Enhancing distributed event predicate detection algorithms

Recently published algorithms for matching concurrent sets of events have the problem of unbounded message queue growth if events arrive in an undesirable order. This paper presents some algorithms that mitigate this problem by examining events waiting to be processed and removing those that cannot be part of a concurrent set     

Machine learning for event selection in high energy physics

The field of high energy physics aims to discover the underlying structure of matter by searching for and studying exotic particles, such as the top quark and Higgs boson, produced in collisions at modern accelerators. Since such accelerators are extraordinarily expensive, extracting maximal information from the resulting data is essential. However, most accelerator events do not produce particles of interest, so making effective measurements requires event selection, in which events producing particles of interest (signal) are separated from events producing other particles (background). This article studies the use of machine learning to aid event selection. First, we apply supervised learning methods, which have succeeded previously in similar tasks. However, they are suboptimal in this case because they assume that the selector with the highest classification accuracy will yield the best final analysis; this is not true in practice, as such analyses are more sensitive to some backgrounds than others. Second, we present a new approach that uses stochastic optimization techniques to directly search for selectors that maximize either the precision of top quark mass measurements or the sensitivity to the presence of the Higgs boson. Empirical results confirm that stochastically optimized selectors result in substantially better analyses. We also describe a case study in which the best selector is applied to real data from the Fermilab Tevatron accelerator, resulting in the most precise top quark mass measurement of this type to date. Hence, this new approach to event selection has already contributed to our knowledge of the top quark's mass and our understanding of the larger questions upon which it sheds light.     

An anomaly-introduced learning method for abnormal event detection

Multimedia Tools and Applications - Abnormal event detection aims at identifying anomalies under specific scene and it is widely utilized in health monitoring, public security and pedestrian...     

Machine learning algorithms for wireless sensor networks: A survey

Wireless sensor network (WSN) is one of the most promising technologies for some real-time applications because of its size, cost-effective and easily deployable nature. Due to some external or internal factors, WSN may change dynamically and therefore it requires depreciating dispensable redesign of the network. The traditional WSN approaches have been explicitly programmed which make the networks hard to respond dynamically. To overcome such scenarios, machine learning (ML) techniques can be applied to react accordingly. ML is the process of self-learning from the experiences and acts without human intervention or re-program. The survey of the ML techniques for WSNs is presented in [1], covering period of 2002–2013. In this survey, we present various ML-based algorithms for WSNs with their advantages, drawbacks, and parameters effecting the network lifetime, covering the period from 2014–March 2018. In addition, we also discuss ML algorithms for synchronization, congestion control, mobile sink scheduling and energy harvesting. Finally, we present a statistical analysis of the survey, the reasons for selection of a particular ML techniques to address an issue in WSNs followed by some discussion on the open issues.     

Adaptive and learning algorithms for seismic detection of personnel

This correspondence is concerned with adaptive digital processing to extract impulse-like signal features from the correlated background noise for detection of intruders with the seismic sensor data. Both the adaptive digital filtering and the adaptive Kalman filtering methods are developed and shown to perform nearly the same for a short data segment. For continued processing of a long duration seismic record, the adaptive Kalman filtering considered has better capability to learn the nonstationary data characteristics than the considered adaptive filtering and to adaptively remove the background noise. Detailed experimental results are presented. Other considerations such as the hardware implementation and the relationships among the parameters are also examined.     

Classification-oriented structure learning in Bayesian networks for multimodal event detection in videos

We investigate the use of structure learning in Bayesian networks for a complex multimodal task of action detection in soccer videos. We illustrate that classical score-oriented structure learning algorithms, such as the K2 one whose usefulness has been demonstrated on simple tasks, fail in providing a good network structure for classification tasks where many correlated observed variables are necessary to make a decision. We then compare several structure learning objective functions, which aim at finding out the structure that yields the best classification results, extending existing solutions in the literature. Experimental results on a comprehensive data set of 7 videos show that a discriminative objective function based on conditional likelihood yields the best results, while augmented approaches offer a good compromise between learning speed and classification accuracy.     

