Remote sensing is considered to be a key technology for the development of smart cities. By analysing the data obtained by remote sensing, it is effective to manage and develop smart cities. However, with the rapid urbanisation and the increase in data capacity, how to store and retrieve remote sensing data which have more potential value and privacy with a more effective and safe method has become an imminent issue. In this paper, we propose an efficient verifiable and dynamic multi-keyword searchable encryption scheme for remote sensing data in smart cities. Moreover, we construct a double-chain index to support a multi-keyword search, where the Verification Index Chain is used to identify the users and the Keyword Index Chain is used to store the information of keywords. In addition, we adopt extended bitmap technology to realise update operations and verify the correctness and integrity of the search results. Experiments show that compared to the related existing schemes, the search time of the proposed scheme is reduced by 35% at most, the verification time is reduced by 14% at most and the update time is reduced by 57% at most.

In an intelligent edge network, data owners encrypt data and outsource it to the edge servers to prevent the leakage of data and user information. It is a research issue to achieve efficient search and data update of the ciphertext stored in the edge servers. For the above problems, we construct a fuzzy multi-keyword search scheme based on a two-level tree index, where the first-level tree index stores keyword tags and the second-level stores encrypted file identifiers and counting bloom filters (CBFs). By constructing a two-level tree index, efficient multi-keyword search is realised, and it also has obvious time advantages when performing the single-keyword search. In addition, the proposed scheme supports index updating by introducing the CBF, and it can realise fuzzy search by calculating the inner product between the CBF in index and search trapdoor. At last, the proposed scheme is proved to be semantically secure under the known ciphertext attack model. Theoretical analysis and simulation test indicate that the proposed scheme spends lower computation overhead than other related schemes, especially in the search phase; as the number of matching files or query keywords grows, it costs less time, at around 2–10 ms.

With the development of social media, the increasing online reviews of products are greatly influencing the electronic market, making sentiment classification the topic of interest for both industry and academia. This paper develops a sentence-based language model to perform sentiment classification at a fine-grained sentence level. The proposed approach applies a machine learning method to determine the sentiment polarity of a sentence at first, then designs statistical algorithm to compute the weight of the sentence in sentiment classification of the whole document and at last aggregates the weighted sentence to predict the sentiment polarity of document. Besides, experiments are carried out on corpuses in different evaluation domains and languages, and the results demonstrate the effectiveness of the sentence-based approach in obtaining a more accurate result of sentiment classification across different reviews. Furthermore, the experimental results also indicate that the position and the sentiment of a sentence have great impact on predicting the sentiment polarity of document, and corpuses with different evaluative objects, languages and sentiments also greatly influence the performance of sentiment classification. It is believed that these conclusions will be a good inspiration for similar researches.

In order to meet the requirement of customised services for online communities, sentiment classification of online reviews has been applied to study the unstructured reviews so as to identify users’ opinions on certain products. The purpose of this article is to select features for sentiment classification of Chinese online reviews with techniques well performed in traditional text classification. First, adjectives, adverbs and verbs are identified as the potential text features containing sentiment information. Then, four statistical feature selection methods, such as document frequency (DF), information gain (IG), chi-squared statistic (CHI) and mutual information (MI), are adopted to select features. After that, the Boolean weighting method is applied to set feature weights and construct a vector space model. Finally, a support vector machine (SVM) classifier is employed to predict the sentiment polarity of online reviews. Comparative experiments are conducted based on hotel online reviews in Chinese. The results indicate that the highest accuracy of the sentiment classification of Chinese online reviews is achieved by taking adjectives, adverbs and verbs together as the feature. Besides that, different feature selection methods make distinct performances on sentiment classification, as DF performs the best, CHI follows and IG ranks the last, whereas MI is not suitable for sentiment classification of Chinese online reviews. This conclusion will be helpful to improve the accuracy of sentiment classification and be useful for further research.

This paper presents an automatic segmentation algorithm for video frames captured by a (monocular) webcam that closely approximates depth segmentation from a stereo camera. The frames are segmented into foreground and background layers that comprise a subject (participant) and other objects and individuals. The algorithm produces correct segmentations even in the presence of large background motion with a nearly stationary foreground. This research makes three key contributions: First, we introduce a novel motion representation, referred to as "motons," inspired by research in object recognition. Second, we propose estimating the segmentation likelihood from the spatial context of motion. The estimation is efficiently learned by random forests. Third, we introduce a general taxonomy of tree-based classifiers that facilitates both theoretical and experimental comparisons of several known classification algorithms and generates new ones. In our bilayer segmentation algorithm, diverse visual cues such as motion, motion context, color, contrast, and spatial priors are fused by means of a conditional random field (CRF) model. Segmentation is then achieved by binary min-cut. Experiments on many sequences of our videochat application demonstrate that our algorithm, which requires no initialization, is effective in a variety of scenes, and the segmentation results are comparable to those obtained by stereo systems.

