Hainan ZHANG Yanjing SUN Song LI Wenjuan SHI Chenglong FENG
The correlation filter-based trackers with an appearance model established by single feature have poor robustness to challenging video environment which includes factors such as occlusion, fast motion and out-of-view. In this paper, a long-term tracking algorithm based on multi-feature adaptive fusion for video target is presented. We design a robust appearance model by fusing powerful features including histogram of gradient, local binary pattern and color-naming at response map level to conquer the interference in the video. In addition, a random fern classifier is trained as re-detector to detect target when tracking failure occurs, so that long-term tracking is implemented. We evaluate our algorithm on large-scale benchmark datasets and the results show that the proposed algorithm have more accurate and more robust performance in complex video environment.
Sho MIZUNO Mitsuhiro HATADA Tatsuya MORI Shigeki GOTO
Damage caused by malware has become a serious problem. The recent rise in the spread of evasive malware has made it difficult to detect it at the pre-infection timing. Malware detection at post-infection timing is a promising approach that fulfills this gap. Given this background, this work aims to identify likely malware-infected devices from the measurement of Internet traffic. The advantage of the traffic-measurement-based approach is that it enables us to monitor a large number of endhosts. If we find an endhost as a source of malicious traffic, the endhost is likely a malware-infected device. Since the majority of malware today makes use of the web as a means to communicate with the C&C servers that reside on the external network, we leverage information recorded in the HTTP headers to discriminate between malicious and benign traffic. To make our approach scalable and robust, we develop the automatic template generation scheme that drastically reduces the amount of information to be kept while achieving the high accuracy of classification; since it does not make use of any domain knowledge, the approach should be robust against changes of malware. We apply several classifiers, which include machine learning algorithms, to the extracted templates and classify traffic into two categories: malicious and benign. Our extensive experiments demonstrate that our approach discriminates between malicious and benign traffic with up to 97.1% precision while maintaining the false positive rate below 1.0%.
Guiping JIN Dan LIU Miaolan LI Yuehui CUI
In this paper, a simple pattern reconfigurable antenna with broadband circular polarization is proposed. The proposed antenna consists of four rectangular loops, a feeding network and four reflectors. Circular polarization is achieved by cutting two slots on opposite sides of the loops. By controlling the states of the four PIN diodes present in the feeding network, the proposed antenna can achieve four different pattern modes at the same frequency. Experiments show that the antenna has a bandwidth of 47.6% covering 1.73-2.81GHz for reflection coefficient (|S11|)<-10dB and a bandwidth of 55% covering 1.62-2.85GHz for axial ratio <3dB. The average gain is 8.5dBi and the radiation patterns are stable.
The isomorphism of polynomials with two secret (IP2S) problem is one candidate of computational assumptions for post-quantum cryptography. The idea of identification scheme based on IP2S is firstly introduced in 1996 by Patarin. However, the scheme was not described concretely enough and no more details are provided on how to transcribe the idea into a real-world implementation. Moreover, the security of the scheme has not been formally proven and the originally proposed security parameters are no longer secure based on the most recent research. In this paper, we propose a concrete identification scheme based on IP2S with the idea of Patarin as the starting point. We provide formal security proof of the proposed scheme against impersonation under passive attack, sequential active attack, and concurrent active attack. We also propose techniques to reduce the implementation cost such that we are able to cut the storage cost and average communication cost to an extent that under parameters for the standard 80-bit security, the scheme is implementable even on the lightweight devices in the current market.
Zhong ZHANG Hong WANG Shuang LIU Tariq S. DURRANI
A rich and robust representation for scene characters plays a significant role in automatically understanding the text in images. In this letter, we focus on the issue of feature representation, and propose a novel encoding method named bilateral convolutional activations encoded with Fisher vectors (BCA-FV) for scene character recognition. Concretely, we first extract convolutional activation descriptors from convolutional maps and then build a bilateral convolutional activation map (BCAM) to capture the relationship between the convolutional activation response and the spatial structure information. Finally, in order to obtain the global feature representation, the BCAM is injected into FV to encode convolutional activation descriptors. Hence, the BCA-FV can effectively integrate the prominent features and spatial structure information for character representation. We verify our method on two widely used databases (ICDAR2003 and Chars74K), and the experimental results demonstrate that our method achieves better results than the state-of-the-art methods. In addition, we further validate the proposed BCA-FV on the “Pan+ChiPhoto” database for Chinese scene character recognition, and the experimental results show the good generalization ability of the proposed BCA-FV.
