Handwriting difficulties (HWDs) in children have adverse effects on their confidence and academic progress. Detecting HWDs is the first crucial step toward clinical or teaching intervention for children with HWDs. To date, how to automatically detect HWDs is still a challenge, although digitizing tablets have provided an opportunity to automatically collect handwriting process information. Especially, to our best knowledge, there is no exploration into the potential of combining machine learning algorithms and the handwriting process information to automatically detect Chinese HWDs in children. To bridge the gap, we first conducted an experiment to collect sample data and then compared the performance of five commonly used classification algorithms (Decision tree, Support Vector Machine (SVM), Artificial Neural Network, Naïve Bayesian and k-Nearest Neighbor) in detecting HWDs. The results showed that: (1) only a small proportion (13%) of children had Chinese HWDs and each classification model on the imbalanced dataset (39 children at risk of HWDs versus 261 typical children) produced the results that were better than random guesses, indicating the possibility of using classification algorithms to detect Chinese HWDs; (2) the SVM model had the best performance in detecting Chinese HWDs among the five classification models; and (3) the performance of the SVM model, especially its sensitivity, could be significantly improved by employing the Synthetic Minority Oversampling Technique to handle the class-imbalanced data. This study gains new insights into which handwriting features are predictive of Chinese HWDs in children and proposes a method that can help the clinical and educational professionals to automatically detect children at risk of Chinese HWDs.
In the model of no-dictionary searchable symmetric encryption (SSE) schemes, the client does not need to keep the list of keywords W. In this paper, we first show a generic method to transform any passively secure SSE scheme to a no-dictionary SSE scheme such that the client can verify search results even if w ∉ W. In particular, it takes only O(1) time for the server to prove that w ∉ W. We next present a no-dictionary SSE scheme such that the client can hide even the search pattern from the server.
We introduce a notion of watermarking for cryptographic functions and propose a concrete scheme for watermarking cryptographic functions. Informally speaking, a digital watermarking scheme for cryptographic functions embeds information, called a mark, into functions such as one-way functions and decryption functions of public-key encryption. There are two basic requirements for watermarking schemes. A mark-embedded function must be functionally equivalent to the original function. It must be difficult for adversaries to remove the embedded mark without damaging the original functionality. In spite of its importance and usefulness, there have only been a few theoretical works on watermarking for functions (or programs). Furthermore, we do not have rigorous definitions of watermarking for cryptographic functions and concrete constructions. To solve the problem above, we introduce a notion of watermarking for cryptographic functions and define its security. Furthermore, we present a lossy trapdoor function (LTF) based on the decisional bilinear Diffie-Hellman problem problem and a watermarking scheme for the LTF. Our watermarking scheme is secure under the symmetric external Diffie-Hellman assumption in the standard model. We use techniques of dual system encryption and dual pairing vector spaces (DPVS) to construct our watermarking scheme. This is a new application of DPVS.
Boolean functions used in stream ciphers and block ciphers should have high second-order nonlinearity to resist several known attacks and some potential attacks which may exist but are not yet efficient and might be improved in the future. The second-order nonlinearity of Boolean functions also plays an important role in coding theory, since its maximal value equals the covering radius of the second-order Reed-Muller code. But it is an extremely hard task to calculate and even to bound the second-order nonlinearity of Boolean functions. In this paper, we present a lower bound on the second-order nonlinearity of the generalized Maiorana-McFarland Boolean functions. As applications of our bound, we provide more simpler and direct proofs for two known lower bounds on the second-order nonlinearity of functions in the class of Maiorana-McFarland bent functions. We also derive a lower bound on the second-order nonlinearity of the functions which were conjectured bent by Canteaut and whose bentness was proved by Leander, by further employing our bound.
Hee-Suk PANG Jun-seok LIM Hyun-Young JIN
We propose a new context-adaptive arithmetic coding (CAAC) scheme for lossless bit rate reduction of parametric stereo (PS) in enhanced aacPlus. Based on the probability analysis of stereo parameters indexes in PS, we propose a stereo band-dependent CAAC scheme for PS. We also propose a new coding structure of the scheme which is simple but effective. The proposed scheme has normal and memory-reduced versions, which are superior to the original and conventional schemes and guarantees significant bit rate reduction of PS. The proposed scheme can be an alternative to the original PS coding scheme at low bit rate, where coding efficiency is very important.
