Feature representation is a key component of most visual tracking algorithms. It is difficult to deal with complex appearance changes with low-level hand-crafted features due to weak representation capacities of such features. In this paper, we propose a novel tracking algorithm through combining a joint dictionary pair learning with convolutional neural networks (CNN). We utilize CNN model that is trained on ImageNet-Vid to extract target features. The CNN includes three convolutional layers and two fully connected layers. A dictionary pair learning follows the second fully connected layer. The joint dictionary pair is learned upon extracted deep features by the trained CNN model. The temporal variations of target appearances are learned in the dictionary learning. We use the learned dictionaries to encode target candidates. A linear combination of atoms in the learned dictionary is used to represent target candidates. Extensive experimental evaluations on OTB2015 demonstrate the superior performances against SOTA trackers.

Tile-based virtual reality (VR) video consists of high-resolution tiles that are displayed in accordance with the users' viewing directions and a low-resolution tile that is the entire VR video and displayed when users change their viewing directions. Whether users perceive quality degradation when watching tile-based VR video depends on high-resolution tile size, the quality of high- and low-resolution tiles, and network condition. The display time of low-resolution tile (hereafter delay) affects users' perceived quality because longer delay makes users watch the low-resolution tiles longer. Since these degradations of low-resolution tiles markedly affect users' perceived quality, these points have to be considered in the quality-estimation model. Therefore, we propose a bitstream-quality-estimation model for tile-based VR video streaming services and investigate the effect of bitstream parameters and delay on tile-based VR video quality. Subjective experiments on several videos of different qualities and a comparison between other video quality-estimation models were conducted. In this paper, we prove that the proposed model can improve the quality-estimation accuracy by using the high- and low-resolution tiles' quantization parameters, resolution, framerate, and delay. Subjective experimental results show that the proposed model can estimate the quality of tile-based VR video more accurately than other video quality-estimation models.

Service mining aims to use process mining for the analysis of services, making it possible to discover, analyze, and improve service processes. In the context of Web services, the recording of all kinds of events related to activities is possible, which can be used to extract new information of service processes. However, the distributed nature of the services tends to generate large-scale service event logs, which complicates the discovery and analysis of service processes. To solve this problem, this research focus on the existing large-scale service event logs, a hybrid genetic service mining based on a trace clustering population method (HGSM) is proposed. By using trace clustering, the complex service system is divided into multiple functionally independent components, thereby simplifying the mining environment; And HGSM improves the mining efficiency of the genetic mining algorithm from the aspects of initial population quality improvement and genetic operation improvement, makes it better handle large service event logs. Experimental results demonstrate that compare with existing state-of-the-art mining methods, HGSM has better characteristics to handle large service event logs, in terms of both the mining efficiency and model quality.

This paper presents a novel blind signal separation method for the measurement of pulse waves at multiple body positions using an array radar system. The proposed method is based on a mathematical model of pulse wave propagation. The model relies on three factors: (1) a small displacement approximation, (2) beam pattern orthogonality, and (3) an impulse response model of pulse waves. The separation of radar echoes is formulated as an optimization problem, and the associated objective function is established using the mathematical model. We evaluate the performance of the proposed method using measured radar data from participants lying in a prone position. The accuracy of the proposed method, in terms of estimating the body displacements, is measured using reference data taken from laser displacement sensors. The average estimation errors are found to be 10-21% smaller than those of conventional methods. These results indicate the effectiveness of the proposed method for achieving noncontact measurements of the displacements of multiple body positions.

Recently several researchers have proposed various methods to build intelligent stock trading and portfolio management systems using rapid advancements in artificial intelligence including machine learning techniques. However, existing technical analysis-based stock price prediction studies primarily depend on price change or price-related moving average patterns, and information related to trading volume is only used as an auxiliary indicator. This study focuses on the effect of changes in trading volume on stock prices and proposes a novel method for short-term stock price predictions based on trading volume patterns. Two rapid volume decrease patterns are defined based on the combinations of multiple volume moving averages. The dataset filtered using these patterns is learned through the supervised learning of neural networks. Experimental results based on the data from Korea Composite Stock Price Index and Korean Securities Dealers Automated Quotation, show that the proposed prediction system can achieve a trading performance that significantly exceeds the market average.

