arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 1,567 records · Page 87Linked to original sources

arXiv2019

Combined Energy and Comfort Optimization of Air Conditioning System in Connected and Automated Vehicles

In this paper, we propose a combined energy and comfort optimization (CECO) strategy for the air conditioning (A/C) system of the connected and automated vehicles (CAVs). By leveraging the weather and traffic predictions enabled by the emerging CAV technologies, the proposed strategy is able to minimize the A/C system energy consumption while maintaining the occupant thermal comfort (OTC) within the comfort constraints, where the comfort is quantified by a modified predictive mean vote (PMV) model adapted for an automotive application. A general CECO problem is formulated and addressed using model predictive control (MPC) and weather/traffic previews. Depending on the ways of exploiting the preview information and enforcing the OTC constraint, different MPCs are developed based on solving different variations of the general CECO problem. The CECO-based MPCs are then tested in simulation using an automotive A/C system simulation model (CoolSim) as the virtual testbed. The simulation results show that, over SC03 driving cycle, the proposed CECO-based MPCs outperform the baseline cabin temperature tracking controller, reducing the A/C system energy consumption by up to 7.6%, while achieving better OTC according to the PMV-based metrics. This energy saving in A/C system translates to 3.1% vehicle fuel economy improvement. The trade-off between energy efficiency and OTC for different control scenarios is also highlighted.

eess.SY↗

arXiv2019

Solar Thermal Energy Conversion Enhanced by Selective Metafilm Absorber under Multiple Solar Concentrations at High Temperatures

Concentrating solar power, particularly parabolic trough system with solar concentrations less than 50, requires spectrally selective solar absorbers that are thermally stable at high temperatures of 400degC above to achieve high efficiency. In this work, the solar-thermal performance of a selective multilayer metafilm absorber is characterized along with a black absorber for comparison by a lab-scale experimental setup that measures the steady-state absorber temperature under multiple solar concentrations. Heat transfer analysis is employed to elucidate different heat transfer modes and validate the solar-thermal experiment. Due to the superior spectral selectivity and excellent thermal stability, the metafilm absorber deposited on the cost-effective stainless steel foil could achieve the solar-thermal efficiency 57% at a steady-state temperature of 371degC under 10 suns during the lab-scale experiment with losses, while a highest efficiency of 83% was projected under the same conditions for practical solar thermal applications. The results here will facilitate the research and development of novel solar materials for high-efficiency solar thermal energy conversion.

physics.app-ph↗

arXiv2019

Information collection for fraud detection in P2P financial market

Fintech companies have been facing challenges from fraudulent behavior for a long time. Fraud rate in Chinese P2P financial market could go as high as 10%. It is crucial to collect sufficient information of the user as input to the anti-fraud process. Data collection framework for Fintech companies are different fro m conventional internet firms. With individual-based crawling request , we need to deal with new challenges negligible elsewhere . In this paper , we give an outline of how we collect data from the web to facilitate our anti-fraud process. We also overview the challenges and solutions to our problems. Our team at HC Financial Service Group is one of the few companies that are capable of developing full-fledged crawlers on our own.

cs.OH↗

arXiv2019

Detection of fraudulent users in P2P financial market

Financial fraud detection is one of the core technological assets of Fintech companies. It saves tens of millions of money fro m Chinese Fintech companies since the bad loan rate is more than 10%. HC Financial Service Group is the 3rd largest company in the Chinese P2P financial market. In this paper we illustrate how we tackle the fraud detection problem at HC Financial. We utilize two powerful workhorses in the machine learning field - random forest and gradient boosting decision tree to detect fraudulent users . We demonstrate that by carefully select features and tune model parameters , we could effectively filter out fraudulent users in the P2P market.

cs.OH↗

arXiv2019

Quantitative analysis of Matthew effect and sparsity problem of recommender systems

Recommender systems have received great commercial success. Recommendation has been used widely in areas such as e-commerce, online music FM, online news portal, etc. However, several problems related to input data structure pose serious challenge to recommender system performance. Two of these problems are Matthew effect and sparsity problem. Matthew effect heavily skews recommender system output towards popular items. Data sparsity problem directly affects the coverage of recommendation result. Collaborative filtering is a simple benchmark ubiquitously adopted in the industry as the baseline for recommender system design. Understanding the underlying mechanism of collaborative filtering is crucial for further optimization. In this paper, we do a thorough quantitative analysis on Matthew effect and sparsity problem in the particular context setting of collaborative filtering. We compare the underlying mechanism of user-based and item-based collaborative filtering and give insight to industrial recommender system builders.

