Error Bounded Line Simplification Algorithms for Trajectory Compression: An Experimental Evaluation

2021 ◽  
Vol 46 (3) ◽  
pp. 1-44
Author(s):  
Xuelian Lin ◽  
Shuai Ma ◽  
Jiahao Jiang ◽  
Yanchen Hou ◽  
Tianyu Wo
Keyword(s):  
Experimental Evaluation ◽  
Real Life ◽  
Average Error ◽  
Distance Metrics ◽  
Trajectory Data ◽  
Practical Applications ◽  
Line Simplification ◽  
Network Bandwidth ◽  
Full Picture ◽  
Life Trajectory

Nowadays, various sensors are collecting, storing, and transmitting tremendous trajectory data, and it is well known that the storage, network bandwidth, and computing resources could be heavily wasted if raw trajectory data is directly adopted. Line simplification algorithms are effective approaches to attacking this issue by compressing a trajectory to a set of continuous line segments, and are commonly used in practice. In this article, we first classify the error bounded line simplification algorithms into different categories and review each category of algorithms. We then study the data aging problem of line simplification algorithms and distance metrics from the views of aging friendliness and aging errors. Finally, we present a systematic experimental evaluation of representative error bounded line simplification algorithms, including both compression optimal and sub-optimal methods, in terms of commonly adopted perpendicular Euclidean, synchronous Euclidean, and direction-aware distances. Using real-life trajectory datasets, we systematically evaluate and analyze the performance (compression ratio, average error, running time, aging friendliness, and query friendliness) of error bounded line simplification algorithms with respect to distance metrics, trajectory sizes, and error bounds. Our study provides a full picture of error bounded line simplification algorithms, which leads to guidelines on how to choose appropriate algorithms and distance metrics for practical applications.

MDTP

2021 ◽  
Vol 14 (8) ◽  
pp. 1289-1297
Author(s):  
Ziquan Fang ◽  
Lu Pan ◽  
Lu Chen ◽  
Yuntao Du ◽  
Yunjun Gao
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Temporal Dynamics ◽  
Real Life ◽  
Feature Modeling ◽  
Traffic Prediction ◽  
Interactive System ◽  
Trajectory Data ◽  
Spatio Temporal ◽  
Prediction Approach

Traffic prediction has drawn increasing attention for its ubiquitous real-life applications in traffic management, urban computing, public safety, and so on. Recently, the availability of massive trajectory data and the success of deep learning motivate a plethora of deep traffic prediction studies. However, the existing neural-network-based approaches tend to ignore the correlations between multiple types of moving objects located in the same spatio-temporal traffic area, which is suboptimal for traffic prediction analytics. In this paper, we propose a multi-source deep traffic prediction framework over spatio-temporal trajectory data, termed as MDTP. The framework includes two phases: spatio-temporal feature modeling and multi-source bridging. We present an enhanced graph convolutional network (GCN) model combined with long short-term memory network (LSTM) to capture the spatial dependencies and temporal dynamics of traffic in the feature modeling phase. In the multi-source bridging phase, we propose two methods, Sum and Concat, to connect the learned features from different trajectory data sources. Extensive experiments on two real-life datasets show that MDTP i) has superior efficiency, compared with classical time-series methods, machine learning methods, and state-of-the-art neural-network-based approaches; ii) offers a significant performance improvement over the single-source traffic prediction approach; and iii) performs traffic predictions in seconds even on tens of millions of trajectory data. we develop MDTP + , a user-friendly interactive system to demonstrate traffic prediction analysis.

scholarly journals Practical Endurance Estimation for Minimizing Energy Consumption of Multirotor Unmanned Aerial Vehicles

Energies ◽  
2018 ◽  
Vol 11 (9) ◽  
pp. 2221 ◽  
Author(s):  
Myeong-hwan Hwang ◽  
Hyun-Rok Cha ◽  
Sung Yong Jung
Keyword(s):  
Drag Coefficient ◽  
Unmanned Aerial Vehicles ◽  
Estimation Method ◽  
Flight Test ◽  
Flight Time ◽  
Average Error ◽  
Practical Applications ◽  
Aerial Vehicles ◽  
Vehicle Shape ◽  
Battery Discharge

