Wyniki wyszukiwania - BazTech

1

Comparative study on the classification methods for breast cancer diagnosis

Qiu Y., Zhou G., Zhao Q., Cichocki A.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2018

|

Vol. 66, nr 6

841--848

EN

Digital mammography is one of the most widely used approaches for breast cancer diagnosis. Many researchers have demonstrated the superiority of machine learning methods in breast cancer diagnosis using different mammography databases. Since these methods often have different pros and cons, which may confuse doctors and researchers, an elaborate comparison and examination among them is urgently needed for practical breast cancer diagnosis. In this study, we conducted a comprehensive comparative study of the state-of-the-art machine learning methods that are promising in breast cancer diagnosis. For this purpose we analyze the largest mammography diagnosis database: Digital Database for Screening Mammography (DDSM). We considered various approaches for feature extraction including principal component analysis (PCA), nonnegative matrix factorization (NMF), spatial-temporal discriminant analysis (STDA) and those for classification including linear discriminant analysis (LDA), random forests (RaF), k-nearest neighbors (kNN), as well as deep learning methods including convolutional neural networks (CNN) and stacked sparse autoencoder (SSAE). This paper can serve as a guideline and useful clues for doctors who are going to select machine learning methods for their breast cancer computer-aided diagnosis (CAD) systems as well for researchers interested in developing more reliable and efficient methods for breast cancer diagnosis.

2

A segment-wise reconstruction method based on bidirectional long short term memory for Power Line Interference suppression

Qiu Y., Huang K., Xiao F., Shen H.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 2

217--227

EN

The overlap between the signal components of Power Line Interference (PLI) and biomedical signals in the frequency domain makes the filtered results prone to severe distortion. Electrocardiogram (ECG) is a type of biomedical electronic signal used for cardiac diagnosis. The objective of this work is to suppress the PLI components from biomedical signals with minimal distortion, and the object of study is mainly the ECG signals. In this study, we propose a novel segment-wise reconstruction method to suppress the PLI in biomedical signals based on the Bidirectional Recurrent Neural Networks with Long Short Term Memory (Bi-LSTM). Experiments are conducted on both synthetic and real signals, and quantitative comparisons are made with a traditional IIR notch filter and two state-of-the-art methods in the literature. The results show that by our method, the output Signal-to-Noise Ratio (SNR) is improved by more than 7 dB and the settling time for step response is reduced to 0.09 s on average. The results also demonstrate that our method has enough generalization ability for unforeseen signals without retraining.

3

Yellowfin tuna (Thunnusalbacares) fishing ground forecasting model based on bayes classifier in the South China Sea

Zhou W., Li A., Ji S., Qiu Y.

Polish Maritime Research

|

2017

|

S 2

140--146

EN

Using the yellowfin tuna (Thunnusalbacares,YFT)longline fishing catch data in the open South China Sea (SCS) provided by WCPFC, the optimum interpolation sea surface temperature (OISST) from CPC/NOAA and multi-satellites altimetric monthly averaged product sea surface height (SSH) released by CNES, eight alternative options based on Bayes classifier were made in this paper according to different strategies on the choice of environment factors and the levels of fishing zones to classify the YFT fishing ground in the open SCS. The classification results were compared with the actual ones for validation and analyzed to know how different plans impact on classification results and precision. The results of validation showed that the precision of the eight options were 71.4%, 75%, 70.8%, 74.4%, 66.7%, 68.5%, 57.7% and 63.7% in sequence, the first to sixth among them above 65% would meet the practical application needs basically. The alternatives which use SST and SSH simultaneously as the environmental factors have higher precision than which only use single SST environmental factor, and the consideration of adding SSH can improve the model precision to a certain extent. The options which use CPUE’s mean ± standard deviation as threshold have higher precision than which use CPUE’s 33.3%-quantile and 66.7%-quantile as the threshold

4

Transport infrastructure development in China

Bouraima M. B., Qiu Y.

Journal of Sustainable Development of Transport and Logistics

|

2017

|

Vol. 2, No. 1

29--39

EN

This paper reviews the historical configuration process of transportation systems in China and examines the relationship between economic development and transport system at three different levels. The current status of transport infrastructure system development in China is summarized at national and regional level. The investment trends for transport infrastructure in China are also depicted. The keys issues relating to government initiatives are presented.

5

Evaluation of physical and mechanical properties of quarry stones in the southern Republic of Benin

Bouraima M. B., Qiu Y.

Journal of Sustainable Development of Transport and Logistics

|

2017

|

Vol. 2, No. 1

61--66

EN

Engineering properties of stones have a crucial importance when they are used for civil engineering works. In this study, the suitability of rocks blocks or stones as a construction material is established. Cove and Dan cities surroundings in the southern part of Zou Province have large blocks and aggregates quarries operated recently. In this study, laboratory tests were carried out to investigate the performance of rocks blocks and aggregates quarried in the region. For this purpose of the study, three wooden containers with rocks blocks and aggregates samples were collected from three different quarries, and so, laboratory tests including particle density and water absorption test, resistance to wear, magnesium sulfate test, compressive strength and methylene blue absorption test were performed in accordance with the international standards to explore the quality of stones to be used for modern construction. Concluding that rocks blocks and aggregates satisfy the relevant regulation (that is, a norm, European standard).

6

Depression effect of corn starch on muscovite mica at different pH values

Peng W., Zhang L., Qiu Y., Song S.

Physicochemical Problems of Mineral Processing

|

2016

|

Vol. 52, iss. 2

780--788

EN

The depression effect of corn starch on the surface of muscovite mica powder at different pulp pH value was investigated. The experiments were performed on single mineral, and its flotation performance was studied by flotation tests, adsorption quantity measurement, zeta-potential technique and Fourier transform infrared (FT-IR). The results indicated that the depression effect was varied with the pulp pH value when dodecylamine chloride (DDA) was used as collector, the strongest inhibitory effect appeared at pH 2 and the zeta-potential of muscovite mica increased overall after conditioned with corn starch solution. It was confirmed by the FT-IR spectra that the corn starch indeed adsorbed on the surface of muscovite mica powder and physical adsorption was occurred between muscovite mica and corn starch. This study leads to a better understanding of the depression effect of corn starch on the surface of muscovite mica powder.

7

Research and Implementation of CATIA Tool Integration Technology Based on CAA

Kong X., Qiu Y., Chang J.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 7b

300--302

EN

In order to implement the integration of the tool libraries from CATIA and the tool database, CATIA software was further developed using CAA. CAA macro-based integration project about the two libraries is proposed, and the development process is presented. In CAA environment provided by CATIA, though further developed using CAA, calling for information, converting information and valuating information of CATIA and TOOLMANAGER were researched. Finally, the dynamic calling, association and driving of CATIA-based tool information were implemented successfully.

PL

W artykule analizuje się możliwości oprogramowania CATIA służącego do projektowania typu CAD/CAE/CAM. W analizie wykorzystano architekturę typu CAA (component application architecture).