Ting Wu

Ting Wu

Auto-generated profile, based on publicly available information

Ting Wu

College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
15 April 2025 in IEEE Access
Verified
Journal Article
Open access
YCYang Chengcheng
Yang Chengcheng
ZLZhiyao Liang
Zhiyao Liang
DYDashun Yan
Dashun Yan
Zeng HuZeng Hu
Zeng Hu
TWTing Wu
Ting Wu
In multimodal sentiment analysis, a significant challenge lies in quantifying the contribution of each modality and achieving effective modality fusion. This paper presents a Hierarchical Gating-Driven Transformer Fusion Model (HGTFM), which effectively achieves multimodal data fusion through an advanced transformer architecture and a Hierarchical Gated Fusion Module (HGFM). The model first encodes audio and video features using LSTM and CNN, respectively, while employing BERT to encode text features. This approach effectively enhances the model ability to manage long-range temporal dependencies. Furthermore, the model introduces HGFM, which dynamically integrates multimodal features across different levels after processing by the modality interaction network (MIN), thus intelligently adjusting the contribution weights of each modality. In particular, the model incorporates a Unimodal Label Generation Module (ULGM), which considers the differences between the modalities. This enables HGFM to more accurately identify the contributions of samples with significant modal variations, thus optimizing the module potential. The experimental results on several established benchmark datasets demonstrate that HGTFM achieves comparable performance improvements in multimodal sentiment analysis tasks.

28 October 2018 in Journal of Sensors
Verified
Journal Article
Open access
PDF file
LYLing Yang
Ling Yang
VBV. Sarath Babu
V. Sarath Babu
JZJuan Zou
Juan Zou
XCXu Can Cai
Xu Can Cai
TWTing Wu
Ting Wu
Li LinLi Lin
Li Lin
To solve the problem of unreliability of traceability information in the traceability system, we developed an intelligent monitoring system to realize the real-time online acquisition of physicochemical parameters of the agricultural inputs and to predict the varieties of input products accurately. Firstly, self-developed monitoring equipment was used to realize real-time acquisition, format conversion and pretreatment of the physicochemical parameters of inputs, and real-time communication with the cloud platform server. In this process, LoRa technology was adopted to solve the wireless communication problems between long-distance, low-power, and multinode environments. Secondly, a deep belief network (DBN) model was used to learn unsupervised physicochemical parameters of input products and extract the input features. Finally, these input features were utilized on the softmax classifier to establish the classification model, which could accurately predict the varieties of agricultural inputs. The results showed that when six kinds of pesticides, chemical fertilizers, and other agricultural inputs were predicted through the system, the prediction accuracy could reach 98.5%. Therefore, the system can be used to monitor the varieties of agrarian inputs effectively and use in real-time to ensure the authenticity and accuracy of the traceability information.

29 November 2024 in IEEE Open Journal of the Communications Society
Verified
Journal Article
Open access
Zeng HuZeng Hu
Zeng Hu
YCYanke Che
Yanke Che
JWJing Wang
Jing Wang
XPXuhong Peng
Xuhong Peng
Chaobo HeChaobo He
Chaobo He
TWTing Wu
Ting Wu
Orthogonal frequency division multiplexing with index modulation (OFDM-IM) is a promising multi-carrier technique for next generation wireless communication networks. In this paper, we propose a generalized joint OFDM-IM scheme, which performs joint modulation on multiple sub-subblocks divided from a subblock, to achieve higher spectral efficiency (SE) and lower complexity for both modulation and detection processes. In GJ-OFDM-IM, the subcarrier activation pattern (SAP) of the subblock is composed of the SAPs of all the sub-subblocks within the subblock, which means a large dimensions IM of the subblock is divided into multiple small size IM of the sub-subblocks by taking advantage of the joint modulation. With the aid of joint modulation, the lookup tables for both modulation and demodulation are only related with the size of sub-subblock and not changed with the size of the subblock. At the receiver, the optimal maximum likelihood (ML) detector and a low complexity subblock wise detector are proposed for GJ-OFDM-IM. Then, a tight upper bound on the bit error rate (BER) is derived in closed form to evaluate the system performance of the proposed GJ-OFDM-IM. Simulation and numerical results verify the analysis and show that the proposed GJ-OFDM-IM can greatly reduce the implementation complexity without causing any system BER performance loss compared with classical OFDM-IM.

