AdaBoost for Improved Voice-Band Signal Classification

A good voice-band signal classification can not only enable the safe application of speech ceding techniques, the implementation of a Digital Signal Interpolation （DSI） system, but also facilitate network administration and planning by providing accurate voice-band traffic analysis. A new method is proposed to detect and classify the presence of various voice-band signals on the General Switched Telephone Network （GSTN）. The method uses a combination of simple base classifiers through the AdaBoost algorithm. The conventional classification features for voice- band data classification are combined and optimized by the AdaBoost algorithm and spectral subtraction method. Experiments show the simpleness, effectiveness, efficiency and flexibility of the method.     

Surface Inspection System for Cold Rolled Strips Based on Image Processing Technique

A new surface inspection system for cold rolled strips based on image processing is introduced. The system is equipped with two different illumination structures and CCD matrix cameras. The structure and image processing of the inspection system are described. Some efficient algorithms for image processing and classification are presented. The system is tested with strip samples from cold rolling plants. The results show that the system can detect and recognize six common defects of cold rolled strips successfully.     

A fast SVM training algorithm based on the set segmentation and k-means clustering

At present, studies on training algorithms for support vector machines (SVM) are important issues in the field of machine learning. It is a challenging task to improve the efficiency of the algorithm without reducing the generalization performance of SVM. To face this challenge, a new SVM training algorithm based on the set segmentation and k-means clustering is presented in this paper. The new idea is to divide all the original training data into many subsets, followed by clustering each subset using k-means clustering and finally train SVM using the new data set obtained from clustering centroids. Considering that the decomposition algorithm such as SVMlight is one of the major methods for solving support vector machines, the SVMlight is used in our experiments. Simulations on different types of problems show that the proposed method can solve efficiently not only large linear classification problems but also large nonlinear ones.     

The stress response factor RpoS is required for the natural transformation of Escherichia coli

The natural transformation of Escherichia coli is a novel and recently developed system that has signifi- cance for genetic studies and the biological safety of genetic engineering. However, the mechanisms of transformation, including development of competence and DNA uptake, are not thoroughly understood. In this study, we demonstrated the effect of the general stress response regulator RpoS, which has been associated with E. coli transformation, on natural transformation performed in an ＂open system＂. We find that RpoS is required for natural transformation but not to artificial transformation and RpoS mainly affect trans- formation in the liquid culture prior to plating. In the liquid culture, RpoS over-expression promotes natural transfor- mation in early exponential phase and static incubation accumulates RpoS and promotes transformation to a limited extent. These findings provide detailed understanding of RpoS function on natural transformation.     

A new theorem to synchronization of unified chaotic systems via adaptive control

Chaos synchronization has been applied in secure communication, chemical reaction, biological systems, and information processing. A new theorem to synchronization of unified chaotic systems via adaptive control is proposed. The consutructive theorem provides the design scheme for adaptive controller such that a respond system can synchronize with respect to an uncertain drive system. One example for discontinuous chaotic system is proposed to illustrate the effectiveness and feasibility.     

Randomness in the Hybrid Modeling and Simulation of Insulin Secretion Pathways in Pancreatic Islets

Insulin secreted by pancreatic islet ˇ-cells is the principal regulating hormone of glucose metabolism.Disruption of insulin secretion may cause glucose to accumulate in the blood, and result in diabetes mellitus.Although deterministic models of the insulin secretion pathway have been developed, the stochastic aspect of this biological pathway has not been explored. The first step in this direction presented here is a hybrid model of the insulin secretion pathway, in which the delayed rectifying KCchannels are treated as stochastic events. This hybrid model can not only reproduce the oscillation dynamics as the deterministic model does, but can also capture stochastic dynamics that the deterministic model does not. To measure the insulin oscillation system behavior, a probability-based measure is proposed and applied to test the effectiveness of a new remedy.     