Takayuki MORI Jiro IDA Shota INOUE Takahiro YOSHIDA
We report the characterization of hysteresis in SOI-based super-steep subthreshold slope FETs, which are conventional floating body and body-tied, and newly proposed PN-body-tied structures. We found that the hysteresis widths of the PN-body-tied structures are smaller than that of the conventional floating body and body-tied structures; this means that they are feasible for switching devices. Detailed characterizations of the hysteresis widths of each device are also reported in the study, such as dependency on the gate length and the impurity concentration.
In this paper, a dual-polarized phased array based polarization state modulation method is proposed to enhance the physical-layer security in millimeter-wave (mm-wave) communication systems. Indeed, we utilize two polarized beams to transmit the two components of the polarized signal, respectively. By randomly selecting the transmitting antennas, both the amplitude and the phase of two beams vary randomly in undesired directions, which lead to the PM constellation structure distortion in side lobes, thus the transmission security is enhanced since the symbol error rate increases at the eavesdropper side. To enhance the security performance when the eavesdropper is close to the legitimate receiver and located in main beam, the artificial noise based on the orthogonal vector approach is inserted randomly between two polarized beams, which can further distort the constellation structure in undesired directions and improve the secrecy capacity in main beam as well. Finally, theoretical analysis and simulation results demonstrate the proposed method can improve the transmission security in mm-wave communication systems.
Naoki TAKEUCHI Yuki YAMANASHI Nobuyuki YOSHIKAWA
We have been investigating reversible quantum-flux-parametron (RQFP), which is a reversible logic gate using adiabatic quantum-flux-parametron (AQFP), toward realizing superconductor reversible computing. In this paper, we review the recent progress of RQFP. Followed by a brief explanation on AQFP, we first review the difference between irreversible logic gates and RQFP in light of time evolution and energy dissipation, based on our previous studies. Numerical calculation results reveal that the logic state of RQFP can be changed quasi-statically and adiabatically, or thermodynamically reversibly, and that the energy dissipation required for RQFP to perform a logic operation can be arbitrarily reduced. Lastly, we show recent experimental results of an RQFP cell, which was newly designed for the latest cell library. We observed the wide operation margins of more than 4.7dB with respect to excitation currents.
Recently, mobile applications for recording everyday meals draw much attention for self dietary. However, most of the applications return food calorie values simply associated with the estimated food categories, or need for users to indicate the rough amount of foods manually. In fact, it has not been achieved to estimate food calorie from a food photo with practical accuracy, and it remains an unsolved problem. Then, in this paper, we propose estimating food calorie from a food photo by simultaneous learning of food calories, categories, ingredients and cooking directions using deep learning. Since there exists a strong correlation between food calories and food categories, ingredients and cooking directions information in general, we expect that simultaneous training of them brings performance boosting compared to independent single training. To this end, we use a multi-task CNN. In addition, in this research, we construct two kinds of datasets that is a dataset of calorie-annotated recipe collected from Japanese recipe sites on the Web and a dataset collected from an American recipe site. In the experiments, we trained both multi-task and single-task CNNs, and compared them. As a result, a multi-task CNN achieved the better performance on both food category estimation and food calorie estimation than single-task CNNs. For the Japanese recipe dataset, by introducing a multi-task CNN, 0.039 were improved on the correlation coefficient, while for the American recipe dataset, 0.090 were raised compared to the result by the single-task CNN. In addition, we showed that the proposed multi-task CNN based method outperformed search-based methods proposed before.
Focusing on the defects of famous defogging algorithms for fog images based on the atmosphere scattering model, we find that it is necessary to obtain accurate transmission map that can reflect the real depths both in large depth and close range. And it is hard to tackle this with just one prior because of the differences between the large depth and close range in foggy images. Hence, we propose a novel prior that simplifies the solution of transmission map by transferring coefficient, called saturation prior. Then, under the Random Walk model, we constrain the transferring coefficient with the color attenuation prior that can obtain good transmission map in large depth regions. More importantly, we design a regularization weight to balance the influences of saturation prior and color attenuation prior to the transferring coefficient. Experimental results demonstrate that the proposed defogging method outperforms the state-of-art image defogging methods based on single prior in terms of details restoring and color preserving.
Hard-type oscillators for ultrahigh frequency applications were proposed based on resonant tunneling diodes (RTDs) and a HEMT trigger circuit. The hard-type oscillators initiate oscillation only after external excitation. This is advantageous for suppressing the spurious oscillation in the bias line, which is one of the most significant problems in the RTD oscillators. We first investigated a series-connected circuit of a resistor and an RTD for constructing a hard-type oscillator. We carried out circuit simulation using the practical device parameters. It was demonstrated that the stable oscillation can be obtained for such oscillators. Next, we proposed to use series-connected RTDs for the gain block of the hard-type oscillators. The series circuits of RTDs show the negative differential resistance in very narrow regions, or no regions at all, which makes impossible to use such circuits for the conventional soft-type oscillators. However, with the trigger circuit, they can be used for hard-type oscillators. We confirmed the oscillation and the bias stability of these oscillators, and also demonstrated that the voltage swing can be easily increased by increasing the number of RTDs connected in series. This is promising method to overcome the power restriction of the RTD oscillators.
