Optimal Machine Learning Enabled Performance Monitoring for Learning Management Systems

Learning Management System (LMS) is an application software that is used in automation, delivery, administration, tracking, and reporting of courses and programs in educational sector. The LMS which exploits machine learning (ML) has the ability of accessing user data and exploit it for improving the learning experience. The recently developed artificial intelligence (AI) and ML models helps to accomplish effective performance monitoring for LMS. Among the different processes involved in ML based LMS, feature selection and classification processes find beneficial. In this motivation, this study introduces Glowworm-based Feature Selection with Machine Learning Enabled Performance Monitoring (GSO-MFWELM) technique for LMS. The key objective of the proposed GSO-MFWELM technique is to effectually monitor the performance in LMS. The proposed GSO-MFWELM technique involves GSO-based feature selection technique to select the optimal features. Besides, Weighted Extreme Learning Machine (WELM) model is applied for classification process whereas the parameters involved in WELM model are optimally fine-tuned with the help of Mayfly Optimization (MFO) algorithm. The design of GSO and MFO techniques result in reduced computation complexity and improved classification performance. The presented GSO-MFWELM technique was validated for its performance against benchmark dataset and the results were inspected under several aspects. The simulation results established the supremacy of GSO-MFWELM technique over recent approaches with the maximum classification accuracy of 0.9589.     

A hybrid disturbance observer for delivery drone’s oscillation suppression

This paper proposes a new hybrid disturbance observer (DOB) to help suppress disturbance to the control systems. The proposed hybrid DOB consists of three main parts: (1) an actual system, (2) a simulated system, and (3) a learning filter that connects the actual and simulated systems. The simulated system aims to replicate the actual system response, where it leverages a neural network model to predict the input disturbance and generate the predicted system response. Such system response is used to generate a learning signal through a learning filter; this learning signal is then added to the feedforward loop of the estimation framework to enhance the disturbance estimate and its suppression performance for the actual system. The proposed hybrid DOB is designed to advance the standard DOB structure with a learning-based feedforward compensation. While the proposed method does not modify the baseline controller, it is well suited to systems whose baseline controllers are difficult or impossible to be changed. Considering the delivery drones are subject to oscillations when dropping payloads, experimental tests with multiple payload dropping scenarios have been conducted using both the hybrid and standard DOB, where the compared results validate the effectiveness and advantages of the proposed hybrid DOB.     

基于对抗深度学习的无人机航拍违建场地识别

对违建场地的检测方法主要是通过人工对无人机航拍视频进行检查,存在检测精度低、识别性能差、工作效率低的问题。提出一种结合空间变换网络与Fast RCNN的生成对抗网络ASTN-Fast RCNN,通过深度学习与无人机航拍视频相结合自动识别检测处在建设初期的违建场地。将空间变换网络作为生成器,生成Fast RCNN目标检测器难以识别的旋转形变样本,并通过目标检测器与生成器的对抗式训练,提高检测器的鲁棒性。实验结果表明,该方法能够有效提高对无人机航拍违建场地的识别性能。     

一种基于YOLOv4-TIA的林业害虫实时检测方法

针对现有基于深度学习的林业昆虫图像检测方法存在检测精度低和检测速度慢的问题,提出一种结合改进PANet结构与三分支注意力机制的目标检测方法YOLOv4-TIA。通过对样本数量较少的昆虫类别进行数据增强,实现样本均衡分布。利用三分支注意力机制改进YOLOv4中的CSPDarkNet53骨干网络,同时通过旋转操作和残差变换建立维度间的依存关系,以提高有效的特征通道权重,在PANet结构上增加将跳跃连接与跨尺度连接相结合的特征融合方式,从而获取更丰富的语义信息和位置信息。在此基础上,采用Focal loss函数优化分类损失,解决正负样本不均衡的问题。实验结果表明,该方法的精确率和召回率分别达到85.9%和91.2%,相比SSD、Faster R-CNN、YOLOv4方法,其在保证检测速度的同时,能够有效提高检测精度,且实现对林业害虫的实时精确监测。     

Learn to survive crises: The role of firm resilience,innovation capabilities and environmental dynamism