Recombinant sTRAIL induces cell death of tumor cell lines as well as primary cancer cells

Tumor necrosis factor (TNF)-related apoptosis-inducing ligand (TRAIL) is a new member of TNF family. It was reported that TRAIL could induce apoptosis of tumor cells but not normal cells in tissue culture system. To further study the biological activity and potential clinical significance, a recombinant soluble TRAIL (rsTRAIL) has been expressed stably in E. coli after transformation of pET28b vector containing the extracellular domain of TRAIL. The yield of rsTRAIL is approximately as high as 60% of whole bacterial proteins. The rsTRAIL, purified by Ni+ -agarose affinity chromatography, could remarkably trigger apoptosis at the concentrations of 0.1-1 μg/mL in all 7 tumor cell lines tested in vitro. However, this killing activity has not been observed in mouse fibroblast cell line (NIH3T3) as normal control. Further investigation shows that the rsTRAIL could also kill primary tumor cells isolated freshly from patients with cardiac cancer, breast cancer and malignant thymoma, while the normal human peripheral blood lymphocytes are not killed under the same conditions. These results provide new evidence that rsTRAIL could induce apoptosis of tumor cells specifically and it could be a new promising medicine for tumor therapy.     

Assessment of rice fields by GIS／GPS-supported classification of MODIS data

The new Moderate-Resolution Imaging Spectroradiometer (MODIS) satellite image offers a large choice of opportunities for operational applications. The 1-km Advanced Very High Resolution Radiometer (AVHRR) image is not suitable for retrieval of field level parameter and Landsat data are not frequent enough for monitoring changes in crop parameters during the critical crop growth periods.A methodology to map areas of paddy fields using MODIS,geographic information system (GIS) and global position system (GPS) is introduced in this paper. Training samples are selected and located with the help of GPS to provide maximal accuracy.A concept of assessing areas of potential cultivation of rice is suggested by means of GIS integration. By integration of MODIS with GIS and GPS technologies the actual areas of rice fields in 2002 have been mapped. The classification accuracy was 95.7% percent compared with the statistical data of the Agricultural Bureau of Zhejiang Province.     

A feature ensemble technology to identify molecular mechanisms for distinction between multiple subtypes of lymphoma

Due to complexities and genetic heterogeneities of biological phenotypes, robust computational approaches are desirable to achieve high generalization performance with multiple classifiers, perturbations of the data structures, and biological interpretations. The purpose of this study is to extend our developed ensemble decision approach to distinguish multiple heterogeneous phenotypes and to elucidate the underlying molecular bridges that intertwine the subtypes. Our work identifies the significant molecular mechanisms （disease-relevant genes and functions） that underpin the complex molecular mechanisms for distinction between multiple phenotypes. Feature genes and hierarchical gene cores identified by our method have achieved high accuracy in the classification of multiple phenotypes. The results show that the proposed analysis strategy is feasible and powerful in the classification of biological subtypes and in the explanation of the molecular connections between clinical phenotypes. Biological interpretations with Gene Ontology revealed concerted genetic pathways for some lymphoma subtypes.     

Identifying Lysine Succinylation Sites in Proteins by Broad Learning System and Optimizing Imbalanced Training Dataset via Randomly Labeling Samples

As one important type of post-translational modifications(PTMs), protein lysine succinylation regulates many important biological processes. It is also closely involved with some major diseases in the aspects of Cardiometabolic, liver metabolic, nervous system and so on. Therefore, it is imperative to predict the succinylation sites in proteins for both basic research and drug development. In this paper, a novel predictor called i Succ Lys-BLS was proposed by not only introducing a new machine learning algorithm—Broad Learning System, but also optimizing the imbalanced data by randomly labeling samples. Rigorous cross-validation and independent test indicate that the success rate of i Succ Lys-BLS for positive samples is overwhelmingly higher than its counterparts.     

Classification of Medical Brain Images

Since brain tumors endanger people‘s living quality and even their lives, the accuracy of classification becomes more important. Conventional classifying techniques are used to deal with thosedatasets with characters and numbers. It is difficult, however, to apply them to datasets that include brain images and medical history (alphanumeric data), especially to guarantee the accuracy.For these datasets, this paper combines the knowledge of medical field and improves the traditional decision tree. The new classification algorithm with the direction of the medical knowledge not only adds the interaction with the doctors, but also enhances the quality of classification. The algorithm has been used on real brain CT images and a precious rule has been gained from the experiments. This oaoer shows that the ahzorithm works well for real CT data.     

