IoT-oriented high-efficient anti-malware hardware focusing on time series metadata extractable from inside a processor core

We aim to improve the efficiency of our previously proposed anti-malware hardware; it is a hardware-implemented malware detection mechanism that uses information inside the processor. We previously evaluated a prototype, but, due to its prototypical nature, there remain limitations, such as only detecting certain behaviors, high power consumption, and a tendency to bloat the training model. In this paper, we propose a circuit and a learning method to achieve high efficiency, low power consumption, and light weight for the model. In considering these three issues, we focus on time-series metadata obtained by transforming the processor information. To improve efficiency, we implement predictive detection to predict the behavior of metadata in the malware detection component. This lets the model detect malware within less than 19% of the number of execution cycles of the conventional method. To reduce power consumption, we implement a sampling circuit that interrupts the input to the detection circuit at regular intervals, reducing the system’s uptime by 99% while maintaining judgment accuracy. Finally, for a light weight, we focus on the training process of the metadata generator based on a machine-learning model. By applying sampling learning and feature dimensionality reduction in the training process, a metadata generator approximately 16% smaller than the previous version is created.

     

Failure detection algorithm for Fail-Lagging model applied to HPC

It is essential to use fault tolerance techniques on exascale high-performance computing systems, but this faces many challenges such as higher probability of failure, more complex types of faults, and greater difficulty in failure detection. In this paper, we designed the Fail-Lagging model to describe HPC process-level failure. The failure model does not distinguish whether the failed process is crashed or slow, but is compatible with the possible behavior of the process due to various failures, such as crash, slow, recovery. The failure detection in Fail-Lagging model is implemented by local detection and global decision among processes, which depend on a robust and efficient communication topology. Robust means that failed processes do not easily corrupt the connectivity of the topology, and efficient means that the time complexity of the topology used for collective communication is as low as possible. For this purpose, we designed a torus-tree topology for failure detection, which is scalable even at the scale of an extremely large number of processes. The Fail-Lagging model supports common fault tolerance methods such as rollback, replication, redundancy, algorithm-based fault tolerance, etc. and is especially able to better enable the efficient forward recovery mode. We demonstrate with large-scale experiments that the torus-tree failure detection algorithm is robust and efficient, and we apply fault tolerance based on the Fail-Lagging model to iterative computation, enabling applications to react to faults in a timely manner.

     

A machine learning based intelligent vision system for autonomous object detection and recognition

Existing object recognition techniques often rely on human labeled data conducting to severe limitations to design a fully autonomous machine vision system. In this work, we present an intelligent machine vision system able to learn autonomously individual objects present in real environment. This system relies on salient object detection. In its design, we were inspired by early processing stages of human visual system. In this context we suggest a novel fast algorithm for visually salient object detection, robust to real-world illumination conditions. Then we use it to extract salient objects which can be efficiently used for training the machine learning-based object detection and recognition unit of the proposed system. We provide results of our salient object detection algorithm on MSRA Salient Object Database benchmark comparing its quality with other state-of-the-art approaches. The proposed system has been implemented on a humanoid robot, increasing its autonomy in learning and interaction with humans. We report and discuss the obtained results, validating the proposed concepts.     

基于递归神经网络的跌倒检测系统

针对现有跌倒检测方法存在适应性差和功能较单一等问题，引入递归神经网络，通过发掘位置传感器数据之间的内在联系提高检测跌倒行为的效果。首先，设计了传感器、训练与检测输入数据的序列化表示方法，为发掘其中与跌倒和接近跌倒行为相关的内在关联提供了基础；接着，给出了用于跌倒检测的RNN训练算法以及基于RNN的跌倒检测算法，将跌倒检测转换为输入序列的分类问题；最后，在前期实现的基于分布式神经元大规模RNN系统的基础上，在Spark平台上实现了基于RNN的跌倒检测系统，使用Fall_adl_data数据集进行了测试与分析，验证了其能有效提高跌倒检测的准确率和召回率，F值相比现有跌倒检测系统提高12%和7%，同时能有效检测出接近跌倒的行为，有助于及时采取保护措施减少伤害。     

