女性运动裤脚款式感知评价与个性化定制推荐

为提升产品核心部件个性化推荐与用户情感需求的匹配度，帮助企业更准确把握用户定制过程的感性偏好，以女性运动裤的裤脚为例，构建基于感性工学的个性化推荐模型。首先采用语意差异法获取消费者对裤脚款式在7个维度的感性评价，建立感性意象空间；然后提取裤脚款式的设计要素，通过偏最小二乘法建立设计要素与消费感知的映射模型；最后采用模糊层次分析法量化消费者的感性需求，结合映射模型建立个性化推荐模型。结果显示：推荐结果与消费者感知评价的平均余弦相似度为0.902,说明设计元素与消费感知存在较高相关性；推荐算法预测结果的平均绝对值误差为0.54,推荐结果与用户需求匹配度较高，能有效将消费感性需求转化为设计元素。     

Representation learning: serial-autoencoder for personalized recommendation

Nowadays, the personalized recommendation has become a research hotspot for addressing information overload. Despite this, generating effective recommendations from sparse data remains a challenge. Recently, auxiliary information has been widely used to address data sparsity, but most models using auxiliary information are linear and have limited expressiveness. Due to the advantages of feature extraction and no-label requirements, autoencoder-based methods have become quite popular. However, most existing autoencoder-based methods discard the reconstruction of auxiliary information, which poses huge challenges for better representation learning and model scalability. To address these problems, we propose Serial-Autoencoder for Personalized Recommendation (SAPR), which aims to reduce the loss of critical information and enhance the learning of feature representations. Specifically, we first combine the original rating matrix and item attribute features and feed them into the first autoencoder for generating a higher-level representation of the input. Second, we use a second autoencoder to enhance the reconstruction of the data representation of the prediciton rating matrix. The output rating information is used for recommendation prediction. Extensive experiments on the MovieTweetings and MovieLens datasets have verified the effectiveness of SAPR compared to state-of-the-art models.     

检测汗液用可穿戴电化学传感器的研究进展

为探究可穿戴电化学传感器在分析汗液中常见的内源性分析物和外源性分析物方面的应用，首先介绍了汗液和电化学传感器的概念以及汗液传统提取方法和新型提取策略，详细分析了2种汗液提取方式的优势与不足。其次阐述了不同分析物和传感器基材材料的研究及其应用现状。从最基础的汗液收集和储备出发，总结了汗液中各种可能存在物质的电化学传感器的检测意义和构建策略，概述了从刚性可穿戴到柔性可穿戴电子设备的发展，并指出可穿戴电化学传感器在纺织行业中发展存在的问题以及对其在纺织行业中的未来发展方向进行了展望。     

时间上可持续的多兴趣偏好推荐系统

近年来, 推荐系统已经成为数据分析与挖掘、信息检索领域方向的热点. 然而, 部分推荐系统应用于用户多兴趣偏好还存在着问题: 首先用户的兴趣不唯一, 且对多个兴趣的偏好不等同; 其次用户当前的兴趣是否会在未来时间中持续. 基于此, 本文通过利用用户产生多兴趣并捕获其个性化需求的可持续性, 提出了一种MIES算法模型, 该模型能够很好捕捉到用户潜在的多种兴趣, 并注重用户兴趣的可持续, 提高了推荐的质量. 通过对比实验表明该模型有效解决了推荐系统对用户多维兴趣的捕捉和个性化兴趣的可持续性.     

The Rising of Fiber Constructed Piezo/Triboelectric Nanogenerators: From Material Selections,Fabrication Techniques to Emerging Applications

Piezo/triboelectric nanogenerators (PTNGs) have become the research frontier in many cutting-edge applications, which open up promising possibilities for broad prospects. Fiber materials are the ideal candidate for constructing high-performance PTNGs owing to the compelling features of lightweight, programmable structure, favorable softness, and brilliant breathability. To this end, working mechanisms, material selections, structural designs and fabrication methods of fiber constructed PTNGs are comprehensively presented. An in-depth analysis of emerging applications ranging from intelligent clothing, smart home, and personalized medicine to artificial intelligence is thoughtfully demonstrated. Furthermore, the current problems and potential challenges that hinder their large-scale commercial applications are systematically discussed, laying emphasis on the future development direction of fiber constructed PTNGs. It is expected that this review will supply the audience with some universal strategies and fresh ideas to conduct deep research on fiber constructed PTNGs toward better performance.     

Experimental study for comparison of thermal comfort and air age between two combined ventilation systems with chilled ceiling considering occupant density

Due to the global spread of diseases and epidemics, the need to maintain a clean indoor atmosphere has received increasing attention in recent years. Therefore, there will be a need to clearly estimate and define the areas that affect human exposure to pollutants, taking into account the occupied density, which is the primary importance of this research. The capacity of the chilled ceiling combined with mixing ventilation and personal ventilation systems has been studied and compared to the chilled ceiling with mixing ventilation in terms of mean air age, temperature distribution, CO₂ concentration, and thermal efficiency, with the best flow rate of the proposed system considering the occupied density in a thermally insulated office room experimentally in the climate of Iraq (Hilla, a hot and dry climate). Twelve tests were performed for four different cooling loads with cooled ceilings (0%, 0.25%, 50%, and 80%), at a constant supply air flow rate with two PV airflow modifiers for three cases. As the cooling load treated by a chilled ceiling increased, the average air temperature increased with height in all cases. The lowest values of average air age appeared in the occupied area in the case of a chilled ceiling with mixing ventilation. This study shows that the chilled ceiling combined with a mixing ventilation and personal ventilation system with a flow rate of 7.5 L/s provides thermal comfort and higher air quality in the occupied area. based on the values of air exchange efficiency and occupants’ air exchange efficiency. As a result, a flow rate of 7.5 L/s is the best option for protecting occupants from direct pollution in the breathing zone and in the surrounding microclimate, because the lower the ventilation rate, the less air is changed for occupants.