Short-Term Relay Quality Prediction Algorithm Based on Long and Short-Term Memory

The fraction defective of semi-finished products is predicted to optimize the process of relay production lines, by which production quality and productivity ar...     

Blended Learning – ein innovatives Weiterbildungskonzept für die Technische Chemie

The ever‐increasing and ever‐changing challenges of the job market require professionals to constantly attend extra occupational education programs. Professionals furthermore express their desire for a compatibility of family and work. Therefore, a general concept for extended vocational training in the field of natural science and technology was developed based on blended learning. As an example, the concept was implemented and tested on the basis of the extended vocational training course “tc‐compact^BL” in Chemical Technology.     

Scalability of assessments of wiki-based learning experiences in higher education

In recent years, the focus on higher education learning has shifted from knowledge to skills, with interpersonal skills likely being the most difficult to assess and work with. Wikis ease open collaboration among peers. A number of these skills can be objectively assessed by using wikis in an educational environment: collaborative writing, conflict resolution, group management, leadership, etc. However, when the number of students increases, their interactions usually increase at a higher rate. Under these circumstances, traditional assessment procedures suffer from scalability problems: manually evaluating in detail the information stored in a wiki to retrieve objective metrics becomes a complex and time-consuming task. Thus, automated tools are required to support the assessment of such processes. In this paper we compare seven case studies conducted in Computer Science courses of two Spanish universities: Cádiz and Seville. We comment on their different settings: durations, milestones, contribution sizes, weights in the final grade and, most importantly, their assessment methods. We discuss and compare the different methodologies and tools used to assess the desired skills in the context of each case study.     

不确定性X-Y定位平台PID控制方法研究

X-Y定位平台属于强耦合非线性系统,且由于结构复杂性及外界干扰,当前测量水平难以获得其精确的数学模型,提出基于自适应神经网络的PID控制策略。考虑到X-Y定位平台系统精确的数学模型难以获得,利用神经网络良好的学习能力来逼近系统未知非线性模型,设计神经网络控制器;为了保证神经网络在学习的初期阶段的控制精度,设计PID控制器来进行辅助补偿控制;为加快学习速度,提高运动控制的实时性,设计变学习率的优化算法来实现神经网络权值的在线调整。试验结果验证了所提控制方法的有效性。     

基于PU学习的链接预测方法

基于分类的链接预测方法中,由于链接未知节点对的大规模性与不确定性,选择可靠负例成为构造链接预测分类器的难点问题.为此,文中提出基于正例和无标识样本(PU)学习的链接预测方法.首先,提取节点对的拓扑信息以构造样本集.再利用社区结构确定候选负例的分布,基于分布进行多次欠采样,获得多个候选负例子集,集成多个负例集与正例集中构建的分类器选择可靠负例.最后基于正例与可靠负例构造链接预测分类器.在4个网络数据集上的实验表明文中方法预测结果较优.     

基于多尺度高斯核的分布式正则化回归学习算法

针对工业、信息等领域出现的基于较大规模、非平稳变化复杂数据的回归问题,已有算法在计算成本及拟合效果方面无法同时满足要求.因此,文中提出基于多尺度高斯核的分布式正则化回归学习算法.算法中的假设空间为多个具有不同尺度的高斯核生成的再生核Hilbert空间的和空间.考虑到整个数据集划分的不同互斥子集波动程度不同,建立不同组合系数核函数逼近模型.利用最小二乘正则化方法同时独立求解各逼近模型.最后,通过对所得的各个局部估计子加权合成得到整体逼近模型.在2个模拟数据集和4个真实数据集上的实验表明,文中算法既能保证较优的拟合性能,又能降低运行时间.     

Experimental evaluation of the impact of b-learning methodologies on engineering students in Spain

The aim of this article is to highlight the importance of an active learning methodology in engineering degrees in Spain. We present the outcomes of an experimental study carried out during the academic years 2007/2008 and 2008/2009 with engineering students at the University of Salamanca (Spain). In the present research, as we have done in previous ones, we have selected a subject which is common to the four degrees under consideration: Computer Science. This study explores in greater depth the validity of experimental designs coming from educational research and the impact of innovative teaching methodologies. The hypothesis that impulses this research is formulated to ascertain that the learning level and the satisfaction of students will be higher after the implementation of new teaching methodologies (based on constructive learning, collaborative work, and blended learning resources), than in more traditional teaching contexts. The obtained results partially confirm this hypothesis. The ultimate purpose of this work is that of providing evidence that contributes to the improvement of education and teaching methods for a better performance of students in engineering.     

Lights and shadows in Evolutionary Deep Learning: Taxonomy,critical methodological analysis,cases of study,learned lessons,recommendations and challenges

Much has been said about the fusion of bio-inspired optimization algorithms and Deep Learning models for several purposes: from the discovery of network topologies and hyperparametric configurations with improved performance for a given task, to the optimization of the model’s parameters as a replacement for gradient-based solvers. Indeed, the literature is rich in proposals showcasing the application of assorted nature-inspired approaches for these tasks. In this work we comprehensively review and critically examine contributions made so far based on three axes, each addressing a fundamental question in this research avenue: (a) optimization and taxonomy (Why?), including a historical perspective, definitions of optimization problems in Deep Learning, and a taxonomy associated with an in-depth analysis of the literature, (b) critical methodological analysis (How?), which together with two case studies, allows us to address learned lessons and recommendations for good practices following the analysis of the literature, and (c) challenges and new directions of research (What can be done, and what for?). In summary, three axes – optimization and taxonomy, critical analysis, and challenges – which outline a complete vision of a merger of two technologies drawing up an exciting future for this area of fusion research.     

Artificial intelligence and healthcare: Forecasting of medical bookings through multi-source time-series fusion

Nowadays, Artificial intelligence (AI), combined with the digitalization of healthcare, can lead to substantial improvements in Patient Care, Disease Management, Hospital Administration, and supply chain effectiveness. Among predictive analytics tools, time series forecasting represents a central task to support healthcare management in terms of bookings and medical services predictions. In this context, the development of flexible frameworks to provide robust and reliable predictions became a central point in this healthcare innovation process. This paper presents and discusses a multi-source time series fusion and forecasting framework relying on Deep Learning. By combining weather, air-quality and medical bookings time series through a feature compression stage which preserves temporal patterns, the prediction is provided through a flexible ensemble technique based on machine learning models and a hybrid neural network. The proposed system is able to predict the number of bookings related to a specific medical examination for a 7-days horizon period. To assess the proposed approach’s effectiveness, we rely on time series extracted from a real dataset of administrative e-health records provided by the Campania Region health department, in Italy.