Nowadays, a rapid increase of demand on high-performance computation causes the enthusiastic research activities regarding massively parallel systems. An interconnection network in a massively parallel system interconnects a huge number of processing elements so that they can cooperate to process tasks by communicating among others. By regarding a processing element and a link between a pair of processing elements as a node and an edge, respectively, many problems with respect to communication and/or routing in an interconnection network are reducible to the problems in the graph theory. For interconnection networks of the massively parallel systems, many topologies have been proposed so far. The hypercube is a very popular topology and it has many variants. The bicube is a such topology and it can interconnect the same number of nodes with the same degree as the hypercube while its diameter is almost half of that of the hypercube. In addition, the bicube keeps the node-symmetric property. Hence, we focus on the bicube and propose an algorithm that gives a minimal or shortest path between an arbitrary pair of nodes. We give a proof of correctness of the algorithm and demonstrate its execution.

This paper presents a fully integrated yet compact receiver front-end for Sub-GHz applications such as Internet-of-Things (IoT). The low noise amplifier (LNA) matching network leverages an inductance boosting technique. A relatively small on-chip inductor with a compact area achieves impedance matching in such a low frequency. Moreover, a passive-mixer-first mode bypasses the LNA to extend the receiver dynamic-range. The passive mixer provides matching to the 50Ω antenna interface to eliminate the need for additional passive components. Therefore, the receiver can be fully-integrated without any off-chip matching components. The flipped-voltage-follower (FVF) cell is adopted in the low pass filter (LPF) and the variable gain amplifier (VGA) for its high linearity and low power consumption. Fabricated in 65nm LP CMOS process, the proposed receiver front-end occupies 0.37mm2 core area, with a tolerable input power ranging from -91.5dBm to -1dBm for 500kbps GMSK signal at 924MHz frequency. The power consumption is 1mW power under a 1.2V supply.

Time-of-flight (TOF) range imaging is a promising technology for various applications such as touchless control, augmented reality interface, and automotive. The TOF range imagers are classified into two methods: direct TOF with single photo avalanche diodes and indirect TOF with lock-in pixels. The indirect TOF range imagers have advantages in terms of a high spatial resolution and high depth precision because their pixels are simple and can handle many photons at one time. This paper reviews and discusses principal lock-in pixels reported both in the past and present, including circuit-based and charge-modulator-based lock-in pixels. In addition, key technologies that include enhancing sensitivity and background suppression techniques are also discussed.

A unified construction for yielding optimal and balanced quaternary sequences from ideal/optimal balanced binary sequences was proposed by Zeng et al. In this paper, the linear complexity over finite field 𝔽2, 𝔽4 and Galois ring ℤ4 of the quaternary sequences are discussed, respectively. The exact values of linear complexity of sequences obtained by Legendre sequence pair, twin-prime sequence pair and Hall's sextic sequence pair are derived.

We propose “Temporal Ensemble SSDLite,” a new method for video object detection that boosts accuracy while maintaining detection speed and energy consumption. Object detection for video is becoming increasingly important as a core part of applications in robotics, autonomous driving and many other promising fields. Many of these applications require high accuracy and speed to be viable, but are used in compute and energy restricted environments. Therefore, new methods that increase the overall performance of video object detection i.e., accuracy and speed have to be developed. To increase accuracy we use ensemble, the machine learning method of combining predictions of multiple different models. The drawback of ensemble is the increased computational cost which is proportional to the number of models used. We overcome this deficit by deploying our ensemble temporally, meaning we inference with only a single model at each frame, cycling through our ensemble of models at each frame. Then, we combine the predictions for the last N frames where N is the number of models in our ensemble through non-max-suppression. This is possible because close frames in a video are extremely similar due to temporal correlation. As a result, we increase accuracy through the ensemble while only inferencing a single model at each frame and therefore keeping the detection speed. To evaluate the proposal, we measure the accuracy, detection speed and energy consumption on the Google Edge TPU, a machine learning inference accelerator, with the Imagenet VID dataset. Our results demonstrate an accuracy boost of up to 4.9% while maintaining real-time detection speed and an energy consumption of 181mJ per image.

