Information and communication technologies (ICTs) has enabled growth in developed countries urban cities through improvements systems, devices applications. In rural areas, especially developing countries, ICT penetration is not as high, often due to lack of available infrastructure funding. With the increasing availability Internet-of-Things (IoT) devices, low-cost large-scale deployments have become possible even areas. We design, develop implement, Near Cloud, a cloud-less platform that...

Modern smart cities are focusing on transportation solutions to detect and mitigate the effects of various traffic incidents in city. To materialize this, roadside units ambient trans-portation sensors being deployed collect vehicular data that provides real-time monitoring. In this paper, we first propose a data-driven anomaly-based incident detection framework for city-scale system. Specifically, an incremental region growing approximation algorithm optimal Spatio-temporal clustering road...

In this paper, we, Ubi-NUTS Japan, introduce a multi-stage activity inference method that can recognize user's mode of locomotion and transportation using mobile device sensors. We use the Sussex-Huawei Locomotion-Transportation (SHL) dataset to tackle SHL recognition challenge, where goal is 8 modes (still, walk, run, bike, car, bus, train, subway) activities from inertial sensor data smartphone. adopt approach class classification problem divided into multiple sub-problems considering...

Recent advancements in cloud computing have driven rapid development data-intensive smart city applications by providing near real time processing and storage scalability. This has resulted efficient centralized route planning services such as Google Maps, upon which millions of users rely. Route algorithms progressed line with the environments they run. Current state art solutions assume a shared memory model, hence deployment is limited to multiprocessing data centers. By centralizing...

The ability to accurately predict public transit ridership demand benefits passengers and agencies. Agencies will be able reallocate buses handle under or over-utilized bus routes, improving resource utilization, adjust plan their schedules avoid overcrowded maintain a certain level of comfort. However, predicting occupancy is non-trivial task. Various reasons such as heterogeneity, evolving patterns, exogenous events like weather, other stochastic variables, make the task much more...

Cities are embracing data-intensive applications to maximize their constrained transportation networks. Platforms such as Google offer route planning services mitigate the effect of traffic congestion. These use remote servers that require an Internet connection, which exposes data increased risk network failures and latency issues. Edge computing, alternative centralized architectures, offers computational power at edge could be used for similar services. Road side units (RSU), Things (IoT)...

Edge and Fog computing paradigms are used to process big data generated by the increasing number of IoT devices. These have enabled cities become smarter in various aspects via real-time data-driven applications. While these addressed some flaws cloud challenges remain particularly terms privacy security. We create a testbed based on distributed processing platform called Information flow Things (IFoT) middleware. briefly describe decentralized traffic speed query routing service implemented...

In this paper, we propose ProceThings, a new middleware platform to provide smart community services by utilizing computational resources of IoT devices in target area. To realize address three key challenges: (1) dynamic load balance management among numerous devices; (2) distributed task assignment/execution over the taking into account fault-tolerance; and (3) fulfillment service level agreement (SLA) for each service. For (1), ProceThings employs heuristic monitoring mechanism which...

Residents in cities typically use third-party platforms such as Google Maps for route planning services. While providing near real-time processing, these state of the art centralized deployments are limited to multiprocessing environments data centers. This raises privacy concerns, increases risk critical and causes vulnerability network failure. In this paper, we propose decentralized road side units (RSU) (owned by city) perform planning. We divide city into grids, each assigned an RSU...

The realization of edge-based cyber-physical systems (CPS) poses important challenges in terms performance, robustness, security, etc. This paper examines a novel approach to providing user-centric adaptive route planning service over network Road Side Units (RSUs) smart cities. key idea is adaptively select routing task parameters such as privacy-cloaked area sizes and number retained intersections balance processing time, privacy protection level, accuracy for privacy-augmented distributed...

In this paper, we propose FedTour, a federated learning-based method for training tourism object recognition models, which utilizes short-distance direct communication between user devices and maximizes the model performance within limited number of updates. whenever two are range, they first exchange metadata including learning degree (e.g., accuracy) their determine whether it is effective to integrate peer by using regressor trained with various pairs models different accuracy predict...

Public bus transit systems provide critical transportation services for large sections of modern communities. On-time performance and maintaining the reliable quality service is therefore very important. Unfortunately, disruptions caused by overcrowding, vehicular failures, road accidents often lead to degradation. Though agencies keep a limited number vehicles in reserve dispatch them relieve affected routes during disruptions, procedure ad-hoc has rely on human experience intuition...

Public transportation systems often suffer from unexpected fluctuations in demand and disruptions, such as mechanical failures medical emergencies. These disruptions lead to delays overcrowding, which are detrimental the passengers' experience overall performance of transit service. To proactively mitigate events, many agencies station substitute (reserve) vehicles throughout their service areas, they can dispatch augment or replace on routes that overcrowding disruption. However,...

Public transit is a vital mode of transportation in urban areas, and its efficiency crucial for the daily commute millions people. To improve reliability predictability systems, researchers have developed separate single-task learning models to predict occupancy delay buses at stop or route level. However, these provide narrow view each do not account correlation between two. We propose novel approach that leverages broader generalizable patterns governing improved prediction. introduce...

Route Planning Systems (RPS) are a core component of autonomous personal transport systems essential for safe and efficient navigation dynamic urban environments with the support edge-based smart city infrastructure, but they also raise concerns about user route privacy in context both privately owned commercial vehicles. Numerous high-profile data breaches recent years have fortunately motivated research on privacy-preserving RPS, most them rendered impractical by greatly increased...

With the number of IoT devices expected to exceed 50 billion in 2023, edge and fog computing paradigms are beginning attract attention as a way process massive amounts raw data being generated. However, these do not consider processing capabilities existing commodity wild. In order solve this challenge, we developing new middleware platform called IFoT, which processes various sensor while considering Quality Service (QoS) by utilizing computational resources heterogeneous within an area....

Modern smart cities need transportation solutions to quickly detect various traffic emergencies and incidents in the city avoid cascading disruptions. To materialize this, roadside units ambient sensors are being deployed collect speed data that enables monitoring of conditions on each road segment. In this article, we first propose a scalable data-driven anomaly-based incident detection framework for city-scale system. Specifically, an incremental region growing approximation algorithm...

The growth of pervasive computing, such as Internet Things, increase the number devices and amount context information being generated. Existing frameworks Cloud computing simply utilize these IoT end-to-end network gateways. Paradigms Edge Fog while able to minimize latency by bringing nearer data source, fail consider utilization computation resource devices. For connectivity challenged environments rural or disaster areas, cloud edge/fog systems are not accessible limited wireless sensor...

The ability to accurately predict public transit ridership demand benefits passengers and agencies. Agencies will be able reallocate buses handle under or over-utilized bus routes, improving resource utilization, adjust plan their schedules avoid overcrowded maintain a certain level of comfort. However, predicting occupancy is non-trivial task. Various reasons such as heterogeneity, evolving patterns, exogenous events like weather, other stochastic variables, make the task much more...