data sources is being investigated. The efficacy of these systems enhancing vast data pools critically enhances the fact-checking process. This study proposes a new approach combining existing QA systems with innovative NLP methodologies to advance the fact-checking capabilities in mitigating misinformation.

ABSTRACT. Safeguarding lives and properties in public places is one of the key components of the smart city. Therefore, the Intelligent Video Surveillance System (IVSS) can use video anomaly detectors to detect various anomalous activities using live streaming of video.Anomaly/Abnormal Activities refer to those acts that occur at unusual locations/periods. Activities such as fighting, vandalism, riots, theft, wrong U-turns, and road accidents are examples of abnormal activities. Various deep-learning algorithms are used to detect anomalies in videos. To evaluate the quality of the generated results of these algorithms, appropriate datasets, evaluation metrics, and hyperparameter optimization are needed preferably combined in one research work. This work focuses on the overview of the state-of-the-art (SOTA) Datasets and evaluation metrics used in assessing the performance of video anomaly detection methods, as well as hyperparameter tuning which provides the best result on the dataset in a realistic time frame (time-to-accuracy). Finally, issues and prospects were given on the topic. A fully implemented IVSS will go a long way in providing safety in public places and transport systems through prompt notification of anomalies to prevent loss of lives and properties.

ABSTRACT. Laws and regulations can be modified by experts in the legal field in response to various changes in the lives of individuals and communities. Massive changes and updates are constantly being made to laws to adapt to societal changes. This creates a huge database of legal information. Manually searching for information in this database takes a lot of time and effort and affects the efficiency and governance of all administrative and community affairs. To solve this problem, this paper proposes a solution based on one of the types of artificial intelligence. It is an ontology-based solution. This paper explains the design and development of an intelligent Arabic legal assistant system that helps in making legal decisions based on a proposed ontological structure using Protégé. A set of tools were also chosen to develop the proposed system. For operation, OwlReady2 with SPARQL query language was also used to extract content from the proposed ontology, Camel tools as a natural language processing (Arabic) tool, and SQLite for the database. This work contributes to filling a gap regarding the Arab cognitive modeling of Arab laws to keep pace in sustainable cognitive cities.

ABSTRACT. This study explores the application of Artificial Neural Networks (ANNs) for predicting the aerodynamic coefficients of airfoils, with a focus on the drag coefficient (C_D), as the literature has not predicted it as precisely as other aerodynamic coefficients. A novel quadratic fitting function is introduced to improve the accuracy of C_D predictions. Two datasets, DI and DII, with varying ranges of Mach numbers, were prepared, and the performance of the ANNs was evaluated. Model I was trained on Dataset I (Mach 0.1 to 0.3), while Model II was trained on Dataset II (Mach 0.1 to 0.8). The results indicate that a larger and more diverse dataset significantly enhances the predictive capabilities of the model. Additionally, the model's ability to generalize to airfoils and flight conditions outside the training data was tested, revealing the generalization power of the model.

ABSTRACT. In today's rapidly changing business landscape, supply chain resilience is paramount, especially in light of unprecedented disruptions like the COVID-19 pandemic. This paper explores the dynamic perspectives of emerging technologies—blockchain, the Internet of Things (IoT), and Artificial Intelligence (AI)—in bolstering supply chain resilience. Leveraging Causal Loop Diagram (CLD) approach, pivotal feedback loops, both virtuous and vicious, are uncovered, highlighting the transformative potential of these technologies. Blockchain offers opportunities for fostering trust, collaboration, and transparency among supply chain stakeholders, while IoT enables real-time monitoring, enhanced visibility, and proactive decision-making. Additionally, AI-powered analytics empower organizations with predictive and prescriptive insights for optimized operations and risk mitigation. Nonetheless, challenges such as governance concerns, operational dependencies, and ethical considerations must be addressed to fully harness the benefits of these technologies. Through a comprehensive analysis, this paper provides insights into how organizations can leverage emerging technologies to construct resilient and adaptive supply chains. As we navigate an increasingly complex and volatile business landscape, the integration of blockchain, IoT, and AI-powered analytics holds the key to building resilient and sustainable supply chains for the future.