This paper presents robust optimization models for minimizing the required backup capacity while providing probabilistic protection against multiple simultaneous failures of physical machines under uncertain virtual machine capacities in a cloud provider. If random failures occur, the required capacities for virtual machines are allocated to the dedicated backup physical machines, which are determined in advance. We consider two uncertainties: failure event and virtual machine capacity. By adopting a robust optimization technique, we formulate six mixed integer linear programming problems. Numerical results show that for a small size problem, our presented models are applicable to the case that virtual machine capacities are uncertain, and by using these models, we can obtain the optimal solution of the allocation of virtual machines under the uncertainty. A simulated annealing heuristic is presented to solve large size problems. By using this heuristic, an approximate solution is obtained for a large size problem.

In this study, we consider fake message attacks in sparse mobile ad hoc networks, in which nodes are chronically isolated. In these networks, messages are delivered to their destination nodes using store-carry-forward routing, where they are relayed by some nodes. Therefore, when a node has messages in its buffer, it can falsify the messages easily. When malicious nodes exist in the network, they alter messages to create fake messages, and then they launch fake message attacks, that is, the fake messages are spread over the network. To analyze the negative effects of a fake message attack, we model the system dynamics without attack countermeasures using a Markov chain, and then formalize some performance metrics (i.e., the delivery probability, mean delivery delay, and mean number of forwarded messages). This analysis is useful for designing countermeasures. Moreover, we consider a hash-based countermeasure against fake message attacks using a hash of the message. Whenever a node that has a message and its hash encounters another node, it probabilistically forwards only one of them to the encountered node. By doing this, the message and the hash value can be delivered to the destination node via different relay nodes. Therefore, even if the destination node receives a fake message, it can verify the legitimacy of the received message. Through simulation experiments, we evaluate the effectiveness of the hash-based countermeasure.

To reduce mutual coupling of a two-level nested array (TLNA) with an even number of sensors, we propose an improved array configuration that exhibits all the good properties of the prototype optimal configuration under the constraint of a fixed number of sensors N and achieves reduction of mutual coupling. Compared with the prototype optimal TLNA (POTLNA), which inner level and outer level both have N/2 sensors, those of the improved optimal TLNA (IOTLNA) are N/2-1 and N/2+1. It is proved that the physical aperture and uniform degrees of freedom (uDOFs) of IOTLNA are the same as those of POTLNA, and the number of sensor pairs with small separations of IOTLNA is reduced. We also construct an improved optimal second-order super nested array (SNA) by using the IOTLNA as the parent nested array, termed IOTLNA-SNA, which has the same physical aperture and the same uDOFs, as well as the IOTLNA. Numerical simulations demonstrate the better performance of the improved array configurations.

In many screen to camera communication (S2C) systems, the barcode preprocessing method is a significant prerequisite because barcodes may be deformed due to various environmental factors. However, previous studies have focused on barcode detection under static conditions; to date, few studies have been carried out on dynamic conditions (for example, the barcode video stream or the transmitter and receiver are moving). Therefore, we present a detection and tracking method for dynamic barcodes based on a Siamese network. The backbone of the CNN in the Siamese network is improved by SE-ResNet. The detection accuracy achieved 89.5%, which stands out from other classical detection networks. The EAO reaches 0.384, which is better than previous tracking methods. It is also superior to other methods in terms of accuracy and robustness. The SE-ResNet in this paper improved the EAO by 1.3% compared with ResNet in SiamMask. Also, our method is not only applicable to static barcodes but also allows real-time tracking and segmentation of barcodes captured in dynamic situations.

Reservoir computing (RC) is an attractive alternative to machine learning models owing to its computationally inexpensive training process and simplicity. In this work, we propose EnsembleBloomCA, which utilizes cellular automata (CA) and an ensemble Bloom filter to organize an RC system. In contrast to most existing RC systems, EnsembleBloomCA eliminates all floating-point calculation and integer multiplication. EnsembleBloomCA adopts CA as the reservoir in the RC system because it can be implemented using only binary operations and is thus energy efficient. The rich pattern dynamics created by CA can map the original input into a high-dimensional space and provide more features for the classifier. Utilizing an ensemble Bloom filter as the classifier, the features provided by the reservoir can be effectively memorized. Our experiment revealed that applying the ensemble mechanism to the Bloom filter resulted in a significant reduction in memory cost during the inference phase. In comparison with Bloom WiSARD, one of the state-of-the-art reference work, the EnsembleBloomCA model achieves a 43× reduction in memory cost while maintaining the same accuracy. Our hardware implementation also demonstrated that EnsembleBloomCA achieved over 23× and 8.5× reductions in area and power, respectively.

