Search

An liquid crystal on silicon (LCoS)-based access node using optical fibers as the transmitter and receiver to deliver high-speed data transmission is proposed and experimentally demonstrated. This access node can be applied to a variety of networks ranging from passive optical networks to indoor home area networks through optical wireless communications without optical/electrical/optical (O/E/O) conversions. The link of system, which operates over ~2.5 m with a possible wide field-of-view of nearly 97°, has been achieved through the implementation of a LCoS-based spatial light modulator in conjunction with a static grating element. A bidirectional optical wireless communication system was established to demonstrate the concept and evaluate the performance of the proposed access node, which uses typical WDM wavelengths (the channel spacing is 100 GHz) and is modulated at a data speed of more than 2.5 Gb/s. The results show that in downlink transmission, the multiple wavelengths delivered from optical fibers can be dynamically transmitted directly to the terminal users through the proposed access node architecture without performing any O/E/O conversion. Similarly in uplink transmission, all the wavelengths received at the proposed node architecture can be arbitrarily switched to a desired output fiber port of the access node to connect with the external fiber networks in the same manner. The bit error ratios of all the transmitted wavelengths in both uplink and downlink transmission scenarios are less than 10-9.

Cyber-physical systems feature the interplay of cyber-network intelligence and physical system dynamics. Agents of artificial intelligence making decisions based on observations result in physical interactions to form social networks in cyber and physical domains. In this paper, we introduce a multi-agent decision model which forms interactive social networks for multi-dimensional physical states and agent decisions. In particular, the cyber and physical interactions in a sequential smart manufacturing process are treated as a collaborative cyber-physical multi-agent system. As the social network topology influences both of the cyber behavior and physical dynamics, we investigate the impacts of different network topologies on the collective performance of cyber-physical system. Numerical results about smart factory uniquely uncover critical factors in the network design for collaborative cyber-physical systems.

The operation of autonomous multi-agent systems (MAS) under the complex interactions among intelligent agents heavily relies on the consensus protocols to facilitate multi-agent collaboration. In this paper, we novelly study the coordination and control strategy for robust consensus building in a distributed MAS of bayesian social learning agents that make sequential decisions with finite horizon. Unlike the conventional consensus problems in literature, the idiosyncratic information cascading behavior arising from multi-agent social learning poses a new challenge to consensus protocol design. Although cascading can alleviate randomness and enhance consensus, cascading in the early stages of sequential decision making may cause error-prone bifurcation behavior. Therefore, how to properly utilize the advantage of information cascade and meanwhile mitigating its undesirable side effect is critical in the design of consensus protocol to control distributed MAS of social learning agents. Considering communication topology, we uniquely develop a robust cascading strategy for agents adapting to local network neighborhood. Our results show that the proposed strategy not only mitigates early cascading failures but also guarantees multiagent consensus in various complex network topologies.

Information cascade characterizes the situation where rational agents are overloaded with social observations and can make decisions ignoring their own personal evidence. If the social observations are misleading, the overall system performance can be subsequently compromised. Therefore, it is of interests to design a socially or interactively networked system falling into undesirable or desirable cascades. In this paper, we study the driving factors of steering information cascades in a socially networked system by considering a sequential Bayesian social learning model with arbitrary network topology and utility function. In particular, we analyze the impacts from different random network topologies on the overall system performance such as error probability, fraction of cascades, and total utility. Furthermore, we demonstrate two systematic approaches, selective rewiring and incentive seeding, which can change the information structure observed by agents and hence steer information cascades. Our results show that when agents restructure their observation network and provide proper incentives for cascades in the correct decisions, the overall social system performance can be well-steered.

Approximate nearest neighbor search is an efficient strategy for large-scale image retrieval. Encouraged by the recent advances in convolutional neural networks (CNNs), we propose an effective deep learning framework to generate binary hash codes for fast image retrieval. Our idea is that when the data labels are available, binary codes can be learned by employing a hidden layer for representing the latent concepts that dominate the class labels. The utilization of the CNN also allows for learning image representations. Unlike other supervised methods that require pair-wised inputs for binary code learning, our method learns hash codes and image representations in a point-wised manner, making it suitable for large-scale datasets. Experimental results show that our method outperforms several state-of-the-art hashing algorithms on the CIFAR-10 and MNIST datasets. We further demonstrate its scalability and efficacy on a large-scale dataset of 1 million clothing images.

With the rapid development of e-commerce and explosive growth of online shopping market, the problem of how to optimize the process of guiding the user to the huge amount of online products have been urgent. Existing recommender systems use information from users' profiles (demographic filtering), similar neighbors (collaborative filtering), and textual description (content-based model) to make recommendations, which easily generate irrelevant suggestions to users due to the ignorance of users' intentions and the visual similarity among products. In this paper, we proposed an interactive product recommendation method, which considers not only the product diversity but also the visual similarity, to interactively capture a user's real intention and refine the product recommendation result based on the user's real product interests. Our algorithm is experimentally evaluated under a real-world user log, and shown to significantly improve recommendation accuracy over the traditional approaches.

Good eating habits are important for maintaining a healthy life and preventing the lifestyle-related disease epidemic. Researches about menu recommendation or diet planning are thus attracting much attention recently. A key factor toward a successful diet planning is an individual's food preference instead of dogmatic nutrition pattern since it is unlikely that an individual would accept the meal plan merely based on the nutrition supplements. However, the extraction of personal preference is definitely not a trivial matter. In this paper, we present the k-comparative annotation and reasoning technique for semi-automatically extracting users' preferences in a more efficient and effective manner. Comparing to conventional methods, the proposed system can not only reveal users' opinions about foods more fairly but also save lots of food annotation efforts during the training data collection stage. The resulted system is thus expected to improve users' diet habit and compliance with healthier lifestyle.

