Search results for: features reduction.

Authors: Tausif A. Ishtiaque, Zarrin T. Tasin, Kazi S. Akter

Abstract:

Current trend of urban expansion, especially in the developing countries has caused significant changes in land cover, which is generating great concern due to its widespread environmental degradation. Energy consumption of the cities is also increasing with the aggravated heat island effect. Distribution of land surface temperature (LST) is one of the most significant climatic parameters affected by urban land cover change. Recent increasing trend of LST is causing elevated temperature profile of the built up area with less vegetative cover. Gradual change in land cover, especially decrease in vegetative cover is enhancing the Urban Heat Island (UHI) effect in the developing cities around the world. Increase in the amount of urban vegetation cover can be a useful solution for the reduction of UHI intensity. LST and Normalized Difference Vegetation Index (NDVI) have widely been accepted as reliable indicators of UHI and vegetation abundance respectively. Chittagong, the second largest city of Bangladesh, has been a growth center due to rapid urbanization over the last several decades. This study assesses the intensity of UHI in Chittagong city by analyzing the relationship between LST and NDVI based on the type of land use/land cover (LULC) in the study area applying an integrated approach of Geographic Information System (GIS), remote sensing (RS), and regression analysis. Land cover map is prepared through an interactive supervised classification using remotely sensed data from Landsat ETM+ image along with NDVI differencing using ArcGIS. LST and NDVI values are extracted from the same image. The regression analysis between LST and NDVI indicates that within the study area, UHI is directly correlated with LST while negatively correlated with NDVI. It interprets that surface temperature reduces with increase in vegetation cover along with reduction in UHI intensity. Moreover, there are noticeable differences in the relationship between LST and NDVI based on the type of LULC. In other words, depending on the type of land usage, increase in vegetation cover has a varying impact on the UHI intensity. This analysis will contribute to the formulation of sustainable urban land use planning decisions as well as suggesting suitable actions for mitigation of UHI intensity within the study area.

Keywords: Land cover change, land surface temperature, normalized difference vegetation index, urban heat island.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1442

Authors: Porag Jyoti Ligira, Gargi Khanna

Abstract:

The paper presents a simulation study of the electrical characteristic of Bulk Planar Junctionless Transistor (BPJLT) using spacer. The BPJLT is a transistor without any PN junctions in the vertical direction. It is a gate controlled variable resistor. The characteristics of BPJLT are analyzed by varying the oxide material under the gate. It can be shown from the simulation that an ideal subthreshold slope of ~60 mV/decade can be achieved by using highk dielectric. The effects of variation of spacer length and material on the electrical characteristic of BPJLT are also investigated in the paper. The ION / IOFF ratio improvement is of the order of 107 and the OFF current reduction of 10-4 is obtained by using gate dielectric of HfO2 instead of SiO2.

Keywords: BPJLT, double gate, high-k, spacer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1777

Authors: Doo-chul Choi, Yong-Ju Jeon, Jong Pil Yun, Sung Wook Yun, Sang Woo Kim

Abstract:

In this study, we developed an algorithm for detecting seam cracks in a steel plate. Seam cracks are generated in the edge region of a steel plate. We used the Gabor filter and an adaptive double threshold method to detect them. To reduce the number of pseudo defects, features based on the shape of seam cracks were used. To evaluate the performance of the proposed algorithm, we tested 989 images with seam cracks and 9470 defect-free images. Experimental results show that the proposed algorithm is suitable for detecting seam cracks. However, it should be improved to increase the true positive rate.

Keywords: Defect detection, Gabor filter, machine vision, surface inspection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2544

Authors: Hsin-Yi Huang, Ming-Sheng Liu, Jiun-Yan Shiau

Abstract:

Planning the order picking lists for warehouses to achieve some operational performances is a significant challenge when the costs associated with logistics are relatively high, and it is especially important in e-commerce era. Nowadays, many order planning techniques employ supervised machine learning algorithms. However, to define features for supervised machine learning algorithms is not a simple task. Against this background, we consider whether unsupervised algorithms can enhance the planning of order-picking lists. A double zone picking approach, which is based on using clustering algorithms twice, is developed. A simplified example is given to demonstrate the merit of our approach.

