Real-time embedded emotional controller

Recent studies show that emotion is a mechanism for fast decision-making in human and other animals. Mathematical models have been developed for describing emotion in mammals. These models, similar to other bioinspired models, must be implemented in embedded platforms for industrial and real applications. In this paper, brain emotional learning based intelligent controller, which is based on mammalian middle brain, is designed and implemented on field-programmable gate arrays, and this emotional controller is applied for controlling of laboratorial overhead traveling crane in model-free and embedded manner. The main features of this controller are leaning capability, providing a model-free control algorithm, robustness and the ability to respond swiftly. By designing appropriate stress signals, a designer can implement a proper trade among control objectives.     

Brain emotional learning based intelligent controller applied to neurofuzzy model of micro-heat exchanger

In this paper, an intelligent controller is applied to govern the dynamics of electrically heated micro-heat exchanger plant. First, the dynamics of the micro-heat exchanger, which acts as a nonlinear plant, is identified using a neurofuzzy network. To build the neurofuzzy model, a locally linear learning algorithm, namely, locally linear mode tree (LoLiMoT) is used. Then, an intelligent controller based on brain emotional learning algorithm is applied to the identified model. The intelligent controller is based on a computational model of limbic system in the mammalian brain. The brain emotional learning based intelligent controller (BELBIC) based on PID control is adopted for the micro-heat exchanger plant. The contribution of BELBIC in improving the control system performance is shown by comparison with results obtained from classic PID controller without BELBIC. The results demonstrate excellent improvements of control action, without any considerable increase in control effort for PID + BELBIC.     

Genetic algorithms based on an intelligent controller

Genetic algorithms (GAs) have been proven as robust search procedures. Numerous researchers have established the validity of GAs in optimization, machine learning and control applications. This paper presents a new intelligent control scheme using the robust sear h feature of GAs incorporating the basic idea of self-tuning regulators. The proposed controller utilized GAs to search for the changes of system parameters and to calculate the corresponding control law. The optimum parameters and control law are chosen based on the selection mechanism of GAs, which employs the square of the difference between the actual and the estimated outputs as the fitness function. The controller has an on-line parameters identification function and does not require prior knowledge or training data for learning.

The proposed intelligent controller is applied to the load frequency control of a power system to investigate the effectiveness from results obtained from computer simulations, the intelligent controller has been proven to provide good system characteristics.     

面向智能客服系统的情感分析技术

该文以阿里小蜜为例,对智能客服系统中的情感分析技术进行比较全面的介绍,包括情感分析算法模型的原理及其在智能客服系统的多个应用场景中的实际落地使用方式和效果分析。智能客服在解决客户高频业务问题的同时,也需要给客户提供多维度的、具有类人能力的助理、导购、语聊和娱乐等服务,提高客户对智能客服机器人的整体满意度。在此过程中,情感分析技术在机器人类人能力建设中起到了至关重要的作用。该文围绕智能客服系统中人机结合的服务形式,从六个维度总结和介绍了情感分析技术在智能客服系统中的应用场景,包括用户情感检测、用户情感安抚、情感生成式语聊、客服服务质检、会话满意度预估和智能人工入口。     

基于情感学习本体的教学反馈策略生成算法的研究

研究如何采用本体建模的方法解决智能教学系统中的情感理解与情感反馈的问题。构建了一个情感学习本体用于描述在学习过程中出现的与情感相关的概念及概念之间的关系,设计了基于该本体的教学反馈策略的生成算法,可以在不需要和学生进行问答交互的情况下获得学生学习过程的感知和理解状态,可以更好地理解学生的学习状态以提供更好的基于"情感触发"的认知和情感支持。并将情感学习本体和一个C语言程序设计领域知识本体以及反馈策略生成算法应用到一个以教学视频为主体学习资料的智能教学系统中。应用实例表明,该教学反馈策略生成算法能对学习者提供有效的认知反馈和情感反馈。     

Enhancing image processing architecture using deep learning for embedded vision systems

In recent years, the success and capabilities of embedded vision have showed up in embedded applications. The embedding of vision into electronic devices such as embedded medical applications is being driven by the availability of high-performance processors, integrating with deep learning algorithms, as well as advances in image processing technology. But, including image processing in embedded vision systems need huge amount of computational capabilities even to process a single image to detect an object and it's extremely challenging to implement in embedded systems. Implementing deep learning algorithms and testing it on a task specific data set could provide enhanced results. In this paper, an approach for enhancing image processing architecture using deep learning for embedded vision systems is proposed and analyzed. Implementing deep learning algorithms and testing it on embedded vision yielded effective results.     

