Search results for: information processing model
26522 One-Shot Text Classification with Multilingual-BERT
Authors: Hsin-Yang Wang, K. M. A. Salam, Ying-Jia Lin, Daniel Tan, Tzu-Hsuan Chou, Hung-Yu Kao
Abstract:
Detecting user intent from natural language expression has a wide variety of use cases in different natural language processing applications. Recently few-shot training has a spike of usage on commercial domains. Due to the lack of significant sample features, the downstream task performance has been limited or leads to an unstable result across different domains. As a state-of-the-art method, the pre-trained BERT model gathering the sentence-level information from a large text corpus shows improvement on several NLP benchmarks. In this research, we are proposing a method to change multi-class classification tasks into binary classification tasks, then use the confidence score to rank the results. As a language model, BERT performs well on sequence data. In our experiment, we change the objective from predicting labels into finding the relations between words in sequence data. Our proposed method achieved 71.0% accuracy in the internal intent detection dataset and 63.9% accuracy in the HuffPost dataset. Acknowledgment: This work was supported by NCKU-B109-K003, which is the collaboration between National Cheng Kung University, Taiwan, and SoftBank Corp., Tokyo.Keywords: OSML, BERT, text classification, one shot
Procedia PDF Downloads 9426521 Media Richness Perspective on Web 2.0 Usage for Knowledge Creation: The Case of the Cocoa Industry in Ghana
Authors: Albert Gyamfi
Abstract:
Cocoa plays critical role in the socio-economic development of Ghana. Meanwhile, smallholder farmers most of whom are illiterate dominate the industry. According to the cocoa-based agricultural knowledge and information system (AKIS) model knowledge is created and transferred to the industry between three key actors: cocoa researchers, extension experts, and cocoa farmers. Dwelling on the SECI model, the media richness theory (MRT), and the AKIS model, a conceptual model of web 2.0-based AKIS model (AKIS 2.0) is developed and used to assess the possible effects of social media usage for knowledge creation in the Ghanaian cocoa industry. A mixed method approach with a survey questionnaire was employed, and a second-order multi-group structural equation model (SEM) was used to analyze the data. The study concludes that the use of web 2.0 applications for knowledge creation would lead to sustainable interactions among the key knowledge actors for effective knowledge creation in the cocoa industry in Ghana.Keywords: agriculture, cocoa, knowledge, media, web 2.0
Procedia PDF Downloads 32326520 Information Technology and Business Alignments among Different Divisions: A Comparative Analysis of Japan and South Korea
Authors: Michiko Miyamoto
Abstract:
This paper empirically investigates whether information technology (IT) strategies, business strategies, and divisions are aligned to meet overall business goals for Korean Small and medium-sized enterprises (SMEs), based on structure based Strategic Alignment Model, and make comparison with those of Japanese SMEs. Using 2,869 valid responses of Korean Human Capital Corporate Panel survey, a result of this study suggests that Korean human resources (HR) departments have a major influence over IT strategy, which is the same as Japanese SMEs, even though their management styles are quite different. As for IT strategy, it is not related to other departments at all for Korean SMEs. The Korean management seems to possess a great power over each division, such as Sales/Service, Research and Development/Technical Experts, HR, and Production.Keywords: IT-business alignment, structured based strategic alignment model, structural equation model, human resources department
Procedia PDF Downloads 26326519 The Design of a Mixed Matrix Model for Activity Levels Extraction and Sub Processes Classification of a Work Project (Case: Great Tehran Electrical Distribution Company)
Authors: Elham Allahmoradi, Bahman Allahmoradi, Ali Bonyadi Naeini
Abstract:
Complex systems have many aspects. A variety of methods have been developed to analyze these systems. The most efficient of these methods should not only be simple, but also provide useful and comprehensive information about many aspects of the system. Matrix methods are considered the most commonly methods used to analyze and design systems. Each matrix method can examine a particular aspect of the system. If these methods are combined, managers can access to more comprehensive and broader information about the system. This study was conducted in four steps. In the first step, a process model of a real project has been extracted through IDEF3. In the second step, activity levels have been attained by writing a process model in the form of a design structure matrix (DSM) and sorting it through triangulation algorithm (TA). In the third step, sub-processes have been obtained by writing the process model in the form of an interface structure matrix (ISM) and clustering it through cluster identification algorithm (CIA). In the fourth step, a mixed model has been developed to provide a unified picture of the project structure through the simultaneous presentation of activities and sub-processes. Finally, the paper is completed with a conclusion.Keywords: integrated definition for process description capture (IDEF3) method, design structure matrix (DSM), interface structure matrix (ism), mixed matrix model, activity level, sub-process
