A queueing-theoretic framework for vehicle dispatching in dynamic car-hailing

With the rapid development of smart mobile devices, the car-hailing platforms (e.g., Uber or Lyft) have attracted much attention from the academia and the industry. In this paper, we consider a dynamic car-hailing problem, namely maximum revenue vehicle dispatching (MRVD), in which rider requests dynamically arrive and drivers need to serve riders such that the entire revenue of the platform is maximized. We prove that the MRVD problem is NP-hard and intractable. To handle the MRVD problem, we propose a queueing-based vehicle dispatching framework, which first uses existing machine learning models to predict the future vehicle demand of each region, then estimates the idle time periods of drivers through a double-sided queueing model for each region. With the information of the predicted vehicle demands and estimated idle time periods of drivers, we propose two batch-based vehicle dispatching algorithms to efficiently assign suitable drivers to riders such that the expected overall revenue of the platform is maximized during each batch processing. Through extensive experiments, we demonstrate the efficiency and effectiveness of our proposed approaches over both real and synthetic datasets. In summary, our methods can achieve 3% ~ 10% increase on overall revenue without sacrificing on running speed compared with the state-of-the-art solutions.

Download Full-text

G-Tric: generating three-way synthetic datasets with triclustering solutions

BMC Bioinformatics ◽

10.1186/s12859-020-03925-4 ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

João Lobo ◽

Rui Henriques ◽

Sara C. Madeira

Keyword(s):

State Of The Art ◽

Synthetic Data ◽

Ground Truth ◽

Real Data ◽

Three Dimensions ◽

Additional Advantage ◽

Urban Dynamics ◽

Data Generator ◽

Real World Datasets ◽

Synthetic Datasets

Abstract Background Three-way data started to gain popularity due to their increasing capacity to describe inherently multivariate and temporal events, such as biological responses, social interactions along time, urban dynamics, or complex geophysical phenomena. Triclustering, subspace clustering of three-way data, enables the discovery of patterns corresponding to data subspaces (triclusters) with values correlated across the three dimensions (observations $$\times$$ × features $$\times$$ × contexts). With increasing number of algorithms being proposed, effectively comparing them with state-of-the-art algorithms is paramount. These comparisons are usually performed using real data, without a known ground-truth, thus limiting the assessments. In this context, we propose a synthetic data generator, G-Tric, allowing the creation of synthetic datasets with configurable properties and the possibility to plant triclusters. The generator is prepared to create datasets resembling real 3-way data from biomedical and social data domains, with the additional advantage of further providing the ground truth (triclustering solution) as output. Results G-Tric can replicate real-world datasets and create new ones that match researchers needs across several properties, including data type (numeric or symbolic), dimensions, and background distribution. Users can tune the patterns and structure that characterize the planted triclusters (subspaces) and how they interact (overlapping). Data quality can also be controlled, by defining the amount of missing, noise or errors. Furthermore, a benchmark of datasets resembling real data is made available, together with the corresponding triclustering solutions (planted triclusters) and generating parameters. Conclusions Triclustering evaluation using G-Tric provides the possibility to combine both intrinsic and extrinsic metrics to compare solutions that produce more reliable analyses. A set of predefined datasets, mimicking widely used three-way data and exploring crucial properties was generated and made available, highlighting G-Tric’s potential to advance triclustering state-of-the-art by easing the process of evaluating the quality of new triclustering approaches.

Download Full-text

On-Shelf Utility Mining of Sequence Data

ACM Transactions on Knowledge Discovery from Data ◽

10.1145/3457570 ◽

2021 ◽

Vol 16 (2) ◽

pp. 1-31

Author(s):

Chunkai Zhang ◽

Zilin Du ◽

Yuting Yang ◽

Wensheng Gan ◽

Philip S. Yu

Keyword(s):