Unsupervised deep learning system for local anomaly event detection in crowded scenes

Multimedia Tools and Applications - Anomaly detection in video surveillance is a significant research subject because of its immense use in real-time applications. These days, open spots like...     

机器学习在乳腺肿瘤分类检测中的应用研究

机器学习算法在医学检测与诊断,尤其是乳腺肿瘤分类检测与诊断中扮演愈发重要的角色。分析比较了几种经典机器学习分类器在乳腺肿瘤分类检测中的性能,并从准确率、灵敏度、特异性及执行效率等方面对各分类器的性能进行了评估比较,根据在不同数据库上的实验结果,总结了各机器学习分类器在乳腺肿瘤分类中的性能特点:线性判别分析和极限学习机两种分类器性能优良且训练效率很高;支持向量机性能较为平均且非常稳定,但训练耗时较长;而人工神经网络分类器虽然可以给出良好的特异性指标,但灵敏度指标不够理想。     

深度学习行人检测方法综述

行人检测技术在智能交通系统、智能安防监控和智能机器人等领域均表现出了极高的应用价值,已经成为计算机视觉领域的重要研究方向之一。得益于深度学习的飞速发展,基于深度卷积神经网络的通用目标检测模型不断拓展应用到行人检测领域,并取得了良好的性能。但是由于行人目标内在的特殊性和复杂性,特别是考虑到复杂场景下的行人遮挡和尺度变化等问题,基于深度学习的行人检测方法也面临着精度及效率的严峻挑战。本文针对上述问题,以基于深度学习的行人检测技术为研究对象,在充分调研文献的基础上,分别从基于锚点框、基于无锚点框以及通用技术改进(例如损失函数改进、非极大值抑制方法等)3个角度,对行人检测算法进行详细划分,并针对性地选取具有代表性的方法进行详细结合和对比分析。本文总结了当前行人检测领域的通用数据集,从数据构成角度分析各数据集应用场景。同时讨论了各类算法在不同数据集上的性能表现,对比分析各算法在不同数据集中的优劣。最后,对行人检测中待解决的问题与未来的研究方法做出预测和展望。如何缓解遮挡导致的特征缺失问题、如何应对单一视角下尺度变化问题、如何提高检测器效率以及如何有效利用多模态信息提高行人检测精度,均是值得进一步...     

Machine learning for intrusion detection in MANET: a state-of-the-art survey

Machine learning consists of algorithms that are first trained with reference input to “learn” its specifics and then used on unseen input for classification purposes. Mobile ad-hoc wireless networks (MANETs) have drawn much attention to research community due to their advantages and growing demand. However, they appear to be more susceptible to various attacks harming their performance than any other kind of network. Intrusion Detection Systems represent the second line of defense against malevolent behavior to MANETs, since they monitor network activities in order to detect any malicious attempt performed by intruders. Due to the inherent distributed architecture of MANET, traditional cryptography schemes cannot completely safeguard MANETs in terms of novel threats and vulnerabilities, thus by applying machine learning methods for IDS these challenges can be overcome. In this paper, we present the most prominent models for building intrusion detection systems by incorporating machine learning in the MANET scenario. We have structured our survey into four directions of machine learning methods: classification approaches, association rule mining techniques, neural networks and instance based learning approaches. We analyze the most well-known approaches and present notable achievements but also drawbacks or flaws that these methods have. Finally, in concluding our survey we provide some findings of paramount importance identifying open issues in the MANET field of interest.     

New algorithms for budgeted learning

We explore the problem of budgeted machine learning, in which the learning algorithm has free access to the training examples’ class labels but has to pay for each attribute that is specified. This learning model is appropriate in many areas, including medical applications. We present new algorithms for choosing which attributes to purchase of which examples, based on algorithms for the multi-armed bandit problem. In addition, we also evaluate a group of algorithms based on the idea of incorporating second-order statistics into decision making. Most of our algorithms are competitive with the current state of art and performed better when the budget was highly limited (in particular, our new algorithm AbsoluteBR2). Finally, we present new heuristics for selecting an instance to purchase after the attribute is selected, instead of selecting an instance uniformly at random, which is typically done. While experimental results showed some performance improvements when using the new instance selectors, there was no consistent winner among these methods.     

