基于Android系统的人脸识别门禁系统的设计

智能门禁系统是安全防护系统中重要的组成部分 ,本文采用人脸识别技术与手机端身份识别技术,设计了一种基于Android的人脸识别门禁系统,实现了用户在Android手机端进行人脸识别身份验证获取服务器发来的二维码作为开门“软钥匙”,用获取到的二维码去智能门禁终端进行扫码开门的功能。在人脸识别方面,采用了Adaboost人脸检测算法和PCA人脸识别算法,并结合OpenCV实现了门禁系统的人脸识别。测试结果表明：本系统具有良好的易用性、安全性,并且获得较高的人脸识别率和识别速度,从而弥补传统门禁的缺陷与不足。     

Developing a module-based security system for an intelligent home

The security system in a workplace or home is important to human life. Unlucky events are often caused by the negligence of humans. We have developed a modulebased security system for home automation. The structure of the security system contains many modules. Each module has two types of interface (wireless RF and speech). There are active and passive modules in the security system. The active security module is a smart robot. We have designed many types of smart robot for the security system. The passive security modules include a fire security module, an intruder security module, an environment security module, a gas security module, an AC power security module, and an appliance control module. In the security module, we use multisensor fusion algorithms to decide the exact output. In these modules, we use a two-wire communication method through the wireless RF interface, and a voice alarm for serious events, and transmit the real-time status to the supervised computer. In the smart robot system, we have designed many types of smart robot for the security system. We have designed a general user interface (GUI) for the intelligent security system. The user interface can supervise these modules and the smart robots via the wireless RF device, and supervise the security system via wireless, Internet, and cell phone.     

基于IPSec VPN的手机安全系统研究

移动网络环境存在诸多安全威胁,为保证信息传输的安全性,该文讨论了移动环境下的安全威胁,实现了一个在移动环境下建立IPSec VPN连接的终端系统。该系统利用NDIS实现防火墙穿越,以保证IPSec数据包的正常传输。同时利用安全智能卡存储X．509证书,用于身份验证,防止非法用户的入侵。     

基于STM8L的门锁控制和状态识别

门禁系统是一种管理人员进出的数字化智能系统,可以实时监控门的状态和合法用户的进出状况,防止非法用户强制闯入。门禁系统作为智能家居系统的一部分,在现代安防领域发挥了巨大作用,也给用户的使用和管理带来了极大的便利性、高效性和安全性。本文介绍了利用具有超低功耗的STM8L微控制器为控制核心,设计了基于125KHz的射频读卡模块,采用EM4100系列ID卡作为用户身份识别卡,实现了对门锁的控制和状态的识别,并通过总线方式与服务器进行通信。实践表明,该系统整体功耗低、性能稳定、使用安全、管理方便。     

基于智能手机的远程家电控制及安防监测系统的设计

设计了基于智能手机和GPRS网络的远程家电控制和安防监测系统.智能手机采用开放式操作系统,第三方可根据操作系统提供的API为其开发各种扩展应用.利用智能手机这一特性,开发用于系统的人机接口,方便了用户的操作.介绍了系统的结构和功能,详细阐述了智能手机监控软件的开发过程.     

面向连续叠写的高精简中文手写识别方法研究

连续手写识别是中文手写输入技术的核心,自然、快捷地输入中文信息一直是模式识别乃至人工智能领域追求的目标。提出了一种有效克服小屏幕限制的连续叠写汉字识别方法。该方法基于切分-识别集成的解码框架,先使用过切分算法处理输入的书写轨迹;然后启用一种新颖的感知机算法判定字符的边界;随后采用来自字符分类模型、几何模型和语言模型的多种上下文信息进行路径解码。为适应不同类型的移动终端,特别提出了一种高效压缩字符分类模型的方法,以有效减少字符识别过程对存储和内存的占用。该识别方法已在Android平台上部署,并进行了大规模的测试实验。实验结果证实了该识别方法的性能和效率。     