The practically applicable endurance estimation method for multirotor unmanned aerial vehicles (UAVs) using a battery as a power source is proposed. The method considers both hovering and steady-level flights. The endurance, thrust, efficiency, and battery discharge are determined with generally available data from the manufacturer. The effects of the drag coefficient related to vehicle shape and payload weight are examined at various forward flight speeds. As the drag coefficient increases, the optimum speed at the minimum required power and the maximum endurance are reduced. However, the payload weight causes an opposite effect, and the optimal flying speed increases with an increase in the payload weight. For more practical applications for common users, the value of S × Cd is determined from a preliminary flight test. Given this value, the endurance is numerically estimated and validated with the measured flight time. The proposed method can successfully estimate the flight time with an average error of 2.3%. This method would be useful for designers who plan various missions and select UAVs.

scholarly journals Illuminance Reconstruction of Road Lighting in Urban Areas for Efficient and Healthy Lighting Performance Evaluation

2018 ◽  
Vol 8 (9) ◽  
pp. 1646 ◽  
Author(s):  
Qi Yao ◽  
Hongbing Wang ◽  
Jim Uttley ◽  
Xiaobo Zhuang
Keyword(s):  
Urban Areas ◽  
Average Error ◽  
Feature Points ◽  
Human Beings ◽  
System Technology ◽  
Practical Applications ◽  
Road Lighting ◽  
Information System Technology ◽  
Traditional Approaches ◽  
Model Approach

Big lighting data are required for evaluation of lighting performance and impacts on human beings, environment, and ecology for smart urban lighting. However, traditional approaches of measuring road lighting cannot achieve this aim. We propose a rule-of-thumb model approach based on some feature points to reconstruct road lighting in urban areas. We validated the reconstructed illuminance with both software simulated and real road lighting scenes, and the average error is between 6 and 19%. This precision is acceptable in practical applications. Using this approach, we reconstructed the illuminance of three real road lighting environments in a block and further estimated the mesopic luminance and melanopic illuminance performance. In the future, by virtue of Geographic Information System technology, the approach may provide big lighting data for evaluation and analysis, and help build smarter urban lighting.

scholarly journals Modified Energy Statistic for Unsupervised Anomaly Detection

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Rupam Mukherjee
Keyword(s):  
Anomaly Detection ◽  
Real Life ◽  
Industrial Applications ◽  
Test Point ◽  
Distance Metrics ◽  
Data Set ◽  
Energy Distance ◽  
New Energy ◽  
Statistical Distance ◽  
Computational Simplicity

For prognostics in industrial applications, the degree of anomaly of a test point from a baseline cluster is estimated using a statistical distance metric. Among different statistical distance metrics, energy distance is an interesting concept based on Newton’s Law of Gravitation, promising simpler computation than classical distance metrics. In this paper, we review the state of the art formulations of energy distance and point out several reasons why they are not directly applicable to the anomaly-detection problem. Thereby, we propose a new energy-based metric called the P-statistic which addresses these issues, is applicable to anomaly detection and retains the computational simplicity of the energy distance. We also demonstrate its effectiveness on a real-life data-set.

