深度学习识别光网络单元故障的设计与应用

为解决依赖装维上门鉴别光网络单元故障带来的不便,可以从机器视觉入手实现自动化故障识别。近年,ImageNet挑战赛的成功推动了物体识别技术的跨越式发展,特别是基于卷积的深度学习技术在视觉识别方面已经达到人类水平,为光网络单元故障的自动识别提供了技术基础。文章对识别光网络单元的工作状态进行了研究,将设备工作状态分为7个场景,提出了利用手机APP采集图片识别故障的解决方案并投入了实际生产;重点阐述了深度学习模块的设计与实现,提出一种通过算法整合的方式综合运用物体检测和图像分类算法,分3阶段逐步求精,解决了图片过滤,光网络单元型号和状态识别等问题,实现了基于计算机视觉自动识别光网络单元故障。从数据上看产品的端到端准确率超过84%,识别速度达到10 FPS,月均提供服务超过1万人次,在减少用户等待的同时节约了人力资源。     

基于深度学习的视频跟踪研究进展综述

近年来深度学习迅猛发展，颠覆了语音识别、图像分类、文本理解等领域的算法设计思路。深度学习因其具备强大的特征提取能力，在图像识别领域的成绩尤为突出。然而深度学习与视频监控领域的结合并不多，由于深度模型具有多层网络结构，算法复杂度大，训练和更新模型时比较耗时，很难满足实时性要求。回顾了深度学习的发展史，介绍了最近10年来国内外深度学习主要模型，论述了基于深度学习的目标跟踪算法，指出了各算法的优缺点，最后对当前该领域存在的问题和发展前景进行了总结和展望。     

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

A Novel Beam Search to Improve Neural Machine Translation for English-Chinese

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality.     

Identification of digital technologies and digitalisation trends in the mining industry

Digitalisation in mining refers to the use of computerised or digital devices or systems and digitised data that are to reduce costs, improve business productivity, and transform mining practices. However, it remains increasingly difficult for mining companies to decide which digital technologies are most relevant to their needs and individual mines. This paper provides an overview of digital technologies currently relevant to mining companies as presented and discussed by mining journals, the media and insight reports of leading consultancy agencies. Relevant technologies were systematically identified using text-mining techniques, and network analyses established the relations between significant technologies. Results demonstrated that currently 107 different digital technologies are pursued in the mining sector. Also, an analysis of the actual implementation of digital technologies in 158 active surface and underground mines reveals a limited uptake of digital technologies in general and that the uptake increases with the run-of-mine production. Large-scale mining operations appear to select and apply digital technologies suitable to their needs, whereas operations with lower production rates do not implement the currently available digital technologies to the same extent. These minor producers may require other digital transformation solutions tailored to their capabilities and needs and applicable to their scale of operations.     

视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。     

Creating the brain and interacting with the brain: an integrated approach to understanding the brain

In the past two decades, brain science and robotics have made gigantic advances in their own fields, and their interactions have generated several interdisciplinary research fields. First, in the ‘understanding the brain by creating the brain’ approach, computational neuroscience models have been applied to many robotics problems. Second, such brain-motivated fields as cognitive robotics and developmental robotics have emerged as interdisciplinary areas among robotics, neuroscience and cognitive science with special emphasis on humanoid robots. Third, in brain–machine interface research, a brain and a robot are mutually connected within a closed loop. In this paper, we review the theoretical backgrounds of these three interdisciplinary fields and their recent progress. Then, we introduce recent efforts to reintegrate these research fields into a coherent perspective and propose a new direction that integrates brain science and robotics where the decoding of information from the brain, robot control based on the decoded information and multimodal feedback to the brain from the robot are carried out in real time and in a closed loop.     

Animations showing Lego manipulative tasks: Three potential moderators of effectiveness

Evidence suggests that transient visual information, such as animations, may be more challenging to learn than static visualizations. However, when a procedural-manipulative task is involved, our evolved embodied cognition seems to reverse this transitory challenge. Hence, for object manipulative tasks, instructional animations may be more suitable than statics. We investigated this argument further by comparing animations with statics using a Lego task shown to university students, by examining three potential moderators of effectiveness: (a) the environment of manipulation (virtual or physical), (b) the quality of visual information (focused or unfocused), and (c) the presence of hands (no hands or with hands). In Experiment 1 we found an advantage of animation over statics, and no differences among the environments. In Experiment 2, we again observed an animation advantage, a small advantage of focused static information compared to unfocused static information, and a positive effect of not showing the hands.     

基于Q-learning的不确定环境BDI Agent最优策略规划研究

BDI模型能够很好地解决在特定环境下的Agent的推理和决策问题,但在动态和不确定环境下缺少决策和学习的能力。强化学习解决了Agent在未知环境下的决策问题,却缺少BDI模型中的规则描述和逻辑推理。针对BDI在未知和动态环境下的策略规划问题,提出基于强化学习Q-learning算法来实现BDI Agent学习和规划的方法,并针对BDI的实现模型ASL的决策机制做出了改进,最后在ASL的仿真平台Jason上建立了迷宫的仿真,仿真实验表明,在加入Q-learning学习机制后的新的ASL系统中,Agent在不确定环境下依然可以完成任务。     

基于聚类的数据加权优化在犯罪预测中的应用

近年来，我国传统暴力犯罪与成年人犯罪呈下降态势，但是，犯罪案由层出不穷。为有效提升公安实践工作中犯罪预测能力，打击各类违法犯罪事件,本文针对犯罪数据，提出一种新型犯罪预测模型。利用密度聚类分析方法将犯罪数据分类，然后进行数据降维提取关键属性生成特征数据，继而对特征数据进行加权优化并采用机器学习的方式对特征数据进行学习，从而预测犯罪案由。实验结果表明，与传统方法相比，本文方法具有更好的预测效果，为公安实践工作中类似案件的侦破和预防，提供新的路径支撑。