Keywords: order picking, warehouse, clustering, unsupervised learning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 498

Authors: S. Ait Ali Yahia

Abstract:

One of the main features of the Maghreb is its linguistic richness. The multilingualism is a fact which always marked the Maghreb since the beginning of the history up to know. Since the arrival of the Phoenicians, followed by the Carthaginians, Romans, and Arabs, etc, there was a social group in the Maghreb which controlled two kinds of idioms. The libyc one remained, despite everything, the local language used by the major part of the population. This language had a support of written transmission attested by many inscriptions. Among all the forms of the Maghreb writing, this alphabet, however, continues to cause a certain number of questions about the origin and the date of its appearance. The archaeological, linguistic and historical data remain insufficient to answer these questions. This did not prevent the researchers from giving an opinion. In order to answer these questions we will expose here the various assumptions adopted by various authors who are founded on more or less explicit arguments. We will also speak about the various forms taken by the libyc writing during antiquity.

Keywords: The alphabet libyc, Eastern libyc, Western libyc.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2626

Authors: Eric Costa, Sara Bragança, Rui Sousa, Anabela Alves

Abstract:

This paper presents an application of the Single-Minute Exchange of Die (SMED) methodology to a turret punching machine in an elevators company, in Portugal. The work was developed during five months, in the ambit of a master thesis in Industrial Engineering and Management. The Lean Production tool SMED was applied to reduce setup times in order to improve the production flexibility of the machine. The main results obtained were a reduction of 64% in setup time (from 15.1 to 5.4min), 50% in work-in-process amount (from 12.8 to 6.4 days) and 99% in the distance traveled by the operator during the internal period (from 136.7 to 1.7m). These improvements correspond to gains of about €7,315.38 per year.

Keywords: Lean production, setup process, SMED.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4077

Authors: Hichem Talbi, Mohamed Batouche, Amer Draa

Abstract:

In this paper we present a new approach to deal with image segmentation. The fact that a single segmentation result do not generally allow a higher level process to take into account all the elements included in the image has motivated the consideration of image segmentation as a multiobjective optimization problem. The proposed algorithm adopts a split/merge strategy that uses the result of the k-means algorithm as input for a quantum evolutionary algorithm to establish a set of non-dominated solutions. The evaluation is made simultaneously according to two distinct features: intra-region homogeneity and inter-region heterogeneity. The experimentation of the new approach on natural images has proved its efficiency and usefulness.

Keywords: Image segmentation, multiobjective optimization, quantum computing, evolutionary algorithms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2346

Authors: Hassan Faraji Baghtash

Abstract:

A high-speed current mirror with low-power method of adjusting current gain is presented. The current mirror provides continuous gain adjustment; yet, its gain can simply be programmed digitally, as well. The structure features the ever interesting merits of linear-in-dB gain control scheme and low power/voltage operation. The performance of proposed structure is verified through the simulation in TSMC 0.18 µm CMOS Technology. The proposed tunable gain current mirror structure draws only 18 µW from 0.9 V power supply and can operate at high frequencies up to 550 MHz in the worst case condition of maximum gain setting.

Keywords: Current mirror, current mode, low power, low voltage, tunable circuit, variable current amplifier.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 818

Authors: Robest Flasza, Milan Rippel, Jan Solc

Abstract:

The main aim of this paper is to develop and calibrate an econometric model for modeling prices of long term electricity futures contracts. The calibration of our model is performed on data from EEX AG allowing us to capture the specific features of German electricity market. The data sample contains several structural breaks which have to be taken into account for modeling. We model the data with an ARIMAX model which reveals high correlation between the price of electricity futures contracts and prices of LT futures contracts of fuels (namely coal, natural gas and crude oil). Besides this, also a share price index of representative electricity companies traded on Xetra, spread between 10Y and 1Y German bonds and exchange rate between EUR and USD appeared to have significant explanatory power over these futures contracts on EEX.

