Search

The communication technology revolution in this era has increased the use of smartphones in the world of transportation. The public transit system wishes to predict the expected ridership at a specific time. The bus system's dream of dynamic routing (i.e., having no more near-empty buses) is close to reality. Our study collected data from the transit bus system in two different countries (USA and Japan). This paper studies the correlation between ridership and weather conditions using a deep learning algorithm. Empirically, an experiment with several bus routes in Japan, was utilized to confirm a high precision level. We compared our deep learning model against three baseline models: linear regression, regression trees, and a wide neural network in two sub-experiments. First, the deep learning model had 23%, 21%, and 14% better mean squared error (MSE) scores compared to linear regression, regression trees, and wide neural networks when trained on three months of historical data. Second, we ran the models on a larger dataset of two years. The result was that the gap between the baseline models and the deep learning model was almost doubled to 56%, 50%, and 35% better MSE scores for predictions in favor of the deep learning model compared to linear regression, regression trees, and wide neural networks, respectively., 2022 IEEE International Conference on Smart Mobility (SM),6-7 March 2022,New Alamein, Egypt

The communication technology revolution in this era has increased the use of smartphones in the world of transportation. In this paper, we propose to leverage IoT device data, capturing passengers' smartphones' Wi-Fi data in conjunction with weather conditions to predict the expected number of passengers waiting at a bus stop at a specific time using deep learning models. Our study collected data from the transit bus system at James Madison University (JMU) in Virginia, USA. This paper studies the correlation between the number of passengers waiting at bus stops and weather conditions. Empirically, an experiment with several bus stops in JMU, was utilized to confirm a high precision level. We compared our Deep Neural Network (DNN) model against two baseline models: Linear Regression (LR) and a Wide Neural Network (WNN). The gap between the baseline models and DNN was 35% and 14% better Mean Squared Error (MSE) scores for predictions in favor of the DNN compared to LR and WNN, respectively., 6 pages, 10figures, PerIoT 2021

Vehicular Clouds are inherited from the cloud computing concept. Vehicles standing in a parking lot can corporate computing, sensing, communication, and physical resources. Vehicular Clouds were motivated by the realization that present- day vehicles are equipped with powerful onboard computers, powerful transceivers, and an impressive array of sensing devices. As it turns out, most of the time, the computing, storage, and communication resources available in our vehicles are chronically under-utilized. We are putting these resources to work in a meaningful way to provide computation power, which plays an essential role for service providers, transportation systems, health care, and online education in our modern society. Vehicular Clouds provide computation power to users based on a resource- sharing model. In this model, vehicle owners rent out their onboard computation powers to receive incentives in the form of payments or free parking spots. To use this computation power, there should be a way to submit jobs to the system. In this work, we develop a framework for the vehicular cloud to manage the onboard computation resource of the vehicles and computation tasks that users submit. This framework will be available to users in a software system called Vehicular Cloud Real-Time System (VCRTS). Random arrival and departure of vehicles in vehicular clouds can impact the computation nodes’ availability and lead to an interruption in the computation process. We design and implement the VCRTS based on a fault-tolerant approach to prevent interruption in job execution. Our approach uses a redundancy mechanism to handle the random nature of arrival and departure of the vehicles that are used as computation nodes.

Contact tracing has become a vital practice in reducing the spread of COVID-19 among staff in all industries, especially those in high-risk occupations such as healthcare workers. Our research team has investigated how wearable IoT devices can alleviate this problem by utilizing 802.11 wireless beacon frames broadcasted from pre-existing access points in a building to achieve room-level localization. Notable improvements to this low-cost localization technique’s accuracy are achieved via machine learning by implementing the random forest algorithm. Using random forest, historical data can train the model and make more informed decisions while tracking other nodes in the future. In this project, employees’ and patients’ locations while in a building (e.g., a healthcare facility) can be time-stamped and stored in a database. With this data available, contact tracing can be automated and accurately conducted, allowing those who have been in contact with a confirmed positive COVID-19 case to be notified and quarantined immediately. This paper presents the application of the random forest algorithm on broadcast frame data collected in February of 2020 at Sentara RMH in Harrisonburg, Virginia, USA. Our research demonstrates the combination of affordability and accuracy possible in an IoT beacon frame-based localization system that allows for historical recall of room-level localization data.