Kehai CHEN Tiejun ZHAO Muyun YANG
Learning semantic representation for translation context is beneficial to statistical machine translation (SMT). Previous efforts have focused on implicitly encoding syntactic and semantic knowledge in translation context by neural networks, which are weak in capturing explicit structural syntax information. In this paper, we propose a new neural network with a tree-based convolutional architecture to explicitly learn structural syntax information in translation context, thus improving translation prediction. Specifically, we first convert parallel sentences with source parse trees into syntax-based linear sequences based on a minimum syntax subtree algorithm, and then define a tree-based convolutional network over the linear sequences to learn syntax-based context representation and translation prediction jointly. To verify the effectiveness, the proposed model is integrated into phrase-based SMT. Experiments on large-scale Chinese-to-English and German-to-English translation tasks show that the proposed approach can achieve a substantial and significant improvement over several baseline systems.
Seiji MIYOSHI Yoshinobu KAJIKAWA
We analyze the behaviors of the FXLMS algorithm using a statistical-mechanical method. The cross-correlation between a primary path and an adaptive filter and the autocorrelation of the adaptive filter are treated as macroscopic variables. We obtain simultaneous differential equations that describe the dynamical behaviors of the macroscopic variables under the condition that the tapped-delay line is sufficiently long. The obtained equations are deterministic and closed-form. We analytically solve the equations to obtain the correlations and finally compute the mean-square error. The obtained theory can quantitatively predict the behaviors of computer simulations including the cases of both not only white but also nonwhite reference signals. The theory also gives the upper limit of the step size in the FXLMS algorithm.
Kento HASEGAWA Masao YANAGISAWA Nozomu TOGAWA
Recently, it has been reported that malicious third-party IC vendors often insert hardware Trojans into their products. Especially in IC design step, malicious third-party vendors can easily insert hardware Trojans in their products and thus we have to detect them efficiently. In this paper, we propose a machine-learning-based hardware-Trojan detection method for gate-level netlists using multi-layer neural networks. First, we extract 11 Trojan-net feature values for each net in a netlist. After that, we classify the nets in an unknown netlist into a set of Trojan nets and that of normal nets using multi-layer neural networks. By experimentally optimizing the structure of multi-layer neural networks, we can obtain an average of 84.8% true positive rate and an average of 70.1% true negative rate while we can obtain 100% true positive rate in some of the benchmarks, which outperforms the existing methods in most of the cases.
Wei LI Huajun GONG Chunlin SHEN Yi WU
Surface light field advances conventional light field rendering techniques by utilizing geometry information. Using surface light field, real-world objects with complex appearance could be faithfully represented. This capability could play an important role in many VR/AR applications. However, an accurate geometric model is needed for surface light field sampling and processing, which limits its wide usage since many objects of interests are difficult to reconstruct with their usually very complex appearances. We propose a novel two-step optimization framework to reduce the dependency of accurate geometry. The key insight is to treat surface light field sampling as a multi-view multi-texture optimization problem. Our approach can deal with both model inaccuracy and image to model misalignment, making it possible to create high-fidelity surface light field models without using high-precision special hardware.
Yundong LI Weigang ZHAO Xueyan ZHANG Qichen ZHOU
Crack detection is a vital task to maintain a bridge's health and safety condition. Traditional computer-vision based methods easily suffer from disturbance of noise and clutters for a real bridge inspection. To address this limitation, we propose a two-stage crack detection approach based on Convolutional Neural Networks (CNN) in this letter. A predictor of small receptive field is exploited in the first detection stage, while another predictor of large receptive field is used to refine the detection results in the second stage. Benefiting from data fusion of confidence maps produced by both predictors, our method can predict the probability belongs to cracked areas of each pixel accurately. Experimental results show that the proposed method is superior to an up-to-date method on real concrete surface images.