Safety-monitoring-type wide-range detectable contact sensor system using ultrasonic waves and viscoelastic tubing

In physical human–robot interaction, a contact sensor is fundamentally required for robots to sense contact with humans and to take appropriate safety measures. This paper proposes a wide-range detectable contact sensor system with a safety monitoring function that uses an ultrasonic wave and a silicone rubber tube. The appropriate threshold voltage for generating a monitoring pulse signal is calculated using the estimation equation derived on the basis of the propagation characteristics of ultrasonic waves in straight and curved tubes. By comparing the periodic time between the generated monitoring signals and self-diagnostic signals, the proposed contact detection algorithm detects both contact due to tube deformation and failure of a sensor system including a stack fault. An experiment investigating the relationship between tube deformation by pushing force and the loss of peak voltage of an ultrasonic wave reveals that the sensor system can detect contact when the tube is deformed by 8 mm.     

Moving people tracking with detection by latent semantic analysis for visual surveillance applications

The latent semantic analysis (LSA) has been widely used in the fields of computer vision and pattern recognition. Most of the existing works based on LSA focus on behavior recognition and motion classification. In the applications of visual surveillance, accurate tracking of the moving people in surveillance scenes, is regarded as one of the preliminary requirement for other tasks such as object recognition or segmentation. However, accurate tracking is extremely hard under challenging surveillance scenes where similarity among multiple objects or occlusion among multiple objects occurs. Usual temporal Markov chain based tracking algorithms suffer from the ‘tracking error accumulation problem’. The accumulated errors can finally make the tracking to drift from the target. To handle the problem of tracking drift, some authors have proposed the idea of using detection along with tracking as an effective solution. However, many of the critical issues still remain unsettled in these detection based tracking algorithms. In this paper, we propose a novel moving people tracking with detection based on (probabilistic) LSA. By employing a novel ‘twin-pipeline’ training framework to find the latent semantic topics of ‘moving people’, the proposed detection can effectively detect the interest points on moving people in different indoor and outdoor environments with camera motion. Since the detected interest points on different body parts can be used to locate the position of moving people more accurately, by combining the detection with incremental subspace learning based tracking, the proposed algorithms resolves the problem of tracking drift during each target appearance update process. In addition, due to the time independent processing mechanism of detection, the proposed method is also able to handle the error accumulation problem. The detection can calibrate the tracking errors during updating of each state of the tracking algorithm. Extensive, experiments on various surveillance environments using different benchmark datasets have proved the accuracy and robustness of the proposed tracking algorithm. Further, the experimental comparison results clearly show that the proposed tracking algorithm outperforms the well known tracking algorithms such as ISL, AMS and WSL algorithms. Furthermore, the speed performance of the proposed method is also satisfactory for realistic surveillance applications.     

一种Hadoop集群下的行为异常检测方法

随着分布式计算技术的发展,Hadoop成为大规模数据处理领域的典型代表,由于安全机制相对薄弱,缺少用户行为活动的监控,容易受到隐藏的安全威胁,如数据泄露等。结合主成分分析计算的特点,基于MapReduce对其做并行化处理,克服了传统主成分分析计算的缺点,提高了模型训练效率。提出了一种基于并行化主成分分析的异常行为检测方法,即比较当前用户的行为模式是否与历史行为模式相匹配作为判定用户行为异常与否的度量标准。实验表明该方法能够较好地发现用户的异常行为。     

Development of misfire detection algorithm using quantitative FDI performance analysis

A model-based misfire detection algorithm is proposed. The algorithm is able to detect misfires and identify the failing cylinder during different conditions, such as cylinder-to-cylinder variations, cold starts, and different engine behavior in different operating points. Also, a method is proposed for automatic tuning of the algorithm based on training data. The misfire detection algorithm is evaluated using data from several vehicles on the road and the results show that a low misclassification rate is achieved even during difficult conditions.     