Spectral algorithms for supervised learning

We discuss how a large class of regularization methods, collectively known as spectral regularization and originally designed for solving ill-posed inverse problems, gives rise to regularized learning algorithms. All of these algorithms are consistent kernel methods that can be easily implemented. The intuition behind their derivation is that the same principle allowing for the numerical stabilization of a matrix inversion problem is crucial to avoid overfitting. The various methods have a common derivation but different computational and theoretical properties. We describe examples of such algorithms, analyze their classification performance on several data sets and discuss their applicability to real-world problems.     

Smart priority queue algorithms for self-optimizing event storage

Low run-time overhead, self-adapting storage policies for priority queues called smart priority queue (SPQ) techniques are developed and evaluated. The proposed SPQ policies employ a low-complexity linear queue for near-head activities and a rapid-indexing variable bin-width calendar queue for distant events. The SPQ configuration is determined by monitoring queue access behavior using cost-scoring factors and then applying heuristics to adjust the organization of the underlying data structures. To illustrate and evaluate the method, an SPQ-based scheduler for discrete event simulation has been implemented and was used to assess the resulting efficiency, components of access time, and queue usage distributions of the existing and proposed algorithms. Results indicate that optimizing storage to the spatial distribution of queue access can decrease HOLD operation cost between 25% and 250% over existing algorithms such as calendar queues.     

Machine learning regression algorithms for biophysical parameter retrieval: Opportunities for Sentinel-2 and -3

ESA's upcoming satellites Sentinel-2 (S2) and Sentinel-3 (S3) aim to ensure continuity for Landsat 5/7, SPOT-5, SPOT-Vegetation and Envisat MERIS observations by providing superspectral images of high spatial and temporal resolution. S2 and S3 will deliver near real-time operational products with a high accuracy for land monitoring. This unprecedented data availability leads to an urgent need for developing robust and accurate retrieval methods. Machine learning regression algorithms may be powerful candidates for the estimation of biophysical parameters from satellite reflectance measurements because of their ability to perform adaptive, nonlinear data fitting.By using data from the ESA-led field campaign SPARC (Barrax, Spain) we have compared the utility of four state-of-the-art machine learning regression algorithms and four different S2 and S3 band settings to assess three important biophysical parameters: leaf chlorophyll content (Chl), leaf area index (LAI) and fractional vegetation cover (FVC). The tested Sentinel configurations were: S2-10 m (4 bands), S2-20 m (8 bands), S2-60 m (10 bands) and S3-300 m (19 bands), and the tested methods were: neural networks (NN), support vector regression (SVR), kernel ridge regression (KRR), and Gaussian processes regression (GPR).GPR outperformed the other retrieval methods for the majority of tested configurations and was the only method that reached the 10% precision required by end users in the estimation of Chl. Also, although validated with an RMSE accuracy around 20%, GPR yielded optimal LAI and FVC estimates at highest S2 spatial resolution of 10 m with only four bands. In addition to high accuracy values, GPR also provided confidence intervals of the estimates and insight in relevant bands, which are key advantages over the other methods. Given all this, GPR proved to be a fast and accurate nonlinear retrieval algorithm that can be potentially implemented for operational monitoring applications.     

Observation strategies for event detection with incidence on runtime verification: theory, algorithms, experimentation

Many applications (such as system and user monitoring, runtime verification, diagnosis, observation-based decision making, intention recognition) all require to detect the occurrence of an event in a system, which entails the ability to observe the system. Observation can be costly, so it makes sense to try and reduce the number of observations, without losing full certainty about the event??s actual occurrence. In this paper, we propose a formalization of this problem. We formally show that, whenever the event to be detected follows a discrete spatial or temporal pattern, then it is possible to reduce the number of observations. We discuss exact and approximate algorithms to solve the problem, and provide an experimental evaluation of them. We apply the resulting algorithms to verification of linear temporal logics formulæ. Finally, we discuss possible generalizations and extensions, and, in particular, how event detection can benefit from logic programming techniques.     

