No-Reference Video Quality Assessment using novel hybrid features and two-stage hybrid regression for score level fusion

This paper presents a novel No-Reference Video Quality Assessment (NR-VQA) model that utilizes proposed 3D steerable wavelet transform-based Natural Video Statistics (NVS) features as well as human perceptual features. Additionally, we proposed a novel two-stage regression scheme that significantly improves the overall performance of quality estimation. In the first stage, transform-based NVS and human perceptual features are separately passed through the proposed hybrid regression scheme: Support Vector Regression (SVR) followed by Polynomial curve fitting. The two visual quality scores predicted from the first stage are then used as features for the similar second stage. This predicts the final quality scores of distorted videos by achieving score level fusion. Extensive experiments were conducted using five authentic and four synthetic distortion databases. Experimental results demonstrate that the proposed method outperforms other published state-of-the-art benchmark methods on synthetic distortion databases and is among the top performers on authentic distortion databases. The source code is available at https://github.com/anishVNIT/two-stage-vqa.     

Neural network-based flight control systems: Present and future

As the first review in this field, this paper presents an in-depth mathematical view of Intelligent Flight Control Systems (IFCSs), particularly those based on artificial neural networks. The rapid evolution of IFCSs in the last two decades in both the methodological and technical aspects necessitates a comprehensive view of them to better demonstrate the current stage and the crucial remaining steps towards developing a truly intelligent flight management unit. To this end, in this paper, we will provide a detailed mathematical view of Neural Network (NN)-based flight control systems and the challenging problems that still remain. The paper will cover both the model-based and model-free IFCSs. The model-based methods consist of the basic feedback error learning scheme, the pseudocontrol strategy, and the neural backstepping method. Besides, different approaches to analyze the closed-loop stability in IFCSs, their requirements, and their limitations will be discussed in detail. Various supplementary features, which can be integrated with a basic IFCS such as the fault-tolerance capability, the consideration of system constraints, and the combination of NNs with other robust and adaptive elements like disturbance observers, would be covered, as well. On the other hand, concerning model-free flight controllers, both the indirect and direct adaptive control systems including indirect adaptive control using NN-based system identification, the approximate dynamic programming using NN, and the reinforcement learning-based adaptive optimal control will be carefully addressed. Finally, by demonstrating a well-organized view of the current stage in the development of IFCSs, the challenging issues, which are critical to be addressed in the future, are thoroughly identified. As a result, this paper can be considered as a comprehensive road map for all researchers interested in the design and development of intelligent control systems, particularly in the field of aerospace applications.     

A signal adaptive diffusion filter for video coding: Mathematical framework and complexity reductions

In this paper we combine video compression and modern image processing methods. We construct novel iterative filter methods for prediction signals based on Partial Differential Equation (PDE) based methods. The mathematical framework of the employed diffusion filter class is given and some desirable properties are stated. In particular, two types of diffusion filters are constructed: a uniform diffusion filter using a fixed filter mask and a signal adaptive diffusion filter that incorporates the structures of the underlying prediction signal. The latter has the advantage of not attenuating existing edges while the uniform filter is less complex. The filters are embedded into a software based on HEVC with additional QTBT (Quadtree plus Binary Tree) and MTT (Multi-Type-Tree) block structure. In this setting, several measures to reduce the coding complexity of the tool are introduced, discussed and tested thoroughly. The coding complexity is reduced by up to 70% while maintaining over 80% of the gain. Overall, the diffusion filter method achieves average bitrate savings of 2.27% for Random Access having an average encoder runtime complexity of 119% and 117% decoder runtime complexity. For individual test sequences, results of 7.36% for Random Access are accomplished.     