Emotion extraction based on multi bio-signal using back-propagation neural network

This study proposes a system that can recognize human emotional state from bio-signal. The technology is provided to improve the interaction between humans and computers to achieve an effective human–machine that is capable for intelligent interaction. The proposed method is able to recognize six emotional states, such as joy, happiness, fear, anger, despair, and sadness. These set of emotional states are widely used for emotion recognition purposes. The result shows that the proposed method can distinguish one emotion compared to all other possible emotional states. The method is composed of two steps: 1) multi-modal bio-signal evaluation and 2) emotion recognition using artificial neural network. In the first step, we present a method to analyze and fix human sensitivity using physiological signals, such as electroencephalogram, electrocardiogram, photoplethysmogram, respiration, and galvanic skin response. The experimental analysis shows that the proposed method has good accuracy performance and could be applied on many human–computer interaction devices for emotion detection.

     

Double-compressed JPEG images steganalysis with transferring feature

Steganalysis is a technology of detecting the presence of secret messages in digital media. Recently, many algorithms have been proposed and achieved satisfactory detection accuracy. However, the performance of these algorithms will be reduced by double-compression, due to the mismatch between training and testing sets. To address this problem, we proposed Transferring Feature on Double-compressed JPEG images (TFD) to improve the detection accuracy. Specifically, our algorithm consists of two parts. First, we detect the double-compression of testing images by constructing multi-classifier with Markov feature. Then we transfer the steganalysis feature into a new feature space, in order to reduce the difference of feature distributions between training and testing sets. We intend to obtain a transformation matrix by adjusting the expectation and standard deviation of training set, minimizing the feature discrepancy between both sets and keeping classification ability of training set, simultaneously. The experimental results show that the proposed algorithm has better performance in double-compressed mismatched steganalysis.

     

Feature engineering strategies for credit card fraud detection

Every year billions of Euros are lost worldwide due to credit card fraud. Thus, forcing financial institutions to continuously improve their fraud detection systems. In recent years, several studies have proposed the use of machine learning and data mining techniques to address this problem. However, most studies used some sort of misclassification measure to evaluate the different solutions, and do not take into account the actual financial costs associated with the fraud detection process. Moreover, when constructing a credit card fraud detection model, it is very important how to extract the right features from the transactional data. This is usually done by aggregating the transactions in order to observe the spending behavioral patterns of the customers. In this paper we expand the transaction aggregation strategy, and propose to create a new set of features based on analyzing the periodic behavior of the time of a transaction using the von Mises distribution. Then, using a real credit card fraud dataset provided by a large European card processing company, we compare state-of-the-art credit card fraud detection models, and evaluate how the different sets of features have an impact on the results. By including the proposed periodic features into the methods, the results show an average increase in savings of 13%.     

Deep learning for vision‐based fall detection system: Enhanced optical dynamic flow

Accurate fall detection for the assistance of older people is crucial to reduce incidents of deaths or injuries due to falls. Meanwhile, vision‐based fall detection system has shown some significant results to detect falls. Still, numerous challenges need to be resolved. The impact of deep learning has changed the landscape of the vision‐based system, such as action recognition. The deep learning technique has not been successfully implemented in vision‐based fall detection system due to the requirement of a large amount of computation power and requirement of a large amount of sample training data. This research aims to propose a vision‐based fall detection system that improves the accuracy of fall detection in some complex environments such as the change of light condition in the room. Also, this research aims to increase the performance of the pre‐processing of video images. The proposed system consists of Enhanced Dynamic Optical Flow technique that encodes the temporal data of optical flow videos by the method of rank pooling, which thereby improves the processing time of fall detection and improves the classification accuracy in dynamic lighting condition. The experimental results showed that the classification accuracy of the fall detection improved by around 3% and the processing time by 40–50 ms. The proposed system concentrates on decreasing the processing time of fall detection and improving the classification accuracy. Meanwhile, it provides a mechanism for summarizing a video into a single image by using dynamic optical flow technique, which helps to increase the performance of image preprocessing steps.     

