One of the interesting and important subjects among researchers in the field of medical and computer science is diagnosing illness by considering the features that have the most impact on recognitions. The subject discusses a new concept which is called Medical Data Mining (MDM). Indeed, data mining methods use different ways such as classification and clustering to classify diseases and their symptoms which are helpful for diagnosing. This paper introduces a new method of liver disease diagnosis to help doctors and their patients in finding the disease symptoms and reduce a long time of diagnosing and prevent deaths. The proposed method will optimize the rules released from Boosted C5.0 classification method with the Genetic Algorithm (GA), to increase the diagnosis time and accuracy. So instead of using an evolutionary algorithm for producing rules, the genetic algorithm is used for improving and reducing rules of another algorithm. We show that our proposed approach has better performance and throughput in comparison with other work in the field. The accuracy is improved from 81% in [1] to 93% in our work.

Rule Optimization of Boosted C5.0 Classification Using Genetic Algorithm for Liver disease Prediction

A method and loop qualification unit for determining loop parameters of a topology of a twisted pair loop for a digital subscriber line system. The parameters are represented by a vector that receives a measurement of a SELT parameter measured at one end of the loop and a measurement of a DELT loop transfer function measured at both ends of the loop. A first model generator generates a first model for the SELT parameter and a second model generator generates a second model for the DELT function based on the loop parameters represented by the vector. A processor then determines the parameters by minimizing the differences between the first model and the SELT parameter, and the second model and the DELT function. The determined parameters are represented by the vector that provides the minimization.

Method and arrangement for loop qualification in a digital subscriber line (dsl) system

The copper access-network operators face the challenge of developing and maintaining cost-effective digital subscriber line (DSL) services that are competitive to other broadband access technologies. The way forward is dictated by the demand of ever increasing data rates on the twisted-pair copper lines. To meet this demand, a relocation of the DSL transceivers in cabinets closer to the customers are often necessary combined with a joint expansion of the accompanying optical-fiber backhaul network. The equipment of the next generation copper network are therefore becoming more scattered and geographically distributed, which increases the requirements of automated line qualification with fault detection and localization. This scenario is addressed in the first five papers of this dissertation where the focus is on estimation and detection of transmission line characteristics in the copper access network. The developed methods apply model-based optimization with an emphasis on using low-order modeling and a priori information of the given problem. More specifically, in Paper I a low-order and causal cable model is derived based on the Hilbert transform. This model is successfully applied in three contributions of this dissertation. In Paper II, a class of low-complexity unbiased estimators for the frequency-dependent characteristic impedance is presented that uses one-port measurements only. The so obtained characteristic impedance paves the way for enhanced time domain reflectometry (a.k.a. TDR) on twisted-pair lines. In Paper III, the problem of estimating a nonhomogeneous and dispersive transmission line is investigated and a space-frequency optimization approach is developed for the DSL application. The accompanying analysis shows which parameters are of interest to estimate and further suggests the introduction of the concept capacitive length that overcomes the necessity of a priori knowledge of the physical line length. In Paper IV, two methods are developed for detection and localization of load coils present in so-called loaded lines. In Paper V, line topology identification is addressed with varying degree of a priori information. In doing so, a model-based optimization approach is employed that utilizes multi-objective evolutionary computation based on one/two-port measurements. A complement to transceiver relocation that potentially enhances the total data throughput in the copper access network is dynamic spectrum management (DSM). This promising multi-user transmission technique aims at maximizing the transmission rates, and/or minimizing the power consumption, by mitigating or cancelling the dominating crosstalk interference between twisted-pair lines in the same cable binder. Hence the spectral utilization is improved by optimizing the transmit signals in order to minimize the crosstalk interference. However, such techniques rely on accurate information of the (usually) unknown crosstalk channels. This issue is the main focus of Paper VI and VII of this dissertation in which Paper VI deals with estimation of the crosstalk channels between twisted-pair lines. More specifically, an unbiased estimator for the square-magnitude of the crosstalk channels is derived from which a practical procedure is developed that can be implemented with standardized DSL modems already installed in the copper access network. In Paper VII the impact such a non-ideal estimator has on the performance of DSM is analyzed and simulated. Finally, in Paper VIII a novel echo cancellation algorithm for DMT-based DSL modems is presented. (Less)

/pdf/estimation-and-detection-of-transmission-line-mz6tbt8m3o.pdf

Estimation and detection of transmission line characteristics in the copper access network

With the development of PLC technology (Power Line Communication), which allows data transmission at high speed by the power grid. Emerged as a technology solution for last mile for transmission triple play. This article presents the analysis of VoIP and streaming videos in high definition through a residential indoor PLC network.

Analysis and Performance of Traffic of Voice and Video in Network Indoor PLC

The present invention refers to a method and device for detecting a bridged tap within a telecommunication line. In order to reliably detect bridged taps of different types, in particular wire pair bridged taps and single wire bridged taps, and/or to determine a type of each detected bridged tap the method includes determining first transfer function data that characterize an actual transfer function of the telecommunication line; detecting the bridged tap depending on the first transfer function data; simulating the telecommunication line based on a result of the detecting; and identifying the type of the bridged tap by comparing results of the simulating with the first transfer function data.