ABSTRACT. Detecting when a person falls poses a substantial challenge to researchers because of the risk of serious injuries like femoral neck fractures, brain hemorrhages, or burns, which can lead to significant discomfort and, in some cases, worsen over time, resulting in complications or even fatalities. The effectiveness of fall detection is linked to promptly alerting caregivers, such as nurses, upon detecting a fall. In our study, we present a technique for identifying falls within a 40-square-meter apartment using data collected from three ultra-wideband radars. Our approach integrates pre-trained computer vision models (ResNet, VGG, and AlexNet) for fall detection, which is a binary classification task aimed at distinguishing between fall and non-fall events. To refine the model’s performance, we utilize data representing various fall scenarios simulated by 10 participants across three locations within the apartment. We evaluate the performance of the presented technique by using the leave-one-subject-out strategy. The results consistently demonstrate the superior performance of the ResNet model compared to the VGG and AlexNet models. Notably, our findings indicate an approximate 95% F1 score in fall detection, suggesting promising prospects for real-world deployment.

ABSTRACT. Recent advances in supply chain and logistics illustrate that consolidation of orders can considerably reduce transportation costs and CO2 emissions. In this paper, we study the impact of consolidation on order fulfillment in e-Commerce. We consider a retailer with an online platform and network of physical stores, who must decide the optimal locations from which to fulfill a set of multi-item orders, as well as the optimal consolidation points for each order. To model the economy of scale obtained by consolidating orders, we consider piecewise-linear concave transportation costs. Our model extends the existing literature by considering multiple orders at a time and stores with limited inventory. We formulate the problem as an MILP and propose a Variable Neighborhood Search (VNS) to find good quality solutions in a short time. We tested the performance of the proposed algorithm on different scenarios, where stores have a varying percentage of overlapping items. Via numerical experiment, we observed a 0.22\% average relative increase in cost using VNS for instances with large overlap in items among stores and a 2.36\% average relative increase for the other scenarios. On average, the VNS is 16 times faster than the MILP formulation

ABSTRACT. Crowdsourced delivery platforms face challenges in matching couriers to customer orders due to fluctuating demand and uncertain courier availability. The platform’s courier workforce has two types: committed couriers who commit to working for a specific time, and occasional couriers who log in to the platform at a time of their choice. Traditionally, these platforms establish “offline” schedules in advance for committed couriers based on forecasts of anticipated deliveries within defined time windows. However, since actual order numbers are unpredictable in real-time, efficient operations require reactive scheduling to optimally match resources with changing demand trends. A recent paper, Saleh et al (2024), proposed a strategy of extending the shifts of committed couriers as needed in response to the change of demand trends throughout the day. The problem was formulated as a Markov Decision Process (MDP) and utilized a popular value-based algorithm, Deep Q-Network (DQN), to maximize the platform’s expected reward. In this work, we extend the work of Saleh et al (2024) by investigating two other alternative approaches belonging to the class of policy gradient-based algorithms, namely, Proximal Policy Optimization (PPO) and Advantage Actor Critic (A2C). PPO and A2C optimize policy parameters to maximize the expected rewards. Through a comparative analysis, we evaluate the effectiveness of PPO and A2C versus DQN in addressing the scheduling challenges faced by crowdsourced delivery platforms. The results show that PPO achieved the best results in terms of total rewards, lost requests, and shift extension costs by effectively learning an optimized policy through its use of the clipping objective function. While A2C had a higher expected reward than DQN, it struggled with directly optimizing its policy and prioritizing timely deliveries. Finally, DQN is found to excessively rely on shift extensions.