An algorithm for detection and phase estimation of protective elements periodic lattice on document image

Various periodic security elements, such as holograms, watermarks, and guilloches, are applied to documents in order to protect against counterfeiting. These elements can be detected and used to automatically check the authenticity of a document and to identify its type. They also make it possible to use special OCR system parameters in areas of security elements. This paper is devoted to developing methods for the detection and localization of periodic background patterns based on two-dimensional discrete Fourier transform. The model of a document image with a periodic background structure is considered. Algorithms for the detection and localization of background structures that follow from the model are discussed. The behavior and accuracy characteristics of the algorithms are tested on samples of Russian passport images. Their tolerance to errors in document boundary detection are experimentally analyzed. Modified detection and localization algorithms that improve the separating detection capability and reduce localization error twofold are proposed such as masking and replacement of noisy parts of document images, background spectrum suppression, and estimation of phase components of a single periodic element.     

Modeling culture in intelligent virtual agents

This work addresses the challenge of creating virtual agents that are able to portray culturally appropriate behavior when interacting with other agents or humans. Because culture influences how people perceive their social reality it is important to have agent models that explicitly consider social elements, such as existing relational factors. We addressed this necessity by integrating culture into a novel model for simulating human social behavior. With this model, we operationalized a particular dimension of culture—individualism versus collectivism—within the context of an interactive narrative scenario that is part of an agent-based tool for intercultural training. Using this scenario we conducted a cross-cultural study in which participants from a collectivistic country (Portugal) were compared with participants from an individualistic country (the Netherlands) in the way they perceived and interacted with agents whose behavior was either individualistic or collectivistic, according to the configuration of the proposed model. In the obtained results, Portuguese subjects rated the collectivistic agents more positively than the Dutch but both countries had a similarly positive opinion about the individualistic agents. This experiment sheds new light on how people from different countries differ when assessing the social appropriateness of virtual agents, while also raising new research questions on this matter.     

Human fall detection using normalized shape aspect ratio

In video surveillance, automatic human fall detection is important to protect vulnerable groups such as the elderly. When the camera layout varies, the shape aspect ratio (SAR) of a human body may change substantially. In order to rectify these changes, in this paper, we propose an automatic human fall detection method using the normalized shape aspect ratio (NSAR). A calibration process and bicubic interpolation are implemented to generate the NSAR table for each camera. Compared with some representative fall detection methods using the SAR, the proposed method integrates the NSAR with the moving speed and direction information to robustly detect human fall, as well as being able to detect falls toward eight different directions for multiple humans. Moreover, while most of the existing fall detection methods were designed only for indoor environment, experimental results demonstrate that this newly proposed method can effectively detect human fall in both indoor and outdoor environments.

     

A proposal of a new rotational-compliant joint with oil-hydraulic McKibben artificial muscles

Abstract

Conventional hydraulic actuators can generate a strong force due to high pressure. However, most of them are heavy and hard because they are made of metal. It is difficult to use such actuators in robots required to be as light as possible. Moreover, the joint mechanisms of these actuators have problems with intrinsic safety and robustness because the compliance is acquired using delicate sensors and advanced controls. Therefore, we propose a new rotational-compliant mechanism that allows the coexistence of strong force and compliance. The proposed mechanism has compliance in an active rotational direction and in two directions orthogonal to it. To realize this mechanism, we have developed a Hydraulic Artificial Muscle (HAM), which is very lightweight and able to generate strong force. Furthermore, the HAM has compliance without any advanced control. By exploiting the characteristics of the HAM, the function of the proposed mechanism can be realized even in conditions of compact dimensions. In this paper, by constructing a simple experimental system that imitates the proposed mechanism, and by modeling it, we verify its compliance from both a theoretical and an experimental point of view. We demonstrate that the mechanism has compliance in the three rotational directions.     