基于DSP的智能电源控制单元设计与实现

本文利用TI公司TMS320F28335芯片高效的浮点运算能力,结合片上丰富的外设,设计并实现了一种具有高可靠性的智能电源控制单元。该控制单元周期性地对各片上外设进行自检维护,完成多路负载通道控制、电压、电流的实时监控,并对故障进行指示、处理和上报,同时提供人机交互界面更新状态信息。经过验证,该控制单元工作稳定,具备良好的工程应用价值。     

Utilizing sensor data to model students’ creativity in a digital environment

While creativity is essential for developing students’ broad expertise in Science, Technology, Engineering, and Math (STEM) fields, many students struggle with various aspects of being creative. Digital technologies have the unique opportunity to support the creative process by (1) recognizing elements of students’ creativity, such as when creativity is lacking (modeling step), and (2) providing tailored scaffolding based on that information (intervention step). However, to date little work exists on either of these aspects. Here, we focus on the modeling step. Specifically, we explore the utility of various sensing devices, including an eye tracker, a skin conductance bracelet, and an EEG sensor, for modeling creativity during an educational activity, namely geometry proof generation. We found reliable differences in sensor features characterizing low vs. high creativity students. We then applied machine learning to build classifiers that achieved good accuracy in distinguishing these two student groups, providing evidence that sensor features are valuable for modeling creativity.     

Augmented context-based recommendation service framework using knowledge over the Linked Open Data cloud

This research proposes ACARDS (Augmented-Context bAsed RecommenDation Service) framework that is able to utilize knowledge over the Linked Open Data (LOD) cloud to recommend context-based services to users. To improve the level of user satisfaction with the result of the recommendation, the ACARDS framework implements a novel recommendation algorithm that can utilize the knowledge over the LOD cloud. In addition, the noble algorithm is able to use new concepts like the enriched tags and the augmented tags that originate from the hashtags on the SNSs materials. These tags are utilized to recommend the most appropriate services in the user’s context, which can change dynamically. Last but not least, the ACARDS framework implements the context-based reshaping algorithm on the augmented tag cloud. In the reshaping process, the ACARDS framework can recommend the highly receptive services in the users’ context and their preferences. To evaluate the performance of the ACARDS framework, we conduct four kinds of experiments using the Instagram materials and the LOD cloud. As a result, we proved that the ACARDS framework contributes to increasing the query efficiency by reducing the search space and improving the user satisfaction on the recommended services.     

A three-dimensional surface measurement system implemented with Gaussian process based adaptive sampling

Self-adaptive surface measurements that can reduce data redundancy and improve time efficiency are in high demand in many fields of science and technology. For this purpose, a system implemented with Gaussian process (GP) adaptive sampling is developed. The non-parametric GP model is applied to reconstruct the topography and guide the subsequent sampling position, which is determined from the inference uncertainty estimation. A criterion is proposed to terminate the GP adaptive measurement automatically without any prior model or data of the topography. Experiments on typical surfaces validate the intelligence, adaptability, and high accuracy of the GP method along with the stabilization of the automatic iteration termination. Compared with traditional raster sampling, data redundancy is reduced and the time efficiency is improved without sacrificing the surface reconstruction accuracy. The proposed method can be implemented in other systems with similar measurement principles, thus benefitting surface characterizations.     

Biologically Inspired Design of Context-Aware Smart Products

The rapid development of information and communication technologies (ICTs) and cyber–physical systems (CPSs) has paved the way for the increasing popularity of smart products. Context-awareness is an important facet of product smartness. Unlike artifacts, various bio-systems are naturally characterized by their extraordinary context-awareness. Biologically inspired design (BID) is one of the most commonly employed design strategies. However, few studies have examined the BID of context-aware smart products to date. This paper presents a structured design framework to support the BID of context-aware smart products. The meaning of context-awareness is defined from the perspective of product design. The framework is developed based on the theoretical foundations of the situated function–behavior–structure ontology. A structured design process is prescribed to leverage various biological inspirations in order to support different conceptual design activities, such as problem formulation, structure reformulation, behavior reformulation, and function reformulation. Some existing design methods and emerging design tools are incorporated into the framework. A case study is presented to showcase how this framework can be followed to redesign a robot vacuum cleaner and make it more context-aware.     

计及Spark和属性权重的售电套餐推荐方法

针对电力市场用户群庞大，交易过程中售电套餐选择困难的问题，在Spark环境下设计了一种售电套餐推荐方法，同时也解决了售电套餐推荐过程中在大数据环境下的可扩展性及实时性问题。首先，计算出每个套餐属性的权重值，从而计算得到售电套餐综合相似度。然后，计及用户和套餐两方面提出一种售电套餐推荐方法，实现售电套餐的精准推荐。实验表明，提出的推荐方法能够明显提高推荐的准确度，并且在分布式环境下具有良好的推荐效率和可扩展性。     

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。