Exogenous crises, while disruptive, may also present learning opportunities that could affect a firm's viability and performance. In this study, we examine how exogenous crises can constitute learning opportunities and assess their impact on firm survival. In particular, we investigate the role of learning in response to exogenous crises and how firm resilience, innovation capabilities, and environmental dynamism influence this relationship. Drawing from crisis management and organisational learning literature, we propose that these factors can bolster the connection between learning from crises and firm survival. To test our hypotheses, we conduct a nuanced analysis using both regression analysis and Fuzzy Set Qualitative Comparative Analysis (fsQCA) on data from 249 Italian manufacturing Small and Medium-sized Enterprises (SMEs). This approach allows us to simultaneously examine the impact of firm resilience, innovation capabilities, and environmental dynamism on the relationship between learning from crises and firm survival. Our findings offer theoretical and practical insights into the role of learning from crises in a firm's survival. They also highlight the importance of embracing learning opportunities in crisis situations and suggest that how firms deal with crises could be an opportunity to fine-tune their internal processes and thrive in the long run.     

Japanese educational and learning systems in the post-industrial society: A value chain of educational and learning systems

Japan's educational system has some major problems. The most important among these concerns is the basic concept of the educational process and the goal of education. The old concept of public educational systems has become outdated in today's Japanese society, although this concept had supported social and spiritual faith, economic success and selfless devotion to one's country for more than 100 years. Now, Japanese people need a new concept of the educational process and the goal of education for the twenty-first century. The paper proposes a value chain of educational and learning systems aimed at building a network consisting of multiple fields for fostering future human resources.     

Pseudo software: A mediating instrument for modeling software requirements

A new synthesis of software requirements models called pseudo software is proposed with the aim to cut requirements-related errors. Pseudo software achieves this aim by serving as a mediating instrument to empower stakeholders to participate in requirements elicitation and validation through model construction and manipulation, and to provide guidance to the development team to correctly interpret the requirements in the downstream development activities. Pseudo software obtains its traits as a mediating instrument through the choice of requirements information bits and the use of multimodal representations with tool support to integrate the requirements. Using historical data of fifty projects in the enterprise computing domain, pseudo software is shown to effectively cut the requirements-related errors committed by both the customer and the development team.     

Guiding students to the right questions: adaptive navigation support in an E‐Learning system for Java programming

Rapid growth of the volume of interactive questions available to the students of modern E‐Learning courses placed the problem of personalized guidance on the agenda of E‐Learning researchers. Without proper guidance, students frequently select too simple or too complicated problems and ended either bored or discouraged. This paper explores a specific personalized guidance technology known as adaptive navigation support. We developed JavaGuide, a system, which guides students to appropriate questions in a Java programming course, and investigated the effect of personalized guidance a three‐semester long classroom study. The results of this study confirm the educational and motivational effects of adaptive navigation support.     

The Digital Learning Classroom: Improving English Language Learners’ academic success in mathematics and reading using interactive whiteboard technology

This study presents the findings from the first-year evaluation of the Round Rock Independent School District’s (ISD) Digital Learning Classroom project, an initiative focused on the improvement of English Language Learners’ (ELL) learning using interactive whiteboard (IWB) technology. An objective of the evaluation was to determine the extent IWB technology could foster performance parity in academic achievement between ELL and regular students, that is, reduce the student achievement gap between these two student groups in 3rd and 5th grade mathematics and reading. These grade levels and subjects were the primary focus of the project because students in grades 3 and 5 that do not pass the state’s standardized assessments in mathematics and reading cannot be promoted to the next grade level and therefore, these are “high stakes” tests for students. A second evaluation objective was to determine whether and the extent to which the Digital Learning Classroom could increase ELL students’ academic learning relative to that of ELL students in traditional classrooms (i.e., without IWBs). Using a quasi-experimental design, the results strongly indicate that IWBs can foster performance parity thereby closing the achievement gap between ELL and regular students while increasing ELL student achievement. Pedagogical implications for teachers of ELL students within the context of Digital Learning Classroom project implementation are presented, as well as recommendations for future study of the Digital Learning Classroom in ELL classroom settings.