卫星初始速度阻尼智能控制器设计

针对卫星入轨后的初始速率阻尼问题,提出一种基于人脑中情绪学习模型的在线自主自适应控制器。该控制器模拟人脑对感官输入和情绪刺激的处理过程,自主选择适当的控制信号,完成控制任务。设计了基于PID控制和PWPF调制的人脑情绪学习模型智能控制器用以完成卫星初始速率阻尼控制。仿真结果表明,该智能控制器对于卫星转动惯量的不确定性具有较强的鲁棒性,在线学习能力使得智能控制器的性能明显优于PID控制器。     

A review of recent advances in learner and skill modeling in intelligent learning environments

In recent years, learner models have emerged from the research laboratory and research classrooms into the wider world. Learner models are now embedded in real world applications which can claim to have thousands, or even hundreds of thousands, of users. Probabilistic models for skill assessment are playing a key role in these advanced learning environments. In this paper, we review the learner models that have played the largest roles in the success of these learning environments, and also the latest advances in the modeling and assessment of learner skills. We conclude by discussing related advancements in modeling other key constructs such as learner motivation, emotional and attentional state, meta-cognition and self-regulated learning, group learning, and the recent movement towards open and shared learner models.     

基于MCU的嵌入式智能网络控制系统设计

根据复杂化、网络化控制系统的要求，工业生产现场需要一种网络功能丰富、综合性能强、智能化程度高、可靠性好的控制器。本文完成以MCU为核心的嵌入式网络控制器设计。主要工作包括移植嵌入式操作系统；使用网络控制芯片CS8900A实现TCP／IP协议的网络通信工作；完成对底层SPI的驱动程序的编写，修改CPLD程序后可通过I／O口读写对控制系统底层的现场设备进行监控：使用Qt／Embedded开发嵌入式网络控制器部分图形界面。     

Shape-based modeling of the fundamental frequency contour for emotion detection in speech

This paper proposes the use of neutral reference models to detect local emotional prominence in the fundamental frequency. A novel approach based on functional data analysis (FDA) is presented, which aims to capture the intrinsic variability of F0 contours. The neutral models are represented by a basis of functions and the testing F0 contour is characterized by the projections onto that basis. For a given F0 contour, we estimate the functional principal component analysis (PCA) projections, which are used as features for emotion detection. The approach is evaluated with lexicon-dependent (i.e., one functional PCA basis per sentence) and lexicon-independent (i.e., a single functional PCA basis across sentences) models. The experimental results show that the proposed system can lead to accuracies as high as 75.8% in binary emotion classification, which is 6.2% higher than the accuracy achieved by a benchmark system trained with global F0 statistics. The approach can be implemented at sub-sentence level (e.g., 0.5 s segments), facilitating the detection of localized emotional information conveyed within the sentence. The approach is validated with the SEMAINE database, which is a spontaneous corpus. The results indicate that the proposed scheme can be effectively employed in real applications to detect emotional speech.     

一种新型的嵌入式智能图像传感器设计

提出并设计一种新型的嵌入式智能图像传感器,该传感器具备一定的室外场景(主要为道路和公共场所)状态感知能力,适用于分布式智能视频监控系统.本文采用基于统计学习的方法实现了运动前景图像检测和阴影消除,并在此基础上完成运动目标行为分析,实现了关键区域保护、监控目标移动检测以及镜头遮挡保护等智能视频监控功能.本文所设计的视觉分析算法适用于复杂的室外环境,适合于实时计算.在算法的实现中充分利用了该嵌入式智能图像传感器硬件设计的优点,在实验中取得了良好的效果.     