Feature Subspace Estimation for Resolving Dimensionality Mismatch in Practical Color-Based Face Recognition Systems

2016 ◽  
Vol 30 (04) ◽  
pp. 1656004 ◽  
Author(s):  
Jae Young Choi
Keyword(s):  
Face Recognition ◽  
Color Image ◽  
Recognition Performance ◽  
Real Life ◽  
Practical Applications ◽  
Novel Approach ◽  
Feature Subspace ◽  
New Feature ◽  
Different Color ◽  
Input Level

Recently, considerable research efforts have been devoted to effective utilization of facial color information for improved recognition performance. Of all color-based face recognition (FR) methods, the most widely used approach is a color FR method using input-level fusion. In this method, augmented input vectors of the color images are first generated by concatenating different color components (including both luminance and chrominance information) by column order at the input level and feature subspace is then trained with a set of augmented input vectors. However, in practical applications, a testing image could be captured as a grayscale image, rather than as a color image, mainly caused by different, heterogeneous image acquisition environment. A grayscale testing image causes so-called dimensionality mismatch between the trained feature subspace and testing input vector. Disparity in dimensionality negatively impacts the reliable FR performance and even imposes a significant restriction on carrying out FR operations in practical color FR systems. To resolve the dimensionality mismatch, we propose a novel approach to estimate new feature subspace, suitable for recognizing a grayscale testing image. In particular, new feature subspace is estimated from a given feature subspace created using color training images. The effectiveness of proposed solution has been successfully tested on four public face databases (DBs) such as CMU, FERET, XM2VTSDB, and ORL DBs. Extensive and comparative experiments showed that the proposed solution works well for resolving dimensionality mismatch of importance in real-life color FR systems.

3D Printing Applications in STEM Education

2018 ◽  
pp. 2626-2640
Author(s):  
Norman Gwangwava ◽  
Catherine Hlahla
Keyword(s):  
3D Printing ◽  
Real Life ◽  
Printing Technology ◽  
Web Based ◽  
Practical Applications ◽  
3D Printing Technology ◽  
Lecture Room ◽  
Storage Products ◽  
Educational Toys ◽  
Learning Institutions

Using 3D printing technology in learning institutions brings an industrial experience to learners as well as an exposure to the same cutting-edge technologies encountered in real life careers. The chapter explores 3D printing technology at kindergarten (preschool), in the lecture room (BEng programme), and ready-to-use 3D printed products. In educational toy applications, the effect of poor product designs that do not meet the children's dimensional and safety requirements can lead to injuries, development of musculoskeletal disorders and health problems, some of which may be experienced by the children when they grow up. In order to address the problem of poor design, measurements of anthropometric dimensions from male and female children, aging from 6 to 7 years old were taken and concepts for educational toys were then generated. Other practical applications of the 3D printing technology explored in the chapter are lecture room demonstrations, prototyping of design projects and a web-based mass-customization of office mini-storage products.

scholarly journals Mobility-Aware Service Caching in Mobile Edge Computing for Internet of Things

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 610 ◽  
Author(s):  
Hua Wei ◽  
Hong Luo ◽  
Yan Sun
Keyword(s):  
Target Location ◽  
Geometric Model ◽  
Back Propagation ◽  
Base Station ◽  
Edge Computing ◽  
Computation Offloading ◽  
Target Area ◽  
Mobile Edge Computing ◽  
Trajectory Data ◽  
Practical Applications

The mobile edge computing architecture successfully solves the problem of high latency in cloud computing. However, current research focuses on computation offloading and lacks research on service caching issues. To solve the service caching problem, especially for scenarios with high mobility in the Sensor Networks environment, we study the mobility-aware service caching mechanism. Our goal is to maximize the number of users who are served by the local edge-cloud, and we need to make predictions about the user’s target location to avoid invalid service requests. First, we propose an idealized geometric model to predict the target area of a user’s movement. Since it is difficult to obtain all the data needed by the model in practical applications, we use frequent patterns to mine local moving track information. Then, by using the results of the trajectory data mining and the proposed geometric model, we make predictions about the user’s target location. Based on the prediction result and existing service cache, the service request is forwarded to the appropriate base station through the service allocation algorithm. Finally, to be able to train and predict the most popular services online, we propose a service cache selection algorithm based on back-propagation (BP) neural network. The simulation experiments show that our service cache algorithm reduces the service response time by about 13.21% on average compared to other algorithms, and increases the local service proportion by about 15.19% on average compared to the algorithm without mobility prediction.