ABSTRACT. Smart city is a concept used to describe a safe and efficient urban environment that uses technologies to enhance its economic growth and residence standards of livings. Smart mobility is an important aspect of smart city concept, and intelligent transportation systems (ITS) is a key component of smart mobility solutions. The ITS technology is one of the oldest smart city technologies and has been implemented in many cities around the world. ITS technology is influenced by the increasing prevalence of autonomous vehicles, and their integration in ITS is a significant step toward a fully automated transportation network. In the meantime, autonomous vehicles have to co-exist with non-autonomous vehicles. Thus, their integration into the system requires careful and gradual planning at vehicular and infrastructure level. The impact of autonomous vehicles on both congestion and safety can be positive and negative at the same time, and depends on autonomous vehicles penetration levels along with implemented traffic management strategies. This paper is a literature review that gives summary about smart cities, smart mobility, ITS, AVs and their integration in ITS. It provides some insights on the effect of autonomous vehicles on traffic congestion and safety.

ABSTRACT. Bicycling is a mode of transport that is both environmentally friendly and provides numerous health benefits. The bicycle infrastructure should be comfortable and safe to attract more people to use bicycles. A poorly maintained bicycle route pavement creates vibration, which is not undesirable for bicyclists because it creates discomfort during the trip. Over the years, bicycle vibration has been used to assess cyclists’ comfort. This research presents a detailed overview of the methods that have utilized bicycle vibration to assess the comfort of bicyclists. Data extraction includes, identification of the authors, year of publication, location, study design, assessment tool, and data source. Fourteen studies satisfied the inclusion criteria and are considered for analysis. The studies were conducted in various geographical locations, most in Europe. Both objective and mixed methods are used. Objective studies only depend on the sensor data, while mixed approaches also include cyclists’ perceptions. The studies used multiple methods to assess the collected data, including Dynamic comfort index (DCI), bicycle comfort mapping, behavioral risk indicator, RMS (Root Mean Square), IRI (International Roughness Index), vibration and visual inspection, BEQI (Bicycle Environmental Quality Index), Cycling Comfort Index (CCI), Dynamic cycling comfort (DCC), Surface condition rating-scale and rolling resistance. Studies are increasingly opting to use mobile applications to take advantage of smartphone sensors. Smart bicycle lights are also used as low-cost alternatives to the expensive instrumented probe bicycle.

ABSTRACT. Automation of berthing manoeuvers in ships is a critical topic since the berthing manoeuver is unique of demanding activities that sailors must do. Following a predefined trajectory or path often solves berthing control issues. Between 2015 and 2020, 46 ships were monitored in the Punta Langosteira Outer Port (A Coruña, Spain) using a ship movement dataset. This research uses this data to train an improved neural network, which forecasts a moored vessel's six degrees of freedom using ship characteristics as well as ocean-meteorological data. Six degrees make up the surge, sway, pitch, yaw heave along with roll movements. The RMSE, or root mean square error, is determined for every one of these degrees. Utilising these models in conjunction with data on weather and sea state predictions, ship attributes, as well as berthing location allows for the prediction of ship movements many times in development. These findings are sufficient to trust the models' predictions when compared to the restrictive sign measures for safe ship unloading operations. This will help us pinpoint the optimal operating location and stop operations at the right times, reducing the cargo ships economic impact that are powerless to operate.

ABSTRACT. The parameters exhibit strong uncertainties in combustion engine speed control; in particular, mass equivalent coefficient ηf and efficiency cf are not easily calibrated and depend on the operation point and the thermal environment. Additionally, heat release Q from a unit air mass of gas is greatly influenced by these external conditions even if the air-fuel ratio is controlled to be constant and the ignition time is also well regulated. Strong uncertainty of parameters is the motivation of this research to develop an adaptive-based self-tuning control design scheme. In contrast to the model’s structure, the considerable variability in parameters serves as the driving force behind this research endeavor, leading to the development of a control design scheme based on adaptive optimization of self-tuning controller gains. Based on feedback from the combustion engine, an optimal solution can be attained through the optimization mechanism and self-learning abilities of Adaptive Particle Swarm Optimization (APSO). To enhance the efficiency of obtaining superior optimization solutions, we introduce the aggregation degree and evolution speed into APSO. These elements dynamically modify the inertia weight during the practical optimization process.

