Search

Anomaly detection plays a key role in air quality analysis by enhancing situational awareness and alerting users to potential hazards. However, existing anomaly detection approaches for air quality analysis have their own limitations regarding parameter selection (e.g., need for extensive domain knowledge), computational expense, general applicability (e.g., require labeled data), interpretability, and the efficiency of analysis. Furthermore, the poor quality of collected air quality data (inconsistently formatted and sometimes missing) also increases the difficulty of analysis substantially. In this paper, we systematically formulate design requirements for a system that can solve these limitations and then propose AQEyes, an integrated visual analytics system for efficiently monitoring, detecting, and examining anomalies in air quality data. In particular, we propose a unified end-to-end tunable machine learning pipeline that includes several data pre-processors and featurizers to deal with data quality issues. The pipeline integrates an efficient unsupervised anomaly detection method that works without the use of labeled data and overcomes the limitations of existing approaches. Further, we develop an interactive visualization system to visualize the outputs from the pipeline. The system incorporates a set of novel visualization and interaction designs, allowing analysts to visually examine air quality dynamics and anomalous events in multiple scales and from multiple facets. We demonstrate the performance of this pipeline through a quantitative evaluation and show the effectiveness of the visualization system using qualitative case studies on real-world datasets., 11 pages, 6 figures

Air pollution has long been a serious environmental health challenge, especially in metropolitan cities, where air pollutant concentrations are exacerbated by the street canyon effect and high building density. Whilst accurately monitoring and forecasting air pollution are highly crucial, existing data-driven models fail to fully address the complex interaction between air pollution and urban dynamics. Our Deep-AIR, a novel hybrid deep learning framework that combines a convolutional neural network with a long short-term memory network, aims to address this gap to provide fine-grained city-wide air pollution estimation and station-wide forecast. Our proposed framework creates 1x1 convolution layers to strengthen the learning of cross-feature spatial interaction between air pollution and important urban dynamic features, particularly road density, building density/height, and street canyon effect. Using Hong Kong and Beijing as case studies, Deep-AIR achieves a higher accuracy than our baseline models. Our model attains an accuracy of 67.6%, 77.2%, and 66.1% in fine-grained hourly estimation, 1-hr, and 24-hr air pollution forecast for Hong Kong, and an accuracy of 65.0%, 75.3%, and 63.5% for Beijing. Our saliency analysis has revealed that for Hong Kong, street canyon and road density are the best estimators for NO2, while meteorology is the best estimator for PM2.5.

While end-to-end neural machine translation (NMT) has achieved notable success in the past years in translating a handful of resource-rich language pairs, it still suffers from the data scarcity problem for low-resource language pairs and domains. To tackle this problem, we propose an interactive multimodal framework for zero-resource neural machine translation. Instead of being passively exposed to large amounts of parallel corpora, our learners (implemented as encoder-decoder architecture) engage in cooperative image description games, and thus develop their own image captioning or neural machine translation model from the need to communicate in order to succeed at the game. Experimental results on the IAPR-TC12 and Multi30K datasets show that the proposed learning mechanism significantly improves over the state-of-the-art methods., Comment: Published at AAAI-18

Facial expressions play an important role in conveying the emotional states of human beings. Recently, deep learning approaches have been applied to image recognition field due to the discriminative power of Convolutional Neural Network (CNN). In this paper, we first propose a novel Multi-Region Ensemble CNN (MRE-CNN) framework for facial expression recognition, which aims to enhance the learning power of CNN models by capturing both the global and the local features from multiple human face sub-regions. Second, the weighted prediction scores from each sub-network are aggregated to produce the final prediction of high accuracy. Third, we investigate the effects of different sub-regions of the whole face on facial expression recognition. Our proposed method is evaluated based on two well-known publicly available facial expression databases: AFEW 7.0 and RAF-DB, and has been shown to achieve the state-of-the-art recognition accuracy., Comment: 10pages, 5 figures, Accepted by ICANN 2018