High Efficiency ◽

Sequence Data ◽

Real Life ◽

Search Space ◽

Upper Bounds ◽

Utility Mining ◽

Limited Memory ◽

Time Periods ◽

High Utility ◽

Synthetic Datasets

Utility mining has emerged as an important and interesting topic owing to its wide application and considerable popularity. However, conventional utility mining methods have a bias toward items that have longer on-shelf time as they have a greater chance to generate a high utility. To eliminate the bias, the problem of on-shelf utility mining (OSUM) is introduced. In this article, we focus on the task of OSUM of sequence data, where the sequential database is divided into several partitions according to time periods and items are associated with utilities and several on-shelf time periods. To address the problem, we propose two methods, OSUM of sequence data (OSUMS) and OSUMS + , to extract on-shelf high-utility sequential patterns. For further efficiency, we also design several strategies to reduce the search space and avoid redundant calculation with two upper bounds time prefix extension utility ( TPEU ) and time reduced sequence utility ( TRSU ). In addition, two novel data structures are developed for facilitating the calculation of upper bounds and utilities. Substantial experimental results on certain real and synthetic datasets show that the two methods outperform the state-of-the-art algorithm. In conclusion, OSUMS may consume a large amount of memory and is unsuitable for cases with limited memory, while OSUMS + has wider real-life applications owing to its high efficiency.

Download Full-text

Dynamic network intelligent hybrid recommendation algorithm and its application in online shopping platform

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-201579 ◽

2021 ◽

pp. 1-13

Author(s):

Yuxuan Gao ◽

Haiming Liang ◽

Bingzhen Sun

Keyword(s):

Online Shopping ◽

Rapid Development ◽

Dynamic Network ◽

Topsis Method ◽

Recommendation Algorithm ◽

Time Periods ◽

The Difference ◽

Relationship Of ◽

Hybrid Recommendation ◽

Novel Model

With the rapid development of e-commerce, whether network intelligent recommendation can attract customers has become a measure of customer retention on online shopping platforms. In the literature about network intelligent recommendation, there are few studies that consider the difference preference of customers in different time periods. This paper proposes the dynamic network intelligent hybrid recommendation algorithm distinguishing time periods (DIHR), it is a integrated novel model combined with the DEMATEL and TOPSIS method to solved the problem of network intelligent recommendation considering time periods. The proposed method makes use of the DEMATEL method for evaluating the preference relationship of customers for indexes of merchandises, and adopt the TOPSIS method combined with intuitionistic fuzzy number (IFN) for assessing and ranking the merchandises according to the indexes. We specifically introduce the calculation steps of the proposed method, and then calculate its application in the online shopping platform.

Download Full-text

Analysis of Synthetic Voltage vs. Capacity Datasets for Big Data Li-ion Diagnosis and Prognosis

Energies ◽

10.3390/en14092371 ◽

2021 ◽

Vol 14 (9) ◽

pp. 2371

Author(s):

Matthieu Dubarry ◽

David Beck

Keyword(s):

Cobalt Oxide ◽

State Of The Art ◽

Data Driven ◽

Nickel Aluminum ◽

Li Ion Battery ◽

Diagnosis And Prognosis ◽

Detailed Statistical Analysis ◽

Li Ion ◽

Synthetic Datasets ◽

Nickel Manganese

The development of data driven methods for Li-ion battery diagnosis and prognosis is a growing field of research for the battery community. A big limitation is usually the size of the training datasets which are typically not fully representative of the real usage of the cells. Synthetic datasets were proposed to circumvent this issue. This publication provides improved datasets for three major battery chemistries, LiFePO4, Nickel Aluminum Cobalt Oxide, and Nickel Manganese Cobalt Oxide 811. These datasets can be used for statistical or deep learning methods. This work also provides a detailed statistical analysis of the datasets. Accurate diagnosis as well as early prognosis comparable with state of the art, while providing physical interpretability, were demonstrated by using the combined information of three learnable parameters.

Download Full-text

Accurate Instance-Based Segmentation for Boundary Detection in Robot Grasping Application

Applied Sciences ◽

10.3390/app11094248 ◽

2021 ◽

Vol 11 (9) ◽

pp. 4248

Author(s):

Hong Hai Hoang ◽

Bao Long Tran

Keyword(s):

