Bo Zhu

Bo Zhu

Auto-generated profile, based on publicly available information

Bo Zhu

ByteDance Inc., China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 May 2022 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
BZBo Zhu
Bo Zhu
DZDaohui Zhang
Daohui Zhang
YCYaqi Chu
Yaqi Chu
YGYalun Gu
Yalun Gu
XZXingang Zhao
Xingang Zhao
In order to reduce the gap between the laboratory environment and actual use in daily life of human-machine interaction based on surface electromyogram (sEMG) intent recognition, this paper presents a benchmark dataset of sEMG in non-ideal conditions ( SeNic ). The dataset mainly consists of 8-channel sEMG signals, and electrode shifts from an 3D-printed annular ruler. A total of 36 subjects participate in our data acquisition experiments of 7 gestures in non-ideal conditions, where non-ideal factors of 1) electrode shifts, 2) individual difference, 3) muscle fatigue, 4) inter-day difference, and 5) arm postures are elaborately involved. Signals of sEMG are validated first in temporal and frequency domains. Results of recognizing gestures in ideal conditions indicate the high quality of the dataset. Adverse impacts in non-ideal conditions are further revealed in the amplitudes of these data and recognition accuracies. To be concluded, SeNic is a benchmark dataset that introduces several non-ideal factors which often degrade the robustness of sEMG-based systems. It could be used as a freely available dataset and a common platform for researchers in the sEMG-based recognition community. The benchmark dataset SeNic are available online via the website ( https://github.com/bozhubo/SeNic and https://gitee.com/bozhubo/SeNic ).

3 September 2018 in IEEE Access
Verified
Journal Article
Open access
BZBo Zhu
Bo Zhu
RHRemigio Hurtado
Remigio Hurtado
JSJESUS BOBADILLA SANCHO
JESUS BOBADILLA SANCHO
Fernando OrtegaFernando Ortega
Fernando Ortega
In this paper, we propose a collaborative filtering method designed to improve the current memory-based prediction times without worsening and even improving the existing accuracy results. The accuracy improvement is achieved by combining the numerical relevance of the ratings with non-numerical information based on the votes structure. The improvement of the prediction time is achieved by setting four actions: 1) simplification of the similarity measure design, in order to minimize the necessary calculations; 2) construction and maintenance of a model that simplifies the predictions processing; 3) optimization of the computation, using a set-based model and a bit-based processing implementation; and 4) switching between the bit processing and the numerical processing, depending on the density of the users' ratings. Experimental results show the improvements both in the prediction time and the accuracy. Experiments have used a significant amount of state-of-the-art baselines and collaborative filtering public data sets.

17 July 2024
Verified
Conference Paper
Open access
SJShaohui Jiao
Shaohui Jiao
DZDehao Zhao
Dehao Zhao
YCYuzhong Chen
Yuzhong Chen
SWShengdong Wang
Shengdong Wang
CXCong Xie
Cong Xie
LZLi Zhang
Li Zhang
We present a novel interactable free-viewpoint video (FVV), which generates photo-realistic and editable volumetric content with high degree of freedom. On the one hand, an enhanced visual hull guided neural representation with higher performance is proposed, an-easy-to-use sparse multi-camera capture system is used, as well as a high performance VH-NeRF is proposed for fast generation of photo-realistic FVV results for live streaming. On the other hand, for monocular panorama video input, high-precision depth and coarse dynamic mesh are calculated, which are used for novel view synthesis of right perspective views with motion parallax on the fly. For better interaction with high realism, dual-channel stereohaptics is implemented and attached on VR headsets to obtain haptic feedback. Last, our FVV solution can do effective compression and transmission on both multi-perspective videos and panorama video with depth data, as well as real-time rendering on consumer-grade hardware. To the best of our knowledge, our work is the first interactable FVV solution with high visual quality and real-time haptic feedback. It is established that the user can do intuitive manipulation for immersive experiences in VR/AR applications.


1 January 2017
Verified
Conference Paper
Open access
PDF file
YPYanjun Pang
Yanjun Pang
HCHuiyan Cao
Huiyan Cao
XZXiaoshu Zhang
Xiaoshu Zhang
XZXinhua Zhao
Xinhua Zhao
MXMei Xu
Mei Xu
BZBo Zhu
Bo Zhu