ABSTRACT. The aerodynamic design is a crucial factor in the performance. The aerodynamic design plays a crucial role in vehicle performance and energy consumption. This study undertakes significant modifications to enhance the performance of the UiTM Hawkeye forward-swept fixed-wing Unmanned Aerial Vehicle (UAV), particularly focusing on achieving higher lift/drag ratios. These modifications include implementing a backward-swept (normal) fixed-wing design. A simulation model using the Vortex Lattice Method (VLM) by OPENVSP is conducted to determine forces and aerodynamic characteristics at 0 to 30-degree angles of attack. The accuracy of the model is verified by comparing it with VLM simulations and validated against published ANSYS Fluent findings and experimental data from wind tunnels. The findings indicate that the UAV's aerodynamic performance is enhanced by approximately 20% with the backward (normal) fixed-wing design compared to the previous model, which utilized a forward-swept fixed-wing on the Hawkeye UAV.

ABSTRACT. This paper aims to understand the readiness of automated vehicles (AVs) technology in New Zealand (NZ). Through the lens of the mobilities paradigm, and by analysing interview data from industry participants, our findings are broadly categorised into three themes: (1) hard infrastructure, (2) soft infrastructure, and (3) future infrastructure development. Hard infrastructure highlights the complexity of urban environments for AVs safe operation. Soft infrastructure focuses on connectivity which may help enhance AVs communication but coverage inconsistencies in NZ may disrupt AVs performance. The findings also show how disruptive events of cybersecurity may influence AVs uptake. Future infrastructure development may help ease introducing AVs in NZ especially through developing collaboration between tech-industry and the government. This paper concludes that achieving driving autonomy is complex. However, there is an opportunity for AVs to be deployed in major cities as shuttles to continuously learn and adapt from operating in complex real-life urban environments. Overall, this paper contributes to the mobilities paradigm by extending our understanding of the unintended technological consequences of AVs uptake, and provides a context-specific insights for policymakers, urban planners, and the industry to better understand the barriers and opportunities towards AVs implementation in future cities.

ABSTRACT. Jakarta has been serving as the capital city of the world's 4th most populated country, Indonesia, for 75 years. Recently, about 3 million people from the city's outskirts commute daily into the city, which already hosts 11 million people. The city has been suffering from chronic traffic congestion. Various policy interventions and infrastructural development were introduced to ease the problem. Since 2014, approaches have been made by the Jakarta city government to transform the city into a smart city. We reviewed the literature to examine whether changes had happened due to the interventions and approaches, and we surveyed 1000 Jakarta commuters to understand their satisfaction with the transport infrastructures. Descriptive statistics and multiple correspondence analysis (MCA) were employed to identify the most satisfied or dissatisfied with the current public transport facilities. Our analysis results show good satisfaction with public transport operating on railways and exclusive lanes. However, there is a lower satisfaction level for public transport operating on regular lanes, possibly due to traffic congestion. Public transport on regular lanes includes taxis, OnDemand cars, motorbike-hailing services, and cost-free feeder buses. Males and those with high income and high occupation categories (professionals, executives, and managers) are particularly concerned about the quality of public transport operating on regular lanes. More efforts should be made to solve the congestion on regular lanes, especially on the routes where feeder vehicles for mass transport operate, so that "seamless transit," which is the goal of smart mobility in the smart Jakarta city, can be achieved.

ABSTRACT. This article explores the critical role of cybersecurity in the design and operation of smart buildings. As the adoption of advanced technologies and interconnected systems in buildings grows, so do the potential cybersecurity risks. The article discusses the importance of integrating cybersecurity norms into building regulations and standards, and highlights the need for a comprehensive approach to mitigate risks. It examines technical examples of potential vulnerabilities in access control systems, building automation, and AI-driven optimization. The article also presents emerging technologies and solutions, such as blockchain, IoT security frameworks, digital twins, and AI-driven threat detection. It emphasizes the significance of interoperability, secure integration, and the adoption of security by design principles and comprehensive cybersecurity policies.