面向智能家居的区块链轻量级认证机制

5G技术为智能家居行业开拓了更大的发展空间,但安全问题也日益突出,用户身份认证作为信息安全防护的第一道关卡备受关注.智能家居系统传统的认证方法存在中心化信任挑战,且资源开销大.区块链技术因其去中心化、不可篡改等优势成为研究热点,为实现分布式智能家居系统安全认证提供了新思路.但无中心认证面临着用户与多个分布式终端认证的效率问题和用户隐私泄露问题两个方面的挑战.提出了一种基于区块链的动态可信轻量级认证机制(dynamic trusted lightweight authentication mechanism, DTL). DTL机制采用联盟链构建区块链系统,既保证了仅授权的智能家居传感器节点可加入网络,又满足分布式高效认证和安全访问需求.DTL具有以下优点:(1)针对认证效率问题,通过改进共识算法建立面向智能家居的动态可信传感设备组(DTsensorgroup,DTSG)认证机制,避免了传统的用户端与传感终端或者网关节点之间一对一的频繁认证引起的接入效率低和用户访问速率低问题,实现了轻量级认证;(2)针对用户隐私保护问题,创新性地设计了DTSG机制和零知识证明结合的认证方案,在不泄露用户...     

A user-guided personalization methodology to facilitate new smart home occupancy

Smart homes are becoming increasingly popular in providing people with the services they desire. Activity recognition is a fundamental task to provide personalised home facilities. Many promising approaches are being used for activity recognition; one of them is data-driven. It has some fascinating features and advantages. However, there are drawbacks such as the lack of ability to providing home automation from the day one due to the limited data available. In this paper, we propose an approach, called READY (useR-guided nEw smart home ADaptation sYstem) for developing a personalised automation system that provides the user with smart home services the moment they move into their new house. The system development process was strongly user-centred, involving users in every step of the system’s design. Later, the user-guided transfer learning approach was introduced that uses an old smart home data set to enhance the existing smart home service with user contributions. Finally, the proposed approach and designed system were tested and validated in the smart lab that showed promising results.

     

Evolution towards smart home environments: empirical evaluation of three user interfaces

Smart home environments have evolved to the point where everyday objects and devices at home can be networked to give the inhabitants new means to control them. Familiar information appliances can be used as user interfaces (UIs) to home functions to achieve a more convenient user experience. This paper reports an ethnographic study of smart home usability and living experience. The purpose of the research was to evaluate three UIs—a PC, a media terminal, and a mobile phone—for smart home environments. The results show two main types of activity patterns, pattern control and instant control, which require different UI solutions. The results suggest that a PC can act as a central unit to control functions for activity patterns that can be planned and determined in advance. The mobile phone, on the other hand, is well suited for instant control. The mobile phone turned out to be the primary and most frequently used UI during the 6-month trial period in the smart apartment.     

Android手机的智能家居语音控制系统设计

设计了一款基于Android手机的智能家居语音控制系统,通过Android手机的APP"语音"按钮实现一键式控制、智能应答,语音识别模块和语音合成模块整合到上位机上,减少了在语音识别和语音合成方面的硬件开支.下位机由STC89C52单片机、HC-06蓝牙模块、1602液晶显示模块及相应的电路组成.系统能够实现语音控制家居照明系统的开关、定时、状态查询与显示,电视的开关、音量和频道切换等功能.     

A soft computing based location-aware access control for smart buildings

The evolution of wireless communications and pervasive computing is transforming current physical spaces into real smart environments. These emerging scenarios are expected to be composed by a potentially huge amount of heterogeneous smart objects which can be remotely accessed by users via their mobile devices anytime, anywhere. In this paper, we propose a distributed location-aware access control mechanism and its application in the smart building context. Our approach is based on an access control engine embedded into smart objects, which are responsible to make authorization decisions by considering both user location data and access credentials. User location data are estimated using a novel indoor localization system based on magnetic field data sent by user through her personal phone. This localization system implements a combination of soft computing techniques over the data collected by smartphones. Therefore, our location-aware access control mechanism does not require any intermediate entity, providing the benefits of a decentralized approach for smart environments. From the results obtained, we can consider our proposal as a promising approach to tackle the challenging security requirements of typical pervasive environments.     