An AI Walk from Pharmacokinetics to Marketing

2011 ◽  
pp. 71-75
Author(s):  
José D. Martín-Guerrero ◽  
Emilio Soria-Olivas ◽  
Paulo J.G. Lisboa ◽  
Antonio J. Serrano-López
Keyword(s):  
Finite Impulse Response ◽  
Clustering Algorithms ◽  
Real Life ◽  
Support Vector ◽  
Conditional Heteroskedasticity ◽  
Resonance Theory ◽  
Adaptive Resonance ◽  
Practical Applications ◽  
Life Problems ◽  
Auto Regressive

This work is intended for providing a review of reallife practical applications of Artificial Intelligence (AI) methods. We focus on the use of Machine Learning (ML) methods applied to rather real problems than synthetic problems with standard and controlled environment. In particular, we will describe the following problems in next sections: • Optimization of Erythropoietin (EPO) dosages in anaemic patients undergoing Chronic Renal Failure (CRF). • Optimization of a recommender system for citizen web portal users. • Optimization of a marketing campaign. The choice of these problems is due to their relevance and their heterogeneity. This heterogeneity shows the capabilities and versatility of ML methods to solve real-life problems in very different fields of knowledge. The following methods will be mentioned during this work: • Artificial Neural Networks (ANNs): Multilayer Perceptron (MLP), Finite Impulse Response (FIR) Neural Network, Elman Network, Self-Oganizing Maps (SOMs) and Adaptive Resonance Theory (ART). • Other clustering algorithms: K-Means, Expectation- Maximization (EM) algorithm, Fuzzy C-Means (FCM), Hierarchical Clustering Algorithms (HCA). • Generalized Auto-Regressive Conditional Heteroskedasticity (GARCH). • Support Vector Regression (SVR). • Collaborative filtering techniques. • Reinforcement Learning (RL) methods.

Development of a Simplified Model of Speed-Specific Vehicle-Specific Power Distribution Based on Vehicle Weight for Fuel Consumption Estimates

2020 ◽  
Vol 2674 (12) ◽  
pp. 52-67
Author(s):  
Zeyu Zhang ◽  
Guohua Song ◽  
Jiaoyang Chen ◽  
Zhiqiang Zhai ◽  
Lei Yu
Keyword(s):  
Fuel Consumption ◽  
Power Distribution ◽  
Motor Vehicle ◽  
Gaussian Function ◽  
Simplified Model ◽  
Specific Power ◽  
Average Error ◽  
Trajectory Data ◽  
Vehicle Weight ◽  
The Relationship

The vehicle-specific power (VSP) distribution, as one of the fundamental inputs of VSP-based emission models such as the motor vehicle emission simulator model, is sensitive to vehicle weight. Developing field VSP distributions requires extensive vehicle type-specific trajectory data, which is expensive and time-consuming. On the other hand, estimating fuel consumption accurately by employing VSP distributions for various vehicle types is computationally highly complex. This study aims to develop a simplified model of speed-specific VSP distribution based on vehicle weight for fuel consumption. First, field speed-specific VSP distributions of eight types of vehicles are developed. Second, the Gaussian function is employed to fit the field speed-specific VSP distributions to “change” the discrete VSP distributions into continuous distributions to facilitate quantifying the relationship between VSP distributions and vehicle weights. Third, the relationship between VSP distributions and vehicle weights is quantified by employing polynomial functions. The results indicate the acceptable accuracy of the simplified model, with 93.8% of R2 of the Gaussian function being greater than 0.90. The error in estimating fuel consumption using the simplified model is acceptable. For vehicles weighing 1.5 t (1.5 metric tons), the average error is 6.3%. Besides the “hole filling” of VSP distributions of inaccessible vehicles, the simplified model will reduce the computational complexity of estimating fuel consumption by about 50%, which is beneficial for the realization of real-time online estimates of fuel consumption.

Sign in / Sign up

Export Citation Format

Share Document