Search results for: Bayesian hierarchical models
1919 Structural Parsing of Natural Language Text in Tamil Using Phrase Structure Hybrid Language Model
Authors: Selvam M, Natarajan. A M, Thangarajan R
Abstract:
Parsing is important in Linguistics and Natural Language Processing to understand the syntax and semantics of a natural language grammar. Parsing natural language text is challenging because of the problems like ambiguity and inefficiency. Also the interpretation of natural language text depends on context based techniques. A probabilistic component is essential to resolve ambiguity in both syntax and semantics thereby increasing accuracy and efficiency of the parser. Tamil language has some inherent features which are more challenging. In order to obtain the solutions, lexicalized and statistical approach is to be applied in the parsing with the aid of a language model. Statistical models mainly focus on semantics of the language which are suitable for large vocabulary tasks where as structural methods focus on syntax which models small vocabulary tasks. A statistical language model based on Trigram for Tamil language with medium vocabulary of 5000 words has been built. Though statistical parsing gives better performance through tri-gram probabilities and large vocabulary size, it has some disadvantages like focus on semantics rather than syntax, lack of support in free ordering of words and long term relationship. To overcome the disadvantages a structural component is to be incorporated in statistical language models which leads to the implementation of hybrid language models. This paper has attempted to build phrase structured hybrid language model which resolves above mentioned disadvantages. In the development of hybrid language model, new part of speech tag set for Tamil language has been developed with more than 500 tags which have the wider coverage. A phrase structured Treebank has been developed with 326 Tamil sentences which covers more than 5000 words. A hybrid language model has been trained with the phrase structured Treebank using immediate head parsing technique. Lexicalized and statistical parser which employs this hybrid language model and immediate head parsing technique gives better results than pure grammar and trigram based model.Keywords: Hybrid Language Model, Immediate Head Parsing, Lexicalized and Statistical Parsing, Natural Language Processing, Parts of Speech, Probabilistic Context Free Grammar, Tamil Language, Tree Bank.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 36311918 An Energy-Efficient Protocol with Static Clustering for Wireless Sensor Networks
Authors: Amir Sepasi Zahmati, Bahman Abolhassani, Ali Asghar Beheshti Shirazi, Ali Shojaee Bakhtiari
Abstract:
A wireless sensor network with a large number of tiny sensor nodes can be used as an effective tool for gathering data in various situations. One of the major issues in wireless sensor networks is developing an energy-efficient routing protocol which has a significant impact on the overall lifetime of the sensor network. In this paper, we propose a novel hierarchical with static clustering routing protocol called Energy-Efficient Protocol with Static Clustering (EEPSC). EEPSC, partitions the network into static clusters, eliminates the overhead of dynamic clustering and utilizes temporary-cluster-heads to distribute the energy load among high-power sensor nodes; thus extends network lifetime. We have conducted simulation-based evaluations to compare the performance of EEPSC against Low-Energy Adaptive Clustering Hierarchy (LEACH). Our experiment results show that EEPSC outperforms LEACH in terms of network lifetime and power consumption minimization.Keywords: Clustering methods, energy efficiency, routingprotocol, wireless sensor networks.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 27091917 Finite Element Modeling of Heat and Moisture Transfer in Porous Material
Authors: V. D. Thi, M. Li, M. Khelifa, M. El Ganaoui, Y. Rogaume
Abstract:
This paper presents a two-dimensional model to study the heat and moisture transfer through porous building materials. Dynamic and static coupled models of heat and moisture transfer in porous material under low temperature are presented and the coupled models together with variable initial and boundary conditions have been considered in an analytical way and using the finite element method. The resulting coupled model is converted to two nonlinear partial differential equations, which is then numerically solved by an implicit iterative scheme. The numerical results of temperature and moisture potential changes are compared with the experimental measurements available in the literature. Predicted results demonstrate validation of the theoretical model and effectiveness of the developed numerical algorithms. It is expected to provide useful information for the porous building material design based on heat and moisture transfer model.Keywords: Finite element method, heat transfer, moisture transfer, porous materials, wood.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 12641916 Assessing Habitat-Suitability Models with a Virtual Species at Khao Nan National Park, Thailand
Authors: W. Srisang, K. Jaroensutasinee, M. Jaroensutasinee
Abstract:
This study examined a habitat-suitability assessment method namely the Ecological Niche Factor Analysis (ENFA). A virtual species was created and then dispatched in a geographic information system model of a real landscape in three historic scenarios: (1) spreading, (2) equilibrium, and (3) overabundance. In each scenario, the virtual species was sampled and these simulated data sets were used as inputs for the ENFA to reconstruct the habitat suitability model. The 'equilibrium' scenario gives the highest quantity and quality among three scenarios. ENFA was sensitive to the distribution scenarios but not sensitive to sample sizes. The use of a virtual species proved to be a very efficient method, allowing one to fully control the quality of the input data as well as to accurately evaluate the predictive power of the analyses.Keywords: Habitat-Suitability Models, Ecological niche factoranalysis, Climatic factors, Geographic information system.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17971915 A Computer Model of Language Acquisition – Syllable Learning – Based on Hebbian Cell Assemblies and Reinforcement Learning
Authors: Sepideh Fazeli, Fariba Bahrami
Abstract:
Investigating language acquisition is one of the most challenging problems in the area of studying language. Syllable learning as a level of language acquisition has a considerable significance since it plays an important role in language acquisition. Because of impossibility of studying language acquisition directly with children, especially in its developmental phases, computer models will be useful in examining language acquisition. In this paper a computer model of early language learning for syllable learning is proposed. It is guided by a conceptual model of syllable learning which is named Directions Into Velocities of Articulators model (DIVA). The computer model uses simple associational and reinforcement learning rules within neural network architecture which are inspired by neuroscience. Our simulation results verify the ability of the proposed computer model in producing phonemes during babbling and early speech. Also, it provides a framework for examining the neural basis of language learning and communication disorders.Keywords: Brain modeling, computer models, language acquisition, reinforcement learning.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15761914 Novel Hybrid Method for Gene Selection and Cancer Prediction
Authors: Liping Jing, Michael K. Ng, Tieyong Zeng
Abstract:
Microarray data profiles gene expression on a whole genome scale, therefore, it provides a good way to study associations between gene expression and occurrence or progression of cancer. More and more researchers realized that microarray data is helpful to predict cancer sample. However, the high dimension of gene expressions is much larger than the sample size, which makes this task very difficult. Therefore, how to identify the significant genes causing cancer becomes emergency and also a hot and hard research topic. Many feature selection algorithms have been proposed in the past focusing on improving cancer predictive accuracy at the expense of ignoring the correlations between the features. In this work, a novel framework (named by SGS) is presented for stable gene selection and efficient cancer prediction . The proposed framework first performs clustering algorithm to find the gene groups where genes in each group have higher correlation coefficient, and then selects the significant genes in each group with Bayesian Lasso and important gene groups with group Lasso, and finally builds prediction model based on the shrinkage gene space with efficient classification algorithm (such as, SVM, 1NN, Regression and etc.). Experiment results on real world data show that the proposed framework often outperforms the existing feature selection and prediction methods, say SAM, IG and Lasso-type prediction model.Keywords: Gene Selection, Cancer Prediction, Lasso, Clustering, Classification.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20311913 Laser Data Based Automatic Generation of Lane-Level Road Map for Intelligent Vehicles
Authors: Zehai Yu, Hui Zhu, Linglong Lin, Huawei Liang, Biao Yu, Weixin Huang
Abstract:
With the development of intelligent vehicle systems, a high-precision road map is increasingly needed in many aspects. The automatic lane lines extraction and modeling are the most essential steps for the generation of a precise lane-level road map. In this paper, an automatic lane-level road map generation system is proposed. To extract the road markings on the ground, the multi-region Otsu thresholding method is applied, which calculates the intensity value of laser data that maximizes the variance between background and road markings. The extracted road marking points are then projected to the raster image and clustered using a two-stage clustering algorithm. Lane lines are subsequently recognized from these clusters by the shape features of their minimum bounding rectangle. To ensure the storage efficiency of the map, the lane lines are approximated to cubic polynomial curves using a Bayesian estimation approach. The proposed lane-level road map generation system has been tested on urban and expressway conditions in Hefei, China. The experimental results on the datasets show that our method can achieve excellent extraction and clustering effect, and the fitted lines can reach a high position accuracy with an error of less than 10 cm.