With the fast increase of wireless technology, more new applications are developed targeting smart cities. It is clear that soon-to-be, each city will be covered with wireless capabilities besides the 5G cellular technology. In a modern city, the bus riders find themselves waiting for a significant amount of time for a bus while checking their smartphones. It is essential to use the numerous amount of data that can be gathered from these devices and surrounding to serve a better quality for the transportation system while preserving the ridership privacy. As to improve the quality of monitoring the transit buses system, we develop a framework using the Internet of Things (IoT) devices. In this paper, a framework is formed, and two case studies are investigated with various implementations. The goal is to use this framework to collect any data that can be used in smart cities to improve planning and increasing bus ridership through better scheduling. A complete comparison between the two case studies is provided with the performance measurement of each technique, and a hybrid methodology is suggested., 2020 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 23-27 March 2020,Austin, TX, USA, USA

Rapid improvements in technology are making autonomous vehicles feasible. Researchers and industry are looking for different methods to implement the concept of smart cities. Autonomous Vehicles provide a unifying framework for several research topics (e.g., navigation, localization and Global Positioning System (GPS) positioning, security, and privacy). Despite significant progress, we believe that fully autonomous vehicles will be deployed initially in constrained environments (e.g., closed-loop areas, gated retirement communities).In this paper, we describe the development of a prototype autonomous golf-cart that can be used as a test-bed for a range of research projects. We explain the details of the conversion from a traditional golf-cart to an autonomously driven one. Our target application is a system of autonomously driven golf-carts for use within a retirement community. We show our testing results, and how Internet of Things (IoT) devices can be used to extend the WiFi coverage for log reporting and to request the golf-cart. Finally, we discuss the challenges and highlight improvements that can be performed on the system.

The Internet of Things (IoT) is connecting the world in a way humanity has never seen before. With applications in healthcare, agricultural, transportation, and more, IoT devices help in bridging the gap between the physical and the virtual worlds. These devices usually carry sensitive data which requires security and protection in transit and rest. However, the limited power and energy consumption make it harder and more challenging to implementing security protocols, especially Public-Key Cryptosystems (PKC). In this paper, we present a hardware/software co-design for Elliptic-Curve Cryptography (ECC) PKC suitable for lightweight devices. We present the implementation results for our design on an edge node to be used for indoor localization in a healthcare facilities.

Indoor localization has been gradually improving over the past decade, utilizing emerging and proliferating wireless technologies. Since its inception, WiFi technology has been increasingly penetrating indoor environments, residential, and nonresidential. Becoming ubiquitous, WiFi was considered a fertile subject for use in indoor localization utilizing the wireless access points that predominantly provide network coverage in indoor environments. As the Internet of Things (IoT) technology is speeding towards pervasiveness, IoT devices can offer substantial aid to improve accuracy, which is at the heart of the indoor localization process. In this paper, we provide a preliminary study of the feasibility of using WiFi-enabled devices, including IoT devices, to improve location signature in indoor localization besides the traditionally used wireless access points. Through field experiments, we provide insights into the coverage and penetration of such devices in different domains characterized by the activities exercised in them. Our conclusions highlight the challenges of incorporating such devices into the fingerprint-based indoor localization. Additionally, we focus on the use of machine learning approaches that recently gained momentum in indoor localization research.