A vertex subset I of a graph G is called a k-path vertex cover if every path on k vertices in G contains at least one vertex from I. The K-PATH VERTEX COVER RECONFIGURATION (K-PVCR) problem asks if one can transform one k-path vertex cover into another via a sequence of k-path vertex covers where each intermediate member is obtained from its predecessor by applying a given reconfiguration rule exactly once. We investigate the computational complexity of K-PVCR from the viewpoint of graph classes under the well-known reconfiguration rules: TS, TJ, and TAR. The problem for k=2, known as the VERTEX COVER RECONFIGURATION (VCR) problem, has been well-studied in the literature. We show that certain known hardness results for VCR on different graph classes can be extended for K-PVCR. In particular, we prove a complexity dichotomy for K-PVCR on general graphs: on those whose maximum degree is three (and even planar), the problem is PSPACE-complete, while on those whose maximum degree is two (i.e., paths and cycles), the problem can be solved in polynomial time. Additionally, we also design polynomial-time algorithms for K-PVCR on trees under each of TJ and TAR. Moreover, on paths, cycles, and trees, we describe how one can construct a reconfiguration sequence between two given k-path vertex covers in a yes-instance. In particular, on paths, our constructed reconfiguration sequence is shortest.

We introduce a hybrid Bayesian-convolutional neural network (hyBCNN) for improving the robustness against adversarial attacks and decreasing the computation time in the Bayesian inference phase. Our hyBCNN models are built from a part of BNN and CNN. Based on pre-trained CNNs, we only replace convolutional layers and activation function of the initial stage of CNNs with our Bayesian convolutional (BC) and Bayesian activation (BA) layers as a term of transfer learning. We keep the remainder of CNNs unchanged. We adopt the Bayes without Bayesian Learning (BwoBL) algorithm for hyBCNN networks to execute Bayesian inference towards adversarial robustness. Our proposal outperforms adversarial training and robust activation function, which are currently the outstanding defense methods of CNNs in the resistance to adversarial attacks such as PGD and C&W. Moreover, the proposed architecture with BwoBL can easily integrate into any pre-trained CNN, especially in scaling networks, e.g., ResNet and EfficientNet, with better performance on large-scale datasets. In particular, under l∞ norm PGD attack of pixel perturbation ε=4/255 with 100 iterations on ImageNet, our best hyBCNN EfficientNet reaches 93.92% top-5 accuracy without additional training.

Parallel computing essentially consists of computation and communication and, in many cases, communication performance is vital. Many parallel applications use collective communications, which often dominate the performance of the parallel execution. This paper focuses on collective communication performance to speed-up the parallel execution. This paper firstly offers our experimental result that splitting a session of collective communication to small portions (slices) possibly enables efficient communication. Then, based on the results, this paper proposes a new concept cup-stacking with a genetic algorithm based methodology. The preliminary evaluation results reveal the effectiveness of the proposed method.

We propose a novel synthetic-benchmarks generation model using partial time-series regression, called Partial-Regression-Integrated Generic Model (PRIGM). PRIGM abstracts the unique characteristics of the input sensor data into generic time-series data confirming the generation similarity and evaluating the correctness of the synthetic benchmarks. The experimental results obtained by the proposed model with its formula verify that PRIGM preserves the time-series characteristics of empirical data in complex time-series data within 10.4% on an average difference in terms of descriptive statistics accuracy.

In recent years, Graph Neural Networks has received enormous attention from academia for its huge potential of modeling the network traits such as macrostructure and single node attributes. However, prior mainstream works mainly focus on homogeneous network and lack the capacity to characterize the network heterogeneous property. Besides, most previous literature cannot the model latent influence link under microscope vision, making it infeasible to model the joint relation between the heterogeneity and mutual interaction within multiple relation type. In this letter, we propose a latent influence based self-attention framework to address the difficulties mentioned above. To model the heterogeneity and mutual interactions, we redesign the attention mechanism with latent influence factor on single-type relation level, which learns the importance coefficient from its adjacent neighbors under the same meta-path based patterns. To incorporate the heterogeneous meta-path in a unified dimension, we developed a novel self-attention based framework for meta-path relation fusion according to the learned meta-path coefficient. Our experimental results demonstrate that our framework not only achieves higher results than current state-of-the-art baselines, but also shows promising vision on depicting heterogeneous interactive relations under complicated network structure.