Shanghai, China

Shanghai Jianqiao College

www.gench.edu.cn
Shanghai, China

Time filter

Source Type

Dai C.,Shanghai Jianqiao College
ICALIP 2016 - 2016 International Conference on Audio, Language and Image Processing - Proceedings | Year: 2016

One of the main problems of object online classification using classifier trained offline is the mismatch of online test images and offline training data. In this paper, we propose an online video object classification algorithm with the mechanism of training data updating. By selecting part of the uncertain test data captured online and labeling them artificially to replace a proportion of the training data, the classifier can be retrained using the renew online training data, and thus the possible mismatch problem can be avoided and then higher classification accuracy can be achieved. From the experiments based on online surveillance video object classification, it was observed that: compared with existing classifier without training-data-updating, the proposed method can achieve up to average 18% classification accuracy increasing. © 2016 IEEE.


Li W.,Shanghai Jianqiao College
2011 International Conference on Multimedia Technology, ICMT 2011 | Year: 2011

This paper offered an idea about the experience of roles in movie and discussed the methods by building models and structures under distributed virtual environment and utilizing the technology of Cloud Computing. It may have some reference value for future development. © 2011 IEEE.


Li W.Y.,Shanghai Jianqiao College
Applied Mechanics and Materials | Year: 2014

There is a clear lack of respect about traditional network adaptive learning system teaching on individualized assessment knowledge and building tacit knowledge, and this paper presents a knowledge model that supports personalized knowledge assessment, knowledge stored in the cloud computing environment, and construct tacit knowledge for learning body, to provide a personalized learning services for learners to achieve user to adapt the system to adapt to the user's system and two-way adaptation, this paper has guiding significance for further studies of adaptive learning systems. © (2014) Trans Tech Publications, Switzerland.


Yin J.,Shanghai Jianqiao College
Applied Mechanics and Materials | Year: 2013

According to the status of lacking fast detection technology to adulteration olive oil, the paper presented a new method based on near infrared spectroscopy technology and pattern recognition. 10 samples of pure olive oil were collected. 2 kinds of adulteration samples were respectively made up with soybean oil and rapeseed oil. The Identification models were build respectively by support vector machines and hierarchial clustering. The result showed that the model's performance built by SVM was better than the model by hierarchial clustering. The recognition ratio and prediction ratio of SVM were 100%.The experiments shown that the fast detection technology based on NIR and pattern recognition had better feasibility and practicability in identifying adulteration olive oil.© (2013) Trans Tech Publications, Switzerland.


Chunni D.,Shanghai Jianqiao College
Proceedings - 2015 6th International Conference on Intelligent Systems Design and Engineering Applications, ISDEA 2015 | Year: 2015

In order to enhance the accuracy rate of video classification, this article proposes a support SVM classification of using genetic algorithm to optimize features weighting (GA-SVM). First, this article extracts the colors and textural features of video, then adopts improved genetic algorithm to determine features weighting, and at last uses support SVM to establish video classifier and implements simulation test of corel video database. The results show that comparing with other video category algorithm, GA-SVM enhances accuracy of video classification. © 2015 IEEE.


Luo Z.H.,Shanghai Jianqiao College
Applied Mechanics and Materials | Year: 2014

This paper conducts a comprehensive study on the optimization design for luffing mechanism of portal slewing crane. First, displacement formulae are derived of crampon hinge point of the luffing mechanism. Secondly, mathematical model is established for luffing mechanism optimization design of portal slewing crane, according to the mechanism characteristics, and, with an aim of making crampon hinge end point to move horizontally, and of satisfying the value of maximum and minimum amplitude, and of saving material, etc. Finally, program of optimization design is compiled for the luffing mechanism of portal slewing crane. The luffing mechanism of M4022 portal slewing crane is optimized, and the optimization result is satisfactory. This paper makes it possible to obtain not only each rod length and cross-section area, but also obtain the counterbalance weight and the each rod maximum force of the luffing mechanism. © (2014) Trans Tech Publications, Switzerland.


Jiang Z.Y.,Shanghai Jianqiao College
Applied Mechanics and Materials | Year: 2014

In the basis of the integration of traditional and network teaching, a network teaching system based on webquest and mindmap was established. Around webquest and mindmap, the main modules of the system had been designed and a new inquiry teaching model had been established, in which the teacher-leading and student-centered idea was introduced and intellectual analysis feedback circle was designed. By inputting teaching tasks, teaching situation and teaching resources, and by means of teacher's just-in-time guidance and student's thinking and inquiry, the system could output the final complete mind maps and inquiry conclusions. The system was applied to the "principles of computer network" course and empirical research was carried out in the experimental class. The experimental results show that, the network teaching system can stimulate student's learning interest, and improve student's comprehensive qualities and innovation ability. © (2014) Trans Tech Publications, Switzerland.


Chunni D.,Shanghai Jianqiao College
Proceedings - 2015 7th International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2015 | Year: 2015

Real-time performance and robust detection plays important roles in smart surveillance. The design and implement of an intelligent surveillance system based on DM6446 is proposed. In this paper, firstly, we design and implement an motion detection system based on DaVinci TI DM8168 which is multi-core structure, including hardware and software. By using median filter in initial phase of ViBe, the true real background would be obtained without ghost. In addition, objects can be tracked via pixel-labeled segmentation method. The algorithm classifies and marks the pixels, then tracks the targets after merging the pixels of same class. The experimental results show that these proposed method perform fast and robustly in the real-time motion detection system based on DaVinci TI DM8168. © 2015 IEEE.


Yin J.,Shanghai Jianqiao College
Applied Mechanics and Materials | Year: 2013

This paper introduces image acquisition display system based on USB binocular camera which is developed by S3C6410 and embedded operating system WinCE 6.0. Hardware system is implemented on OK6410 development board, extending double camera by USB HUB as binocular camera. Software application is programmed by MFC. The system provides a feasible hardware plat form for subsequent three-dimensional visual system development. © (2013) Trans Tech Publications, Switzerland.


Yin J.,Shanghai Jianqiao College
Applied Mechanics and Materials | Year: 2013

To effectively recognize gait signal between healthy people and patients with Parkinson, a gait signal recognition model is established based on neural network of error back propagation (EBP),and a method is proposed to effectively extract characteristic parameters. In this paper, coefficient of variation is applied in the research of gait-pressure multi-characteristic parameters through gait-pressure signal, and the neural network model can automatically recognize gait-pressure characteristics between healthy people and patients with Parkinson. This can contribute to the recognition and diagnosis of patients with Parkinson. Experiment results show a recognition rate of 90%. © (2013) Trans Tech Publications, Switzerland.

Loading Shanghai Jianqiao College collaborators
Loading Shanghai Jianqiao College collaborators