王 洲浩
Tokyo
王 洲浩
interested in IT/Data Science/Machine Learning
My name is Wang Zhouhao, 王洲浩 in Chinese and Japanese. I'm graduated from Software Engineering, Zhejiang University in China, and now pursuing my master's degree at the University of Tokyo, Graduate School of Engineering. Currently, I'm focusing on learning and studying of machine learning techniques for data mining. I'm also slightly interested in network technics. I'm willing to become an eng
The University of Tokyo
System Innovation, Graduate School of Engineering
Taking courses related to Machine Learning, Deep Learning, and Data Science. Researching on NLP, matching passages/sentences with the same meaning in different languages.
- Emotion-Driven Music Data Mining
The purpose of Research：To do the research on emotional recognition algorithms of music for realizing music emotion theme and find out a possible matching method of music and emotion. Process of Research： 1．Search and revise various existing possible emotion recognizations models, and establish our own emotion model. 2．Using open source software Marsyas to extract to original features of music samples. Artificially we mark each music fragments with appropriate emotion labels. 3．Search the papers and publishments about algorithms related to emotional recognition and the progress of the latest research. Make sure we understand the algorithms and decide the appropriate algorithm to use. 4. We tried to establish the model which links the music and emotional marks. We designed the experiment through machine learning algorithms, during this process we adjusted models and algorithms, evaluated accuracy and adequacy of the model. 5.Finally, we decided the appropriate emotion model, developed the software playing the music fragment and applied for the patent. Research Result： 1.We tried and figured one matching method of music and emotion, but its accuracy is insufficient. 2.Zhejiang University acquired copyright patent, and our group members got a practical new type patent(ZL 2015 2 0138998.1).
- Distribution analysis and demand forecasting using taxi GPS data
The purpose of Research：In this research, we propose a demand prediction of a specific location(Tsukuba City) using the GPS taxi allocation history data for sales. The taxi delivery is based on the location recorded by the telephone receiver for the customer. We can also mine the GPS data to propose a taxi waiting for places and decide the number of waiting vehicles in each area, making efforts to improve the efficiency of the taxi business. Process of Research： 1．GPS data processing. Handling telephone reception, decide the starting position and the destination of the customer. 2.Evaluate the algorithm, do the investment about the recent progress about network structure and algorithms. 3.During the process of the experiment, we adjusted models and algorithms, evaluated accuracy and adequacy of the model. 4.Publish the result as the finish of our project. Research Result：Research report and a part of collaborating research paper.
- Engineering Traffic Uncertainty in the OpenFlow Data Plane
The purpose of Research：We were driven by a simple question of whether traffic engineering in Software Defined Networking (SDN) can react quickly to bursty and unpredictable changes in traffic demand. The key challenge is to strike a careful balance between the overhead (frequently involving the SDN controller) and performance (the degree of congestion measured as the maximum load and the balance between the minimum and the maximum loads). Exploiting OpenFlow (OF) features, a quick shift of routing paths for unpredictable traffic bursty is the focal point of this work. Process of Research： 1．Establish the traffic model, do the investment about the recent progress about network structure and algorithms. Decide our new model of traffic delivery.（Primary working part of Dr.Chen Fei） 2.Evaluate the algorithm, and simultaneously determine the simulation model, create a simulation environment.（My primary working part） 4.We designed the simulation experiment through simulator I developed, during this process we adjusted models and algorithms, evaluated accuracy and adequacy of the model. 5. Write the paper, and finally, our paper was luckily accepted by IEEE INFOCOM conference, April 2016 Research Result：Our purpose was achieved by using a dual routing scheme and letting the data plane to select the appropriate path in reacting to uncertainty in traffic load. The proposed work is called DUCE (Demand Uncertainty Configuration selection). Further, we describe a traffic distribution model, an optimization solution that calculates congestion-free traffic distribution plan which guarantees that each switch can select one of the paths in a distributed way, and moreover, of details about detaching the functionality of responding to the demand uncertainty from the control plane and delegating it to the data plane. Simulations are performed validating the efficiency of DUCE under various network scenarios.
- Research related with EEG intelligent home control applications
The purpose of Research：Neurophysiological studies has offered us a foundation so we can find some correlation between EEG and human consciousness and actions. Based on this technology, EEG as a means of control are constantly improved and developed, and EEG helmet devices are emerging on the market. For possible use in smart home control products based on, this study of EEG helmets carried EEG acquisition and processing, this research focuses on the software signal processing, classification algorithms, and hardware to minimize the number of electrode contacts. Process of Research： 1．Search and revise various existing recognization models, and establish our own emotion model. 2．Using software offered by Emotiv to extract to original features of EEG signals. Artificially we mark each signal fragments with appropriate labels. 3．Search the papers and publishments about algorithms related to EEG recognition and the progress of the latest research. Make sure we understand the algorithms and decide the appropriate algorithm to use. 4. We tried to establish the model which links the EEG signal and the motivation marks. We designed the experiment through machine learning algorithms, during this process we adjusted models and algorithms, evaluated accuracy and adequacy of the model. 5.Finally, we decided the appropriate relation model. 6.Publish the result and write the graduate paper. Research Result： Graduate paper for my Bachelor's degree in Engineering
Zhejiang University
Software Engineering, College of Compurter Science & Technology
GPA 3.48/4.0 (3.66/4.0 for last 2 years' core courses) with certificate of 15% Joined in several research programs and a paper published.(listed in programs)