会议名称:
18th IEEE International Conference on Trust, Security and Privacy in Computing and Communications (IEEE TrustCom) / 13th IEEE International Conference on Big Data Science and Engineering (IEEE BigDataSE)
会议时间:
AUG 05-08, 2019
会议地点:
Rotorua, NEW ZEALAND
会议主办单位:
[Mo, Ran;Jiang, Fu;Zhao, Xiaoshuai;Liu, Weirong;Peng, Jun] Cent South Univ, Sch Comp Sci & Engn, Changsha, Peoples R China.^[Liu, Jianfeng;Gu, Xin] Cent South Univ, Sch Automat, Changsha, Peoples R China.^[Yu, Wentao] Cent South Univ Forestry & Technol, Coll Comp & Informat Engn, Changsha, Peoples R China.^[Mo, Ran;Liu, Jianfeng;Yu, Wentao;Jiang, Fu;Gu, Xin;Zhao, Xiaoshuai;Liu, Weirong;Peng, Jun] Hunan Engn Lab Rail Vehicles Braking Technol, Changsha, Peoples R China.
会议论文集名称:
IEEE Trustcom BigDataSE ISPA
关键词:
Differential privacy;data mining;distance based clustering;adaptive mechanism
摘要:
Analyzing clustering results may lead to the privacy disclosure issue in big data mining. In this paper, we put forward a differential privacy-based protecting data preprocessing method for distance-based clustering. Firstly, the data distortion technique differential privacy is used to prevent the distances in distance-based clustering from disclosing the relationships. Differential privacy may affect the clustering results while protecting privacy. Then an adaptive privacy budget parameter adjustment mechanism is applied for keeping the balance between the privacy protection and the clustering results. By solving the maximum and minimum problems, the differential privacy budget parameter can be obtained for different clustering algorithms. Finally, we conduct extensive experiments to evaluate the performance of our proposed method. The results demonstrate that our method can provide privacy protection with precise clustering results.
作者机构:
[Nan, Fang; Yang, Yun; Ren, Xiao-ping; Chi, Jing-ru; Li, Zi-yu] Natl Ctr Sci & Technol Evaluat, Dept Int Evaluat & Res, Beijing 100081, Peoples R China.;[Ren, Xiao-ping] Natl Inst Metrol, Dept Res & Sci Management, Beijing 100029, Peoples R China.;[Yang, Fan] Cent South Univ Forestry & Technol, Sch Comp & Informat Engn, Changsha 410004, Peoples R China.
会议名称:
31st Chinese Control And Decision Conference (CCDC)
会议时间:
JUN 03-05, 2019
会议地点:
Nanchang, PEOPLES R CHINA
会议主办单位:
[Ren, Xiao-ping;Yang, Yun;Nan, Fang;Li, Zi-yu;Chi, Jing-ru] Natl Ctr Sci & Technol Evaluat, Dept Int Evaluat & Res, Beijing 100081, Peoples R China.^[Ren, Xiao-ping] Natl Inst Metrol, Dept Res & Sci Management, Beijing 100029, Peoples R China.^[Yang, Fan] Cent South Univ Forestry & Technol, Sch Comp & Informat Engn, Changsha 410004, Peoples R China.
会议论文集名称:
Chinese Control and Decision Conference
关键词:
Research Evaluation;Indicator Determination;Monte Carlo Method;Delphi Approach
摘要:
During a research evaluation, a set of indicators is gathered according to evaluation target. The rationality measurement of these indicators is essential but difficult. In a traditional Delphi Approach (DA), experts grade the importance and feasibility of indicators, and then propose refinements to the initial indicators. Only those rated above average will be retained. During multi-round DA processes, the calculation is complex and may repeat several rounds. This study aimed to describe a new indicator selecting technique, by applying Monte Carlo simulation method onto Delphi Approach(MCDA). The modification of Delphi Approach, including its underlying assumptions and strengths, are explained in this article. To present this modified Delphi Approach, a brief demonstration is also discussed.
通讯机构:
[Cao, Jiwu] C;Cent South Univ Forestry & Technol, Changsha 410004, Hunan, Peoples R China.
会议名称:
International Conference on Frontiers of Biological Sciences and Engineering (FBSE)
会议时间:
NOV 23-24, 2018
会议地点:
Chongqing, PEOPLES R CHINA
会议主办单位:
[Wu, Yi;Cao, Jiwu;Peng, Jiqing;Xu, Yongfu;Liu, Chunlin;Zhou, Guoying] Cent South Univ Forestry & Technol, Changsha 410004, Hunan, Peoples R China.
会议论文集名称:
AIP Conference Proceedings
关键词:
Magnolia 'Wulin';Magnolia Officinalis;New Cultivar;South China
摘要:
Magnolia ‘Wulin’ is a new cultivar of Magnolia officinalis. It belongs to small evergreen or semi-evergreen trees, with leathery leaves and slender petioles. It has fragrant flowers, and solitary branches top, petals are pink, filaments are deep red. The flowering period is from mid-April to mid-May. It is a kind of valuable plant with great potential value.
会议名称:
Photonics and Electromagnetics Research Symposium - Fall (PIERS - Fall)
会议时间:
DEC 17-20, 2019
会议地点:
Xiamen, PEOPLES R CHINA
会议主办单位:
[Zhai, Shengqing;Yang, Yusi;Lin, Lan] Tongji Univ, Dept Elect Sci & Technol, Shanghai, Peoples R China.^[Ou, Wenbo] Cent South Univ Forestry & Technol, Dept Automat, Changsha, Peoples R China.