Tetsunao MATSUTA Tomohiko UYEMATSU
We normally hold a lot of confidential information in hard disk drives and solid-state drives. When we want to erase such information to prevent the leakage, we have to overwrite the sequence of information with a sequence of symbols independent of the information. The overwriting is needed only at places where overwritten symbols are different from original symbols. Then, the cost of overwrites such as the number of overwritten symbols to erase information is important. In this paper, we clarify the minimum cost such as the minimum number of overwrites to erase information under weak and strong independence criteria. The former (resp. the latter) criterion represents that the mutual information between the original sequence and the overwritten sequence normalized (resp. not normalized) by the length of the sequences is less than a given desired value.
Kosuke TAKAHASHI Dan MIKAMI Mariko ISOGAWA Akira KOJIMA Hideaki KIMATA
In this paper, we propose a novel method to extrinsically calibrate a camera to a 3D reference object that is not directly visible from the camera. We use a human cornea as a spherical mirror and calibrate the extrinsic parameters from the reflections of the reference points. The main contribution of this paper is to present a cornea-reflection-based calibration algorithm with a simple configuration: five reference points on a single plane and one mirror pose. In this paper, we derive a linear equation and obtain a closed-form solution of extrinsic calibration by introducing two ideas. The first is to model the cornea as a virtual sphere, which enables us to estimate the center of the cornea sphere from its projection. The second is to use basis vectors to represent the position of the reference points, which enables us to deal with 3D information of reference points compactly. We demonstrate the performance of the proposed method with qualitative and quantitative evaluations using synthesized and real data.
Chanyoung OH Saehanseul YI Youngmin YI
As energy efficiency has become a major design constraint or objective, heterogeneous manycore architectures have emerged as mainstream target platforms not only in server systems but also in embedded systems. Manycore accelerators such as GPUs are getting also popular in embedded domains, as well as the heterogeneous CPU cores. However, as the number of cores in an embedded GPU is far less than that of a server GPU, it is important to utilize both heterogeneous multi-core CPUs and GPUs to achieve the desired throughput with the minimal energy consumption. In this paper, we present a case study of mapping LBP-based face detection onto a recent CPU-GPU heterogeneous embedded platform, which exploits both task parallelism and data parallelism to achieve maximal energy efficiency with a real-time constraint. We first present the parallelization technique of each task for the GPU execution, then we propose performance and energy models for both task-parallel and data-parallel executions on heterogeneous processors, which are used in design space exploration for the optimal mapping. The design space is huge since not only processor heterogeneity such as CPU-GPU and big.LITTLE, but also various data partitioning ratios for the data-parallel execution on these heterogeneous processors are considered. In our case study of LBP face detection on Exynos 5422, the estimation error of the proposed performance and energy models were on average -2.19% and -3.67% respectively. By systematically finding the optimal mappings with the proposed models, we could achieve 28.6% less energy consumption compared to the manual mapping, while still meeting the real-time constraint.
Vince Jebryl MONTERO Yong-Jin JEONG
This paper presents an approach for developing an algorithm for automatic license plate recognition system (ALPR) on complex scenes. A plate-style classification method is also proposed in this paper to address the inherent challenges for ALPR in a system that uses multiple plate-styles (e.g., different fonts, multiple plate lay-out, variations in character sequences) which is the case in the current Philippine license plate system. Methods are proposed for each ALPR module: plate detection, character segmentation, and character recognition. K-nearest neighbor (KNN) is used as a classifier for character recognition together with a proposed confidence scoring to rate the decision made by the classifier. A small dataset of Philippine license plates but with relevant features of complex scenarios for ALPR is prepared. Using the proposed system on the prepared dataset, the performance of the system is evaluated on different categories of complex scenes. The proposed algorithm structure shows promising results and yielded an overall accuracy higher than the existing ALPR systems on the dataset consisting mostly of complex scenes.
Many single model methods have been applied to real-time short-term traffic flow prediction. However, since traffic flow data is mixed with a variety of ingredients, the performance of single model is limited. Therefore, we proposed Multi-Long-Short Term Memory Models, which improved traffic flow prediction accuracy comparing with state-of-the-art models.
A parallel phrase matching (PM) engine for dictionary compression is presented. Hardware based parallel chaining hash can eliminate erroneous PM results raised by hash collision; while newly-designed storage architecture holding PM results solved the data dependency issue; Thus, the average compression speed is increased by 53%.
