学习矢量量化算法的性能分析

本文针对学习矢量量化算法Ⅰ型和Ⅱ型（ＬＶＱ１、ＬＶＱ２）进行了深入的分析研究，取得了以下结果：（１）对应于ＬＶＱ１算法，提出了一种选取学习步长的优化方案；（２）得到了ＬＶＱ１算法关于线性可分模式分类问题的一个重要结论；（３）严格推导出ＬＶＱ２算法实质上是一种使分类错误减小的梯度下降法；（４）得出了ＬＶＱ２算法对于类间混叠的模式分类问题不存在稳定平衡状态这一重要结论；（５）针对ＬＶＱ２算法处理类间混     

Internet of things intrusion detection model and algorithm based on cloud computing and multi-feature extraction extreme learning machine

With the rapid development of the Internet of Things (IoT), there are several challenges pertaining to security in IoT applications. Compared with the characteristics of the traditional Internet, the IoT has many problems, such as large assets, complex and diverse structures, and lack of computing resources. Traditional network intrusion detection systems cannot meet the security needs of IoT applications. In view of this situation, this study applies cloud computing and machine learning to the intrusion detection system of IoT to improve detection performance. Usually, traditional intrusion detection algorithms require considerable time for training, and these intrusion detection algorithms are not suitable for cloud computing due to the limited computing power and storage capacity of cloud nodes; therefore, it is necessary to study intrusion detection algorithms with low weights, short training time, and high detection accuracy for deployment and application on cloud nodes. An appropriate classification algorithm is a primary factor for deploying cloud computing intrusion prevention systems and a prerequisite for the system to respond to intrusion and reduce intrusion threats. This paper discusses the problems related to IoT intrusion prevention in cloud computing environments. Based on the analysis of cloud computing security threats, this study extensively explores IoT intrusion detection, cloud node monitoring, and intrusion response in cloud computing environments by using cloud computing, an improved extreme learning machine, and other methods. We use the Multi-Feature Extraction Extreme Learning Machine (MFE-ELM) algorithm for cloud computing, which adds a multi-feature extraction process to cloud servers, and use the deployed MFE-ELM algorithm on cloud nodes to detect and discover network intrusions to cloud nodes. In our simulation experiments, a classical dataset for intrusion detection is selected as a test, and test steps such as data preprocessing, feature engineering, model training, and result analysis are performed. The experimental results show that the proposed algorithm can effectively detect and identify most network data packets with good model performance and achieve efficient intrusion detection for heterogeneous data of the IoT from cloud nodes. Furthermore, it can enable the cloud server to discover nodes with serious security threats in the cloud cluster in real time, so that further security protection measures can be taken to obtain the optimal intrusion response strategy for the cloud cluster.     

Convolution Neural Network based lossy compression of hyperspectral images

The large size of hyperspectral imaging poses a significant threat to its potential use in real life due to the abundant information stored in it. The use of deep learning for such data processing is visible in recent applications. In this work, we propose a lossy hyperspectral image compression algorithm based on the concept of autoencoders. It uses a combination of the convolution layer and max-pooling layer to reduce the dimensions of the input image and generate a compressed image. The original image with some loss of information is reconstructed using transpose convolution layer that uses reverse of the procedure used by the encoder. The compressed image has been entropy coded using an adaptive arithmetic coder for transmission or storage application. The method provides an improvement of 28% in PSNR with 21 times increment in the compression ratio. The effect of compression on classification has also been evaluated in the experiment using state of art classification algorithm. Negligible difference in classification accuracy was obtained that proves the effectiveness of the proposed algorithm.     

基于口袋实验的电子技术课程混合式教学探索

针对电子技术类课程理论实验易脱节的问题,基于“以学员为中心,突出能力培养”的现代教育理念,提出一种理论实践相结合的新型混合式教学模式。通过线上线下、课内课外联动”的方式,实现课堂有效互动,较好地解决了理论和现实脱节的矛盾。     

自组织学习联想神经树在氟化物非晶态形成的判别条件中的应用

运用自组织学习联想神经树，利用化学键参数法，研究了三元系氟化物非晶态形成的判别条件，建立了相应的计算机判别智能专家系统。对３个未知样本进行判别，分类结果正确。该方法可望成为研究化合物非晶态形成条件的有效辅助手段。     

Spatial visualization and measurement of area: A case study in spatialized mathematics instruction

The purpose of this study was to explore the influence of spatial visualization skills when students solve area tasks. Spatial visualization is closely related to mathematics achievement, but little is known about how these skills link to task success. We examined middle school students’ representations and solutions to area problems (both non-metric and metric) through qualitative and quantitative task analysis. Task solutions were analyzed as a function of spatial visualization skills and links were made between student solutions on tasks with different goals (i.e., non-metric and metric). Findings suggest that strong spatial visualizers solved the tasks with relative ease, with evidence for conceptual and procedural understanding. By contrast, Low and Average Spatial students more frequently produced errors due to failure to correctly determine linear measurements or apply appropriate formula, despite adequate procedural knowledge. A novel finding was the facilitating role of spatial skills in the link between metric task representation and success in determining a solution. From a teaching and learning perspective, these results highlight the need to connect emergent spatial skills with mathematical content and support students to develop conceptual understanding in parallel with procedural competence.     