There is a dramatic increase in the deployment of Internet of Things (IoT) devices in the last couple of years. In Intelligent Transportation Systems (ITS), we introduced a cyber-physical system that monitors the quality of service (QoS) for transit buses around a mid-size university city using Internet of Things (IoT). The sensing IoT devices detected the number of riders waiting for the bus system at each bus station. The experiments ran for six weeks continuously to monitor seven different bus stations around the university. The collected data reports the number of people waiting for the bus at each station, the wait time for a particular bus station at different time/day(s). In this paper, we analyze the collected data for the various bus stations and the origin/destination of some riders who used one of the seven stations as origin and destination stations. Also, several security measurements have been added to address privacy concerns that might occur with the collection, transmission, and storage of data in the Cloud (e.g., the privacy of the ridership Media Access Control (MAC) addresses and tracking of a particular bus rider in the system). We implement security measurements to emphasize the privacy protection of bus riders.

With the ever-increasing capacity of the Internet and demand for human lives, Internet of Things (IoT) applications is increasing like never before, primarily to facilitate smart homes and smart cities. However, consumers have become increasingly cognizant of the negative effects of energy consumption as well as the importance of footprint reduction. Despite the increased interest in energy reduction and consumption, the average consumer still feels intimidated and unsure of how to start. In this paper, we propose an energy monitoring system (Watts On) to be used per room within a house that is efficient, intuitive, and economic (cost effective). The significant contribution of this paper is the design and development details of WattsOn prototype application. WattsOn is a low-cost IoT and cloud-based system that allows end-users to monitor, store and display energy usage data in an intuitive graphical user interface. As part of this system, we have also developed companion mobile applications in both platforms (Android and iOS), which allows the users to look at the real-time energy usage for the entire house or building to best pinpoint where excess energy is being used to understand better how to reduce consumption. The widespread use of our system will provide several benefits like saving on electricity bills by monitoring the usage and conserving the precious natural resources by reducing electrical energy consumption.

The growing affordability and power of the Internet of Things (IoT) technology are enabling researchers to find solutions to problems in all aspects of life. One of these applications is health-care facilities where medical doctors and other medical staff members are in an environment that often needs to locate at moments a patient or other health specialists. In this paper, we propose a solution for the Localization of health Center Assets Through an IoT Environment (LoCATE) system, which allows tracking patients and medical staff in near real time. LoCATE makes use of the current 802.11 wireless networks within a health-care facility and edge node technology as its tracking technique. The edge nodes continuously communicate with the infrastructure's wireless network Access Points (APs)in a nonintrusive manner. The data, collected from the APs by the edge nodes, is processed by a calculation algorithm based on the signal strength to locate the person in possession of the edge node within a reasonable range of variability. We also address privacy and security concerns regarding the system and the proposed solution. Our solution shows accuracy and reliability in locating the nodes as well as cost efficiency and ease of protability.

Nowadays, the technical feasibility of autonomous driving is out of the question. This technology opens the door for several research topics (e.g., information exchange, security of information) in the IoT domain. One such application is platooning: coordinated driving of vehicles in convoys. Therefore, such platoons set up Internet-of-Vehicles. Although platooning has been mainly researched on highways, the idea of platooning in smart cities can have several benefits, such as efficient use of roads, time-saving through route optimization, and minimizing traffic in peak times. In this position paper, we present our vision of a traffic management approach for combining platooning on highways and urban areas. We explain the idea of platooning, how to manage it efficiently, and the differences between platooning on the freeway and in smart cities.

Public transportation around midsize educational cities has become increasingly vital as residential and commuter populations continue to grow every year. Our research team proposes a cyber-physical system that monitors the quality of service of the transit bus system around James Madison University (JMU), located in Harrisonburg, Virginia, USA. By utilizing the power of Internet of Things (IoT) devices, such as Raspberry Pi computing devices, it is possible to create a network of smart nodes that collect data on the bus routing efficiency and ridership. Using the collected data and using big data analysis, improvements can be made to bus route efficiency and traffic congestion in Harrisonburg, as well as similar college towns. This paper presents data analysis for the first deployment of the IoT nodes at seven JMU bus shelters, during the Spring 2017. Data stations compile and submit the Media Access Control (MAC) addresses and timestamps of wireless devices surrounding the bus stations. This information is stored in a Cloud Storage database that allows for big data analysis and convenient access. In this paper we present the usage of the data collected, modifications to improve both the transit system as well as the data collection methods for future node deployments. Our results show the average passenger waiting times at a sample of the seven bus stations. Route optimization and dynamic changes for the route are discussed. Also, we discuss several concerns on security and privacy related to the collection, transmission, and storage of data in the Cloud (e.g., privacy of the ridership MAC addresses, tracking of a specific bus rider in the system …etc.). Additional security implementation has been suggested to emphasize security and privacy protection.