cs.IR↗

arXiv2019

Big Data Analytics for Large Scale Wireless Networks: Challenges and Opportunities

The wide proliferation of various wireless communication systems and wireless devices has led to the arrival of big data era in large scale wireless networks. Big data of large scale wireless networks has the key features of wide variety, high volume, real-time velocity and huge value leading to the unique research challenges that are different from existing computing systems. In this paper, we present a survey of the state-of-art big data analytics (BDA) approaches for large scale wireless networks. In particular, we categorize the life cycle of BDA into four consecutive stages: Data Acquisition, Data Preprocessing, Data Storage and Data Analytics. We then present a detailed survey of the technical solutions to the challenges in BDA for large scale wireless networks according to each stage in the life cycle of BDA. Moreover, we discuss the open research issues and outline the future directions in this promising area.

cs.NI↗

arXiv2019

Big Data Analytics for Manufacturing Internet of Things: Opportunities, Challenges and Enabling Technologies

The recent advances in information and communication technology (ICT) have promoted the evolution of conventional computer-aided manufacturing industry to smart data-driven manufacturing. Data analytics in massive manufacturing data can extract huge business values while can also result in research challenges due to the heterogeneous data types, enormous volume and real-time velocity of manufacturing data. This paper provides an overview on big data analytics in manufacturing Internet of Things (MIoT). This paper first starts with a discussion on necessities and challenges of big data analytics in manufacturing data of MIoT. Then, the enabling technologies of big data analytics of manufacturing data are surveyed and discussed. Moreover, this paper also outlines the future directions in this promising area.

cs.CY↗

arXiv2019

Learning with Noisy Labels for Sentence-level Sentiment Classification

Deep neural networks (DNNs) can fit (or even over-fit) the training data very well. If a DNN model is trained using data with noisy labels and tested on data with clean labels, the model may perform poorly. This paper studies the problem of learning with noisy labels for sentence-level sentiment classification. We propose a novel DNN model called NetAb (as shorthand for convolutional neural Networks with Ab-networks) to handle noisy labels during training. NetAb consists of two convolutional neural networks, one with a noise transition layer for dealing with the input noisy labels and the other for predicting 'clean' labels. We train the two networks using their respective loss functions in a mutual reinforcement manner. Experimental results demonstrate the effectiveness of the proposed model.

cs.CL↗

arXiv2019

A Data-Validated Host-Parasite Model for Infectious Disease Outbreaks

The use of model experimental systems and mathematical models is important to further understanding of infectious disease dynamics and strategize disease mitigation. Gyrodactylids are helminth ectoparasites of teleost fish which have many dynamical characteristics of microparasites but offer the advantage that they can be quantified and tracked over time, allowing further insight into within-host and epidemic dynamics. In this paper, we design a model to describe host-parasite dynamics of the well-studied guppy-Gyrodactylus turnbulli system, using experimental data to estimate parameters and validate it. We estimate the basic reproduction number (R_0), for this system. Sensitivity analysis reveals that parasite growth rate, and the rate at which the guppy mounts an immune response have the greatest impact on outbreak peak and timing both for initial outbreaks and on longer time scales. These findings highlight guppy population resistance and parasite virulence as key factors in disease control, and future work should focus on incorporating heterogeneity in host resistance into disease models and extrapolating to other host-parasite systems.

q-bio.PE↗

arXiv2019

The Dynamic Shift of Neuron Excitability Observed with Enveloped High Frequency Stimulation

Neuronal excitability is known to be affected by transcranial electrical stimulation. However, due to the existence of both excitatory and inhibitory neurons in the cortex, the mechanism of neuronal excitability shift is still not clear. Here, we study electrical stimulation disturbance on neuronal excitability in the neuromuscular system on an acute rat model. We design a special stimulation waveform of enveloped high frequency stimulation (EHFS). With modeling and in vivo measurements, EHFS is confirmed to synchronize the neuronal recruitment at the positive and negative electrode. This unique synchronization property of EHFS amplifies the electrical stimulation disturbance on neuronal excitability, to enable the macroscopic observations of large increase and decrease of force output. By eliminating the complicated inhibitory interneuron effects in the cortex, our observations on the neuromuscular system supports the argument that electrical stimulation dynamically shifts neuronal excitability, by inducing depolarization during anodal stimulation and hyperpolarization during cathodal stimulation.