Keywords: electricity futures, EEX, ARIMAX, emissionallowances

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1996

Authors: Ran-Zan Wang, Yao-Ting Lee

Abstract:

This paper proposes a visual cryptography by random grids scheme with identifiable shares. The method encodes an image O in two shares that exhibits the following features: (1) each generated share has the same scale as O, (2) any share singly has noise-like appearance that reveals no secret information on O, (3) the secrets can be revealed by superimposing the two shares, (4) folding a share up can disclose some identification patterns, and (5) both of the secret information and the designated identification patterns are recognized by naked eye without any computation. The property to show up identification patterns on folded shares establishes a simple and friendly interface for users to manage the numerous shares created by VC schemes.

Keywords: Image Encryption, Image Sharing, Secret Sharing, Visual Cryptography.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1753

Authors: Yeskendirov N.R., Karjaubaeva S.K., Ahmet A. K.

Abstract:

A number of theoretical and methodological problems connected with substantiation of a new approach and searches of a new research paradigm and the analysis of features of formation and development of the Kazakh stage are considered in the article. The wide spectrum of questions connected with genesis of the Kazakh stage art has caused necessity of consideration of world outlook and social cultural aspects which have affected formation of the given phenomenon in the Kazakh culture. But how can we define the form of expression and aesthetics of the national theatre? Probably, the answer to this question we will find if we apply to deep world view sources, and, as a consequence, it is necessary to study deeply the plot dramaturgy, which is based on myths, rites and eposes, mastering of symbolic gestures and mimics, allegory of a word, etc.

Keywords: Tradition, theater, art, culture, nomadic Kazakhs.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1498

Authors: Xingsheng Yuan, Zhengzhi Wang

Abstract:

Color constancy algorithms are generally based on the simplified assumption about the spectral distribution or the reflection attributes of the scene surface. However, in reality, these assumptions are too restrictive. The methodology is proposed to extend existing algorithm to applying color constancy locally to image patches rather than globally to the entire images. In this paper, a method based on low-level image features using superpixels is proposed. Superpixel segmentation partition an image into regions that are approximately uniform in size and shape. Instead of using entire pixel set for estimating the illuminant, only superpixels with the most valuable information are used. Based on large scale experiments on real-world scenes, it can be derived that the estimation is more accurate using superpixels than when using the entire image.

Keywords: color constancy, illuminant estimation, superpixel

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1452

Authors: Muhammad R Ahmed, Xu Huang, Dharmendra Sharma

Abstract:

Developments in communication technologies especially in wireless have enabled the progress of low-cost and lowpower wireless sensor networks (WSNs). The features of such WSN are holding minimal energy, weak computational capabilities, wireless communication and an open-medium nature where sensors are deployed. WSN is underpinned by application driven such as military applications, the health sector, etc. Due to the intrinsic nature of the network and application scenario, WSNs are vulnerable to many attacks externally and internally. In this paper we have focused on the types of internal attacks of WSNs based on OSI model and discussed some security requirements, characterizers and challenges of WSNs, by which to contribute to the WSN-s security research.

Keywords: Wireless sensor network, internal attacks, security, OSI model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3012

Authors: N. Todorovic, I. Bikit, J. Nikolov, S. Forkapic, D. Mrdja, S. Todorovic

Abstract:

Interventional cardiologists are at greater risk from radiation exposure as a result of the procedures they undertake than most other medical specialists. A study was performed to evaluate operator dose during interventional cardiology procedures and to establish methods of operator dose reduction with a radiation protective device. Different procedure technique and use of protective tools can explain big difference in the annual equivalent dose received by the professionals. Strategies to prevent and monitor radiation exposure, advanced protective shielding and effective radiation monitoring methods should be applied.