Secured data transmissions in corporeal unmanned device to device using machine learning algorithm

Cyber–physical systems (CPS) for device-to-device (D2D) communications are gaining prominence in today’s sophisticated data transmission infrastructures. This research intends to develop a new model for UAV transmissions across distinct network nodes, which is necessary since an automatic monitoring system is required to enhance the current D2D application infrastructure. The real time significance of proposed UAV for D2D communications can be observed during data transmission state where individual data will have huge impact on maximizing the D2D security. Additionally, through the use of simulation, an exploratory persistence tool is offered for CPS networks with fully characterized energy issues. This UAV CPS paradigm is based on mobility nodes, which host concurrent systems and control algorithms. In sixth-generation networks, when there are no barriers and the collision rate is low and the connectivity is fast, the method is also feasible. Unmanned aerial vehicles (UAVs) can now cover great distances, even while encountering hazardous obstacles. When compared to the preexisting models, the simulated values for autonomous, collision, and parametric reliability are much better by an average of 87%. The proposed model, however, is shown to be highly independent and exhibits stable perceptual behaviour. The proposed UAV approach is optimal for real-time applications due to its potential for more secure operation via a variety of different communication modules.     

Structure and Bonding in Amorphous Red Phosphorus**

Amorphous red phosphorus (a-P) is one of the remaining puzzling cases in the structural chemistry of the elements. Here, we elucidate the structure, stability, and chemical bonding in a-P from first principles, combining machine-learning and density-functional theory (DFT) methods. We show that a-P structures exist with a range of energies slightly higher than those of phosphorus nanorods, to which they are closely related, and that the stability of a-P is linked to the degree of structural relaxation and medium-range order. We thus complete the stability range of phosphorus allotropes [Angew. Chem. Int. Ed. 2014 , 53, 11629] by now including the previously poorly understood amorphous phase, and we quantify the covalent and van der Waals interactions in all main phases of phosphorus. We also study the electronic densities of states, including those of hydrogenated a-P. Beyond the present study, our structural models are expected to enable wider-ranging first-principles investigations—for example, of a-P-based battery materials.     

Two-dimensional Pure Isotropic Proton Solid State NMR

One key bottleneck of solid-state NMR spectroscopy is that ¹H NMR spectra of organic solids are often very broad due to the presence of a strong network of dipolar couplings. We have recently suggested a new approach to tackle this problem. More specifically, we parametrically mapped errors leading to residual dipolar broadening into a second dimension and removed them in a correlation experiment. In this way pure isotropic proton (PIP) spectra were obtained that contain only isotropic shifts and provide the highest ¹H NMR resolution available today in rigid solids. Here, using a deep-learning method, we extend the PIP approach to a second dimension, and for samples of L-tyrosine hydrochloride and ampicillin we obtain high resolution ¹H-¹H double-quantum/single-quantum dipolar correlation and spin-diffusion spectra with significantly higher resolution than the corresponding spectra at 100 kHz MAS, allowing the identification of previously overlapped isotropic correlation peaks.     

Students’ and Teachers’ Conceptual Metaphors for Mathematical Problem Solving

Metaphors are regularly used by mathematics teachers to relate difficult or complex concepts in classrooms. A complex topic of concern in mathematics education, and most STEM‐based education classes, is problem solving. This study identified how students and teachers contextualize mathematical problem solving through their choice of metaphors. Twenty‐two high‐school student and six teacher interviews demonstrated a rich foundation for these shared experiences by identifying the conceptual metaphors. This mixed‐methods approach qualitatively identified conceptual metaphors via interpretive phenomenology and then quantitatively analyzed the frequency and popularity of the metaphors to explore whether a coherent metaphorical system exists with teachers and students. This study identified the existence of a set of metaphors that describe how multiple classrooms of geometry students and teachers make sense of mathematical problem solving. Moreover, this study determined that the most popular metaphors for problem solving were shared by both students and teachers. The existence of a coherent set of metaphors for problem solving creates a discursive space for teachers to converse with students about problem solving concretely. Moreover, the methodology provides a means to address other complex concepts in STEM education fields that revolve around experiential understanding.