真实环境下的多模态情感数据集MED

目的 情感识别的研究一直致力于帮助系统在人机交互的环节中以更合适的方式来对用户的需求进行反馈。但它在现实应用中的表现却较差。主要原因是缺乏与现实应用环境类似的大规模多模态数据集。现有的野外多模态情感数据集很少,而且受试者数量有限,使用的语言单一。方法 为了满足深度学习算法对数据量的要求,本文收集、注释并准备公开发布一个全新的自然状态下的视频数据集（multimodal emotion dataset,MED）。首先收集人员从电影、电视剧、综艺节目中手工截取视频片段,之后通过注释人员对截取视频片段的标注最终得到了1 839个视频片段。这些视频片段经过人物检测、人脸检测等操作获得有效的视频帧。该数据集包含7种基础情感和3种模态：人脸表情,身体姿态,情感语音。结果 为了提供情感识别的基准,在本文的实验部分,利用机器学习和深度学习方法对MED数据集进行了评估。首先与CK+数据集进行了对比实验,结果表明使用实验室环境下收集的数据开发算法很难应用到实际中,然后对各个模态进行了基线实验,并给出了各个模态的基线。最后多模态融合的实验结果相对于单模态的人脸表情识别提高了4.03%。结论 多模态情感数据库MED扩充了现有的真实环境下多模态数据库,以推进跨文化（语言）情感识别和对不同情感评估的感知分析等方向的研究,提高自动情感计算系统在现实应用中的表现。     

基于ConvLSTM网络的维度情感识别模型研究

学业情绪能够影响和调节学习者的注意、记忆、思维等认知活动,情绪自动识别是智慧学习环境中情感交互和教学决策的基础。目前情绪识别研究主要集中在离散情绪的识别,其在时间轴上是非连续的,无法精准刻画学生学业情绪演变过程,为解决这个问题,基于众包方法建立真实在线学习情境中的中学生学习维度情感数据集,设计基于连续维度情感预测的深度学习分析模型。实验中根据学生学习风格确定触发学生学业情绪的学习材料,并招募32位实验人员进行自主在线学习,实时采集被试面部图像,获取157个学生学业情绪视频;对每个视频进行情感Arousal和Valence二维化,建立包含2 178张学生面部表情的维度数据库;建立基于ConvLSTM网络的维度情感模型,并在面向中学生的维度情感数据库上进行实验,得到一致性相关系数（Concordance Correlation Coefficient,CCC）均值为0.581,同时在Aff-Wild公开数据集上进行实验,得到的一致相关系数均值为0.222。实验表明,提出的基于维度情感模型在Aff-Wild公开数据集维度情绪识别中CCC相关度系数指标提升了7.6%~43.0%。     

深度学习支持下的情感识别探讨

随着人工神经网络技术的发展,深度学习逐渐成为人工智能领域的研究重点。在情感识别领域,深度学习也有着极为强大的理论与技术优势,其能够显著提升情感识别的准确性。同时,深度学习下的情感识别对于智慧化学习环境的营造有着积极意义,所以将之应用到教育教学工作中是切实可行的。本文对深度学习进行了简单介绍,并分析了当前情感识别的研究进展,进而对深度学习支持下的情感识别构建和应用展开探讨。     

Embedded MPC Controller Based on Interior‐Point Method with Convergence Depth Control

To allow the implementation of model predictive control on the chip, we first propose a primal–dual interior point method with convergence depth control to solve the quadratic programming problem of model predictive control. Compared with algorithms based on traditional termination criterion, the proposed method can significantly reduce the computation cost while obtaining an approximate solution of the quadratic programming problem with acceptable optimality and precision. Thereafter, an embedded model predictive controller based on the quadratic programming solver is designed and implemented on a digital signal processor chip and a prototype system is built on a TMDSEVM6678LE digital signal processor chip. The controller is verified on two models by using the hardware in loop frame to mimic real applications. The comparison shows that the whole design is competitive in real‐time applications. The typical computation time for quadratic programming problems with 5 decision variables and 110 constraints can be reduced to less than 2 ms on an embedded platform.     