The use of technology has become an essential part of improving lifestyle, work efficiency, and a catalyst for economic growth. The benefit of the Internet of Things (IoT) and connected nodes has been on a steep incline in recent years. This paper aims to research, build, test and implement a low-cost energy monitoring and control system using IoT devices. Electrical appliances (e.g., air conditioning units and overhead lighting) can be controlled and monitored using IoT technology from any place in the world. In order to accomplish this goal, a complete front-end to back-end system that includes a smart device application (iOS platform), a cloud-based database, an Application Programming Interface (API), and a hardware development is proposed. A small programmable specialized computing device (e.g., Raspberry Pi) for preliminary testing. This smart node was chosen due to familiarity, and its capabilities, such as general purpose pins and built-in Wi-Fi chip. The end goal is to observe energy efficiency by monitoring and controlling air conditioning appliances and standard overhead lighting units. These smart IoT devices allow for the usage energy data from each unit to be collected and stored in a Cloud-based database that can be analyzed and reported for energy conservation and analysis.

In today's world, the rapid advancement of technology allows us to find new solutions to old problems in critical areas, namely patient and staff tracking in healthcare facilities. The medical staff within these facilities are in an environment where they depend on immediately knowing the location of a patient or other medical staff. McAllister et al. [1] proposed a solution named LoCATE (Localization of Health Center Assets Through an IoT Environment) which uses existing technology to track all patients and medical staff in near real time. LoCATE makes use of the current wireless networks (e.g., WiFi) within a healthcare facility by using edge node technology as its tracking solution. It can locate an object within three to five feet of its calculated position. The ubiquity of WiFi infrastructure in healthcare facilities makes it an attractive option to use, as the backbone for a patient and staff tracking system. However, Internet of Things (IoT) devices and edge nodes create security holes in networks and leak data to the open world. This paper aims to analyze what security holes and data leaks LoCATE creates in a healthcare facility. In this paper, we show the dangers of using simple and default passwords, the need to physically secure edge nodes, and the importance of securing data before transmission. We exploit the system's weak security measures by forging edge node data, gaining unauthorized access, performing denial of service attack, and launching other attacks. We analyze the successfulness of these attacks to offer mitigation techniques for future devices located in other critical areas similar to the healthcare facilities.

Dimensionality reduction is a significant task in machine learning. It simplifies classification, compression, and visualization of high-dimensional data by identifying and extracting the manifold from the high-dimensional space. In this paper, a comparison between several approaches of dimensionality reduction methods are introduced, namely: principal component analysis (PCA), kernel PCA (KPCA), multidimensional scaling (MDS), Isomap, Fast maximum variance unfolding (FastMVU), and Diffusion Maps (DM). Then, the features extracted from137Cs radiation signal using the above techniques are investigated by feeding them to artificial neural network (ANN). A comparison between the studied techniques is performed according to the pattern recognition rate and execution time using a MATLAB program. In order to test the performance of these algorithms, the pileup signal is embedded in a different types of noises. Results showed that the KPCA approach has the highest recognition rate of the pileup signal.

