S. Kalyani^*, A. Mary Sowjanya, K. Venkat Rao

Journal on Internet of Things, Vol.3, No.1, pp. 27-38, 2021, DOI:DOI:10.32604/jiot.2021.013163

Abstract Increased smart devices in various industries are creating numerous sensors in each of the equipment prompting the need for methods and models for sensor data. Current research proposes a systematic approach to analyze the data generated from sensors attached to industrial equipment. The methodology involves data cleaning, preprocessing, basics statistics, outlier, and anomaly detection. Present study presents the prediction of RUL by using various Machine Learning models like Regression, Polynomial Regression, Random Forest, Decision Tree, XG Boost. Hyper Parameter Optimization is performed to find the optimal parameters for each variable. In each of the model for RUL prediction RMSE, MAE… More >

Samreen Mahmood^*

Journal on Internet of Things, Vol.3, No.1, pp. 19-26, 2021, DOI:10.32604/jiot.2021.013071

Abstract Human beings and their activities are now connected through Internet of Things (IoT) with the evolution of wireless communication technologies. IoT is becoming popular and its usage is immensely increasing among various sectors. In this research paper, a comprehensive review has been conducted by considering recent and important literature review on IoT applications being operated in three major sectors. The three sectors studied are health, sports and transportation and logistics. Paper explored that with the help of IoT techniques, different miniature sized devices are invented which can record various parameters of human body, wearables devices have been invented which are… More >

Zhoulei Cao¹, Qijun Wen¹, Xiaoliang Wang^1,*, Qing Yang¹, Frank Jiang²

Journal on Internet of Things, Vol.3, No.1, pp. 11-17, 2021, DOI:10.32604/jiot.2021.010404

Abstract The miniaturization and endurance of wearable devices have been the research direction for a long time. With the development of nanotechnology and the emergence of microelectronics products, people have explored many new strategies that may be applied to wearable devices. In this overview, we will summarize the recent research of wearable devices in these two directions, and summarize some available related technologies. More >

Xiaokan Wang^*, Qiong Wang

Journal on Internet of Things, Vol.3, No.1, pp. 1-9, 2021, DOI:10.32604/jiot.2021.010228

Abstract A multi-objective improved genetic algorithm is constructed to solve the train operation simulation model of urban rail train and find the optimal operation curve. In the train control system, the conversion point of operating mode is the basic of gene encoding and the chromosome composed of multiple genes represents a control scheme, and the initial population can be formed by the way. The fitness function can be designed by the design requirements of the train control stop error, time error and energy consumption. the effectiveness of new individual can be ensured by checking the validity of the original individual when… More >

Jianwei Zhang, Zhenxing Wang, Yuhui Zheng, Guoqing Zhang^*

Journal of New Media, Vol.3, No.1, pp. 29-39, 2021, DOI:10.32604/jnm.2021.018383

Abstract Image super resolution is an important field of computer research. The current mainstream image super-resolution technology is to use deep learning to mine the deeper features of the image, and then use it for image restoration. However, most of these models mentioned above only trained the images in a specific scale and do not consider the relationships between different scales of images. In order to utilize the information of images at different scales, we design a cascade network structure and cascaded super-resolution convolutional neural networks. This network contains three cascaded FSRCNNs. Due to each sub FSRCNN can process a specific… More >

Mingming Yang^*, Junchuan Yang

Journal of New Media, Vol.3, No.1, pp. 19-27, 2021, DOI:10.32604/jnm.2021.018267

Abstract Every day we receive a large amount of information through different social media and software, and this data and information can be realized with the advent of data mining methods. In the process of data mining, to solve some high-dimensional problems, feature selection is carried out in limited training samples, and effective features are selected. This paper focuses on two Relief feature selection algorithms: Relief and ReliefF algorithm. The differences between them and their respective applicable scopes are analyzed. Based on Relief algorithm, the high weight feature subset is obtained, and the correlation between features is calculated according to the… More >

Zhiyuan Luo^*

Journal of New Media, Vol.3, No.1, pp. 11-17, 2021, DOI:10.32604/jnm.2021.018027

Abstract Person re-ID is becoming increasingly popular in the field of modern surveillance. The purpose of person re-ID is to retrieve person of interests in non-overlapping multi-camera surveillance system. Due to the complexity of the surveillance scene, the person images captured by cameras often have problems such as size variation, rotation, occlusion, illumination difference, etc., which brings great challenges to the study of person re-ID. In recent years, studies based on deep learning have achieved great success in person re-ID. The improvement of basic networks and a large number of studies on the influencing factors have greatly improved the accuracy of… More >

Jiancheng Zou¹, Na Zhu^1,*, Bailin Ge¹, Don Hong²

Journal of New Media, Vol.3, No.1, pp. 1-10, 2021, DOI:10.32604/jnm.2021.017763

Abstract We propose an improved a single-shot detector (SSD) algorithm to detect falls of the elderly. The VGG16 network part of the SSD network is replaced with the MobilenetV2 network. At the same time, we change the infrastructure of MobilenetV2 network, the three layers that were not downsampled at the end were removed, which can make the model structure simpler and faster to detect. The complete Intersection-over-Union (CIoU) loss function is introduced to get a good regression of the target borders that have different sizes and different proportions. We use Feature Pyramid Network (FPN) for upsampling, it can fuse low-level feature… More >

Zhihang Wang^1,*, Jinyu Xu^1,2, Xin Meng¹, Conigjin Zhu¹

Journal of Renewable Materials, Vol.9, No.6, pp. 1157-1168, 2021, DOI:10.32604/jrm.2021.014878

Abstract In this paper, the specimens of polymer-cement composites after 1 d, 7 d, 15 d, and 30 d aging without aging and UV aging are subjected to fixed extension test and tensile test. By observing the mode of the composite in the fixed-elongation test, and measuring the elastic recovery rate, tensile strength, elongation at break, peak tensile strain, tensile toughness and pre-peak tensile toughness of the composite, the effects of UV aging on the bonding and the tensile properties of the composite were studied. And combining with scanning electron microscopy experiments, the micro-mechanism of the effect of ultraviolet aging on… More >

Yiwei Xuan^1,3, Haitao Li^1,*, Zhemin Bei¹, Zhenhua Xiong², Rodolfo Lorenzo⁴, Ileana Corbi⁵, Ottavia Corbi⁵

Journal of Renewable Materials, Vol.9, No.6, pp. 1143-1156, 2021, DOI:10.32604/jrm.2021.015292

Abstract This research studied the ultimate bearing capacity of laminated bamboo lumber (LBL) unit and thereby calculated the maximum bending moment. The load-displacement chart for all specimens was obtained. Then the flexural capacity of members with and without bamboo nodes in the middle section was coMPared. The bending experiment phenomenon of LBL unit was concluded. Different failure modes of bending components were analysed and concluded. Finally, the bending behaviour of LBL units is coMPared with other bamboo and timber products. It is shown that the average ultimate load of BS members is 866.1 N, the average flexural strength is 101 MPa,… More >