Keywords: Curve fitting, lane-level road map, line recognition, multi-thresholding, two-stage clustering.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5001912 An Analytical Electron Mobility Model based on Particle Swarm Computation for Siliconbased Devices
Authors: F. Djeffal, N. Lakhdar, T. Bendib
Abstract:
The study of the transport coefficients in electronic devices is currently carried out by analytical and empirical models. This study requires several simplifying assumptions, generally necessary to lead to analytical expressions in order to study the different characteristics of the electronic silicon-based devices. Further progress in the development, design and optimization of Silicon-based devices necessarily requires new theory and modeling tools. In our study, we use the PSO (Particle Swarm Optimization) technique as a computational tool to develop analytical approaches in order to study the transport phenomenon of the electron in crystalline silicon as function of temperature and doping concentration. Good agreement between our results and measured data has been found. The optimized analytical models can also be incorporated into the circuits simulators to study Si-based devices without impact on the computational time and data storage.Keywords: Particle Swarm, electron mobility, Si-based devices, Optimization.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15261911 Multidimensional Sports Spectators Segmentation and Social Media Marketing
Authors: B. Schmid, C. Kexel, E. Djafarova
Abstract:
Understanding consumers is elementary for practitioners in marketing. Consumers of sports events, the sports spectators, are a particularly complex consumer crowd. In order to identify and define their profiles different segmentation approaches can be found in literature, one of them being multidimensional segmentation. Multidimensional segmentation models correspond to the broad range of attitudes, behaviours, motivations and beliefs of sports spectators, other than earlier models. Moreover, in sports there are some well-researched disciplines (e.g. football or North American sports) where consumer profiles and marketing strategies are elaborate and others where no research at all can be found. For example, there is almost no research on athletics spectators. This paper explores the current state of research on sports spectators segmentation. An in-depth literature review provides the framework for a spectators segmentation in athletics. On this basis, additional potential consumer groups and implications for social media marketing will be explored. The findings are the basis for further research.Keywords: Multidimensional segmentation, social media, sports marketing, sports spectators segmentation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 25931910 An Interactive Web-based Simulation Tool for Surgical Thread
Authors: A. Ruimi, S. Goyal, B. M. Nour
Abstract:
Interactive web-based computer simulations are needed by the medical community to replicate the experience of surgical procedures as closely and realistically as possible without the need to practice on corpses, animals and/or plastic models. In this paper, we offer a review on current state of the research on simulations of surgical threads, identify future needs and present our proposed plans to meet them. Our goal is to create a physics-based simulator, which will predict the behavior of surgical thread when subjected to conditions commonly encountered during surgery. To that end, we will i) develop three dimensional finite element models based on the Cosserat theory of elasticity ii) test and feedback results with the medical community and iii) develop a web-based user interface to run/command our simulator and visualize the results. The impacts of our research are that i) it will contribute to the development of a new generation of training for medical school students and ii) the simulator will be useful to expert surgeons in developing new, better and less risky procedures.Keywords: Cosserat rod-theory, FEM simulations, Modeling, Surgical thread.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16451909 Comparison of Neural Network and Logistic Regression Methods to Predict Xerostomia after Radiotherapy
Authors: Hui-Min Ting, Tsair-Fwu Lee, Ming-Yuan Cho, Pei-Ju Chao, Chun-Ming Chang, Long-Chang Chen, Fu-Min Fang
Abstract:
To evaluate the ability to predict xerostomia after radiotherapy, we constructed and compared neural network and logistic regression models. In this study, 61 patients who completed a questionnaire about their quality of life (QoL) before and after a full course of radiation therapy were included. Based on this questionnaire, some statistical data about the condition of the patients’ salivary glands were obtained, and these subjects were included as the inputs of the neural network and logistic regression models in order to predict the probability of xerostomia. Seven variables were then selected from the statistical data according to Cramer’s V and point-biserial correlation values and were trained by each model to obtain the respective outputs which were 0.88 and 0.89 for AUC, 9.20 and 7.65 for SSE, and 13.7% and 19.0% for MAPE, respectively. These parameters demonstrate that both neural network and logistic regression methods are effective for predicting conditions of parotid glands.