Zhangkai LUO Huali WANG Kaijie ZHOU
In this letter, a novel transmission scheme is proposed to eliminate the polarization dependent loss (PDL) effect in dual-polarized satellite systems. In fact, the PDL effect is the key problem that limits the performance of the systems based on the PM technique, while it is naturally eliminated in the proposed scheme since we transmit the two components of the polarized signal in turn in two symbol periods. Moreover, a simple and effective detection method based on the signal's power is proposed to distinguish the polarization characteristic of the transmit antenna. In addition, there is no requirement on the channel state information at the transmitter, which is popular in satellite systems. Finally, superiorities are validated by the theoretical analysis and simulation results in the dual-polarized satellite systems.
In this paper, we present self-interference (SI) cancellation techniques in the digital domain for in-band full-duplex systems employing orthogonal frequency division multiple access (OFDMA) in the downlink (DL) and single-carrier frequency division multiple access (SC-FDMA) in the uplink (UL), as in the long-term evolution (LTE) system. The proposed techniques use UL subcarrier nulling to accurately estimate SI channels without any UL interference. In addition, by exploiting the structures of the transmitter imperfection and the known or estimated parameters associated with the imperfection, the techniques can further improve the accuracy of SI channel estimation. We also analytically derive the lower bound of the mean square error (MSE) performance and the upper bound of the signal-to-interference-plus-noise ratio (SINR) performance for the techniques, and show that the performance of the techniques are close to the bounds. Furthermore, by utilizing the SI channel estimates and the nonlinear signal components of the SI caused by the imperfection to effectively eliminate the SI, the proposed techniques can achieve SINR performance very close to the one in perfect SI cancellation. Finally, because the SI channel estimation of the proposed techniques is performed in the time domain, the techniques do not require symbol time alignment between SI and UL symbols.
Masahiro YAMAGUCHI Trong Phuc TRUONG Shohei MORI Vincent NOZICK Hideo SAITO Shoji YACHIDA Hideaki SATO
In this paper, we propose a method to generate a three-dimensional (3D) thermal map and RGB + thermal (RGB-T) images of a scene from thermal-infrared and RGB images. The scene images are acquired by moving both a RGB camera and an thermal-infrared camera mounted on a stereo rig. Before capturing the scene with those cameras, we estimate their respective intrinsic parameters and their relative pose. Then, we reconstruct the 3D structures of the scene by using Direct Sparse Odometry (DSO) using the RGB images. In order to superimpose thermal information onto each point generated from DSO, we propose a method for estimating the scale of the point cloud corresponding to the extrinsic parameters between both cameras by matching depth images recovered from the RGB camera and the thermal-infrared camera based on mutual information. We also generate RGB-T images using the 3D structure of the scene and Delaunay triangulation. We do not rely on depth cameras and, therefore, our technique is not limited to scenes within the measurement range of the depth cameras. To demonstrate this technique, we generate 3D thermal maps and RGB-T images for both indoor and outdoor scenes.
Nawfal AL-ZUBAIDI R-SMITH Lubomír BRANČÍK
Numerical inverse Laplace transform (NILT) methods are potential methods for time domain simulations, for instance the analysis of the transient phenomena in systems with lumped and/or distributed parameters. This paper proposes a numerical inverse Laplace transform method based originally on hyperbolic relations. The method is further enhanced by properly adapting several convergence acceleration techniques, namely, the epsilon algorithm of Wynn, the quotient-difference algorithm of Rutishauser and the Euler transform. The resulting accelerated models are compared as for their accuracy and computational efficiency. Moreover, an expansion to two dimensions is presented for the first time in the context of the accelerated hyperbolic NILT method, followed by the error analysis. The expansion is done by repeated application of one-dimensional partial numerical inverse Laplace transforms. A detailed static error analysis of the resulting 2D NILT is performed to prove the effectivness of the method. The work is followed by a practical application of the 2D NILT method to simulate voltage/current distributions along a transmission line. The method and application are programmed using the Matlab language.