We perform real-time American Sign Language (ASL) phrase verification for an educational game, CopyCat, which is designed to improve deaf children's signing skills. Taking advantage of context information in the game we verify a phrase, using Hidden Markov Models (HMMs), by applying a rejection threshold on the probability of the observed sequence for each sign in the phrase. We tested this approach using 1204 signed phrase samples from 11 deaf children playing the game during the phase two deployment of CopyCat. The CopyCat data set is particularly challenging because sign samples are collected during live game play and contain many variations in signing and disfluencies. We achieved a phrase verification accuracy of 83% compared to 90% real-time performance by a sign linguist. We report on the techniques required to reach this level of performance.

The natural language for most deaf signers in the United States is American Sign Language (ASL). ASL has internal structure like spoken languages, and ASL linguists have introduced several phonemic models. The study of ASL phonemes is not only interesting to linguists, but also useful for scalability in recognition by machines. Since machine perception is different than human perception, this paper learns the basic units for ASL directly from data. Comparing with previous studies, our approach computes a set of data-driven units (fenemes) discriminatively from the results of segmental feature selection. The learning iterates the following two steps: first apply discriminative feature selection segmentally to the signs, and then tie the most similar temporal segments to re-train. Intuitively, the sign parts indistinguishable to machines are merged to form basic units, which we call ASL fenemes. Experiments on publicly available ASL recognition data show that the extracted data-driven fenemes are meaningful, and recognition using those fenemes achieves improved accuracy at reduced model complexity.

We address the feature selection problem for hidden Markov models (HMMs) in sequence classification. Temporal correlation in sequences often causes difficulty in applying feature selection tech niques. Inspired by segmental k-means segmentation (SKS) [B. Juang and L. Rabiner, 1990], we propose Segmentally Boosted HMMs (SBHMMs), where the state-optimized features are constructed in a segmental and discriminative manner. The contributions are twofold. First, we introduce a novel feature selection algorithm, where the temporal dynamics are decoupled from the static learning procedure by assuming that the sequential data are piecewise independent and identically distributed. Second, we show that the SBHMM consistently improves traditional HMM recognition in various domains. The reduction of error compared to traditional HMMs ranges from 17% to 70% in American Sign Language recognition, human gait identification, lip reading, and speech recognition.

Identifying the active speaker in a video of a distributed meeting can be very helpful for remote participants to understand the dynamics of the meeting. A straightforward application of such analysis is to stream a high resolution video of the speaker to the remote participants. In this paper, we present the challenges we met while designing a speaker detector for the Microsoft RoundTable distributed meeting device, and propose a novel boosting-based multimodal speaker detection (BMSD) algorithm. Instead of separately performing sound source localization (SSL) and multiperson detection (MPD) and subsequently fusing their individual results, the proposed algorithm fuses audio and visual information at feature level by using boosting to select features from a combined pool of both audio and visual features simultaneously. The result is a very accurate speaker detector with extremely high efficiency. In experiments that includes hundreds of real-world meetings, the proposed BMSD algorithm reduces the error rate of SSL-only approach by 24.6%, and the SSL and MPD fusion approach by 20.9%. To the best of our knowledge, this is the first real-time multimodal speaker detection algorithm that is deployed in commercial products.

This paper presents an algorithm for the automatic segmentation of monocular videos into foreground and background layers. Correct segmentations are produced even in the presence of large background motion with nearly stationary foreground. There are three key contributions. The first is the introduction of a novel motion representation, "motons", inspired by research in object recognition. Second, we propose learning the segmentation likelihood from the spatial context of motion. The learning is efficiently performed by Random Forests. The third contribution is a general taxonomy of tree-based classifiers, which facilitates theoretical and experimental comparisons of several known classification algorithms, as well as spawning new ones. Diverse visual cues such as motion, motion context, colour, contrast and spatial priors are fused together by means of a conditional random field (CRF) model. Segmentation is then achieved by binary min-cut. Our algorithm requires no initialization. Experiments on many video-chat type sequences demonstrate the effectiveness of our algorithm in a variety of scenes. The segmentation results are comparable to those obtained by stereo systems.

Speaker detection is a very important task in distributed meeting applications. This paper discusses a number of challenges we met while designing a speaker detector for the Microsoft RoundTable distributed meeting device, and proposes a boosting-based multimodal speaker detection (BMSD) algorithm. Instead of performing sound source localization (SSL) and multi-person detection (MPD) separately and subsequently fusing their individual results, the proposed algorithm uses boosting to select features from a combined pool of both audio and visual features simultaneously. The result is a very accurate speaker detector with extremely high efficiency. The algorithm reduces the error rate of SSL-only approach by 47%, and the SSL and MPD fusion approach by 27%

Text superimposed on the video frames provides supplemental but important information for video indexing and retrieval. Many efforts have been made for videotext detection and recognition (video OCR). The main difficulties of video OCR are the low resolution and the background complexity. We present efficient schemes to deal with the second difficulty by sufficiently utilizing multiple frames that contain the same text to get every clear word from these frames. Firstly, we use multiple frame verification to reduce text detection false alarms. We then choose those frames where the text is most likely clear, thus it is more possible to be correctly recognized. We then detect and joint every clear text block from those frames to form a clearer "man-made" frame. Later we apply a block-based adaptive thresholding procedure on these "man-made" frames. Finally, the binarized frames are sent to an OCR engine for recognition. Experiments show that the word recognition rate has been increased over 28% by these methods.