Modern wireless technology opens the door for several new Intelligent Transportation applications. In an academic environment, students use transit bus system on a daily base. El-Tawab et al. [1] introduced a cyber-physical system to monitor the quality of service for transit buses around an academic campus. This cyber-physical system detects the number of riders waiting for the bus system at each bus station and number of riders on each bus. In this paper, we examine the security and vulnerability of the bus data collection system and provide remedies. Smart units are used to collect data (e.g., Media Access Control (MAC) Addresses) to uniquely identify students' smart phone waiting times for the bus at each station. The goals of this system are to identify the average waiting times at each bus station, route optimization and dynamic routing. Several security concerns occur with the collection, transmission, and storage of data in the Cloud (e.g., Man in the middle attacks, unauthorized access, denial of services, theft, etc). We analyze some of these cyber-attack vectors and provides mitigation techniques, cyber hygiene best practices, and suggest ways to balance security versus convenience.

The rapid advances in modern wireless technology opens the door for new applications using the Internet of Things (IoT) technology. In the medical field, staff members of a certain hospital are in need for a system that tracks where patients/medical staff/devices are at any given time. LoCATE, which is Localization of Health Center Assets Through an IoT Environment, provides a near-real time tracking tool for medical systems using the existing 802.11 WiFi infrastructure. The primary goal of this system is to track assets and personnel at any hospital (e.g., Sentara® RMH hospital) and continuously log a real-time location data on a cloud computing platform such as Amazon Web Services (AWS). Using LoCATE, administrators can view the location of doctors, patients, and assets in real-time via a web UI or a mobile app, within the organization. The collected data, stored and processes on a Cloud Storage platform, is then analyzed to expose inefficiencies in daily operations and improve the health care system. Low-level functionality of the LoCATE system is unlike that of typical Radio-frequency identification (RFID) technologies. The spirit of the IoT paradigm employed by LoCATE makes the system both flexible and scalable, by leveraging collaboration between embedded and cloud systems. This flexibility will allow for the future support of additional applications such as hardware integration (e.g., New hardware components). This can include data acquisition such as usage statistics and historical patient health data. Compiling this data might pave the way for future research into disease vectors or could be used to optimize care delivered for specific conditions. While implications for an IoT system such as LoCATE are wide-ranging; its primary objective is to provide an easy to use, low-cost solution to track the location of medical assets in real-time.

At high count rate gamma (γ) ray spectroscopy, the pile-up problem appears as important obstacle not only to high detection efficiency but also to efficient energy resolution. In this paper, three different algorithms for digitally determining the basic pulse parameters and solving pulse pile-up in γ-ray spectroscopy are introduced. They are called scale-space peak picking, noise tolerant fast peak finding, and delta method peak determine. These algorithms are tested by original experimental random signal generated from a 137Cs point source. This original signal were processed by the three different algorithms before and after denoising. A denoising method based on discrete wavelet transform (DWT) was used. Simulation results compares between the three different digital pileup algorithms applied on noisy and denoised signal, also a comparison in terms of number of peaks and execution time of algorithms before and after denoising are introduced. It is shown that the noise reduction algorithm improved the performance of the pileup algorithms.

The rapid increase of modern wireless technology opens the door for several new applications using the Internet of Things (IoT) technology. In an educational environment, students depend on the transit bus system for their daily routine and there is a high demand of people to be served by buses around university campuses in the United States of America. Often times, the members of university communities find themselves waiting for a significant amount of time for a bus to arrive at the bus station. Universities have numerous bus stops as well as routes on which riders can use for travel. Several of these bus stops are covered by WiFi capabilities, and usually students are checking their smart phones while waiting for bus arrival. In order to monitor the quality of transit buses and passengers' services, we design, develop, and demonstrate a low cost IoT system that detects the majority of the riders on the bus system at each station. In this paper, the IoT devices collect, analyze and archive transit and passenger data (e.g., waiting times) to Cloud Storage from each bus station. The goal is to improve the passenger's experience by refining the current infrastructure in place, focusing on better planning and increasing bus ridership through better scheduling. By collecting such data (e.g., waiting times), the performance of the bus system can be further analyzed and suggest changes to a route in order to achieve a more efficient and sustainable urban transportation system.