Object Segmentation ◽

State Of The Art ◽

Rapid Development ◽

Spatial Relationship ◽

Learning Technologies ◽

Average Precision ◽

Novel Approach ◽

3D Camera ◽

Robot Grasping ◽

Instance Segmentation

With the rapid development of cameras and deep learning technologies, computer vision tasks such as object detection, object segmentation and object tracking are being widely applied in many fields of life. For robot grasping tasks, object segmentation aims to classify and localize objects, which helps robots to be able to pick objects accurately. The state-of-the-art instance segmentation network framework, Mask Region-Convolution Neural Network (Mask R-CNN), does not always perform an excellent accurate segmentation at the edge or border of objects. The approach using 3D camera, however, is able to extract the entire (foreground) objects easily but can be difficult or require a large amount of computation effort to classify it. We propose a novel approach, in which we combine Mask R-CNN with 3D algorithms by adding a 3D process branch for instance segmentation. Both outcomes of two branches are contemporaneously used to classify the pixels at the edge objects by dealing with the spatial relationship between edge region and mask region. We analyze the effectiveness of the method by testing with harsh cases of object positions, for example, objects are closed, overlapped or obscured by each other to focus on edge and border segmentation. Our proposed method is about 4 to 7% higher and more stable in IoU (intersection of union). This leads to a reach of 46% of mAP (mean Average Precision), which is a higher accuracy than its counterpart. The feasibility experiment shows that our method could be a remarkable promoting for the research of the grasping robot.

Download Full-text

A Multi-Branch Feature Fusion Strategy Based on an Attention Mechanism for Remote Sensing Image Scene Classification

Remote Sensing ◽

10.3390/rs13101950 ◽

2021 ◽

Vol 13 (10) ◽

pp. 1950

Author(s):

Cuiping Shi ◽

Xin Zhao ◽

Liguo Wang

Keyword(s):

Remote Sensing ◽

Feature Extraction ◽

Classification Accuracy ◽

Feature Fusion ◽

State Of The Art ◽

Rapid Development ◽

Remote Sensing Image ◽

Classification Performance ◽

Attention Mechanism ◽

Scene Classification

In recent years, with the rapid development of computer vision, increasing attention has been paid to remote sensing image scene classification. To improve the classification performance, many studies have increased the depth of convolutional neural networks (CNNs) and expanded the width of the network to extract more deep features, thereby increasing the complexity of the model. To solve this problem, in this paper, we propose a lightweight convolutional neural network based on attention-oriented multi-branch feature fusion (AMB-CNN) for remote sensing image scene classification. Firstly, we propose two convolution combination modules for feature extraction, through which the deep features of images can be fully extracted with multi convolution cooperation. Then, the weights of the feature are calculated, and the extracted deep features are sent to the attention mechanism for further feature extraction. Next, all of the extracted features are fused by multiple branches. Finally, depth separable convolution and asymmetric convolution are implemented to greatly reduce the number of parameters. The experimental results show that, compared with some state-of-the-art methods, the proposed method still has a great advantage in classification accuracy with very few parameters.

Download Full-text

Evaluation of the effectiveness and efficiency of state-of-the-art features and models for automatic speech recognition error detection

Journal Of Big Data ◽

10.1186/s40537-020-00391-w ◽

2021 ◽

Vol 8 (1) ◽

Author(s):

Asmaa El Hannani ◽

Rahhal Errattahi ◽

Fatima Zahra Salmam ◽

Thomas Hain ◽

Hassan Ouahmane

Keyword(s):

Speech Recognition ◽

Automatic Speech Recognition ◽

Error Detection ◽

State Of The Art ◽

Rapid Development ◽

Unified Framework ◽

Human Machine Interaction ◽

Detection Analysis ◽

Extensive Evaluation ◽

Effectiveness And Efficiency

AbstractSpeech based human-machine interaction and natural language understanding applications have seen a rapid development and wide adoption over the last few decades. This has led to a proliferation of studies that investigate Error detection and classification in Automatic Speech Recognition (ASR) systems. However, different data sets and evaluation protocols are used, making direct comparisons of the proposed approaches (e.g. features and models) difficult. In this paper we perform an extensive evaluation of the effectiveness and efficiency of state-of-the-art approaches in a unified framework for both errors detection and errors type classification. We make three primary contributions throughout this paper: (1) we have compared our Variant Recurrent Neural Network (V-RNN) model with three other state-of-the-art neural based models, and have shown that the V-RNN model is the most effective classifier for ASR error detection in term of accuracy and speed, (2) we have compared four features’ settings, corresponding to different categories of predictor features and have shown that the generic features are particularly suitable for real-time ASR error detection applications, and (3) we have looked at the post generalization ability of our error detection framework and performed a detailed post detection analysis in order to perceive the recognition errors that are difficult to detect.

