Zhen Fan's research while affiliated with Zhejiang University and other places

... In addition, sensor networks have been used in several domains such as user behaviors [4], testing blood sugar [5], or in robots [6]. However, this technology has been predominantly utilized in the field of energy. ...

... The λ t is set to be 0.2, which gives the optimum solution ofW t . The penalty term λ t is set to 0.2 for reduced position RMSE, and velocity RMSE of the moving target, accurately estimating the initial position, and velocity of moving targets shown in Fig. 4, Fig. 5 [18,31,48,56]. By using theW t in Eq. (52), we estimate the initial position ðm 0 Þ, and velocity ðvÞ of moving targets. ...

... Scholars have been trying for decades to artificially extract features from underwater acoustic targets [6][7][8], and the methods include short-time Fourier transform (STFT) [9], low frequency analysis and recording (LOFAR) [10], Mel-frequency spectrum [6], demon noise envelope modulation detection (DEMON) [11], and Mel Frequency Cepstral Coefficients (MFCC) [12]. Traditional algorithm, such as GMM [13] and SVM [14], were used for the underwater acoustic field. These manually extracted features and algorithms have played a significant role in the underwater acoustic field, for example, MFCC features were extracted in a lot of work [15][16][17] for UATR. ...

... No se proporciona información sobre el ltrado de la nube, lo que podría causar errores en la estimación nal de la forma del objeto. Los trabajos presentados en (Liu et al., 2019;Lin et al., 2021;Grinvald et al., 2019;Qi et al., 2020) generan mapas semánticos con objetos basados en SLAM. En todos estos casos, se aplica un ltro después de recortar la nube de puntos. ...

... Typically, literatures [19,20] integrated the attention module, Suppression Network into Mask RCNN to improve the detection performance, but the category was single. Wang et al. [21] proposed a solution for common items misplaced in the indoor scene. Through wearable motion sensor, service robot can perform data fusion and planning on the human movement path, and use YOLOv1 to detect items, but the detection accuracy needs to be improved. ...

... Accuracy of the studied schemes on the NSL-KDD dataset [3,19,20,22,24,25,[28][29][30][31][32][33]35,36,38,39,44,47,49,50,58,59,61,62,64,68,70,75,76,78,111]. Figure 11. Accuracy of the studied schemes on the KDD Cup99 dataset [16,17,19,23,26,39,40,62,65,69,72,74,76,77]. [15,18,41,[44][45][46]48,52,66,68,71,73,76]. Figure 13. ...

... We also developed a simple interface to allows users to initiate and set-up various system functions for the robot, camera, and calibration system ( Figure 7). Our initial evaluation of latency, based on the network latency method [50,51] indicates an average of 11.64 ms (SD = 3.40), which was measured from the moment positional and rotational data of the IK model were read in the Unity3D environment to the moment the servomotor angles are executed on Piton. Previous works in telexistence and virtual reality indicate that latency should be less than 200 ms in order to provide a smooth experience and not induce simulator sickness [52,53]. ...

... Considering the situation with the COVID-19 pandemic in the world [4], Social Companion Robots (SCRs) integrated with various sensing technologies such as vision, voice, or touch to interact with other smart devices in the home can enable the development of advanced artificial intelligence solutions towards Smart Home Care with assistive services to address the needs of the elderly and disabled [1]. The knowledge of the spatial distribution of physical quantities in Smart Home (SH) supports the development of new context-aware applications where new methodologies for multi-sensor data fusion and information processing are needed [5], with possible applications such as multi-point path planning for a home mobile robot [6]. The increasing isolation of elderly people in their own homes and in homes for the elderly has made the problem of caring for the elderly living alone an urgent priority. ...

... Expanding on this work, AN et al. Recently, convolutional neural networks (CNNs) have played astonishing performance in various domains, including object recognition [25] [26], tracking [27]. CNNs excel at recognizing patterns in images by automatically learning high-level descriptive features, eliminating the need for manual feature engineering employed in old-fashioned mechanisms. ...

... Target tracking refers to the estimation of the motion state of the interest target, considering factors such as noisy measurements, false alarm clutter, and imperfect measurements (Da et al., 2021;Zhu et al., 2021). It is widely used in various fields, such as aircraft target tracking (Zhou et al., 2020;Zheng and Cai, 2021) and underwater target tracking (Zhang D et al., 2018). Depending on the nature of the tracked targets, target tracking algorithms can be categorized into point target tracking, extended target tracking, and group target tracking (Guo et al., 2019(Guo et al., , 2020aWang et al., 2021). ...