Chengquan Hu

Wireless Digital Gas Meter with Lower Power Consumption

Energy is a limited resource in wireless sensors networks. One kind of digital wireless gas node with low power consumption is designed and implemented, the main point of energy saving technology is advanced and the design of each model is given in details. With analysis and computation of the energy consumption of real gas node, the following conclusion is made: the gas node with low power consumption can normally work for 3 to 5 years, and it is suitable for the gas automatic reading system.

Wireless Sensor Network Time Synchronization Algorithm Based on SFD

Time synchronization is an important supporting technology for wireless sensor network (WSN). In most existing WSN time synchronization algorithms, timestamp is recorded by software when sending and receiving synchronization messages, which involving synchronization errors like send time and access time. In this paper, a WSN time synchronization algorithm based on SFD is proposed. In the novel algorithm, timestamp of synchronization message is recorded by SFD hardware capture. It can effectively eliminate send time, access time and other synchronization errors. Experiments based on proposed algorithm have been done to verify the effectiveness and time synchronization errors are analyzed.

A Machine Learning Approach to Argo Data Analysis in a Thermocline

With the rapid development of sensor networks, big marine data arises. To efficiently use these data to predict thermoclines, we propose a machine learning approach. We firstly focus on analyzing how temperature, salinity, and geographic location features affect the formation of thermocline. Then, an improved model based on entropy value method for the thermocline selection is demonstrated. The experiments adopt BOA Argo data sets and the experimental results show that our novel model can predict thermoclines and related data effectively.

A parallel FP-growth algorithm on World Ocean Atlas data with multi-core CPU

Abstract According to the complexity of ocean data, this paper adopts a parallel mining algorithm of association rules to explore the correlation and regularity of oxygen, temperature, phosphate, nitrate and silicate in the ocean. After the marine data is interpolated, this paper utilizes the parallel FP-growth algorithm to mine the data and then briefly analyzes the mining results of the frequent itemsets and association rules. The relationship between the parallel efficiency and the core number of CPU is analyzed through datasets with different scales. The experimental results indicate that the acceleration effect is ideal when each thread scored 200,000–300,000 data, which leads to more than 1.2 times of performance improvement.

A New Method of Arm Motion Detection Based on MEMS Sensor

This paper proposed a new arm motion detection method based on a MEMS sensor. The method gets three-dimensional accelerations and angular velocities of user’s arm motions from a MEMS sensor. Then calculate the correlation coefficients between the data of the current motion cycle and each set of data in the feature database after normalize the data. Thereby, the system can successfully detect 2 specific motions, and the accuracy rate of the detection is 90%.

Construction of High Resolution Thermocline Grid Data Sets

Thermocline has always been the emphasis of marine research. In this paper, we propose a method to construct high resolution marine grid data sets on the basis of MLP. Data used in the article is from World Ocean Atlas 2013. The experiments show that high resolution data can calculate the depth, thickness and strength of thermocline precisely. The method is vital to thermocline gridding.

Thermocline Analysis Based on Entropy Value Methods

Temperature, salinity, and geographic locations are three important factors while determining thermocline. We mainly focus on analyzing how these factors affect the formation of thermocline using machine learning methods. An improvement based on ‘entropy value method’ while choosing thermocline is demonstrated in the paper. The experiments adopt Argo data sets and the experimental results show that machine learning methods can compute thermocline and related data effectively.

Fitness Device Based on MEMS Sensor

Nowadays, motion detection technology is an important field of investigation especially for those researchers whose field is human-computer interaction. Visual algorithms are generally getting complicated when the scale of information is huge. Under most of the situations, calculations need to be done rapidity. Vision sensor may not that appropriate. MEMS provides low dimensional data with stronger adaptability for various occasions. This paper represents a fitness device in which an acceleration sensor can capture users’ movements. Experimental results confirm the feasibility of the fitness devices.

Analysis of Thermocline Influencing Factors Based on Decision Tree Methods

Natural phenomena disturb marine ordinary states mainly by disturb the sea surface temperature. As temperature is the main factor that affects thermocline, in this paper we propose a method to quantitative analyze the correlation between El Nino and thermocline based on decision tree methods rather than qualitative analysis. The experiments use the refined BOA_Argo data and the decision trees are constructed with these data. We aim at making better use of thermocline and trying not to be harmed by natural disasters such as El Nino.

Comparison with Recommendation Algorithm Based on Random Forest Model

Product recommendation based on user behavior is a hot research topic In the Internet era in the same data set, the features that the results of the various classifications are a greater difference were handled with random forest model. This paper compares the mainstream classification algorithm C4.5 and CART and analyzes 578,906,480 user behavior records on the results of actual transaction in Alibaba. The results show that CART decision tree algorithm is more suitable for large e-commerce data mining.