Method and device for detecting a bridged tap within a telecommunication line

This paper presents methodologies that could be used for characterizing subscriber telephone loops that carry DSL services (ADSL and ADSL2+), by determination and analysis of frequency response, time domain reflectometry, and impulse response of the line. From this analysis, the subscriber loop length, identification and location of impairments such as bridged taps, gauge changes, and open ended termination across the line are carried out. To verify the methodologies presented, results obtained from measurements are drawn and compared to results obtained from computational simulations.

/pdf/characterization-of-subscriber-local-loop-by-measures-and-1frdg98zv7.pdf

Characterization of subscriber local loop by measures and analysis of frequency and impulse responses

This work presents results for multimedia transmission using wireless broadband networks installed in some remote cities in Amazon region. In 15 cities at State of Para, Brazil, the local government is installing wireless networks to provide wideband internet access to public agents, such as schools, hospitals, police stations and office buildings in a great project named NavegaPara. Each city has a base station working on 5.7 GHz and serving around 30 subscribers, which use an individual broadband transceiver (IBT) to access the network. The aggregate throughput (downstream + upstream) for each client is 7 Mbps, 14 Mbps or 30 Mbps depending on the installed equipment and the distance between the base station and the client unit. It is presented a typical scenario for multimedia transmission using the available infrastructure. In this case, an IBT is connected directly to a computer, which is connected to a video camera transmitting video traffic. The available infrastructure is useful for broadcasting the public television signal (Funtelpa) in uncovered areas of State of Para. Metrics such as throughput and latency are collected and analyzed. Obtained results show that multimedia transmission using NavegaPara infrastructure has satisfactory results.

Multimedia transmission on Amazon region using wireless broadband networks

Broadband services require data rates that can only be achieved by using relatively high spectrum frequencies. At such high frequencies, the DSL (Digital Subscriber Line) signal is more susceptible to external noise sources, such as radio frequency interference and impulsive noise. This paper aims to characterize how the impulsive noise impacts on services and applications for a broadband system using an ADSL2+ loop. The first approach was to use the impulsive noise defined in the standards G.996.1 (Test Procedures for DSL Transceivers) from ITU-T and TR-048 (ADSL Interoperability Test Plan) from DSL Forum. In this approach we have also used a HDSL (High Bit Rate DSL) and white noise disturbers on the line. The impulsive noises c1 and c2 (defined in G.996.1) are injected into the circuit at the CO (Central Office) end and CPE (Customer Premises Equipment) end of the loop simulator. Additionally, it was analyzed the spikes of noise's impact on the ADSL2+ line. In this case, pre-defined models of NEXT (Near-end crosstalk) and white noise are injected on CO and CPE side, simultaneously. Metrics like packet rate, lost packet count, bandwidth, short-term average transfer delay, and errored seconds are used to characterize the DSL loop under the noise impairments. (Less)

/pdf/impact-of-non-stationary-noise-on-xdsl-systems-an-2rq61v4u48.pdf

Impact of non-stationary noise on xDSL systems: an experimental analysis

This paper proposes a new methodology to diagnose the rheumatology manifestations and HTLV-I-Associated Myelopathy/Tropical Spastic Paraparesis, or HAM/TSP, in patients who have Lymphotropic virus of T cells in Humans or HTLV of type I and II. Computational intelligence algorithms are used to classify HTLV patient carriers with or without the presence of rheumatology manifestations and of HAM / TSP. A benchmarking is performed among artificial neural intelligence, naive bayes, Bayesian networks and decision tree to evaluate the most suitable technique for solving this application issue. The obtained results demonstrate the potential of the methodology on the helping non-specialist doctors to classify the patient with the disease suspicion.

/pdf/data-mining-applied-to-diagnose-diseases-caused-by-3bbyjfxsh8.pdf

Data Mining Applied to Diagnose Diseases Caused by Lymphotropic Virus: a Performance Analysis

The increasing trend of triple play traffic transmission (voice, video and data) over internet is a worldwide phenomenon. However, to get a satisfactory communication, we need study the process on end-the-end way. Into regions with little infrastructure of telecommunications, one of the concerns is about used technologies of access. This work presents an analysis based on an IPTV (Television Internet Protocol) transmission generated on two combined technologies of access, PLC (PowerLine Communications) and ADSL2+ (Asymmetric Digital Subscriber Line), using a combination of electric network and telephony infrastructure, called of pDSL. This technology is a viable combination for regions with poor infrastructure of telecommunications. The results are evaluated with intention to present the viability of this kind of the telecommunication environment and with a simulation for extrapolation study.

http://www.lea.ufpa.br/producaocientifica/seminarios/2007/Performance%20evaluation%20of%20IPTV%20traffic%20over%20pDSL.pdf

Lamartine V. de Souza

Papers

Characterization of subscriber local loop by measures and analysis of frequency and impulse responses

Multimedia transmission on Amazon region using wireless broadband networks

Impact of non-stationary noise on xDSL systems: an experimental analysis

Data Mining Applied to Diagnose Diseases Caused by Lymphotropic Virus: a Performance Analysis

Performance evaluation of IPTV traffic over pDSL