Keywords: absorbed dose rate measurements, annualequivalent dose, protective device.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1523

Authors: Ainul Akmar Mokhtar, Masdi Muhammad, Hilmi Hussin, Mohd Amin Abdul Majid

Abstract:

A reliability, availability and maintainability (RAM) model has been built for acid gas removal plant for system analysis that will play an important role in any process modifications, if required, for achieving its optimum performance. Due to the complexity of the plant, the model was based on a Reliability Block Diagram (RBD) with a Monte Carlo simulation engine. The model has been validated against actual plant data as well as local expert opinions, resulting in an acceptable simulation model. The results from the model showed that the operation and maintenance can be further improved, resulting in reduction of the annual production loss.

Keywords: Acid gas removal plant, RAM model, Reliabilityblock diagram

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2324

Authors: Nebi Gedik

Abstract:

Regardless of age or gender, cardiovascular illnesses are a serious health concern because of things like poor eating habits, stress, a sedentary lifestyle, hard work schedules, alcohol use, and weight. It tends to happen suddenly and has a high rate of recurrence. Machine learning models can be implemented to assist healthcare systems in the accurate detection and diagnosis of cardiovascular disease (CVD) in patients. Improved heart failure prediction is one of the primary goals of researchers using the heart disease dataset. The purpose of this study is to identify the feature or features that offer the best classification prediction for CVD detection. The support vector machine classifier is used to compare each feature's performance. It has been determined which feature produces the best results.

Keywords: Cardiovascular disease, feature extraction, supervised learning, support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 134

Authors: M.A.A. Younis, N. A. Rahim, S. Mekhilef

Abstract:

This paper presents the design and analysis of a parallel connected inverter configuration of. The configuration consists of parallel connected three-phase dc/ac inverter. Series resistors added to the inverter output to maintain same current in each inverter of the two parallel inverters, and to reduce the circulating current in the parallel inverters to the minimum. High frequency third harmonic injection PWM (THIPWM) employed to reduce the total harmonic distortion and to make maximum use of the voltage source. DSP was used to generate the THIPWM and the control algorithm for the converter. Selected experimental results have been shown to validate the proposed system.

Keywords: Three-phase inverter, Third harmonic injection PWM, inverters parallel connection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3764

Authors: Jagdeep Kaur, Parvinder S. Sandhu, Birinderjit Singh, Amit Verma, Sanyam Anand

Abstract:

In today-s hip hop world where everyone is running short of time and works hap hazardly,the similar scene is common on the roads while in traffic.To do away with the fatal consequences of such speedy traffics on rushy lanes, a software to analyse and keep account of the traffic and subsequent conjestion is being used in the developed countries. This software has being implemented and used with the help of a suppprt tool called Critical Analysis Reporting Environment.There has been two existing versions of this tool.The current research paper involves examining the issues and probles while using these two practically. Further a hybrid architecture is proposed for the same that retains the quality and performance of both and is better in terms of coupling of components , maintainence and many other features.

Keywords: Critical Analysis Reporting Environment, coupling, hybrid architecture etc.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1518

Authors: Bahareh Gholamzadeh, Hooman Nabovati

Abstract:

Fiber optic sensor technology offers the possibility of sensing different parameters like strain, temperature, pressure in harsh environment and remote locations. these kinds of sensors modulates some features of the light wave in an optical fiber such an intensity and phase or use optical fiber as a medium for transmitting the measurement information. The advantages of fiber optic sensors in contrast to conventional electrical ones make them popular in different applications and now a day they consider as a key component in improving industrial processes, quality control systems, medical diagnostics, and preventing and controlling general process abnormalities. This paper is an introduction to fiber optic sensor technology and some of the applications that make this branch of optic technology, which is still in its early infancy, an interesting field.

Keywords: Fiber optic sensors, distributed sensors, sensorapplication, crack sensor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6496

Authors: Jingyu Hou

Abstract:

This paper proposes a new teaching and learning approach-project and module based teaching and learning (PMBTL). The PMBTL approach incorporates the merits of project/problem based and module based learning methods, and overcomes the limitations of these methods. The correlation between teaching, learning, practice and assessment is emphasized in this approach, and new methods have been proposed accordingly. The distinct features of these new methods differentiate the PMBTL approach from conventional teaching approaches. Evaluation of this approach on practical teaching and learning activities demonstrates the effectiveness and stability of the approach in improving the performance and quality of teaching and learning. The approach proposed in this paper is also intuitive to the design of other teaching units. 