Keywords: NPC, ANN, logistic regression, xerostomia.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16231908 The Relationship between Citizenship Acquisition and Ethnic Identity of Immigrant Women in Taiwan
Authors: Yuan-Yu Chiang, Yu-Han Tseng, Chin-Chen Wen
Abstract:
In the last few decades, many southeast-Asia women migrate to Taiwan by marriage, and it usually takes several years for them to acquire Taiwanese citizenship. This study investigates the relationship between their citizenship acquisition and whether they develop Taiwanese identities, and how does it affect their ethnical identity towards their original ethnics. Furthermore, the present study also explores that whether citizenship acquisition help the immigrant women to explore the host society further and make commitment to it, or the identification towards mainstream Taiwanese society is only symbolic and superficial? One hundred and ninety-two immigrant women were measured using Multigroup Ethnic Identity Measure-Revised and a global 10-point ethnic identity question. Correlation tests, t-test, and hierarchical regression were performed to answer the above questions. The results revealed that citizenship acquisition does help immigrant women to identify with Taiwanese society, but it does not affect how they identify with their own ethnics. Furthermore, the results also indicated that acquiring citizenship would not help these immigrant women become involved in deeper cultural exploration of Taiwan nor would it encourage them to make commitments to the host society.
Keywords: Immigrants, international marriage, ethnic identity, Taiwan.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16481907 The Use of Thermal Infrared Wavelengths to Determine the Volcanic Soils
Authors: Levent Basayigit, Mert Dedeoglu, Fadime Ozogul
Abstract:
In this study, an application was carried out to determine the Volcanic Soils by using remote sensing. The study area was located on the Golcuk formation in Isparta-Turkey. The thermal bands of Landsat 7 image were used for processing. The implementation of the climate model that was based on the water index was used in ERDAS Imagine software together with pixel based image classification. Soil Moisture Index (SMI) was modeled by using the surface temperature (Ts) which was obtained from thermal bands and vegetation index (NDVI) derived from Landsat 7. Surface moisture values were grouped and classified by using scoring system. Thematic layers were compared together with the field studies. Consequently, different moisture levels for volcanic soils were indicator for determination and separation. Those thermal wavelengths are preferable bands for separation of volcanic soils using moisture and temperature models.
Keywords: Landsat 7, soil moisture index, temperature models, volcanic soils.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 10861906 Adsorption of Cadmium onto Activated and Non-Activated Date Pits
Authors: Munther I. Kandah, Fahmi A. Abu Al-Rub, Lucy Bawarish, Mira Bawarish, Hiba Al-Tamimi, Reem Khalil, Raja'a Sa, ada
Abstract:
In this project cadmium ions were adsorbed from aqueous solutions onto either date pits; a cheap agricultural and nontoxic material, or chemically activated carbon prepared from date pits using phosphoric acid. A series of experiments were conducted in a batch adsorption technique to assess the feasibility of using the prepared adsorbents. The effects of the process variables such as initial cadmium ions concentration, contact time, solution pH and adsorbent dose on the adsorption capacity of both adsorbents were studied. The experimental data were tested using different isotherm models such as Langmuir, Freundlich, Tempkin and Dubinin- Radushkevich. The results showed that although the equilibrium data could be described by all models used, Langmuir model gave slightly better results when using activated carbon while Freundlich model, gave better results with date pits.Keywords: Adsorption, Cadmium, Chemical Activation, DatePits.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17991905 Fingerprint Compression Using Multiwavelets
Authors: Sudhakar.R, Jayaraman.S
Abstract:
Large volumes of fingerprints are collected and stored every day in a wide range of applications, including forensics, access control etc. It is evident from the database of Federal Bureau of Investigation (FBI) which contains more than 70 million finger prints. Compression of this database is very important because of this high Volume. The performance of existing image coding standards generally degrades at low bit-rates because of the underlying block based Discrete Cosine Transform (DCT) scheme. Over the past decade, the success of wavelets in solving many different problems has contributed to its unprecedented popularity. Due to implementation constraints scalar wavelets do not posses all the properties which are needed for better performance in compression. New class of wavelets called 'Multiwavelets' which posses more than one scaling filters overcomes this problem. The objective of this paper is to develop an efficient compression scheme and to obtain better quality and higher compression ratio through multiwavelet transform and embedded coding of multiwavelet coefficients through Set Partitioning In Hierarchical Trees algorithm (SPIHT) algorithm. A comparison of the best known multiwavelets is made to the best known scalar wavelets. Both quantitative and qualitative measures of performance are examined for Fingerprints.Keywords: Mutiwavelet, Modified SPIHT Algorithm, SPIHT, Wavelet.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15941904 A Context-Aware Supplier Selection Model
Authors: Mohammadreza Razzazi, Maryam Bayat
Abstract:
Selection of the best possible set of suppliers has a significant impact on the overall profitability and success of any business. For this reason, it is usually necessary to optimize all business processes and to make use of cost-effective alternatives for additional savings. This paper proposes a new efficient context-aware supplier selection model that takes into account possible changes of the environment while significantly reducing selection costs. The proposed model is based on data clustering techniques while inspiring certain principles of online algorithms for an optimally selection of suppliers. Unlike common selection models which re-run the selection algorithm from the scratch-line for any decision-making sub-period on the whole environment, our model considers the changes only and superimposes it to the previously defined best set of suppliers to obtain a new best set of suppliers. Therefore, any recomputation of unchanged elements of the environment is avoided and selection costs are consequently reduced significantly. A numerical evaluation confirms applicability of this model and proves that it is a more optimal solution compared with common static selection models in this field.Keywords: Supplier Selection, Context-Awareness, OnlineAlgorithms, Data Clustering.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18041903 A Framework for Product Development Process including HW and SW Components
Authors: Namchul Do, Gyeongseok Chae
Abstract:
This paper proposes a framework for product development including hardware and software components. It provides separation of hardware dependent software, modifications of current product development process, and integration of software modules with existing product configuration models and assembly product structures. In order to decide the dependent software, the framework considers product configuration modules and engineering changes of associated software and hardware components. In order to support efficient integration of the two different hardware and software development, a modified product development process is proposed. The process integrates the dependent software development into product development through the interchanges of specific product information. By using existing product data models in Product Data Management (PDM), the framework represents software as modules for product configurations and software parts for product structure. The framework is applied to development of a robot system in order to show its effectiveness.Keywords: HW and SW Development Integration, ProductDevelopment with Software.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 25891902 Application of Feed-Forward Neural Networks Autoregressive Models with Genetic Algorithm in Gross Domestic Product Prediction
Authors: E. Giovanis
Abstract:
In this paper we present a Feed-Foward Neural Networks Autoregressive (FFNN-AR) model with genetic algorithms training optimization in order to predict the gross domestic product growth of six countries. Specifically we propose a kind of weighted regression, which can be used for econometric purposes, where the initial inputs are multiplied by the neural networks final optimum weights from input-hidden layer of the training process. The forecasts are compared with those of the ordinary autoregressive model and we conclude that the proposed regression-s forecasting results outperform significant those of autoregressive model. Moreover this technique can be used in Autoregressive-Moving Average models, with and without exogenous inputs, as also the training process with genetics algorithms optimization can be replaced by the error back-propagation algorithm.Keywords: Autoregressive model, Feed-Forward neuralnetworks, Genetic Algorithms, Gross Domestic Product
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16601901 Brand Equity and Factors Affecting Consumer-s Purchase Intention towards Luxury Brands in Bangkok Metropolitan Area
Authors: Sumalee Lekprayura
Abstract:
The purposes of this research were 1) to study consumer-based equity of luxury brands, 2) to study consumers- purchase intention for luxury brands, 3) to study direct factors affecting purchase intention towards luxury brands, and 4) to study indirect factors affecting purchase intention towards luxury brands through brand consciousness and brand equity to analyze information by descriptive statistic and hierarchical stepwise regression analysis. The findings revealed that the eight variables of the framework which were: need for uniqueness, normative susceptibility, status consumption, brand consciousness, brand awareness, perceived quality, brand association, and brand loyalty affected the purchase intention of the luxury brands (at the significance of 0.05). Brand Loyalty had the strongest direct effect while status consumption had the strongest indirect effect affecting the purchase intention towards luxury brands. Brand consciousness and brand equity had the mediators through the purchase intention of the luxury brands (at the significance of 0.05).Keywords: Brand Consciousness, Brand Equity, Luxury Brands, Purchase intention.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 51721900 Optimizing usage of ICTs and Outsourcing Strategic in Business Models and Customer Satisfaction
Authors: Saeed Rahmani Bagha, Mohammad Mirzahosseinian, Sonatkhatoon Kashanimotlagh
Abstract:
Nowadays, under developed countries for progress in science and technology and decreasing the technologic gap with developed countries, increasing the capacities and technology transfer from developed countries. To remain competitive, industry is continually searching for new methods to evolve their products. Business model is one of the latest buzzwords in the Internet and electronic business world. To be successful, organizations must look into the needs and wants of their customers. This research attempts to identify a specific feature of the company with a strong competitive advantage by analyzing the cause of Customer satisfaction. Due to the rapid development of knowledge and information technology, business environments have become much more complicated. Information technology can help a firm aiming to gain a competitive advantage. This study explores the role and effect of Information Communication Technology in Business Models and Customer satisfaction on firms and also relationships between ICTs and Outsourcing strategic.Keywords: Information Communication Technology, Outsourcing, Customer Satisfaction, Business Plan
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16841899 An Empirical Model of Correlated Traffics in LTE-Advanced System through an Innovative Simulation Tool
Authors: Ghassan A. Abed, Mahamod Ismail, Samir I. Badrawi, Bayan M. Sabbar
Abstract:
Long Term Evolution Advanced (LTE-Advanced) LTE-Advanced is not new as a radio access technology, but it is an evolution of LTE to enhance the performance. This generation is the continuation of 3GPP-LTE (3GPP: 3rd Generation Partnership Project) and it is targeted for advanced development of the requirements of LTE in terms of throughput and coverage. The performance evaluation process of any network should be based on many models and simulations to investigate the network layers and functions and monitor the employment of the new technologies especially when this network includes large-bandwidth and low-latency links such as LTE and LTE-Advanced networks. Therefore, it’s necessary to enhance the proposed models of high-speed and high-congested link networks to make these links and traffics fulfill the needs of the huge data which transferred over the congested links. This article offered an innovative model of the most correlated links of LTE-Advanced system using the Network Simulator 2 (NS-2) with investigation of the link parameters.
Keywords: 3GPP, LTE, LTE-Advanced, NS-2.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 24171898 Metrology-Inspired Methods to Assess the Biases of Artificial Intelligence Systems
Authors: Belkacem Laimouche
Abstract:
With the field of Artificial Intelligence (AI) experiencing exponential growth, fueled by technological advancements that pave the way for increasingly innovative and promising applications, there is an escalating need to develop rigorous methods for assessing their performance in pursuit of transparency and equity. This article proposes a metrology-inspired statistical framework for evaluating bias and explainability in AI systems. Drawing from the principles of metrology, we propose a pioneering approach, using a concrete example, to evaluate the accuracy and precision of AI models, as well as to quantify the sources of measurement uncertainty that can lead to bias in their predictions. Furthermore, we explore a statistical approach for evaluating the explainability of AI systems based on their ability to provide interpretable and transparent explanations of their predictions.
