Performance Measurement System (PeMS) is a freeway performance measurement system for all of California. It processes 2 GB/day 30-s loop detector data in real time to produce useful information. At any managers can have uniform, comprehensive assessment performance. Traffic engineers base their operational decisions on knowledge the current status network. Planners determine whether congestion bottlenecks be alleviated by improving operations or minor capital improvements. Travelers obtain...

Physical Internet (PI, π) has been widely used for transforming and upgrading the logistics supply chain management worldwide. This study extends PI concept into manufacturing shop floors where typical resources are converted smart objects (SMOs) using of Things (IoT) wireless technologies to create a RFID-enabled intelligent floor environment. In such PI-based environment, enormous RFID data could be captured collected. introduces Big Data Analytics by defining different behaviours SMOs....

GPS-equipped taxis can be viewed as pervasive sensors and the large-scale digital traces produced allow us to reveal many hidden "facts" about city dynamics human behaviors. In this paper, we aim discover anomalous driving patterns from taxi's GPS traces, targeting applications like automatically detecting taxi frauds or road network change in modern cites. To achieve objective, firstly group all trajectories crossing same source destination cell-pair represent each trajectory a sequence of...

Sensing cost and data quality are two primary concerns in mobile crowd sensing. In this article, we propose a new sensing paradigm, sparse sensing, which leverages the spatial temporal correlation among sensed different sub-areas to significantly reduce required number of tasks allocated, thus lowering overall (e.g., smartphone energy consumption incentives) while ensuring quality. Sparse crowdsensing applications intelligently select only small portion target area for inferring remaining...

In modern cities, more and vehicles, such as taxis, have been equipped with GPS devices for localization navigation. Gathering analyzing these large-scale real-world digital traces provided us an unprecedented opportunity to understand the city dynamics reveal hidden social economic "realities". One innovative pervasive application is provide correct driving strategies taxi drivers according time location. this paper, we aim discover both efficient inefficient passenger-finding from a...

Despite the great demand on and attempts at package express shipping services, online retailers have not yet had a practical solution to make such services profitable. In this paper, we propose an economical approach delivery, i.e., exploiting relays of taxis with passengers help transport collectively, without degrading quality passenger services. Specifically, two-phase framework called crowddeliver for delivery path planning. first phase, mine historical taxi trajectory data offline...

Abstract Short‐term traffic speed prediction is one of the most critical components an intelligent transportation system (ITS). The accurate and real‐time speeds can support travellers’ route choices guidance/control. In this article, a vector machine model (single‐step model) composed spatial temporal parameters proposed. Furthermore, short‐term developed based on single‐step model. To test accuracy proposed model, its application illustrated using GPS data from taxis in Foshan city, China....

Current neural networks for 3D object recognition are vulnerable to rotation. Existing works mostly rely on massive amounts of rotation-augmented data alleviate the problem, which lacks solid guarantee rotation invariance. In this paper, we address issue by introducing a novel point cloud representation that can be mathematically proved rigorously rotation-invariant, i.e., identical clouds in different orientations unified as unique and consistent representation. Moreover, proposed is...

A multifactorial evolutionary algorithm (MFEA) is a recently proposed for multitasking, which optimizes multiple optimization tasks simultaneously. With the design of knowledge transfer among different tasks, MFEA has demonstrated capability to outperform its single-task counterpart in terms both convergence speed and solution quality. In MFEA, across realized via crossover between solutions that possess skill factors. This thus essential performance MFEA. However, we note present most...

The efficient and accurate prediction of building energy consumption can improve the management power systems. In this paper, rough set theory was used to reduce redundant influencing factors find critical consumption. These key were then as input a deep neural network with "deep" architecture powerful capabilities in extracting features. Building is output network. This study collected data from 100 civil public buildings for reduction, laboratory university Dalian nearly year train test...

Recent years witness the increasing popularity of ride-on-demand (RoD) services such as Uber and Didi. Compared with traditional taxi, RoD service is more "data-driven" adopts dynamic pricing to manipulate supply demand in real time. Dynamic price could be viewed an accurate quantitative indicator demand, provide clues drivers, passengers, providers, possibly reshaping ways which some problems are solved. In this paper, we focus on seeking route recommendation problem that aims at driver...

Single-loop detectors provide the most abundant source of traffic data in California, but loop samples are often missing or invalid. A method is described that detects bad and imputes to form a complete grid clean data, real time. The diagnostics algorithm imputation implement this operational on 14,871 loops six districts California Department Transportation. (malfunctioning) single-loop from their volume occupancy measurements. Its novelty its use time series many samples, instead basing...

Statistics from a corridor along Interstate 5 in Los Angeles show that average travel time and travel-time variability are meaningful measures of freeway performance. Variability is an important measure service quality for travelers. Travel can be used to quantify the effect incidents, incident information help reduce uncertainty. Predictability benefits intelligent transportation systems. These differ those defined Highway Capacity Manual other aggregate delay.

Trajectories obtained from Global Position System (GPS)-enabled taxis grant us an opportunity not only to extract meaningful statistics, dynamics, and behaviors about certain urban road users but also monitor adverse and/or malicious events. In this paper, we focus on the problem of detecting anomalous routes by comparing latter against time-dependent historically "normal" routes. We propose online method that is able detect trajectories "on-the-fly" identify which parts trajectory are...

Data quality and budget are two primary concerns in urban-scale mobile crowdsensing applications. In this paper, we leverage the spatial temporal correlation among data sensed different sub-areas to significantly reduce required number of sensing tasks allocated (corresponding budget), yet ensuring quality. Specifically, propose a novel framework called CCS-TA, combining state-of-the-art compressive sensing, Bayesian inference, active learning techniques, dynamically select minimum for task...

Taxi service strategies, as the crowd intelligence of massive taxi drivers, are hidden in their historical time-stamped GPS traces. Mining traces to understand strategies skilled drivers can benefit themselves, passengers, and city planners a number ways. This paper intends uncover efficient inefficient based on large-scale database approximately 7600 taxis over one year China. First, we separate individual link them with revenue generated. Second, investigate from three perspectives,...

Travel behavior understanding is a long-standing and critically important topic in the area of smart cities. Big volumes various GPS-based travel data can be easily collected, among which taxi GPS trajectory typical example. However, data, there usually little information on travelers' activities, thereby they only support limited applications. Quite few studies have been focused enriching semantic meaning for raw such as mode/purpose inferring. Unfortunately, trip purpose imputation...

Task allocation is a fundamental research issue in mobile crowd sensing. While earlier focused mainly on single tasks, recent studies have started to investigate multi-task allocation, which considers the interdependency among multiple tasks. A common drawback shared by existing approaches that, although overall utility of tasks optimized, sensing quality individual may become poor as number increases. To overcome this drawback, we re-define problem introducing task-specific minimal...

Planning an itinerary before traveling to a city is one of the most important travel preparation activities. In this paper, we propose novel framework called TripPlanner, leveraging combination location-based social network (i.e., LBSN) and taxi GPS digital footprints achieve personalized, interactive, traffic-aware trip planning. First, construct dynamic point-of-interest model by extracting relevant information from crowdsourced LBSN traces. Then, two-phase approach for personalized route...

The inaccuracy of manually created digital road maps is a persistent problem, despite their high economic value. We present CrowdAtlas, which automates map update based on people's travels, either individually or crowdsourced. Its mobile navigation app detects significant portions GPS traces that do not conform to the existing map, as determined by state-of-the-art Viterbi matching. When there sufficient evidence collected, inference algorithms can automatically map. CrowdAtlas server...