Yoshikatsu NAKAJIMA Hideo SAITO
We propose a novel object recognition system that is able to (i) work in real-time while reconstructing segmented 3D maps and simultaneously recognize objects in a scene, (ii) manage various kinds of objects, including those with smooth surfaces and those with a large number of categories, utilizing a CNN for feature extraction, and (iii) maintain high accuracy no matter how the camera moves by distributing the viewpoints for each object uniformly and aggregating recognition results from each distributed viewpoint as the same weight. Through experiments, the advantages of our system with respect to current state-of-the-art object recognition approaches are demonstrated on the UW RGB-D Dataset and Scenes and on our own scenes prepared to verify the effectiveness of the Viewpoint-Class-based approach.
Ziwei DENG Yilin HOU Xina CHENG Takeshi IKENAGA
3D ball tracking is of great significance in ping-pong game analysis, which can be utilized to applications such as TV contents and tactic analysis, with some of them requiring real-time implementation. This paper proposes a CPU-GPU platform based Particle Filter for multi-view ball tracking including 4 proposals. The multi-peak estimation and the ball-like observation model are proposed in the algorithm design. The multi-peak estimation aims at obtaining a precise ball position in case the particles' likelihood distribution has multiple peaks under complex circumstances. The ball-like observation model with 4 different likelihood evaluation, utilizes the ball's unique features to evaluate the particle's similarity with the target. In the GPU implementation, the double-queue structure and the vectorized data combination are proposed. The double-queue structure aims at achieving task parallelism between some data-independent tasks. The vectorized data combination reduces the time cost in memory access by combining 3 different image data to 1 vector data. Experiments are based on ping-pong videos recorded in an official match taken by 4 cameras located in 4 corners of the court. The tracking success rate reaches 99.59% on CPU. With the GPU acceleration, the time consumption is 8.8 ms/frame, which is sped up by a factor of 98 compared with its CPU version.
Chunyan HOU Chen CHEN Jinsong WANG
In the era of e-commerce, purchase behavior prediction is one of the most important issues to promote both online companies' sales and the consumers' experience. The previous researches usually use the feature engineering and ensemble machine learning algorithms for the prediction. The performance really depends on designed features and the scalability of algorithms because the large-scale data and a lot of categorical features lead to huge samples and the high-dimensional feature. In this study, we explore an alternative to use tree-based Feature Transformation (FT) and simple machine learning algorithms (e.g. Logistic Regression). Random Forest (RF) and Gradient Boosting decision tree (GB) are used for FT. Then, the simple algorithm, rather than ensemble algorithms, is used to predict purchase behavior based on transformed features. Tree-based FT regards the leaves of trees as transformed features, and can learn high-order interactions among original features. Compared with RF, if GB is used for FT, simple algorithms are enough to achieve better performance.
Leilei KONG Zhongyuan HAN Haoliang QI Zhimao LU
This paper addresses the issue of text matching for plagiarism detection. This task aims at identifying the matching plagiarism segments in a pair of suspicious document and its plagiarism source document. All the time, heuristic-based methods are mainly utilized to resolve this problem. But the heuristics rely on the experts' experiences and fail to integrate more features to detect the high obfuscation plagiarism matches. In this paper, a statistical machine learning approach, named the Ranking-based Text Matching Approach for Plagiarism Detection, is proposed to deal with the issues of high obfuscation plagiarism detection. The plagiarism text matching is formalized as a ranking problem, and a pairwise learning to rank algorithm is exploited to identify the most probable plagiarism matches for a given suspicious segment. Especially, the Meteor evaluation metrics of machine translation are subsumed by the proposed method to capture the lexical and semantic text similarity. The proposed method is evaluated on PAN12 and PAN13 text alignment corpus of plagiarism detection and compared to the methods achieved the best performance in PAN12, PAN13 and PAN14. Experimental results demonstrate that the proposed method achieves statistically significantly better performance than the baseline methods in all twelve document collections belonging to five different plagiarism categories. Especially at the PAN12 Artificial-high Obfuscation sub-corpus and PAN13 Summary Obfuscation plagiarism sub-corpus, the main evaluation metrics PlagDet of the proposed method are even 22% and 43% relative improvements than the baselines. Moreover, the efficiency of the proposed method is also better than that of baseline methods.
Naoki HOSOYA Atsushi MIYAMOTO Junichiro NAGANUMA
Nuclear power plants require in-vessel inspections for soundness checks and preventive maintenance. One inspection procedure is visual testing (VT), which is based on video images of an underwater camera in a nuclear reactor. However, a lot of noise is superimposed on VT images due to radiation exposure. We propose a technique for improving the quality of those images by image processing that reduces radiation noise and enhances signals. Real-time video processing was achieved by applying the proposed technique with a parallel processing unit. Improving the clarity of VT images will lead to reducing the burden on inspectors.