Infrared detector is a device that can detect infrared signals on the surface of objects and convert them into electrical signals, which has been widely used in military and industrial fields such as the Internet of Things, communications, guidance, thermal imaging, and surveillance. Using the black body as the calibrator, it can test the parameters of the infrared detector and detect whether the performance indicators of the infrared detector meet the standard. This article describes a test system that uses NI Virtual Instruments and LabVIEW Software to test the performance of infrared detectors. The system provides the bias voltage and signal required for detector performance testing, and data acquisition. At the same time, a method for measuring the DC level, noise, response rate, noise equivalent temperature difference, normalized detection rate and bad pixel of the detector by using the system is given. Finally, the influencing factors of the test results were analyzed to provide reference for related research.
Given the widespread availability of multi-view data in the real world, multi-view Fuzzy C-Means clustering (FCM) has garnered significant attention in recent years, leading to the development of various multi-view fuzzy clustering algorithms. However, existing algorithms still exhibit room for improvement. Firstly, most existing algorithms only utilize the shallow information of the view data and fail to delve into the mining and utilization of deeper representations. Secondly, existing algorithms tend to extract common representations among the views first and then implement clustering separately, which may lack a collaborative linkage between representation learning and the clustering task. Lastly, multi-view clustering algorithms based on representation learning often overlook the importance of effectively preserving similarity information within the views. To address these limitations, we propose a novel algorithm called Pseudo-Label Enhanced Multi-View Deep Concept Factorization Fuzzy Clustering (PE-MV-DCFCM). The algorithm first introduces a deep concept factorization method to uncover the deep information of the view data. Subsequently, it employs pseudo-label learning to preserve intra-view similarity information during the learning of common representations among the views, based on non-negative matrix factorization (NMF). Finally, this algorithm integrates deep concept factorization, representation learning, and fuzzy clustering into a unified framework to enhance the collaboration among the various sub-steps of the algorithm. Experiments on several benchmark datasets show that the proposed PE-MV-DCFCM algorithm outperformed other state-of-the-art algorithms.
The traditional teaching effect evaluation system lacks the application of potential evaluation data of medical online teaching, resulting in incomplete statistics of teaching evaluation data. Therefore, a medical online teaching effect evaluation system based on data mining technology is designed. In terms of hardware, Network Attached Storage（NAS） file storage and digital signal processor chip are used as the main body of hardware. In terms of software, the information collection and editing module is designed, and the data mining technology is used to mine and process the collected information to obtain the potential evaluation information. The teaching effect is evaluated with reference to the potential evaluation information and evaluation criteria, and the teaching effect is statistically analyzed according to the audit results, and finally the teaching evaluation analysis chart is output. The test results show that the system has good performance and can accurately evaluate the effect of medical online teaching.
文章基于《中国统计年鉴》公布的数据,通过建立反向传播(Back Propagation,BP)神经网络预测算法,使用多项式拟合算法模型和修正的Logistic模型两种算法进行对比,对2030年的人口进行预测.预测数据结论表明,3种算法预测的人口总数同国家人口发展报告预测的人口总数相比,其绝对误差均在误差范围内.其中,误差最小的是BP神经网络预测模型,该模型预测2030年总人数为14.33亿,绝对误差为0.006.
随着时代的发展,我国的科学技术水平明显提升,尤其是无人机技术,已广泛应用在各行各业中.同时,随着通信技术的持续发展,5G网络能够提供更加快速的数据传输支持,4K高清数据传输逐渐成为现实.基于此,在分析海上作业需求的基础上,分析了无人机搭载宽带5G通信技术在海上作业中的应用,同时进行了可用性测试,希望能够为相关研究提供理论支持.