17 April 2023 in IEEE Access
Verified
Journal Article
Open access
JYJun Yao
Jun Yao
ZSZechen Shi
Zechen Shi
HJHanjing Jiang
Hanjing Jiang
QWQingxiu Wang
Qingxiu Wang
NCNingxia Chen
Ningxia Chen
JZJuan Zou
Juan Zou
Deploying pigeon age detection model on edge equipment can solve the problem of video transmission delay and reduce the pressure of network transmission. Based on the deployment of edge devices, we made some improvements to You Only Look Once version 5 (YOLOv5) to form a new, lightweight, high-performance detector named LN-STEP-YOLO. In order to reduce the size of the model, we halved the number of channels in the YOLOv5s model. However, the decrease in the number of channels brings some problems, such as low global information acquisition, retention of image redundancy information, attention deficit, etc. To solve these problems, we did the following work. First, we proposed a new convolution structure with the effect of a large convolution kernel, StepConv. Second, a 2 × 2 convolution with step size 2 was used at the input to split each image into individual patches. Third, External Attention (EA) was introduced in the bottleneck structure. Fourth, a modified extremely separated convolutional block (XsepConv) was used for downsampling. Finally, we replaced the batch normalization (BN) of all non-downsampled layers with layer normalization (LN). The results showed that the improved algorithm outperformed generic lightweight networks such as Mixnet, Mobilenetv3, and Ghostnet to distinguish small-sized, overlapping pigeons, achieving 92.8% mean average precision (mAP) at about 17% of YOLOv5s parameters, 0.1% lower than that achieved by use of YOLOv5s. In addition, the improved method had 3.7G floating point operations (FLOPs) and 1.25G parameters, which allowed the detection of the growth stages of pigeons in real environments and provided a reference to guide placement of feeders in automated pigeon farming.

2 April 2025 in Journal of Food Measurement and Characterization
Verified
Journal Article
Closed access
PDF file
TWTing Wu
Ting Wu
LLLei Li
Lei Li
LZLonghui Zhu
Longhui Zhu
WBWeidong Bai
Weidong Bai
LLLi Lin
Li Lin
LYLing Yang
Ling Yang

27 May 2025 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
Zeng HuZeng Hu
Zeng Hu
YLYun Liu
Yun Liu
YCYinming Cui
Yinming Cui
DWDehuan Wan
Dehuan Wan
JWJing Wang
Jing Wang
TWTing Wu
Ting Wu
Multiple-mode orthogonal frequency division multiplexing with index modulation (MM-OFDM-IM) is a promising multicarrier transmission technique proposed recently, which focus on exploiting the index domain of the multiple distinguishable modes (constellations) and uses full permutations of the indices of multiple symbol modes to transmit information bits implicitly. Compared to conventional OFDM-IM, a factorial increase of the IM patterns in MM-OFDM-IM prohibits its application in realistic communication systems due to exponentially increased modulation and demodulation complexity when the number of symbol modes is large. In this paper, we propose a novel and efficient MM-OFDM with cascade IM (MM-OFDM-CIM) scheme, which first selects partial symbol modes for multiple mode index modulation (MM-IM) of the first subblock in the cluster and then performs MM-IM based on the rest symbol modes for the second subblock. The proposed CIM method divides the IM process into two steps and achieves considerably low computational complexity in detection. Furthermore, physical layer security can be realized by adjusting the size of subblocks within the cluster due to the flexible CIM designs. Computer simulations show that the proposed MM-OFDM-CIM has potential to achieve near the same bit error rate performance with considerably low computational complexity and achieves excellent secure communication performance between the legitimate users.