Download Full-text

Active Learning in the Geometric Block Model

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5772 ◽

2020 ◽

Vol 34 (04) ◽

pp. 3641-3648 ◽

Cited By ~ 1

Author(s):

Eli Chien ◽

Antonia Tulino ◽

Jaime Llorca

Keyword(s):

Active Learning ◽

Community Detection ◽

Random Graphs ◽

State Of The Art ◽

Superior Performance ◽

Model Parameters ◽

Block Model ◽

Stochastic Block Model ◽

Synthetic Datasets ◽

Community Detection Problems

The geometric block model is a recently proposed generative model for random graphs that is able to capture the inherent geometric properties of many community detection problems, providing more accurate characterizations of practical community structures compared with the popular stochastic block model. Galhotra et al. recently proposed a motif-counting algorithm for unsupervised community detection in the geometric block model that is proved to be near-optimal. They also characterized the regimes of the model parameters for which the proposed algorithm can achieve exact recovery. In this work, we initiate the study of active learning in the geometric block model. That is, we are interested in the problem of exactly recovering the community structure of random graphs following the geometric block model under arbitrary model parameters, by possibly querying the labels of a limited number of chosen nodes. We propose two active learning algorithms that combine the use of motif-counting with two different label query policies. Our main contribution is to show that sampling the labels of a vanishingly small fraction of nodes (sub-linear in the total number of nodes) is sufficient to achieve exact recovery in the regimes under which the state-of-the-art unsupervised method fails. We validate the superior performance of our algorithms via numerical simulations on both real and synthetic datasets.

Download Full-text

A DIY Fabrication Approach for Ultra-Thin Focus-Tunable Liquid Lens Using Electrohydrodynamic Pump

Micromachines ◽

10.3390/mi12121452 ◽

2021 ◽

Vol 12 (12) ◽

pp. 1452

Author(s):

Taichi Murakami ◽

Yu Kuwajima ◽

Ardi Wiranata ◽

Ayato Minaminosono ◽

Hiroki Shigemune ◽

...

Keyword(s):

Low Cost ◽

Rapid Development ◽

Pure Water ◽

Dielectric Fluid ◽

Copper Sheet ◽

Fluidic Channel ◽

Liquid Lens ◽

Do It Yourself ◽

Tunable Lenses ◽

Smart Mobile

Demand for variable focus lens is increasing these days due to the rapid development of smart mobile devices and drones. However, conventional mechanical systems for lenses are generally complex, cumbersome, and rigid (e.g., for motors and gears). This research proposes a simple and compact liquid lens controlled by an electro hydro dynamics (EHD) pump. In our study, we propose a do-it-yourself (DIY) method to fabricate the low-cost EHD lens. The EHD lens consists of a polypropylene (PP) sheet for the exterior, a copper sheet for the electrodes, and an acrylic elastomer for the fluidic channel where dielectric fluid and pure water are filled. We controlled the lens magnification by changing the curvature of the liquid interface between the dielectric fluid and pure water. We evaluated the magnification performance of the lens. Moreover, we also established a numerical model to characterize the lens performance. We expect to contribute to the miniaturization of focus-tunable lenses.

Download Full-text

The Audio Auditor: User-Level Membership Inference in Internet of Things Voice Services

Proceedings on Privacy Enhancing Technologies ◽

10.2478/popets-2021-0012 ◽

2021 ◽

Vol 2021 (1) ◽

pp. 209-228

Author(s):

Yuantian Miao ◽

Minhui Xue ◽

Chao Chen ◽

Lei Pan ◽

Jun Zhang ◽

...

Keyword(s):

Internet Of Things ◽

State Of The Art ◽

Rapid Development ◽

Black Box ◽

Problem Space ◽

Specific Data ◽

Learning Techniques ◽

Audio Data ◽

Iot Devices ◽

Asr System

AbstractWith the rapid development of deep learning techniques, the popularity of voice services implemented on various Internet of Things (IoT) devices is ever increasing. In this paper, we examine user-level membership inference in the problem space of voice services, by designing an audio auditor to verify whether a specific user had unwillingly contributed audio used to train an automatic speech recognition (ASR) model under strict black-box access. With user representation of the input audio data and their corresponding translated text, our trained auditor is effective in user-level audit. We also observe that the auditor trained on specific data can be generalized well regardless of the ASR model architecture. We validate the auditor on ASR models trained with LSTM, RNNs, and GRU algorithms on two state-of-the-art pipelines, the hybrid ASR system and the end-to-end ASR system. Finally, we conduct a real-world trial of our auditor on iPhone Siri, achieving an overall accuracy exceeding 80%. We hope the methodology developed in this paper and findings can inform privacy advocates to overhaul IoT privacy.

Download Full-text