ABSTRACT. Global supply chains have become dynamic and complex over the past years, and this is expected to increase in the future. Logistics planning is a key part of supply chain management; hence it is crucial to shift towards agile and automated logistics models with the utilization of advanced information and communication technologies. The scope of this paper is the use of multi-agent systems for selection of Logistics service providers in cargo shipping. Cargos are modeled within auction-based mechanisms to automate the supplier selection and negotiation procedure between a client and multiple logistics service providers to find the best offer. FIPA English Auction Interaction Protocol is investigated to manage different actions between the agents, and a new model is proposed by applying communication acts of (Cancel, Refuse, and Failure) with different levels of credibility (Low, Moderate, and High). It was found that introducing an individual act into the interaction protocol can increase the number of interactions between agents from 24 to 26 up to 30 in case of introducing all the three acts into the interaction protocol. This means that the entire system will spend more time and energy in analyzing and responding to the additional acts. It is concluded that the higher the credibility, the lower the interactions between agents as the system will spend less time and power in communication, which leads to enhance the performance and the efficiency of the system and the network. Therefore, a trade-off between maintaining the commutation speed and the system performance and reliability is vital.

ABSTRACT. The production of high-performance rigid and lightweight composite materials is a top priority in automotive, defense, and aerospace industries. Therefore, it is crucial to introduce technologies related to Industry 4.0 to innovate the industrial production process. In the recent era, the technology of Digital Twin has exponentially grown and obtained significance as a powerful tool for simulating and modelling complex physical systems. Specifically, the autoclaving process facilitates the curing of composite materials of high-performance aerospace, automotive, and ships to get the desired strength and rigidness of the final product. The composite materials are subjected to high pressure and temperature to get durable, lightweight, and rigid products. Therefore, it is necessary to predict the actual temperature of an autoclave to obtain the desired strength and rigid products. In this work, we designed the digital twin using different machine learning (ML) approaches, namely, random forest, decision tree, gradient boosting, linear, multilayer perceptron, ridge, and balanced-ElasticNet regression. The elastic Net regression combines the penalties of both lasso and ridge regression and addresses the limitations of both. However, we introduced a balanced-ElasticNet by equaling both penalties to get the regularization and to handle the multicollinearity. The digital twin based on balanced-ElasticNet performs better compared to other ML approaches. Furthermore, we evaluated the performance using the historical data of 13 different batches and it obtained mean absolute error, root mean square error, R-2 squared error, and temperature relative error of 1.95, 5.71, 0.90, and 0.05, respectively. We also made a comparative analysis using different machine-learning approaches to check the reliability of digital twins for accurate prediction of the actual temperature of an autoclave. However, the comparative analysis confirms the reliability of the balanced-ElasticNet-based digital twin for accurate prediction of an autoclave’s temperature. Furthermore, the digital twin can assess, monitor, and improve the curing production processes of Dallara, which can lead to the production of the safest and most reliable lightweight and rigid products in the world.

ABSTRACT. Logistic hubs play a pivotal role in the last-mile delivery distance; even a slight increment in distance negatively impacts the business of the e-commerce industry while also increasing its carbon footprint. The growth of this industry, particularly after Covid-19, has further intensified the need for optimized allocation of resources in an urban environment. In this study, we use a hybrid approach to optimize the placement of logistic hubs. The approach sequentially employs different techniques. Initially, delivery points are clustered using K-Means in relation to their spatial locations. The clustering method utilizes road network distances as opposed to Euclidean distances. Non-road network-based approaches have been avoided since they lead to erroneous and misleading results. Finally, hubs are located using the P-Median method. The P-Median method also incorporates the number of deliveries and population as weights. Real-world delivery data from Muller and Phipps (M&P) is used to demonstrate the effectiveness of the approach. Serving deliveries from the optimal hub locations results in the saving of 815 (10%) meters per delivery

ABSTRACT. Serendipity oriented recommender system facilities surpriseful encounters to the users. In field of smart transportation, it's important to investigate how recent development in Chabot based on large language models (LLM) when integrated in smart transportation can help commuter use serendipity of recommendation to their advantage. These studies involve user study of a recommendations experience of large language models and understand the serendipity facilitating aspects of large language model. The study collected feedback from 48 users of LLM basesed chatbot. This study reveals the potential and useful applications of LLM, facilitating serendipity to commuters in context of smart transportation. LLM's aspect of facilitating serendipity and recommending items to users, will not only benefits commuters but to a large audience of smart transportation users.