Procedia PDF Downloads 48826518 The Effect of Information Technology on the Quality of Accounting Information
Authors: Mohammad Hadi Khorashadi Zadeh, Amin Karkon, Hamid Golnari
Abstract:
This study aimed to investigate the impact of information technology on the quality of accounting information was made in 2014. A survey of 425 executives of listed companies in Tehran Stock Exchange, using the Cochran formula simple random sampling method, 84 managers of these companies as the sample size was considered. Methods of data collection based on questionnaire information technology some of the questions of the impact of information technology was standardized questionnaires and the questions were designed according to existing components. After the distribution and collection of questionnaires, data analysis and hypothesis testing using structural equation modeling Smart PLS2 and software measurement model and the structure was conducted in two parts. In the first part of the questionnaire technical characteristics including reliability, validity, convergent and divergent validity for PLS has been checked and in the second part, application no significant coefficients were used to examine the research hypotheses. The results showed that IT and its dimensions (timeliness, relevance, accuracy, adequacy, and the actual transfer rate) affect the quality of accounting information of listed companies in Tehran Stock Exchange influence.Keywords: information technology, information quality, accounting, transfer speed
Procedia PDF Downloads 27126517 Effects of the Air Supply Outlets Geometry on Human Comfort inside Living Rooms: CFD vs. ADPI
Authors: Taher M. Abou-deif, Esmail M. El-Bialy, Essam E. Khalil
Abstract:
The paper is devoted to numerically investigating the influence of the air supply outlets geometry on human comfort inside living looms. A computational fluid dynamics model is developed to examine the air flow characteristics of a room with different supply air diffusers. The work focuses on air flow patterns, thermal behavior in the room with few number of occupants. As an input to the full-scale 3-D room model, a 2-D air supply diffuser model that supplies direction and magnitude of air flow into the room is developed. Air distribution effect on thermal comfort parameters was investigated depending on changing the air supply diffusers type, angles and velocity. Air supply diffusers locations and numbers were also investigated. The pre-processor Gambit is used to create the geometric model with parametric features. Commercially available simulation software “Fluent 6.3” is incorporated to solve the differential equations governing the conservation of mass, three momentum and energy in the processing of air flow distribution. Turbulence effects of the flow are represented by the well-developed two equation turbulence model. In this work, the so-called standard k-ε turbulence model, one of the most widespread turbulence models for industrial applications, was utilized. Basic parameters included in this work are air dry bulb temperature, air velocity, relative humidity and turbulence parameters are used for numerical predictions of indoor air distribution and thermal comfort. The thermal comfort predictions through this work were based on ADPI (Air Diffusion Performance Index),the PMV (Predicted Mean Vote) model and the PPD (Percentage People Dissatisfied) model, the PMV and PPD were estimated using Fanger’s model.Keywords: thermal comfort, Fanger's model, ADPI, energy effeciency
Procedia PDF Downloads 40526516 Motion Estimator Architecture with Optimized Number of Processing Elements for High Efficiency Video Coding
Authors: Seongsoo Lee
Abstract:
Motion estimation occupies the heaviest computation in HEVC (high efficiency video coding). Many fast algorithms such as TZS (test zone search) have been proposed to reduce the computation. Still the huge computation of the motion estimation is a critical issue in the implementation of HEVC video codec. In this paper, motion estimator architecture with optimized number of PEs (processing element) is presented by exploiting early termination. It also reduces hardware size by exploiting parallel processing. The presented motion estimator architecture has 8 PEs, and it can efficiently perform TZS with very high utilization of PEs.Keywords: motion estimation, test zone search, high efficiency video coding, processing element, optimization
Procedia PDF Downloads 35626515 Adaptive Data Approximations Codec (ADAC) for AI/ML-based Cyber-Physical Systems
Authors: Yong-Kyu Jung
Abstract:
The fast growth in information technology has led to de-mands to access/process data. CPSs heavily depend on the time of hardware/software operations and communication over the network (i.e., real-time/parallel operations in CPSs (e.g., autonomous vehicles). Since data processing is an im-portant means to overcome the issue confronting data management, reducing the gap between the technological-growth and the data-complexity and channel-bandwidth. An adaptive perpetual data approximation method is intro-duced to manage the actual entropy of the digital spectrum. An ADAC implemented as an accelerator and/or apps for servers/smart-connected devices adaptively rescales digital contents (avg.62.8%), data processing/access time/energy, encryption/decryption overheads in AI/ML applications (facial ID/recognition).Keywords: adaptive codec, AI, ML, HPC, cyber-physical, cybersecurity
Procedia PDF Downloads 7426514 Identifying the Structural Components of Old Buildings from Floor Plans
Authors: Shi-Yu Xu
Abstract:
The top three risk factors that have contributed to building collapses during past earthquake events in Taiwan are: "irregular floor plans or elevations," "insufficient columns in single-bay buildings," and the "weak-story problem." Fortunately, these unsound structural characteristics can be directly identified from the floor plans. However, due to the vast number of old buildings, conducting manual inspections to identify these compromised structural features in all existing structures would be time-consuming and prone to human errors. This study aims to develop an algorithm that utilizes artificial intelligence techniques to automatically pinpoint the structural components within a building's floor plans. The obtained spatial information will be utilized to construct a digital structural model of the building. This information, particularly regarding the distribution of columns in the floor plan, can then be used to conduct preliminary seismic assessments of the building. The study employs various image processing and pattern recognition techniques to enhance detection efficiency and accuracy. The study enables a large-scale evaluation of structural vulnerability for numerous old buildings, providing ample time to arrange for structural retrofitting in those buildings that are at risk of significant damage or collapse during earthquakes.Keywords: structural vulnerability detection, object recognition, seismic capacity assessment, old buildings, artificial intelligence
Procedia PDF Downloads 7926513 The Need for Automation in the Domestic Food Processing Sector and its Impact
Authors: Shantam Gupta
Abstract:
The objective of this study is to address the critical need for automation in the domestic food processing sector and study its impact. Food is the one of the most basic physiological needs essential for the survival of a living being. Some of them have the capacity to prepare their own food (like most plants) and henceforth are designated as primary food producers; those who depend on these primary food producers for food form the primary consumers’ class (herbivores). Some of the organisms relying on the primary food are the secondary food consumers (carnivores). There is a third class of consumers called tertiary food consumers/apex food consumers that feed on both the primary and secondary food consumers. Humans form an essential part of the apex predators and are generally at the top of the food chain. But still further disintegration of the food habits of the modern human i.e. Homo sapiens, reveals that humans depend on other individuals for preparing their own food. The old notion of eating raw/brute food is long gone and food processing has become very trenchant in lives of modern human. This has led to an increase in dependence on other individuals for ‘processing’ the food before it can be actually consumed by the modern human. This has led to a further shift of humans in the classification of food chain of consumers. The effects of the shifts shall be systematically investigated in this paper. The processing of food has a direct impact on the economy of the individual (consumer). Also most individuals depend on other processing individuals for the preparation of food. This dependency leads to establishment of a vital link of dependency in the food web which when altered can adversely affect the food web and can have dire consequences on the health of the individual. This study investigates the challenges arising out due to this dependency and the impact of food processing on the economy of the individual. A comparison of Industrial food processing and processing at domestic platforms (households and restaurants) has been made to provide an idea about the present scenario of automation in the food processing sector. A lot of time and energy is also consumed while processing food at home for consumption. The high frequency of consumption of meals (greater than 2 times a day) makes it even more laborious. Through the medium of this study a pressing need for development of an automatic cooking machine is proposed with a mission to reduce the inter-dependency & human effort of individuals required for the preparation of food (by automation of the food preparation process) and make them more self-reliant The impact of development of this product has also further been profoundly discussed. Assumption used: The individuals those who process food also consume the food that they produce. (They are also termed as ‘independent’ or ‘self-reliant’ modern human beings.)Keywords: automation, food processing, impact on economy, processing individual