Inspection of pipeline girth welds with ultrasonic phased array technique

A novel automatic ultrasonic system used for the inspection of pipeline girth welds is developed, in which a linear phased array transducer using electronic scan is adopted. Optimal array parameters are determined based on a mathematical model of acoustic field for linear phased army derived from Huygens＇ principle. The testing method and the system structure are introduced. The experimental results show that the phased array transducer system has the same detectability as that of conventional ultrasonic transducer system, but the system architecture can be simplified greatly, and the testing flexibility and the testing speed can be improved greatly.     

Reduction zero-knowledge

The nature of zero-knowledge is re-examined and the evidence for the following belief is shown:the classic simulation based definitions of zero-knowledge(simulation zero-knowledge)may be somewhat too strong to include some "nice" protocols in which the malicious verifier seems to learn nothing but we do not know how to construct a zero-knowledge simulator for it.To overcome this problem a new relaxation of zero-knowledge,reduction zero-knowledge,is introduced.It is shown that reduction zero-knowledge just lies between simulation zero-knowledge and witness indistinguishability.Under the assumption of existence of one-way permutations a 4-round public-coin reduction zero-knowledge proof system for NP is presented and in practice this protocol works in 3 rounds since the first verifier's message can be fixed once and for all.     

A thermodynamic hypothesis regarding optimality principles for flow processes in geosystems

This paper proposes a new thermodynamic hypothesis that states that a nonlinear natural system that is not isolated and involves positive feedbacks tends to minimize its resistance to the flow process through it that is imposed by its environment. We demonstrate that the hypothesis is consistent with flow behavior in saturated and unsaturated porous media, river basins, and the Earth-atmosphere system. While optimization for flow processes has been previously discussed by a number of researchers in the literature, the unique contribution of this work is to indicate that only the driving process is subject to opti-mality when multiple flow processes are simultaneously involved in a system.     

Research on transferable off-line electronic cash system

In this paper, a new cash scheme is proposed for electronic payment system, in which the cash can be transferred several times. When this kind of cash is used, the fraud such as double spending can be found out but the bank and the trusted party needs not be involved online in each transaction. This cash system is anonymous in normal transactions. But if a fraud happens, the trusted party can withdraw the anonymity to find out the cheater. The new cash scheme is transferable, anonymous, off-line and efficient.     

Techniques of Image Processing Based on Artificial Neural Networks

This paper presented an online quality inspection system based on artificial neural networks. Chromatism classification and edge detection are two difficult problems in glass steel surface quality inspection. Two artificial neural networks were made and the two problems were solved. The one solved chromatism classification. Hue, saturation and their probability of three colors, whose appearing probabilities were maximum in color histogram, were selected as input parameters, and the number of output node could be adjusted with the change of requirement. The other solved edge detection. In this neutral network, edge detection of gray scale image was able to be tested with trained neural networks for a binary image. It prevent the difficulty that the number of needed training samples was too large if gray scale images were directly regarded as training samples. This system is able to be applied to not only glass steel fault inspection but also other product online quality inspection and classification.     

一种新的考虑启动压力梯度产能方程的建立

The flowing mechanism of a low permeability gas reservoir is different from a conventional gas reservoir,especially for that with higher irreducible water saturation the threshold pressure gradient exists. At present,in all the deliverability equation,the additional pressure drop caused by the threshold pressure gradient is viewed as constant,but this method has big error in the practical application. Based on the non-Darcy steady flow equation,the limited integral of the additional pressure drop is solved in this paper and it is realized that the additional pressure drop is not a constant but has something to do with production data,and a new deliverability equation is derived,with the relevant processing method for modified isochronal test data. The new deliverability equation turns out to be practical through onsite application.     

Decoupling Control of Lateral Dynamics for 4WS Vehicle

An four wheel steering (4WS) feedback control system that simultaneously achieves both body sideslip angle and yaw rate responses always desirable regardless of changes in vehicle dynamics. Quantitative feedback theory (QFT) is offered as the main tool for designing the control law. Inverted decoupling is also employed to make multivariable quantitative feedback design easier. Various nonlinear analyses are carried out and show that the proposed control system is a robust decoupling controller which not only makes body sideslip angle and yaw rate of the vehicle track the desired reference input signals respectively, but also satisfies the requirement of robustness for the control system. The results also indicate that the control system can make it available to realize ideal lateral steering dynamics tracking for vehicles.