q-bio.NC↗

arXiv2019

Data Augmentation for Object Detection via Progressive and Selective Instance-Switching

Collection of massive well-annotated samples is effective in improving object detection performance but is extremely laborious and costly. Instead of data collection and annotation, the recently proposed Cut-Paste methods [12, 15] show the potential to augment training dataset by cutting foreground objects and pasting them on proper new backgrounds. However, existing Cut-Paste methods cannot guarantee synthetic images always precisely model visual context, and all of them require external datasets. To handle above issues, this paper proposes a simple yet effective instance-switching (IS) strategy, which generates new training data by switching instances of same class from different images. Our IS naturally preserves contextual coherence in the original images while requiring no external dataset. For guiding our IS to obtain better object performance, we explore issues of instance imbalance and class importance in datasets, which frequently occur and bring adverse effect on detection performance. To this end, we propose a novel Progressive and Selective Instance-Switching (PSIS) method to augment training data for object detection. The proposed PSIS enhances instance balance by combining selective re-sampling with a class-balanced loss, and considers class importance by progressively augmenting training dataset guided by detection performance. The experiments are conducted on the challenging MS COCO benchmark, and results demonstrate our PSIS brings clear improvement over various state-of-the-art detectors (e.g., Faster R-CNN, FPN, Mask R-CNN and SNIPER), showing the superiority and generality of our PSIS. Code and models are available at: https://github.com/Hwang64/PSIS.

cs.CV↗

arXiv2019

Leveraging Socioeconomic Information and Deep Learning for Residential Load Pattern Prediction

Advanced metering infrastructure systems record a high volume of residential load data, opening up an opportunity for utilities to understand consumer energy consumption behaviors. Existing studies have focused on load profiling and prediction, but neglected the role of socioeconomic characteristics of consumers in their energy consumption behaviors. In this paper, we develop a prediction model using deep neural networks to predict load patterns of consumers based on their socioeconomic information. We analyze load patterns using the K-means clustering method and use an entropy-based feature selection method to select the key socioeconomic characteristics that affect consumers' load patterns. Our prediction method with feature selection achieves a higher prediction accuracy compared with the benchmark schemes, e.g. 80% reduction in the prediction error.

eess.SP↗

arXiv2019

Second-generation stoichiometric mathematical model to predict methane emissions from oil sands tailings

Microbial metabolism of fugitive hydrocarbons produces greenhouse gas (GHG) emissions from oil sands tailings ponds (OSTP) and end pit lakes (EPL) that retain semisolid wastes from surface mining of oil sands ores. Predicting GHG production, particularly methane (CH4), would help oil sands operators mitigate tailings emissions and would assist regulators evaluating the trajectory of reclamation scenarios. Using empirical datasets from laboratory incubation of OSTP sediments with pertinent hydrocarbons, we developed a stoichiometric model for CH4 generation by indigenous microbes. This model improved on previous first-approximation models by considering long-term biodegradation kinetics for 18 relevant hydrocarbons from three different oil sands operations, lag times, nutrient limitations, and microbial growth and death rates. Laboratory measurements were used to estimate model parameter values and to validate the new model. Goodness of fit analysis showed that the stoichiometric model predicted CH4 production well; normalized mean square error analysis revealed that it surpassed previous models. Comparison of model predictions with field measurements of CH4 emissions further validated the new model. Importantly, the model also identified parameters that are currently lacking but are needed to enable future robust modeling of CH4 production from OSTP and EPL in situ.

q-bio.QM↗

arXiv2019

Txilm: Lossy Block Compression with Salted Short Hashing

Current blockchains are restricted by the low throughput. Aimed at this problem, we propose Txilm, a protocol that compresses the size of transaction presentation in each block to save the bandwidth of the network. In this protocol, a block carries short hashes of TXIDs instead of complete transactions. Combined with the sorted transactions based on TXIDs, Txilm realizes 80 times of data size reduction compared with the original blockchains. We also evaluate the probability of hash collisions, and provide methods of resolving such collisions. Finally, we design strategies to protect against potential attacks on Txilm.