Jinfa WANG Siyuan JIA Hai ZHAO Jiuqiang XU Chuan LIN
Detecting anomalies, such as network failure or intentional attack in Internet, is a vital but challenging task. Although numerous techniques have been developed based on Internet traffic, detecting anomalies from the perspective of Internet topology structure is going to be possible because the anomaly detection of structured datasets based on complex network theory has become a focus of attention recently. In this paper, an anomaly detection method for the large-scale Internet topology is proposed to detect local structure crashes caused by the cascading failure. In order to quantify the dynamic changes of Internet topology, the network path changes coefficient (NPCC) is put forward which highlights the Internet abnormal state after it is attacked continuously. Furthermore, inspired by Fibonacci Sequence, we proposed the decision function that can determine whether the Internet is abnormal or not. That is the current Internet is abnormal if its NPCC is out of the normal domain calculated using the previous k NPCCs of Internet topology. Finally the new Internet anomaly detection method is tested against the topology data of three Internet anomaly events. The results show that the detection accuracy of all events are over 97%, the detection precision for three events are 90.24%, 83.33% and 66.67%, when k=36. According to the experimental values of index F1, larger values of k offer better detection performance. Meanwhile, our method has better performance for the anomaly behaviors caused by network failure than those caused by intentional attack. Compared with traditional anomaly detection methods, our work is more simple and powerful for the government or organization in items of detecting large-scale abnormal events.
Kohei MATSUZAKI Kazuyuki TASAKA Hiromasa YANAGIHARA
We propose a feature design method for a mobile visual search based on binary features and a bag-of-visual words framework. In mobile visual search, detection error and quantization error are unavoidable due to viewpoint changes and cause performance degradation. Typical approaches to visual search extract features from a single view of reference images, though such features are insufficient to manage detection and quantization errors. In this paper, we extract features from multiview synthetic images. These features are selected according to our novel reliability measure which enables robust recognition against various viewpoint changes. We regard feature selection as a maximum coverage problem. That is, we find a finite set of features maximizing an objective function under certain constraints. As this problem is NP-hard and thus computationally infeasible, we explore approximate solutions based on a greedy algorithm. For this purpose, we propose novel constraint functions which are designed to be consistent with the match conditions in the visual search method. Experiments show that the proposed method improves retrieval accuracy by 12.7 percentage points without increasing the database size or changing the search procedure. In other words, the proposed method enables more accurate search without adversely affecting the database size, computational cost, and memory requirement.
Chuang ZHU Xiao Feng HUANG Guo Qing XIANG Hui Hui DONG Jia Wen SONG
In this paper, we propose a highly efficient mobile visual search algorithm. For descriptor extraction process, we propose a low complexity feature detection which utilizes the detected local key points of the coarse octaves to guide the scale space construction and feature detection in the fine octave. The Gaussian and Laplacian operations are skipped for the unimportant area, and thus the computing time is saved. Besides, feature selection is placed before orientation computing to further reduce the complexity of feature detection by pre-discarding some unimportant local points. For the image retrieval process, we design a high-performance reranking method, which merges both the global descriptor matching score and the local descriptor similarity score (LDSS). In the calculating of LDSS, the tf-idf weighted histogram matching is performed to integrate the statistical information of the database. The results show that the proposed highly efficient approach achieves comparable performance with the state-of-the-art for mobile visual search, while the descriptor extraction complexity is largely reduced.
Chun-Lin LIN Tzu-Hsiang LIN Ruey-Yi WEI
Bit-interleaved coded modulation with iterative decoding (BICM-ID) is suitable for correlated Rayleigh fading channels. Additionally, BICM-ID using differential encoding can avoid the pilot overhead. In this paper, we consider BICM-ID using 16-DAPSK (differential amplitude and phase-shift keying). We first derive the probability of receiving signals conditioned on the transmission of input bits for general differential encoding; then we propose two new 16-DAPSK bit labeling methods. In addition, convolutional codes for the new bit labeling are developed. Both the minimum distance and the simulation results show that the proposed labeling has better error performance than that of the original differential encoding, and the searched new codes can further improve the error performance.