A Novel Framework for Human Activity Recognition with Time Labelled Real Time Sensor Data

Human activity recognition is an effective approach for identifying the characteristics of historical data. In the past decades, different shallow classifiers and handcrafted features were used to identify the activities from the sensor data. These approaches are configured for offline processing and are not suitable for sequential data. This article proposes an adaptive framework for human activity recognition using a deep learning mechanism. This deep learning approach forms the deep belief network (DBN), which contains a visible layer and hidden layers. The processing of raw sensor data is performed by these layers and the activity is identified at the top most layers. The DBN is tested using the real time environment with the help of mobile devices that contain an accelerometer, a magnetometer, and a gyroscope. The results are analyzed with the metrics of precision, recall, and the F1-score. The results proved that the proposed method has a higher F1_score when compared to the existing approach.     

大规模隐式反馈的词向量音乐推荐模型

现有音乐推荐系统在大规模隐式反馈场景下存在推荐困难的问题,提出大规模隐式反馈的词向量音乐推荐模型（Word-Embedding Based Implicit Music Recommender）.本模型借鉴了自然语言处理领域的Word2Vec技术,通过学习用户音乐收藏播放记录里的歌曲共现信息,获得用户、音乐在分布式空间的低维、紧致的向量表示,从而得到用户、音乐之间的相似度进行推荐,并且在理论上论述了Word2Vec技术应用在推荐系统上的正确性.该模型在保证准确率和召回率几乎不变的同时,收敛速度快,占用内存小,试验结果表明该模型有效的解决了大规模隐性反馈场景下音乐推荐困难的问题.     

基于3D-CNN的暴力行为检测

大量的研究行为识别方法集中在检测简单的动作,如：步行,慢跑或者跳跃等;针对于打斗或者动作复杂的攻击性行为则研究较少;而这些研究在某些监控场景下非常有用,如：监狱,自助银行,商场等. 传统的暴力行为识别研究方法主要利用先验知识来手动设计特征,而本文提出了一种基于3D-CNN结构的暴力检测方法,通过三维深度神经网络直接对输入进行操作,能够很好的提取暴力行为的时空特征信息,从而进行检测. 从实验结果可以看出,本文方法能较好地识别出暴力行为,准确率要高于人工设计特征的方法.     

计算机视觉技术的车型识别应用研究

针对目前立体停车库主要采用传统的传感器入库检测系统来识别车辆信息,存在施工周期长、器件损坏率较高,维护成本较高的问题,提出了一种应用计算机视觉技术的车型识别解决方案.应用卷积神经网络框架Caffe,基于Caf-feNet模型,通过fine-tuning模型优化以及参数优化,最终得到了一个性能较优异的识别模型.实验结果表明,该模型可克服输入图片背景复杂多变,目标被遮挡的情况,对轿车车型识别这一问题鲁棒性好,具有一定的可行性及应用价值.     

Finite Element Analysis of 6300 Deep Groove Ball Bearing

Rolling bearing is widely used in mechanical support, its general components are the inner ring, outer ring, the ball, retainer etc.. Now many companies in developed countries and university in the rolling bearing as the research object, and has made great progress in design theory, the experiment method and production technology etc. We will use the finite element ANSYS to establish the model of deep groove ball bearing. Through the contact analysis, we can get the contact stress between the rings and balls, strain, contact state, penetration, sliding distance and the friction stress distribution. These values are compared to the theoretical values with Hertz theory, and they have better consistency, provide the good theoretical basis for the optimization design of rolling bearings.     

底层相关的VLSI高层次设计策略

在ＶＬＳＩ系统设计、行为设计和逻辑设计过程中,未考虑到的与半导体制造工艺有关的因素（如延迟、功耗问题等）严重影响设计结果的性能,以至使物理设计结果的性能远离原来的设计目标,针对这个问题,文中提出与底层有关的ＶＬＳＩ高层次设计策略,将影响性能的底层参数和信息引入高层次设计中,使得高层次设计结果在进行物理实现之时能满足性能要求。     

弹性波硬度传感器的设计应用

介绍采用磁弹性波检测材料硬度的一种新技术 ,采用该技术可实现在线、无损、便携测量 ,测量时间短 ,准确度高等特点     

Classical Modal Display Logic in the Calculus of Structures and Minimal Cut-free Deep Inference Calculi for S5

We begin by showing how to faithfully encode the Classical ModalDisplay Logic (CMDL) of Wansing into the Calculus of Structures(CoS) of Guglielmi. Since every CMDL calculus enjoys cut-elimination,we obtain a cut-elimination theorem for all corresponding CoScalculi. We then show how our result leads to a minimal cut-freeCoS calculus for modal logic S5. No other existing CoS calculifor S5 enjoy both these properties simultaneously.     

On the complexity of approximating k-set packing

Given a k-uniform hypergraph, the Maximum k -Set Packing problem is to find the maximum disjoint set of edges. We prove that this problem cannot be efficiently approximated to within a factor of unless P = NP. This improves the previous hardness of approximation factor of by Trevisan. This result extends to the problem of k-Dimensional-Matching.     

包钢焦化厂水处理技术的研究及应用经验

针对包钢焦化厂高硬度、高浊度的水质条件,用静态和动态方法研究了一类水质配方的缓蚀、阻垢性能.实践证明,该配方具有良好的缓蚀、阻垢性能.同时,通过水处理的10年应用,积累了丰富的经验.为焦化厂换热设备安全、稳定、高效运行提供了保证.