Search-based automated testing of continuous controllers: Framework,tool support,and case studies

ContextTesting and verification of automotive embedded software is a major challenge. Software production in automotive domain comprises three stages: Developing automotive functions as Simulink models, generating code from the models, and deploying the resulting code on hardware devices. Automotive software artifacts are subject to three rounds of testing corresponding to the three production stages: Model-in-the-Loop (MiL), Software-in-the-Loop (SiL) and Hardware-in-the-Loop (HiL) testing.ObjectiveWe study testing of continuous controllers at the Model-in-Loop (MiL) level where both the controller and the environment are represented by models and connected in a closed loop system. These controllers make up a large part of automotive functions, and monitor and control the operating conditions of physical devices.MethodWe identify a set of requirements characterizing the behavior of continuous controllers, and develop a search-based technique based on random search, adaptive random search, hill climbing and simulated annealing algorithms to automatically identify worst-case test scenarios which are utilized to generate test cases for these requirements.ResultsWe evaluated our approach by applying it to an industrial automotive controller (with 443 Simulink blocks) and to a publicly available controller (with 21 Simulink blocks). Our experience shows that automatically generated test cases lead to MiL level simulations indicating potential violations of the system requirements. Further, not only does our approach generate significantly better test cases faster than random test case generation, but it also achieves better results than test scenarios devised by domain experts. Finally, our generated test cases uncover discrepancies between environment models and the real world when they are applied at the Hardware-in-the-Loop (HiL) level.ConclusionWe propose an automated approach to MiL testing of continuous controllers using search. The approach is implemented in a tool and has been successfully applied to a real case study from the automotive domain.     

Using learning automata in brain emotional learning for speech emotion recognition

We propose an improved version of brain emotional learning (BEL) model trained via learning automata (LA) for speech emotion recognition. Inspiring from the limbic system in mammalian brain, the original BEL model is composed of two neural network components, namely amygdala and orbitofrontal cortex. In this modified BEL model, named brain emotional learning based on learning automata (BELBLA), we have employed the theory of the stochastic LA in error back-propagation to train the BEL model in decreasing the high computational complexity of the traditional gradient method. Hence, the performance of the model can be enhanced. For a speech emotion recognition task, we extract the usual features, such as energy, pitch, formants, amplitude, zero crossing rate and MFCC, from average short-term signals of the emotional Berlin dataset. The experimental results show that the BELBLA outperforms some opponents, like hidden Markov model, Gaussian mixture model, k-nearest neighbor, support vector machines and artificial neural networks, for this application.     

基于ARM9的工业以太网控制系统智能节点控制器设计

文章提出了一种基于ARM9处理器S3C2410的工业以太网控制系统智能节点控制器的设计方案.该控制器作为工业以太网控制系统的现场控制级,采用Linux作为嵌入式操作系统.主要用于对现场设备进行监控,能够向上位级发送现场实时数据,并接受上位机发送的控制信息,对现场设备进行控制.     

Intelligent control of DC motor driven mechanical systems: a robust learning control approach

A robust learning controller is presented for DC motor driven mechanical systems with friction. The proposed controller takes advantage of both robust and learning control approaches to learn and compensate periodic and non‐periodic uncertain dynamics. In the learning controller, a set of learning rules is implemented in which three types of learnings occur: one is direct learning of desired inverse dynamics input and the other two learning of unknown linear parameters and nonlinear bounding functions in the models of system dynamics and friction. The global asymptotic stability of learning control system is shown by using the Lyapunov stability theory. Experimental data demonstrate the effectiveness of developed learning approach to tracking of DC motor driven mechanical systems. Copyright © 2002 John Wiley & Sons, Ltd.     

Physiological hemostasis based intelligent integrated cooperative controller for precise fault-tolerant control of redundant parallel manipulator

This paper focuses on precise fault-tolerant control for actual redundant parallel manipulator. Based on kinematic redundancy, some unnoticed influences such as mechanical clearance have been considered to design a more precise and intelligent fault-tolerant plan for actual plants. According to regulation principles in human hemostasis system, a bio-inspired intelligent integrated cooperative controller (BIICC) is developed including system structure, algorithm and step in parameter tuning. The proposed BIICC optimises partial error signal and improves control performance in each sub-channel. Moreover, the new controller transfers and disposes cooperative control signals among different sub-channels to achieve an intelligent integrated fault-tolerant system. The proposed BIICC is applied to an actual 2-DOF (degrees of freedom) redundant parallel manipulator where the feasibility of the new controller is demonstrated. The BIICC is beneficial to control precision and fault-tolerant capability of redundant plant. The improvements are more obvious in cases where extra actuators of redundant manipulator are broken.