一种使用视觉反馈与行为记忆的蚁群优化算法

在分析现有改进算法的基础上,结合视知觉及认知心理学的相关理论,提出一种具备视觉反馈与行为记忆学习能力的新型蚁群算法:首先,建立视觉模型使得蚂蚁能够通过人工视觉感知周围目标城市的分布,用视知觉修正信息素噪声,提高蚂蚁探索质量;其次,建立行为记忆学习模型,使蚂蚁能够从已经走过的局部最优路径中提取经验来指导周游活动,加快算法收敛速度并强化寻优能力.经过与传统改进策略比较发现,新算法在求解质量与求解时间上均有明显改进.     

基于压力式光纤液位传感器的变压器油高度监测系统

针对传统电力变压器绝缘油位测量的局限性,提出一种压力式光纤液位传感器的变压器绝缘油位监测系统.系统采用压力式光纤液位传感器作为绝缘油位的传感器件,该传感器对光源强度变化、光纤传输过程中的光功率损耗具有光强起伏补偿功能;以数字信号处理器TMS320F2812为处理和控制核心,实现对变压器油位的无人实时在线监测.分析了油位...     

高灵敏度金属分离器传感线圈的设计

分析了电感线圈探测金属的理论,针对传统的金属探测传感器灵敏度低,抗干扰能力差和结构复杂的缺点,根据电磁感应原理提出了一种具有高探测精度和高抗干扰能力的新型金属探测传感器,并描述了其结构和材料设计方案。最后用试验验证了设计思想和设计方案的正确性和实用性。     

差动吸收式SO2光纤传感器的研究

本文基于气体的窄带光吸收特性 ,研究了 SO2 气体浓度与载波光强的关系 ,在此基础上 ,设计了一种检测该气体浓度的差动光纤传感器及其系统 ,对改善仪器精度等特性指标的主要因素进行分析。实验结果表明该仪器具有较高的灵敏度和精度。     

Structured Reactive Controllers

Service robots, such as autonomous office couriers or robot tourguides, must be both reliable and efficient. This requires them to flexibly interleave their tasks, exploit opportunities, quickly plan their course of action, and, if necessary, revise their intended activities. In this paper, we show how structured reactive controllers (SRCs) satisfy these requirements. The novel feature of SRCs is that they employ and reason about plans that specify and synchronize concurrent percept-driven behavior. Powerful control abstractions enable SRCs to integrate physical action, perception, planning, and communication in a uniform framework and to apply fast but imperfect computational methods without sacrificing reliability and flexibility. Concurrent plans are represented in a transparent and modular form so that automatic planning processes can reason about the plans and revise them. We present experiments in which SRCs are used to control two autonomous mobile robots. In one of them an SRC controlled the course of action of a museum tourguide robot that has operated for thirteen days, more than ninetyfour hours, completed 620 tours, and presented 2668 exhibits.     

基于彩色图像的色系坐标变换的面部定位与跟踪法

文中通过对彩色图像的色彩因素的分析,得出了关于色度与彩色坐标系的关系,建立了相应的肤色,唇色色系的坐标变换方法,基于这种坐标系,可以通过简单的阈值 定,得到彩色图像的人睑面部定位与跟踪的方法,此方法能有效、稳健地测得目标的位置,不受对象姿态、背景的影响,通过在线学习还可以支除光照条件变化的影响及摄像设备的影响,它是利用彩色图像中对亮度信息规一化处理后、提取出来的相对稳定的色义来检测和确定目标,进行     

可信度理论与测试

软件的可靠性估计、程序结构及测试之间存在着重要的联合,针对一个程序及其输入值有限集,可以由测试来处理所精心定义的程序状态。但是,程序测试的基本理论仍不明了,其部分原因是测试的目标不明确,对测试或者测试方法的评价也没有统一的标准,测试不应该以纠错为最终目标,其最终目标应该是精度量被估测软件的可靠性。其于这个目标,需要提出蝗可信度理论,并以它为基础,明确应该使用什么样的测试方法及测试环境。目前可信度理     

基于知觉加工模式的发展式分词算法

分词是自然语言理解的一个重要过程,由于语言问题又是最重要的心理学问题之一,所以从认知心理学和发展心理学的观点出发,将分词问题看成是知觉问题在语言信息处理过程中的一部分,把知觉表达和知觉的双向加工过程引入对分词问题的分析,并同时考虑言语发展的心理过程,把对言语发展规律的归纳作为构造学习算法的基础和模板,以进化的方式来逐步改进自然语言理解系统的性能,从而避免知识获取瓶颈在自然语言理解问题中的出现。     

Accident history,risk perception and traffic safe behaviour

Abstract

This study clarifies the associations between accident history, perception of the riskiness of road travel and traffic safety behaviours by taking into account the number and severity of accidents experienced. A sample of 525 road users in Cameroon answered a questionnaire comprising items on perception of risk, safe behaviour and personal accident history. Participants who reported involvement in more than three accidents or involvement in a severe accident perceived road travel as less risky and also reported behaving less safely compared with those involved in fewer, or less severe accidents. The results have practical implications for the prevention of traffic accidents.

Practitioner Summary: The associations between accident history, perceived risk of road travel and safe behaviour were investigated using self-report questionnaire data. Participants involved in more than three accidents, or in severe accidents, perceived road travel as less risky and also reported more unsafe behaviour compared with those involved in fewer, or less severe accidents. Campaigns targeting people with a less serious, less extensive accident history should aim to increase awareness of hazards and the potential severity of their consequences, as well as emphasising how easy it is to take the recommended preventive actions. Campaigns targeting those involved in more frequent accidents, and survivors of serious accidents, should address feelings of invulnerability and helplessness.     

Surface exploration using laparoscopic surgical instruments: The perception of surface roughness

During laparoscopic surgery video images are used to guide the movements of the hand and instruments, and objects in the operating field often obscure these images. Thus, surgeons often rely heavily on tactile information (sense of touch) to help guide their movements. It is important to understand how tactile perception is affected when using laparoscopic instruments, since many surgical judgements are based on how a tissue ‘feels’ to the surgeon, particularly in situations where visual inputs are degraded. Twelve naïve participants used either their index finger or a laparoscopic instrument to explore sandpaper surfaces of various grits (60, 100, 150 and 220). These movements were generated with either vision or no vision. Participants were asked to estimate the roughness of the surfaces they explored. The normal and tangential forces of either the finger or instrument on the sandpaper surfaces were measured. Results showed that participants were able to judge the roughness of the sandpaper surfaces when using both the finger and the instrument. However, post hoc comparisons showed that perceptual judgements of surface texture were altered in the no vision condition compared to the vision condition. This was also the case when using the instrument, compared to the judgements provided when exploring with the finger. This highlights the importance of the completeness of the video images during laparoscopic surgery. More normal and tangential force was used when exploring the surfaces with the finger as opposed to the instrument. This was probably an attempt to increase the contact area of the fingertip to maximize tactile input. With the instrument, texture was probably sensed through vibrations of the instrument in the hand. Applications of the findings lie in the field of laparoscopic surgery simulation techniques and tactile perception.