Keywords: Artificial intelligence, metrology, measurement uncertainty, prediction error, bias, machine learning algorithms, probabilistic models, inter-laboratory comparison, data analysis, data reliability, bias impact assessment, bias measurement.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 841897 Modeling Football Penalty Shootouts: How Improving Individual Performance Affects Team Performance and the Fairness of the ABAB Sequence
Authors: Pablo Enrique Sartor Del Giudice
Abstract:
Penalty shootouts often decide the outcome of important soccer matches. Although usually referred to as ”lotteries”, there is evidence that some national teams and clubs consistently perform better than others. The outcomes are therefore not explained just by mere luck, and therefore there are ways to improve the average performance of players, naturally at the expense of some sort of effort. In this article we study the payoff of player performance improvements in terms of the performance of the team as a whole. To do so we develop an analytical model with static individual performances, as well as Monte Carlo models that take into account the known influence of partial score and round number on individual performances. We find that within a range of usual values, the team performance improves above 70% faster than individual performances do. Using these models, we also estimate that the new ABBA penalty shootout ordering under test reduces almost all the known bias in favor of the first-shooting team under the current ABAB system.Keywords: Football, penalty shootouts, Montecarlo simulation, ABBA.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 8301896 WEMax: Virtual Manned Assembly Line Generation
Authors: Won Kyung Ham, Kang Hoon Cho, Yongho Chung, Sang C. Park
Abstract:
Presented in this paper is a framework of a software ‘WEMax’. The WEMax is invented for analysis and simulation for manned assembly lines to sustain and improve performance of manufacturing systems. In a manufacturing system, performance, such as productivity, is a key of competitiveness for output products. However, the manned assembly lines are difficult to forecast performance, because human labors are not expectable factors by computer simulation models or mathematical models. Existing approaches to performance forecasting of the manned assembly lines are limited to matters of the human itself, such as ergonomic and workload design, and non-human-factor-relevant simulation. Consequently, an approach for the forecasting and improvement of manned assembly line performance is needed to research. As a solution of the current problem, this study proposes a framework that is for generation and simulation of virtual manned assembly lines, and the framework has been implemented as a software.
Keywords: Performance Forecasting, Simulation, Virtual Manned Assembly Line.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18851895 A Method to Improve Test Process in Federal Enterprise Architecture Framework Using ISTQB Framework
Authors: Hamideh Mahdavifar, Ramin Nassiri, Alireza Bagheri
Abstract:
Enterprise Architecture (EA) is a framework for description, coordination and alignment of all activities across the organization in order to achieve strategic goals using ICT enablers. A number of EA-compatible frameworks have been developed. We, in this paper, mainly focus on Federal Enterprise Architecture Framework (FEAF) since its reference models are plentiful. Among these models we are interested here in its business reference model (BRM). The test process is one important subject of an EA project which is to somewhat overlooked. This lack of attention may cause drawbacks or even failure of an enterprise architecture project. To address this issue we intend to use International Software Testing Qualification Board (ISTQB) framework and standard test suites to present a method to improve EA testing process. The main challenge is how to communicate between the concepts of EA and ISTQB. In this paper, we propose a method for integrating these concepts.
Keywords: Business Reference Model (BRM), Federal Enterprise Architecture (FEA), ISTQB, Test Techniques.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19551894 Incorporating Lexical-Semantic Knowledge into Convolutional Neural Network Framework for Pediatric Disease Diagnosis
Authors: Xiaocong Liu, Huazhen Wang, Ting He, Xiaozheng Li, Weihan Zhang, Jian Chen
Abstract:
The utilization of electronic medical record (EMR) data to establish the disease diagnosis model has become an important research content of biomedical informatics. Deep learning can automatically extract features from the massive data, which brings about breakthroughs in the study of EMR data. The challenge is that deep learning lacks semantic knowledge, which leads to impracticability in medical science. This research proposes a method of incorporating lexical-semantic knowledge from abundant entities into a convolutional neural network (CNN) framework for pediatric disease diagnosis. Firstly, medical terms are vectorized into Lexical Semantic Vectors (LSV), which are concatenated with the embedded word vectors of word2vec to enrich the feature representation. Secondly, the semantic distribution of medical terms serves as Semantic Decision Guide (SDG) for the optimization of deep learning models. The study evaluates the performance of LSV-SDG-CNN model on four kinds of Chinese EMR datasets. Additionally, CNN, LSV-CNN, and SDG-CNN are designed as baseline models for comparison. The experimental results show that LSV-SDG-CNN model outperforms baseline models on four kinds of Chinese EMR datasets. The best configuration of the model yielded an F1 score of 86.20%. The results clearly demonstrate that CNN has been effectively guided and optimized by lexical-semantic knowledge, and LSV-SDG-CNN model improves the disease classification accuracy with a clear margin.