基于区块链应用模式的铁路旅客身份认证系统

采用“区块链技术+不对称加密+生物识别+身份认证”应用模式，依托智能手机客户端设计与开发一套铁路旅客身份认证系统.基于Ethereum开发平台，应用truffle开发框架，实现铁路旅客身份认证系统智能合约的编写与部署.系统针对传统铁路身份认证模式的不足，将旅客身份数据分布式存储，弱化中心化服务器的压力，提升旅客身份数据的安全性和鲁棒性；进行生物信息认证确保旅客对身份信息的所有权；利用非对称加密技术在保护旅客隐私、实现实名制的前提下增强数据的透明性.基于区块链应用模式的铁路旅客身份认证系统能够让用户身份实现本地存储、信息摘要链上校验，实现铁路旅客身份信息数据访问的细粒度控制，保障铁路旅客身份信息安全，提升铁路旅客的乘车体验.     

An optimal cluster based security and resilience of smart home environments using hybrid soft computing techniques

Smart home is the main part of smart intelligent system here the remote users share the sensitive information through an insecure medium to access such smart devices, which becomes security issues. The recent user authentication protocols have used to solve those problems and provide secure communication. Consumer traffic increase the risk of illegal user as legal user and radio channels are extra vulnerable to listeners. For further security enhancement, we proposed an optimal cluster based remote user authentication (OCRUA) protocol for smart home environment using hybrid soft computing techniques. The first contribution of proposed protocol is to introduce squirrel induced butterfly optimization (SBO) algorithm for cluster formation, which groups the smart devices. Then, we compute the cluster head (CH) using the teacher learning based deep neural network (TL-DNN) based on multiple design constraints. The second contribution is to illustrate remote user authentication using optimal elliptic curve cryptography (OECC) which encrypts the sensitive information before forward to gateway. At long last, the concert of planned OCRUA protocol evaluates use different replication scenarios and shows the effectiveness over the existing state-of-art protocols.     

基于实时样本采集的个性化手写汉字输入系统设计

手写汉字识别是手写汉字输入的基础。目前智能设备中的手写汉字输入法无法根据用户的汉字书写习惯,动态调整识别模型以提升手写汉字的正确识别率。通过对最新深度学习算法及训练模型的研究,提出了一种基于用户手写汉字样本实时采集的个性化手写汉字输入系统的设计方法。该方法将采集用户的手写汉字作为增量样本,通过对服务器端训练生成的手写汉字识别模型的再次训练,使识别模型能够更好地适应该用户的书写习惯,提升手写汉字输入系统的识别率。最后,在该理论方法的基础上,结合新设计的深度残差网络,进行了手写汉字识别的对比实验。实验结果显示,通过引入实时采集样本的再次训练,手写汉字识别模型的识别率有较大幅度的提升,能够更有效的满足用户在智能设备端对手写汉字输入系统的使用需求。     

Supporting social interaction with smart phones

The smart phone offers communication, connectivity, content consumption, and content creativity. Seven different systems exemplify its ability to support a wide range of social interactions, helping make pervasive computing a reality. For smart phones to become successful pervasive system components, they must support and enhance various user activities and offer useful, effective functionality. The systems the author have built focuses on augmenting and enhancing communication; they're communication devices first and computers second. The system supports social interaction between people n particular, interaction that would be difficult if not impossible to achieve without the smart phone technology. This dependency on the system endows them with a degree of utility that drives their effectiveness, which is key to increasing the use of pervasive systems.     