The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework to learn a more discriminative metric space by augmenting the classification loss function with a large margin distance loss function for training. Extensive experiments on two state-of-the-art few-shot learning methods, graph neural networks and prototypical networks, show that our method can improve the performance of existing models substantially with very little computational overhead, demonstrating the effectiveness of the large margin principle and the potential of our method., Comment: 17 pages, 5 figures, 7 tables

In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first stage--retrieval stage--, an off-the-shelf, black-box search engine is used to retrieve a small subset of sentence pairs from a training set given a source sentence. These pairs are further filtered based on a fuzzy matching score based on edit distance. In the second stage--translation stage--, a novel translation model, called translation memory enhanced NMT (TM-NMT), seamlessly uses both the source sentence and a set of retrieved sentence pairs to perform the translation. Empirical evaluation on three language pairs (En-Fr, En-De, and En-Es) shows that the proposed approach significantly outperforms the baseline approach and the improvement is more significant when more relevant sentence pairs were retrieved., Accepted by AAAI 2018

We report an inconsistency found in probability theory (also referred to as measure-theoretic probability). For probability measures induced by real-valued random variables, we deduce an "equality" such that one side of the "equality" is a probability, but the other side is not. For probability measures induced by extended random variables, we deduce an "equality" such that its two sides are unequal probabilities. The deduced expressions are erroneous only when it can be proved that measure-theoretic probability is a theory free from contradiction. However, such a proof does not exist. The inconsistency appears only in the theory rather than in the physical world, and will not affect practical applications as long as ideal events in the theory (which will not occur physically) are not mistaken for observable events in the real world. Nevertheless, unlike known paradoxes in mathematics, the inconsistency cannot be explained away and hence must be resolved. The assumption of infinite additivity in the theory is relevant to the inconsistency, and may cause confusion of ideal events and real events. As illustrated by an example in this article, since abstract properties of mathematical entities in theoretical thinking are not necessarily properties of physical quantities observed in the real world, mistaking the former for the latter may lead to misinterpreting random phenomena observed in experiments with microscopic systems. Actually the inconsistency is due to the notion of "numbers" adopted in conventional mathematics. A possible way to resolve the inconsistency is to treat "numbers" from the viewpoint of constructive mathematics., 15 pages, 1 figure

Previous neural machine translation models used some heuristic search algorithms (e.g., beam search) in order to avoid solving the maximum a posteriori problem over translation sentences at test phase. In this paper, we propose the \textit{Gumbel-Greedy Decoding} which trains a generative network to predict translation under a trained model. We solve such a problem using the Gumbel-Softmax reparameterization, which makes our generative network differentiable and trainable through standard stochastic gradient methods. We empirically demonstrate that our proposed model is effective for generating sequences of discrete words.

Existing approaches to neural machine translation condition each output word on previously generated outputs. We introduce a model that avoids this autoregressive property and produces its outputs in parallel, allowing an order of magnitude lower latency during inference. Through knowledge distillation, the use of input token fertilities as a latent variable, and policy gradient fine-tuning, we achieve this at a cost of as little as 2.0 BLEU points relative to the autoregressive Transformer network used as a teacher. We demonstrate substantial cumulative improvements associated with each of the three aspects of our training strategy, and validate our approach on IWSLT 2016 English-German and two WMT language pairs. By sampling fertilities in parallel at inference time, our non-autoregressive model achieves near-state-of-the-art performance of 29.8 BLEU on WMT 2016 English-Romanian., Comment: Accepted by ICLR 2018

Due to the increasing concern for greenhouse gas emissions and fossil fuel security, electric vehicles (EVs) have attracted much attention in recent years. EVs can aggregate together constituting the vehicle-to-grid system. Coordination of EVs is beneficial to the power system in many ways. In this paper, we formulate a novel large-scale EV charging problem with energy trading in order to maximize the aggregator profit. This problem is non-convex and can be solved with a centralized iterative approach. To overcome the computation complexity issue brought by the non-convexity, we develop a distributed optimization-based heuristic. To evaluate our proposed approach, a modified IEEE 118 bus testing system is employed with 10 aggregators serving 30 000 EVs. The simulation results indicate that our proposed distributed heuristic with energy trading can effectively increase the total profit of aggregators. In addition, the proposed distributed optimization-based heuristic strategy can achieve near-optimal performance.