Keywords: lexical semantics, feature representation, semantic decision, convolutional neural network, electronic medical record
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5701893 Piezoelectric Transducer Modeling: with System Identification (SI) Method
Authors: Nora Taghavi, Ali Sadr
Abstract:
System identification is the process of creating models of dynamic process from input- output signals. The aim of system identification can be identified as “ to find a model with adjustable parameters and then to adjust them so that the predicted output matches the measured output". This paper presents a method of modeling and simulating with system identification to achieve the maximum fitness for transformation function. First by using optimized KLM equivalent circuit for PVDF piezoelectric transducer and assuming different inputs including: sinuside, step and sum of sinusides, get the outputs, then by using system identification toolbox in MATLAB, we estimate the transformation function from inputs and outputs resulted in last program. Then compare the fitness of transformation function resulted from using ARX,OE(Output- Error) and BJ(Box-Jenkins) models in system identification toolbox and primary transformation function form KLM equivalent circuit.Keywords: PVDF modeling, ARX, BJ(Box-Jenkins), OE(Output-Error), System Identification.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 27231892 Cirrhosis Mortality Prediction as Classification Using Frequent Subgraph Mining
Authors: Abdolghani Ebrahimi, Diego Klabjan, Chenxi Ge, Daniela Ladner, Parker Stride
Abstract:
In this work, we use machine learning and data analysis techniques to predict the one-year mortality of cirrhotic patients. Data from 2,322 patients with liver cirrhosis are collected at a single medical center. Different machine learning models are applied to predict one-year mortality. A comprehensive feature space including demographic information, comorbidity, clinical procedure and laboratory tests is being analyzed. A temporal pattern mining technic called Frequent Subgraph Mining (FSM) is being used. Model for End-stage liver disease (MELD) prediction of mortality is used as a comparator. All of our models statistically significantly outperform the MELD-score model and show an average 10% improvement of the area under the curve (AUC). The FSM technic itself does not improve the model significantly, but FSM, together with a machine learning technique called an ensemble, further improves the model performance. With the abundance of data available in healthcare through electronic health records (EHR), existing predictive models can be refined to identify and treat patients at risk for higher mortality. However, due to the sparsity of the temporal information needed by FSM, the FSM model does not yield significant improvements. Our work applies modern machine learning algorithms and data analysis methods on predicting one-year mortality of cirrhotic patients and builds a model that predicts one-year mortality significantly more accurate than the MELD score. We have also tested the potential of FSM and provided a new perspective of the importance of clinical features.
Keywords: machine learning, liver cirrhosis, subgraph mining, supervised learning
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4241891 Assessment of the Influence of External Earth Terrain at Construction of the Physicmathematical Models or Finding the Dynamics of Pollutants' Distribution in Urban Atmosphere
Authors: Stanislav Aryeh V. Fradkin, Sharif E.Guseynov
Abstract:
There is a complex situation on the transport environment in the cities of the world. For the analysis and prevention of environmental problems an accurate calculation hazardous substances concentrations at each point of the investigated area is required. In the turbulent atmosphere of the city the wellknown methods of mathematical statistics for these tasks cannot be applied with a satisfactory level of accuracy. Therefore, to solve this class of problems apparatus of mathematical physics is more appropriate. In such models, because of the difficulty as a rule the influence of uneven land surface on streams of air masses in the turbulent atmosphere of the city are not taken into account. In this paper the influence of the surface roughness, which can be quite large, is mathematically shown. The analysis of this problem under certain conditions identified the possibility of areas appearing in the atmosphere with pressure tending to infinity, i.e. so-called "wall effect".
Keywords: Air pollution, concentration of harmful substances, physical-mathematical model, urban area.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 13321890 Annotations of Gene Pathways Images in Biomedical Publications Using Siamese Network
Authors: Micheal Olaolu Arowolo, Muhammad Azam, Fei He, Mihail Popescu, Dong Xu
Abstract:
As the quantity of biological articles rises, so does the number of biological route figures. Each route figure shows gene names and relationships. Manually annotating pathway diagrams is time-consuming. Advanced image understanding models could speed up curation, but they must be more precise. There is rich information in biological pathway figures. The first step to performing image understanding of these figures is to recognize gene names automatically. Classical optical character recognition methods have been employed for gene name recognition, but they are not optimized for literature mining data. This study devised a method to recognize an image bounding box of gene name as a photo using deep Siamese neural network models to outperform the existing methods using ResNet, DenseNet and Inception architectures, the results obtained about 84% accuracy.
Keywords: Biological pathway, gene identification, object detection, Siamese network, ResNet.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 225