- Cryptography and Data Security
- Chaos-based Image/Signal Encryption
- Computational Drug Discovery Methods
- Advanced Photocatalysis Techniques
- Data Management and Algorithms
- Machine Learning in Materials Science
- Industrial Vision Systems and Defect Detection
- Surface Roughness and Optical Measurements
- Natural Language Processing Techniques
- Radiomics and Machine Learning in Medical Imaging
- Neural dynamics and brain function
- Manufacturing Process and Optimization
- Advanced Clustering Algorithms Research
- Vehicle License Plate Recognition
- Cold Atom Physics and Bose-Einstein Condensates
- Evacuation and Crowd Dynamics
- Scheduling and Optimization Algorithms
- Advanced Steganography and Watermarking Techniques
- Privacy-Preserving Technologies in Data
- Data Stream Mining Techniques
- Fire effects on concrete materials
- Atomic and Subatomic Physics Research
- Direction-of-Arrival Estimation Techniques
- Molecular spectroscopy and chirality
- Supply Chain and Inventory Management
Qufu Normal University
2023-2025
Hebei University of Engineering
2021-2024
Tianjin University of Science and Technology
2022-2023
Wuhan Institute of Technology
2023
Chongqing Jiaotong University
2023
Georgia Institute of Technology
2023
Northwest University
2022
Zhejiang Lab
2022
Shanghai Micro Satellite Engineering Center
2022
Shandong Jianzhu University
2022
Breast density and background parenchymal enhancement (BPE) are suggested to be related the risk of breast cancer. The first step quantitative analysis BPE is segmenting from body. Nowadays, convolutional neural networks (CNNs) widely used in image segmentation work well semantic segmentation, however, CNNs have been rarely region segmentation. In this paper, CNN was employed segment transverse fat-suppressed dynamic contrast enhanced magnetic resonance imaging (DCE-MRI). Image normalization...
The current manual reading of substation pointer meters wastes human resources, and existing algorithms have limitations in accuracy robustness for detecting various meters. This paper proposes a method recognizing based on Yolov7 Hough transform to improve their automatic readability. proposed consists three main contributions: (1) Using object detection technology, which is the latest Yolo enhance instrument recognition accuracy. (2) Providing formula calculating angle square meter after...
Multi-key homomorphic encryption is widely applied into outsourced computing and privacy-preserving applications in multi-user scenarios. However, the existence of CRS weakens ability users to independently generate public keys, it difficult implement decentralized systems or scenarios with low trust requirements. In order reduce excessive reliance on parameters, a multi-key scheme without pre-setting proposed based distributed key generation protocol. The does not require pre-generation...
Multi-key homomorphic encryption is widely applied into outsourced computing and privacy-preserving applications in multi-user scenarios. However, the existence of Common Random Strings (CRSs) weakens ability users to independently generate public keys, it difficult implement decentralized systems or scenarios with low trust requirements. In order reduce excessive reliance on parameters, a multi-key scheme without pre-setting CRSs proposed based distributed key generation protocol. The does...
This paper sets out to examine the problems which exist with newly published Contemporary Chinese Dictionary (6th edition), particular reference establishment of definitions, exemplifications and word class labels its entries, selection neologisms, as well reader-friendly considerations. The examination is conducted based on query results from available corpora, an aim highlight urgent necessity use large-scale corpora for lexicography. study concludes that it now imperative build...
A better scheme is proposed for image authentication and restoration based on standard deviation (STD) using two watermarks, one detecting tampered regions the other retrieval. The main contribution of this work a decrease recovery watermark, which compressed from three categories according to STD values every quantization discrete cosine transformation coefficients block. In addition, blocks corresponding different are encoded variable lengths then encrypted index chaotic sequence in an...
This study's research objectives are investigating the status and understanding correlation between creative teaching behavior, school principals' servant leadership at elementary schools in Tainan City's rural remote areas. On method, questionnaire was designed objects of this study were public teachers within Taiwan. Data analysis conducted for 723 effective questionnaires from 84 schools. The valid return rate 85%. Research findings shown as follows: There is positive Creative behavior.
Chiral compounds are very important in drug development, organic synthesis, materials science, toxicology, or environmental chemistry. Therefore, for creating new drugs, several methods have been suggested recent years. In laboratories the world, some derivations of parameters were constructed and used studies on quantitative structure–activity/property relationships chiral molecules. The algorithms reviewed this paper involve Zargeb group indices, molecular connectivity index, topological...
ABSTRACT With the rapid development of social economy, importance water resources is becoming increasingly prominent. Urban demand in Beijing has been growing rapidly. Accurate consumption forecasting utmost for reasonable allocation and optimization supply systems. In this study, an innovative multi-variable grey prediction model with adjacent accumulation (AOGM(1,N)) proposed to predict Beijing's annual four different usage scenarios (domestic water, agricultural industrial environmental...
Layered adhesive structures are widely used in the aerospace field, and thus their defect detection is a critical part of quality control. Hence, this paper proposes method to identify bonding defects relying on dynamic time warping (DTW) simulation analysis. Based transfer matrix method, propagation model layered structure established, signal normal area characteristic interval obtained. DTW adopted regularize simulated real signals, then Pearson correlation coefficient employed calculate...
In recent years, multi-task learning models based on deep in recommender systems have attracted increasing attention from researchers industry and academia. Accurately estimating post-click conversion rate (CVR) is often considered as the primary task of systems. However, some advertisers may try to get higher click-through rates (CTR) by over-decorating their ads, which result excessive exposure samples with lower CVR. For example, only eye-catching clickbait CTR, but actually, CVR very...
In this paper, SEPAM_HRNet, a high-resolution pose-estimation model that incorporates the squeeze-and-excitation and pixel-attention-mask (SEPAM) module is proposed. Feature pyramid extraction, channel attention, pixel-attention masks are integrated into SEPAM module, resulting in improved performance. The construction of involves replacing ordinary convolutions with plug-and-play which leads to creation SEPAMneck SEPAMblock module. To evaluate model’s performance, YOGA2022 human yoga poses...
We report a quasicontinuous wave (CW) linearly polarized rubidium vapor laser. The pumping source consists of five laser diode bars and its linewidth is reduced from the raw 1.8 to 0.2 nm by bulk volume Bragg grating. Instead adopting “quasi-waveguide structure” gain cell, light propagates freely in cell. with polarization perpendicular one coupled into resonator cavity beam splitter. This configuration suitable for convection-cooling diode-pumped alkali
After analyzing the disadvantages of sensitivity to initial selection center, low clustering accuracy and poor global search ability k-medoids algorithm, a algorithm based on improved artificial bee colony (ABC) is proposed.By improving initialization colony, adjusting step dynamically with iteration increasing , then introducing probability sorting instead depending fitness directly, ABC will quickly converge optimal.This paper further optimize improve performance algorithm.The experimental...