基于深度学习的图像边缘检测算法综述

边缘检测是将图像中的突变的重要信息提取出来的过程,是计算机视觉领域研究热点,也是图像分割、目标检测与识别等多种中高层视觉任务的基础。近几年来,针对边缘轮廓线过粗以及检测精度不高等问题,业内提出了谱聚类、多尺度融合、跨层融合等基于深度学习的边缘检测算法。为了使更多研究者了解边缘检测的研究现状,首先,介绍了传统边缘检测的实现理论及方法;然后,总结了近年来基于深度学习的主要边缘检测方法,并依据实现技术对这些方法进行了分类,对其涉及的关键技术进行分析,发现对多尺度多层次融合与损失函数的选择是重要的研究方向。通过评价指标对各类方法进行了比较,可知边缘检测算法在伯克利大学数据集（BSDS500）上的最优数据集规模（ODS）经过多年研究从0.598提高到了0.828,接近人类视觉水平。最后,展示了边缘检测算法研究的发展方向。     

基于深度学习的图像边缘检测算法综述

边缘检测是将图像中的突变的重要信息提取出来的过程，是计算机视觉领域研究热点，也是图像分割、目标检测与识别等多种中高层视觉任务的基础。近几年来，针对边缘轮廓线过粗以及检测精度不高等问题，业内提出了谱聚类、多尺度融合、跨层融合等基于深度学习的边缘检测算法。为了使更多研究者了解边缘检测的研究现状，首先，介绍了传统边缘检测的实现理论及方法；然后，总结了近年来基于深度学习的主要边缘检测方法，并依据实现技术对这些方法进行了分类，对其涉及的关键技术进行分析，发现对多尺度多层次融合与损失函数的选择是重要的研究方向。通过评价指标对各类方法进行了比较，可知边缘检测算法在伯克利大学数据集（BSDS500）上的最优数据集规模（ODS）经过多年研究从0.598提高到了0.828，接近人类视觉水平。最后，展示了边缘检测算法研究的发展方向。     

基于遗传算法和强化学习的贝叶斯网络结构学习算法

遗传算法是基于自然界中生物遗传规律的适应性原则对问题解空间进行搜寻和最优化的方法。贝叶斯网络是对不确定性知识进行建模、推理的主要方法,Bayesian网中的学习问题(参数学习与结构学习)是个NP-hard问题。强化学习是利用新顺序数据来更新学习结果的在线学习方法。介绍了利用强化学习指导遗传算法,实现对贝叶斯网结构进行有效学习。     

Integrating the enriched feature with machine learning algorithms for human movement and fall detection

Movement detection is gaining more and more attention among various pattern recognition problems. Recognizing human movement activity types is extremely useful for fall detection for elderly people. Wireless sensor network technology enables human motion data from wearable wireless sensor devices be transmitted for remote processing. This paper studies methods to process the human motion data received from wearable wireless sensor devices for detecting different types of human movement activities such as sitting, standing, lying, fall, running, and walking. Machine learning methods K Nearest Neighbor algorithm (KNN) and the Back Propagation Neural Network (BPNN) algorithm are used to classify the activities from the data acquired from sensors based on sample data. As there are a large amount of real-time raw data received from sensors and there are noises associated with these data, feature construction and reduction are used to preprocess these raw sensor data obtained from accelerometers embedded in wireless sensing motes for learning and processing. The singular value decomposition (SVD) technique is used for constructing the enriched features. The enriched features are then integrated with machine learning algorithms for movement detection. The testing data are collected from five adults. Experimental results show that our methods can achieve promising performance on human movement recognition and fall detection.