Keywords: Computer science education, project and module based, software engineering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3436

Authors: Chanchai Supaartagorn

Abstract:

E-retailing is the sale of goods online that takes place over the Internet. The Internet has shrunk the entire World. World eretailing is growing at an exponential rate in the Americas, Europe and Asia. However, e-retailing costs require expensive investment, such as hardware, software, and security systems. Cloud computing technology is internet-based computing for the management and delivery of applications and services. Cloud-based e-retailing application models allow enterprises to lower their costs with their effective implementation of e-retailing activities. In this paper, we describe the concept of cloud computing and present the architecture of cloud computing, combining the features of e-retailing. In addition, we propose a strategy for implementing cloud computing with e-retailing. Finally, we explain the benefits from the architecture.

Keywords: Architecture, cloud computing, e-retailing, internet-based.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3153

Authors: Morteza Moazami-Goudarzi, Mohammad H. Moradi, Ali Taheri

Abstract:

In this paper we introduce an effective ECG compression algorithm based on two dimensional multiwavelet transform. Multiwavelets offer simultaneous orthogonality, symmetry and short support, which is not possible with scalar two-channel wavelet systems. These features are known to be important in signal processing. Thus multiwavelet offers the possibility of superior performance for image processing applications. The SPIHT algorithm has achieved notable success in still image coding. We suggested applying SPIHT algorithm to 2-D multiwavelet transform of2-D arranged ECG signals. Experiments on selected records of ECG from MIT-BIH arrhythmia database revealed that the proposed algorithm is significantly more efficient in comparison with previously proposed ECG compression schemes.

Keywords: ECG signal compression, multi-rateprocessing, 2-D Multiwavelet, Prefiltering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2022

Authors: Nelly К. Akhmatova, Оlga V. Lebedinskaya, Stanislav G. Markushin, Elvin А. Akhmatov, Lidiya A. Geiderova, Еlena А. Lebedinskaya, Vera M. Axenova, Аnatoliy P. Godovalov

Abstract:

The study of cytokine expression in mice under the influence of inactivated poliovirus and Imovaks polio vaccine in combination with derivatives of chitosan shows various kinds of processes. There is a significant increase in IL-12 in the serum of immunized animals, which should stimulate the production of IFN-γ NK-cells and T-cells and polarize the immune response to Th1 type. Thus, the derivatives of chitosan can promote cell component of the immune response, providing a full antiviral immunity.

Keywords: Poliovirus, chitosan, cytokine expression, antiviral immunity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1970

Authors: Akihiro Iijima, Kimiyo Kumagai

Abstract:

A long-term campaign for monitoring the concentration of atmospheric Particulate Matter (PM) was conducted at multiple sites located in the center and suburbs of the Tokyo Metropolitan Area in Japan. The concentration of fine PM has shown a declining trend over the last two decades. A positive matrix factorization model elucidated that the contribution of combustion sources was drastically reduced. In Japan, the regulations on vehicle exhaust emissions were phased in and gradually tightened over the last two decades, which has triggered a notable reduction in PM emissions from automobiles and has contributed to the mitigation of the problem of fine PM pollution.

Keywords: Air pollution, Diesel-powered vehicle, Positive matrix factorization, Receptor modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1754

Authors: Michal Duchek, Jan Palán, Tomas Kubina

Abstract:

Bars made of titanium grade 2 and grade 4 were subjected to rotary forging with up to 2.2 true strain reduction in the cross-section from 10 to 3.81 mm. During progressive deformation, grain refinement in the transverse direction took place. In the longitudinal direction, ultrafine microstructure has not developed. It has been demonstrated that titanium grade 2 strengthens more than grade 4. The ultimate tensile strength increased from 650 MPa to 1040 MPa in titanium grade 4. Hardness profiles on the cross section in both materials show an increase in the centre of the wire.