Vehicular energy network (VEN) is a vehicular network which can transport energy over a large geographical area by means of electric vehicles (EVs). In the near future, an abundance of EVs, plentiful generation of the renewables, and mature wireless energy transfer and vehicular communication technologies will expedite the realization of VEN. To transmit energy from a source to a destination, we need to establish energy paths, which are composed of segments of vehicular routes, while satisfying various design objectives. In this paper, we develop a method to construct all energy paths for a particular energy source-destination pair, followed by some analytical results of the method. We describe how to utilize the energy paths to develop optimization models for different design goals and propose two solutions. We also develop a heuristic for the power loss minimization problem. We compare the performance of the three solution methods with artificial and real-world traffic networks and provide a comprehensive comparison in terms of solution quality, computation time, solvable problem size, and applicability. This paper lays the foundations of VEN routing., 13 pages

Resource-constrained systems are prevalent in communications. Such a system is composed of many components but only some of them can be allocated with resources such as time slots. According to the amount of information about the system, algorithms are employed to allocate resources and the overall system performance depends on the result of resource allocation. We do not always have complete information, and thus, the system performance may not be satisfactory. In this work, we propose a general model for the resource-constrained communication systems. We draw the relationship between system information and performance and derive the performance bounds for the optimal algorithm for the system. This gives the expected performance corresponding to the available information, and we can determine if we should put more efforts to collect more accurate information before actually constructing an algorithm for the system. Several examples of applications in communications to the model are also given., Submitted to IEEE Transactions on Communications

A number has the "collective" property if the number is the greatest lower bound of a bounded, strictly decreasing sequence on the real line. We prove that numbers with the collective property constitute an empty set., 4 pages

This report presents the results of an evaluation of project in which spread spectrum radio networks (SSRN) were used for traffic monitoring and control in the City of Los Angeles. The focus of SSRN is to reduce construction costs, construction time and future plant maintenance costs. A field operational test was conducted to test and evaluate the applicability of SSRN communications in traffic control.

The objective of this study is to address the communication system design issues of Intelligent Vehicle Highway Systems (IVHS). The focus of Phase I of this research is the design for California Advanced Driver Information Systems (CADIS). The emphasis is on the architecture and topology aspects of the physical link and access layers connecting the moving layers with the fixed infrastructure. The work is divided into the following categories: Automatic Vehicle Identification (AVI), IVHS communications survey and functional requirements, modeling of IVHS fading channels, multiple-access performance analysis, simulation for IVHS communications, system layout and architectural tradeoffs, throughput/ delay analysis, and FM Subcarrier and the IVHS environment.

© Springer-Verlag London 2014. Smart grids have attracted significant attention lately, and one can even speak of hype. However, much of the attention is paid to the distribution side and consumer interaction. Nevertheless, also at the transmission-level important improvements can be achieved through farsighted and careful intelligent grid design and implementation. This chapter describes and proposes a realistic research agenda in which smart transmission grid (STG) research may operate, with focus on operational planning and operations of the pan-European electricity grid. Firstly, a research outlook seen from current European policy is laid out to redefine the most consequential research directions liked to the needs of transmission systems from real time up to planning. Secondly, operations (real time to hours) of the transmission system are discussed, and monitoring and control technologies that can be achieved through the application of synchronized phasor measurement technology are highlighted as a means toward a STG. Next, challenges related to planning (hours to years) are discussed keeping in mind the need of flexibility, coordination, and new methods for assessing system security. Going beyond the purely academic point of view, this chapter specifically aims to bring a realistic approach toward research for electric power transmission to be able to transform into a STG. ispartof: Smart Grid Applications and Developments pages:185-220 ispartof: SMART GRID APPLICATIONS AND DEVELOPMENTS issue:9781447162803 pages:185-220 status: published