User adaptive handwriting recognition by self-growing probabilistic decision-based neural networks

Based on self-growing probabilistic decision-based neural networks (SPDNNs), user adaptation of the parameters of SPDNN is formulated as incremental reinforced and anti-reinforced learning procedures, which are easily integrated into the batched training procedures of the SPDNN. In this study, we developed: 1) an SPDNN based handwriting recognition system; 2) a two-stage recognition structure; and 3) a three-phase training methodology for a global coarse classifier (stage 1), a user independent hand written character recognizer (stage 2), and a user adaptation module on a personal computer. With training and testing on a 600-word commonly used Chinese character set, the recognition results indicate that the user adaptation module significantly improved the recognition accuracy. The average recognition rate increased from 44.2% to 82.4% in five adapting cycles, and the performance could finally increase up to 90.2% in ten adapting cycles.     

Mutual authentication scheme for smart devices in IoT-enabled smart home systems

The emergence of Internet of Things (IoT) technology has yielded a firm technical basis for the construction of a smart home. A smart home system offers occupants the convenience of remote control and automation of household systems. However, there are also potential security risks associated with smart home technologies. The security of users in a smart home environment is related to their life and possessions. A significant amount of research has been devoted to studying the security risks associated with IoT-enabled smart home systems. The increasing intelligence of devices has led to a trend of independent authentication between devices in smart homes. Therefore, mutual authentication for smart devices is essential in smart home systems. In this paper, a mutual authentication scheme is proposed for smart devices in IoT-enabled smart home systems. Signature updates are provided for each device. In addition, with the assistance of a home gateway, the proposed scheme can enable devices to verify the identity of each other. According to the analysis, the proposed scheme is secure against a forged SD or a semi-trusted HG. The computational cost of the proposed scheme in the simulation is acceptable for the application in smart home systems.     

语音对抗攻击与防御方法综述

人工智能的不断发展,使得人与机器的交互变得至关重要.语音是人与智能通讯设备之间通信的重要手段,在近几年飞速发展,说话人识别、情感识别、语音识别得到广泛地普及与应用.特别的,随着深度学习的兴起,基于深度学习的语音技术使机器理解语音内容、识别说话人方面达到近似人的水平,无论是效率还是准确度都得到了前所未有的提升.例如手机语...     

RGB-D行为识别研究进展及展望

行为识别是计算机视觉领域很重要的一个研究问题，其在安全监控、机器人设计、无人驾驶和智能家庭设计等方面都有着非常重要的应用.基于传统RGB视频的行为识别方法由于容易受背景、光照等行为无关因素的影响，导致识别精度不高.廉价RGB-D摄像头出现之后，人们开始从一个新的途径解决行为识别问题.基于RGB-D摄像头的行为识别通过聚合RGB、深度和骨架三种模态的行为数据，可以融合不同模态的行为信息，从而可以克服传统RGB视频行为识别的缺陷，也因此成为近几年的一个研究热点.本文系统地综述了RGB-D行为识别领域的研究进展和展望.首先，对近年来RGB-D行为识别领域中常用的公共数据集进行简要的介绍；同时也系统地介绍了多模态RGB-D行为识别研究领域的典型模型和最新进展，其中包括卷积神经网络（Convolution neural network，CNN）和循环神经网络（Recurrent neural network，RNN）等深度学习技术在RGB-D行为识别的应用；最后，在三个公共RGB-D行为数据库上对现有方法的优缺点进行了比较和分析，并对未来的相关研究进行了展望.     

基于RNN的多传感器融合室内定位方法

针对室内空间内的人员定位困难问题进行了研究,提出了一种基于Wi-Fi指纹法和循环神经网络(re-current neural network,RNN)的多传感器融合室内定位算法.该算法将智能手机接收到的路由器信号强度作为时间序列输入RN N,通过RN N获得对行人精度较高的定位,与此同时获取智能手机中惯性测量单元提供的位置信息.随后,通过粒子滤波算法对两种定位方式的定位结果进行融合.在实际场景下设计了多组实验进行对比.实验结果表明,该算法定位平均误差为0.9 m,优于加权K近邻等算法,可以为行人提供实时的定位.