Keywords: Commercial-purity titanium, wire, rotary swaging, tensile test, hardness, modulus of elasticity, microstructure.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 726

Authors: Al-Amin Bhuiyan, Chang Hong Liu

Abstract:

Gabor-based face representation has achieved enormous success in face recognition. This paper addresses a novel algorithm for face recognition using neural networks trained by Gabor features. The system is commenced on convolving a face image with a series of Gabor filter coefficients at different scales and orientations. Two novel contributions of this paper are: scaling of rms contrast and introduction of fuzzily skewed filter. The neural network employed for face recognition is based on the multilayer perceptron (MLP) architecture with backpropagation algorithm and incorporates the convolution filter response of Gabor jet. The effectiveness of the algorithm has been justified over a face database with images captured at different illumination conditions.

Keywords: Fuzzily skewed filter, Gabor filter, rms contrast, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3083

Authors: A.T.Z. Mahamat, A.M. A Rani, Patthi Husain

Abstract:

Copper based composites reinforced with WC and Ti particles were prepared using planetary ball-mill. The experiment was designed by using Taguchi technique and milling was carried out in an air for several hours. The powder was characterized before and after milling using the SEM, TEM and X-ray for microstructure and for possible new phases. Microstructures show that milled particles size and reduction in particle size depend on many parameters. The distance d between planes of atoms estimated from X-ray powder diffraction data and TEM image. X-ray diffraction patterns of the milled powder did not show clearly any new peak or energy shift, but the TEM images show a significant change in crystalline structure of corporate on titanium in the composites.

Keywords: ball milling, microstructures, titanium, tungstencarbides, X-ray

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1589

Authors: Sangjun Park, Jungpyo Hong, Byung-Ok Kang, Yun-keun Lee, Minsoo Hahn

Abstract:

In this paper, an algorithm for detecting and attenuating puff noises frequently generated under the mobile environment is proposed. As a baseline system, puff detection system is designed based on Gaussian Mixture Model (GMM), and 39th Mel Frequency Cepstral Coefficient (MFCC) is extracted as feature parameters. To improve the detection performance, effective acoustic features for puff detection are proposed. In addition, detected puff intervals are attenuated by high-pass filtering. The speech recognition rate was measured for evaluation and confusion matrix and ROC curve are used to confirm the validity of the proposed system.

Keywords: Gaussian mixture model, puff detection and cancellation, speech enhancement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2223

Authors: Jian-hua Yeh, Shi-yi Kuo

Abstract:

This paper discusses the classification process for medical data. In this paper, we use the data from ACM KDDCup 2008 to demonstrate our classification process based on latent topic discovery. In this data set, the target set and outliers are quite different in their nature: target set is only 0.6% size in total, while the outliers consist of 99.4% of the data set. We use this data set as an example to show how we dealt with this extremely biased data set with latent topic discovery and noise reduction techniques. Our experiment faces two major challenge: (1) extremely distributed outliers, and (2) positive samples are far smaller than negative ones. We try to propose a suitable process flow to deal with these issues and get a best AUC result of 0.98.

Keywords: classification, latent topics, outlier adjustment, feature scaling

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1632

Authors: Agnieszka Danek, Rafał Pokrzywa

Abstract:

Approximate tandem repeats in a genomic sequence are two or more contiguous, similar copies of a pattern of nucleotides. They are used in DNA mapping, studying molecular evolution mechanisms, forensic analysis and research in diagnosis of inherited diseases. All their functions are still investigated and not well defined, but increasing biological databases together with tools for identification of these repeats may lead to discovery of their specific role or correlation with particular features. This paper presents a new approach for finding approximate tandem repeats in a given sequence, where the similarity between consecutive repeats is measured using the Hamming distance. It is an enhancement of a method for finding exact tandem repeats in DNA sequences based on the Burrows- Wheeler transform.

Keywords: approximate tandem repeats, Burrows-Wheeler transform, Hamming distance, suffix array

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1526