Care coordination services bring together a multitude of providers to deliver continuity of care outside clinical settings. The coordinated services improve wellness management and operational outcomes but pose challenges on privacy when integrating multiple sources of personal health data and providing a data access and sharing mechanism to third party providers. In this paper, we particularly address the privacy challenges associated with data integration and sharing in a multi-tenant cloud environment for healthcare. We present three care coordination use cases and detail the functional requirements across different stages of a personal data service cycle. Additionally, reflecting on technical challenges associated with privacy-preserving data integration and sharing, we introduce a set of common data services to handle these issues, which ultimately lend support to the development of accountable coordinated care services.

With the number of people considered to be obese and having chronic disease rising across the world, the role of IT solution in nutrition management and planning has been receiving increased attention by medical professionals in recent years. A key factor toward a successful personalized nutrition planning is an individual's food preference instead of dogmatic nutrition pattern since it is unlikely that an individual would accept the meal plan merely based on the nutrition supplements. However, personal preferences about foods are obviously relatively harder to acquire comparing to common nutrition requirements that can be easily obtained from guidelines. In this paper, we proposed a personalized nutrition planning method based on random walks theory to maximize the planning satisfaction. The personal guidelines generated by the proposed method are expected to potentially improve the healthy diet compliance and thus reduce the risk of chronic diseases of individuals.

One current direction to enhance the search accuracy in visual object retrieval is to reformulate the original query through (pseudo-)relevance feedback, which augments a query with visual terms from the image documents most highly ranked by an initial search or identified by user. However, query and feedback images usually contain multiple objects or aspects, and as a consequence the original query's focus may drift because of the newly added terms and noises. The results of using an augmented query are thus often inferior to that of using only the original one. In this paper we propose the topic-sensitive image retrieval with noise-proof relevance feedback to address the query drift problem in visual object retrieval. The proposed method removes irrelevant noises and topics from both query and feedback images to prevent query drift. A discriminative learning strategy is then employed to re-rank and improve the initial search result. Experiments on a real world data set demonstrate the effectiveness of our approach and show that the proposed approach can better learn user intention.

Effective personal dietary guidelines are essential for health management and preventing chronic diseases. The objective of this research is to achieve nutrient-balanced food recommendations for each individual, while considering individual's requirements at the same time. To reach this goal, we developed a location-aware interactive diet consultant named SmartDiet based on the multi-objective optimization. The proposed personalized diet planning approach not only translates nutrient recommendations into realistic dish choices, but also accepts feedbacks from users to fine-tune their meal plans. The results showed that daily nutrition needs can be fulfilled by the designated meals, and the interactive diet planning scheme helps a user adjust the plan in an easier way. The guidelines generated by SmartDiet are expected to potentially improve the overall health and reduce the risk of chronic diseases of individuals.

We study the problem of event detection from realistic videos with repetitive sequential human activities. Despite the large body of work on event detection and recognition, very few have addressed low-quality videos captured from realistic environments. Our framework is based on solving the shortest path on a temporal-event graph constructed from the video content. Graph vertices correspond to detected event primitives, and edge weights are set according to generic knowledge of the event patterns and the discrepancy between event primitives based on a greedy matching of their visual features. Experimental results on videos collected from a retail environment validate the usefulness of the proposed approach.

One leading framework for image object mining is the bag-of-words (BOW) approach. The idea is to encode an image as a collection of visual words of the quantized local patches. Objects in the image can then be retrieved through inferring the semantic topics associated with the set of visual words. However, the visual BOW mining framework is apt to suffer from the so-called term-mismatch problem (a.k.a. vocabulary problem). This is caused by the poverty of query information, and consequently becomes an obstacle to deal with synonymy (i.e., different visual words for describing the same object). In this paper, we propose a novel language-model-based approach with pseudo-relevance feedback for addressing the vocabulary problem in visual BOW mining. We employ the pseudo positive images produced in response to the original query as a set of "cues" to gradually refine the query language model. Unlike traditional approaches that only ruggedly append feedback information into the original query, the proposed approach reconstructs the query language model with finer granularities so that the query concepts can be captured more accurately. The proposed approach is experimentally evaluated using two different types of image object databases. Our algorithms are shown to bring significant improvement in the retrieval accuracy over a non-feedback baseline, and achieve better performance than conventional feedback approaches.

We aim to improve the bag-of-visual-words (BOW) model for near-duplicate image retrieval, by introducing a more fine-grained pseudo-relevance feedback process. The BOW method is based on vector quantization of affine invariant descriptors of image patches. Despite its popularity and simplicity, the retrieval performance of BOW is often unsatisfactory due to the large and diverse variations of near-duplicate images. We thus propose an information-theoretic feedback framework that employs available cues in the search result to find more relevant duplicate images which are hard to retrieve by using conventional BOW approaches. Our algorithm is experimentally evaluated under a severely attacked image database, and shown to significantly improve the retrieval accuracy over a non-feedback baseline.

In the past, many researches on image copy detection focused on finding a feature that is robust enough for various kinds of image attacks. But it is difficult to find a globally effective feature that is appropriate for many situations. In this paper, we introduce a classification framework to this problem, instead of solving the feature-selection problem. In our approach, novel features are generated by applying virtual prior attacks to copyrighted images, and the copy-detection problem is converted to a classification one that is more robust to solve. Our approach can combine existing image copy detectors and further raise their performances.