cs.CR↗

arXiv2019

Confluent-Drawing Parallel Coordinates: Web-Based Interactive Visual Analytics of Large Multi-Dimensional Data

Parallel coordinates plot is one of the most popular and widely used visualization techniques for multi-dimensional data sets. Its main challenges for large-scale data sets are visual clutter and overplotting which hamper the recognition of patterns and trends in the data. In this paper, we propose a confluent drawing approach of parallel coordinates to support the web-based interactive visual analytics of large multi-dimensional data. The proposed method maps multi-dimensional data to node-link diagrams through the data binning-based clustering for each dimension. It uses density-based confluent drawing to visualize clusters and edges to reduce visual clutter and overplotting. Its rendering time is independent of the number of data items. It supports interactive visualization of large data sets without hardware acceleration in a normal web browser. Moreover, we design interactions to control the data binning process with this approach to support interactive visual analytics of large multi-dimensional data sets. Based on the proposed approach, we implement a web-based visual analytics application. The efficiency of the proposed method is examined through experiments on several data sets. The effectiveness of the proposed method is evaluated through a user study, in which two typical tasks of parallel coordinates plot are performed by participants to compare the proposed method with another parallel coordinates bundling technique. Results show that the proposed method significantly enhances the web-based interactive visual analytics of large multi-dimensional data.

cs.CV↗

arXiv2019

MPC-Based Precision Cooling Strategy (PCS) for Efficient Thermal Management of Automotive Air Conditioning System

In this paper, we propose an MPC-based precision cooling strategy (PCS) for energy efficient thermal management of automotive air conditioning (A/C) system. The proposed PCS is able to provide precise tracking of the time-varying cooling power trajectory, which is assumed to match the passenger comfort requirements. In addition, by leveraging the emerging connected and automated vehicles (CAVs) technology, vehicle speed preview can be incorporated in our A/C thermal management strategy for further energy efficiency improvement. This proposed A/C thermal management strategy is developed and evaluated based on a physics-based A/C system model (ACSim) from Ford Motor Company for the vehicles with electrified powertrains. In a comparison with Ford benchmark case over SC03 cycle, for tracking the same cooling power trajectory, the proposed PCS provides 4.9% energy saving at the cost of a slight increase in the cabin temperature (less than 1$^oC$). It is also demonstrated that by coordinating with future vehicle speed and shifting the A/C power load, the A/C energy consumption can be further reduced.

eess.SY↗

arXiv2019

Forward and Backward Knowledge Transfer for Sentiment Classification

This paper studies the problem of learning a sequence of sentiment classification tasks. The learned knowledge from each task is retained and used to help future or subsequent task learning. This learning paradigm is called Lifelong Learning (LL). However, existing LL methods either only transfer knowledge forward to help future learning and do not go back to improve the model of a previous task or require the training data of the previous task to retrain its model to exploit backward/reverse knowledge transfer. This paper studies reverse knowledge transfer of LL in the context of naive Bayesian (NB) classification. It aims to improve the model of a previous task by leveraging future knowledge without retraining using its training data. This is done by exploiting a key characteristic of the generative model of NB. That is, it is possible to improve the NB classifier for a task by improving its model parameters directly by using the retained knowledge from other tasks. Experimental results show that the proposed method markedly outperforms existing LL baselines.

cs.AI↗

arXiv2019

Integrated Optimization of Power Split, Engine Thermal Management, and Cabin Heating for Hybrid Electric Vehicles

Cabin heating demand and engine efficiency degradation in cold weather lead to considerable increase in fuel consumption of hybrid electric vehicles (HEVs), especially in congested traffic conditions. This paper presents an integrated power and thermal management (i-PTM) scheme for the optimization of power split, engine thermal management, and cabin heating of HEVs. A control-oriented model of a power split HEV, including power and thermal loops, is developed and experimentally validated against data collected from a 2017 Toyota Prius HEV. Based on this model, the dynamic programming (DP) technique is adopted to derive a bench-mark for minimal fuel consumption, using 2-dimensional (power split and engine thermal management) and 3-dimensional (power split, engine thermal management, and cabin heating) formulations. Simulation results for a real-world congested driving cycle show that the engine thermal effect and the cabin heating requirement can significantly influence the optimal behavior for the power management, and substantial potential on fuel saving can be achieved by the i-PTM optimization as compared to conventional power and thermal management strategies.

eess.SY↗