Periodic and non-concurrent error detection and identification in one-hot encoded FSMs

State-transition faults in digital sequential systems, such as finite-state logic controllers, have traditionally been handled by embedding the given system into a larger one, in a way that preserves the state evolution of the original system while enabling an external mechanism to concurrently perform checks to detect, identify and correct errors. In this paper, we develop a methodology for systematically constructing embeddings of one-hot encoded finite-state machines (FSMs) in a way that allows the external mechanism to capture transient state-transition faults via checks that are performed in a non-concurrent manner (e.g., periodically). More specifically, by employing coding techniques over finite fields, we completely characterize an appropriate class of redundant FSM embeddings and its corresponding non-concurrent error-detecting/identifying capabilities. These embeddings can be used to construct a redundant version of the given one-hot encoded FSM so that the external mechanism can detect and identify errors due to past state-transition faults based on an analysis of the current, possibly corrupted FSM state. As a result, the proposed error detection and identification approach relaxes the stringent requirements on the reliability of the checker and avoids the slowdown associated with concurrent checking.     

软件定义卫星网络的链路故障检测和恢复方案

针对具有星间链路的卫星网络,提出了一种软件定义卫星网络架构下的链路故障检测和恢复方案。首先基于软件定义卫星网络架构设计了一种主动上报式故障检测机制,并设计了链路故障检测算法,实现对卫星网络中链路故障的快速发现和准确定位。在此基础上,提出了一种保护加恢复式故障恢复机制来快速恢复因故障导致的业务中断。最后在原型系统中对该方案进行了验证。实验结果表明,该方案可以在毫秒级的时间内快速检测并准确定位到链路故障,并可以在10±2ms的时间内对故障进行快速恢复。同时,该方案可适用于多种卫星网络拓扑。     

Asymptotic tracking control of uncertain MIMO nonlinear systems with extended condition for controllability

For uncertain multiple-inputs multi-outputs nonlinear systems, it is nontrivial to achieve asymptotic tracking due to the intrinsic coupling among inputs, while the controllability conditions in most existing methods are rather restrictive or even impractical especially when unexpected actuator faults are involved. In this article, we focus on extending such controllability condition by resorting to the existence (instead of a priori knowledge) of some feasible auxiliary matrix, upon which a robust adaptive control scheme is first presented in the absence of actuator faults that is not only able to achieve asymptotic tracking even in the presence of non-parametric uncertainties with all the closed-loop signals globally ultimately uniformly bounded, but also able to deal with a larger class of system models. Furthermore, for the case with intermittent actuator faults, we develop a fault-tolerant control scheme with extended condition for controllability that is able to accommodate such faults automatically without using any fault detection or fault diagnosis unit. The effectiveness and benefits of the proposed method are verified via simulation on robotic systems.     

Toward designing intelligent PDEs for computer vision: An optimal control approach

Many computer vision and image processing problems can be posed as solving partial differential equations (PDEs). However, designing a PDE system usually requires high mathematical skills and good insight into the problems. In this paper, we consider designing PDEs for various problems arising in computer vision and image processing in a lazy manner: learning PDEs from training data via an optimal control approach. We first propose a general intelligent PDE system which holds the basic translational and rotational invariance rule for most vision problems. By introducing a PDE-constrained optimal control framework, it is possible to use the training data resulting from multiple ways (ground truth, results from other methods, and manual results from humans) to learn PDEs for different computer vision tasks. The proposed optimal control based training framework aims at learning a PDE-based regressor to approximate the unknown (and usually nonlinear) mapping of different vision tasks. The experimental results show that the learnt PDEs can solve different vision problems reasonably well. In particular, we can obtain PDEs not only for problems that traditional PDEs work well but also for problems that PDE-based methods have never been tried before, due to the difficulty in describing those problems in a mathematical way.