会议论文集名称:
Progress in Electromagnetics Research Symposium
摘要:
There are many kinds of hepatic lesions which threaten human healthy by high incidence. Analyzing CT images is an effective method to evaluate the type of hepatic lesions. The original evaluation method is that medical personnel assessment by images, but abdominal CT images are complex, and the accuracy of the discrimination depends strongly on the subjective factors, knowledge level and experience of medical personnel. With the development of artificial intelligence technology, the hepatic lesions recognition technology based on deep visual feature learning can achieve a higher accuracy. While reducing the workload for doctors, this technology can assist doctors to diagnose the disease, so as to obtain more objective and accurate diagnosis results. The database established in this paper mainly includes three kinds of CT images: primary liver cancer, cirrhosis and normal liver. After the database pretreatment with image de-noise algorithms based on median filter and picture enhancement algorithms based on histogram equalization, the convolution neural network CaffeNet was taken as the main framework, and a large number of labeled liver CT images were used to train the network in the experimental process. Meanwhile, the network parameters were continuously updated according to the cost function. Traditional hepatic lesion recognition technology only depends on the surface features from the image, such as gray scale, statistical structure and texture. Deep learning, a tool with high precision and robustness, could be used to mine the hidden features in the huge database. Through testing the trained deep learning model, the average recognition accuracy of 96.67% and the average single sample recognition time of 1.28 seconds could be achieved perfectly. Therefore, there is no doubt that hepatic lesion recognition technology based on deep visual feature learning will greatly liberate doctors' physical strength and promote the development of pathology in the near future.
作者机构:
[Chen, Hui] Cent South Univ Forestry & Technol, Coll Mech & Elect Engn, Changsha 410004, Peoples R China.;[Shi, Lei] Cent South Univ Forestry & Technol, Informat Ctr, Changsha 410004, Peoples R China.
会议名称:
2nd International Conference on Advanced Electronic Materials, Computers and Materials Engineering (AEMCME)
会议时间:
APR 19-21, 2019
会议地点:
Changsha, PEOPLES R CHINA
会议主办单位:
[Chen, Hui] Cent South Univ Forestry & Technol, Coll Mech & Elect Engn, Changsha 410004, Peoples R China.^[Shi, Lei] Cent South Univ Forestry & Technol, Informat Ctr, Changsha 410004, Peoples R China.
会议论文集名称:
IOP Conference Series-Materials Science and Engineering
摘要:
Silicon material is a widely used substrate in micro-electromechanical systems, and its micro-fabrication technology has always been a research hotspot. The main micro-fabrication methods of silicon material are chemical etching, electrochemical machining (ECM) and electrical discharge machining (EDM). The electrochemical and electrical discharge compound machining technology is a kind of machining method for non-conductive materials. In this paper, the compound machining technology was studied and applied to the microfabrication of silicon material. The machining principle of silicon material in hydrochloric acid solution was studied, and the influence of silicon material type and voltage on the machining was analyzed. It is found that n-type silicon can be machined, while p-type silicon can hardly be machined. With this technology, micro three-dimensional structures can be fabricated on silicon material.
作者机构:
[Sun Yurong; Xie Chuang; Li Pin] Cent South Univ Forestry & Technol, Dept Sci, Changsha 410000, Hunan, Peoples R China.
会议名称:
International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS)
会议时间:
JAN 12-13, 2019
会议地点:
Changsha, PEOPLES R CHINA
会议主办单位:
[Xie Chuang;Li Pin;Sun Yurong] Cent South Univ Forestry & Technol, Dept Sci, Changsha 410000, Hunan, Peoples R China.
关键词:
pedestrian detection;CNN;deep learning;YOLO
摘要:
This paper studies the insufficient extracted image feature in CNN basic network towards large model parameters quantity in convolutional neural network-based target detection model. First, it analyzes calculating method and parameter quantity of separable convolution and standard convolution, and processes original image through increasing sampling layer and blocking area extraction layer on Kronecker. Then, original image will be sampled with two different ratios to form image pyramid sequence and splice two-layered pyramid image in order to guarantee the same original image size. Furthermore, a better learning ability in network can be enhanced under condition without increasing networked scale through multi-scaled training methods. The experiment shows target detection algorithm in this paper cannot only be superior to traditional algorithm but it can also be superior to YOLO model and SSD model in comprehensive performance.
摘要:
The contradiction among population, resource and environment has become increasingly evident that requires the manufacturing industry to improve the compatibility of its activities and the environment. Green supply chain management is a valid way to resolve the conflict between manufacturing industry and the environment based on a systems point of view and the concept of integration. In the content of this paper, the concept of green supply chain would be combined with the method of DEA and it is established from the perspective of input and output in order to offer academic reference and practical guidance to automobile manufacturing industry for moving toward green development that is a set of complete carbon performance evaluation system of automobile manufacturing industry in green supply chain.
通讯机构:
[Cao, Jiwu] C;Cent South Univ Forestry & Technol, Changsha 410004, Hunan, Peoples R China.
会议名称:
International Conference on Frontiers of Biological Sciences and Engineering (FBSE)
会议时间:
NOV 23-24, 2018
会议地点:
Chongqing, PEOPLES R CHINA
会议主办单位:
[Wu, Yi;Cao, Jiwu;Xu, Yongfu;Peng, Jiqing;Liu, Chunlin;Zhou, Guoying] Cent South Univ Forestry & Technol, Changsha 410004, Hunan, Peoples R China.
会议论文集名称:
AIP Conference Proceedings
关键词:
'Yuxia';Interspecific Hybrid;Michelia Maccluri;Michelia Yunnanensis;South China
摘要:
Breeding new varieties of Michelia with Michelia maccluri as male parent and Michelia yunnanensis as female parent. The results showed that: ‘Yuxia’ has the characteristics of excellent ornamental characters, stable ornamental characters and wide adaptability. It is suitable for cultivation in southern China, especially in most areas of the Yangtze River, and has a good application prospect.