Procedia PDF Downloads 46526512 Extracting the Coupled Dynamics in Thin-Walled Beams from Numerical Data Bases
Authors: Mohammad A. Bani-Khaled
Abstract:
In this work we use the Discrete Proper Orthogonal Decomposition transform to characterize the properties of coupled dynamics in thin-walled beams by exploiting numerical simulations obtained from finite element simulations. The outcomes of the will improve our understanding of the linear and nonlinear coupled behavior of thin-walled beams structures. Thin-walled beams have widespread usage in modern engineering application in both large scale structures (aeronautical structures), as well as in nano-structures (nano-tubes). Therefore, detailed knowledge in regard to the properties of coupled vibrations and buckling in these structures are of great interest in the research community. Due to the geometric complexity in the overall structure and in particular in the cross-sections it is necessary to involve computational mechanics to numerically simulate the dynamics. In using numerical computational techniques, it is not necessary to over simplify a model in order to solve the equations of motions. Computational dynamics methods produce databases of controlled resolution in time and space. These numerical databases contain information on the properties of the coupled dynamics. In order to extract the system dynamic properties and strength of coupling among the various fields of the motion, processing techniques are required. Time- Proper Orthogonal Decomposition transform is a powerful tool for processing databases for the dynamics. It will be used to study the coupled dynamics of thin-walled basic structures. These structures are ideal to form a basis for a systematic study of coupled dynamics in structures of complex geometry.Keywords: coupled dynamics, geometric complexity, proper orthogonal decomposition (POD), thin walled beams
Procedia PDF Downloads 41326511 Synthesis and Characterisation of Bi-Substituted Magnetite Nanoparticles by Mechanochemical Processing (MCP)
Authors: Morteza Mohri Esfahani, Amir S. H. Rozatian, Morteza Mozaffari
Abstract:
Single phase magnetite nanoparticles and Bi-substituted ones were prepared by mechanochemical processing (MCP). The effects of Bi-substitution on the structural and magnetic properties of the nanoparticles were studied by X-ray Diffraction (XRD) and magnetometry techniques, respectively. The XRD results showed that all samples have spinel phase and by increasing Bi content, the main diffraction peaks were shifted to higher angles, which means the lattice parameter decreases from 0.843 to 0.838 nm and then increases to 0.841 nm. Also, the results revealed that increasing Bi content lead to a decrease in saturation magnetization (Ms) from 74.9 to 48.8 emu/g and an increase in coercivity (Hc) from 96.8 to 137.1 Oe.Keywords: bi-substituted magnetite nanoparticles, mechanochemical processing, X-ray diffraction, magnetism
Procedia PDF Downloads 52826510 Controlling the Expense of Political Contests Using a Modified N-Players Tullock’s Model
Abstract:
This work introduces a generalization of the classical Tullock’s model of one-stage contests under complete information with multiple unlimited numbers of contestants. In classical Tullock’s model, the contest winner is not necessarily the highest bidder. Instead, the winner is determined according to a draw in which the winning probabilities are the relative contestants’ efforts. The Tullock modeling fits well political contests, in which the winner is not necessarily the highest effort contestant. This work presents a modified model which uses a simple non-discriminating rule, namely, a parameter to influence the total costs planned for an election, for example, the contest designer can control the contestants' efforts. The winner pays a fee, and the losers are reimbursed the same amount. Our proposed model includes a mechanism that controls the efforts exerted and balances competition, creating a tighter, less predictable and more interesting contest. Additionally, the proposed model follows the fairness criterion in the sense that it does not alter the contestants' probabilities of winning compared to the classic Tullock’s model. We provide an analytic solution for the contestant's optimal effort and expected reward.Keywords: contests, Tullock's model, political elections, control expenses
Procedia PDF Downloads 13826509 The Effectiveness of a Hybrid Diffie-Hellman-RSA-Advanced Encryption Standard Model
Authors: Abdellahi Cheikh
Abstract:
With the emergence of quantum computers with very powerful capabilities, the security of the exchange of shared keys between two interlocutors poses a big problem in terms of the rapid development of technologies such as computing power and computing speed. Therefore, the Diffie-Hellmann (DH) algorithm is more vulnerable than ever. No mechanism guarantees the security of the key exchange, so if an intermediary manages to intercept it, it is easy to intercept. In this regard, several studies have been conducted to improve the security of key exchange between two interlocutors, which has led to interesting results. The modification made on our model Diffie-Hellman-RSA-AES (DRA), which encrypts the information exchanged between two users using the three-encryption algorithms DH, RSA and AES, by using stenographic photos to hide the contents of the p, g and ClesAES values that are sent in an unencrypted state at the level of DRA model to calculate each user's public key. This work includes a comparative study between the DRA model and all existing solutions, as well as the modification made to this model, with an emphasis on the aspect of reliability in terms of security. This study presents a simulation to demonstrate the effectiveness of the modification made to the DRA model. The obtained results show that our model has a security advantage over the existing solution, so we made these changes to reinforce the security of the DRA model.Keywords: Diffie-Hellmann, DRA, RSA, advanced encryption standard
Procedia PDF Downloads 8426508 Efficient Pre-Processing of Single-Cell Assay for Transposase Accessible Chromatin with High-Throughput Sequencing Data
Authors: Fan Gao, Lior Pachter
Abstract:
The primary tool currently used to pre-process 10X Chromium single-cell ATAC-seq data is Cell Ranger, which can take very long to run on standard datasets. To facilitate rapid pre-processing that enables reproducible workflows, we present a suite of tools called scATAK for pre-processing single-cell ATAC-seq data that is 15 to 18 times faster than Cell Ranger on mouse and human samples. Our tool can also calculate chromatin interaction potential matrices, and generate open chromatin signal and interaction traces for cell groups. We use scATAK tool to explore the chromatin regulatory landscape of a healthy adult human brain and unveil cell-type specific features, and show that it provides a convenient and computational efficient approach for pre-processing single-cell ATAC-seq data.Keywords: single-cell, ATAC-seq, bioinformatics, open chromatin landscape, chromatin interactome
Procedia PDF Downloads 15126507 Derivation of Bathymetry from High-Resolution Satellite Images: Comparison of Empirical Methods through Geographical Error Analysis
Authors: Anusha P. Wijesundara, Dulap I. Rathnayake, Nihal D. Perera
Abstract:
Bathymetric information is fundamental importance to coastal and marine planning and management, nautical navigation, and scientific studies of marine environments. Satellite-derived bathymetry data provide detailed information in areas where conventional sounding data is lacking and conventional surveys are inaccessible. The two empirical approaches of log-linear bathymetric inversion model and non-linear bathymetric inversion model are applied for deriving bathymetry from high-resolution multispectral satellite imagery. This study compares these two approaches by means of geographical error analysis for the site Kankesanturai using WorldView-2 satellite imagery. Based on the Levenberg-Marquardt method calibrated the parameters of non-linear inversion model and the multiple-linear regression model was applied to calibrate the log-linear inversion model. In order to calibrate both models, Single Beam Echo Sounding (SBES) data in this study area were used as reference points. Residuals were calculated as the difference between the derived depth values and the validation echo sounder bathymetry data and the geographical distribution of model residuals was mapped. The spatial autocorrelation was calculated by comparing the performance of the bathymetric models and the results showing the geographic errors for both models. A spatial error model was constructed from the initial bathymetry estimates and the estimates of autocorrelation. This spatial error model is used to generate more reliable estimates of bathymetry by quantifying autocorrelation of model error and incorporating this into an improved regression model. Log-linear model (R²=0.846) performs better than the non- linear model (R²=0.692). Finally, the spatial error models improved bathymetric estimates derived from linear and non-linear models up to R²=0.854 and R²=0.704 respectively. The Root Mean Square Error (RMSE) was calculated for all reference points in various depth ranges. The magnitude of the prediction error increases with depth for both the log-linear and the non-linear inversion models. Overall RMSE for log-linear and the non-linear inversion models were ±1.532 m and ±2.089 m, respectively.Keywords: log-linear model, multi spectral, residuals, spatial error model
Procedia PDF Downloads 28926506 Resource Framework Descriptors for Interestingness in Data
Authors: C. B. Abhilash, Kavi Mahesh
Abstract:
Human beings are the most advanced species on earth; it's all because of the ability to communicate and share information via human language. In today's world, a huge amount of data is available on the web in text format. This has also resulted in the generation of big data in structured and unstructured formats. In general, the data is in the textual form, which is highly unstructured. To get insights and actionable content from this data, we need to incorporate the concepts of text mining and natural language processing. In our study, we mainly focus on Interesting data through which interesting facts are generated for the knowledge base. The approach is to derive the analytics from the text via the application of natural language processing. Using semantic web Resource framework descriptors (RDF), we generate the triple from the given data and derive the interesting patterns. The methodology also illustrates data integration using the RDF for reliable, interesting patterns.Keywords: RDF, interestingness, knowledge base, semantic data
Procedia PDF Downloads 15426505 An Assistive Robotic Arm for Defence and Rescue Application
Authors: J. Harrison Kurunathan, R. Jayaparvathy
Abstract:
"Assistive Robotics" is the field that deals with the study of robots that helps in human motion and also empowers human abilities by interfacing the robotic systems to be manipulated by human motion. The proposed model is a robotic arm that works as a haptic interface on the basis on accelerometers and DC motors that will function with respect to the movement of the human muscle. The proposed model would effectively work as a haptic interface that would reduce human effort in the field of defense and rescue. This can be used in very critical conditions like fire accidents to avoid causalities.Keywords: accelerometers, haptic interface, servo motors, signal processing
Procedia PDF Downloads 38526504 The Patterns of Cross-Sentence: An Event-Related Potential Study of Mathematical Word Problem
Authors: Tien-Ching Yao, Ching-Ching Lu
Abstract:
Understanding human language processing is one of the main challenges of current cognitive neuroscience. The aims of the present study were to use a sentence decision task combined with event-related potentials to investigate the psychological reality of "cross-sentence patterns." Therefore, we take the math word problems the experimental materials and use the ERPs' P600 component to verify. In this study, the experimental material consisted of 200 math word problems with three different conditions were used ( multiplication word problems、division word problems type 1、division word problems type 2 ). Eighteen Mandarin native speakers participated in the ERPs study (14 of whom were female). The result of the grand average waveforms suggests a later posterior positivity at around 500ms - 900ms. These findings were tested statistically using repeated measures ANOVAs at the component caused by the stimulus type of different questions. Results suggest that three conditions present significant (P < 0.05) on the Mean Amplitude, Latency, and Peak Amplitude. The result showed the characteristic timing and posterior scalp distribution of a P600 effect. We interpreted these characteristic responses as the psychological reality of "cross-sentence patterns." These results provide insights into the sentence processing issues in linguistic theory and psycholinguistic models of language processing and advance our understanding of how people make sense of information during language comprehension.Keywords: language processing, sentence comprehension, event-related potentials, cross-sentence patterns
Procedia PDF Downloads 14426503 Exploring Pre-Trained Automatic Speech Recognition Model HuBERT for Early Alzheimer’s Disease and Mild Cognitive Impairment Detection in Speech
Authors: Monica Gonzalez Machorro
Abstract:
Dementia is hard to diagnose because of the lack of early physical symptoms. Early dementia recognition is key to improving the living condition of patients. Speech technology is considered a valuable biomarker for this challenge. Recent works have utilized conventional acoustic features and machine learning methods to detect dementia in speech. BERT-like classifiers have reported the most promising performance. One constraint, nonetheless, is that these studies are either based on human transcripts or on transcripts produced by automatic speech recognition (ASR) systems. This research contribution is to explore a method that does not require transcriptions to detect early Alzheimer’s disease (AD) and mild cognitive impairment (MCI). This is achieved by fine-tuning a pre-trained ASR model for the downstream early AD and MCI tasks. To do so, a subset of the thoroughly studied Pitt Corpus is customized. The subset is balanced for class, age, and gender. Data processing also involves cropping the samples into 10-second segments. For comparison purposes, a baseline model is defined by training and testing a Random Forest with 20 extracted acoustic features using the librosa library implemented in Python. These are: zero-crossing rate, MFCCs, spectral bandwidth, spectral centroid, root mean square, and short-time Fourier transform. The baseline model achieved a 58% accuracy. To fine-tune HuBERT as a classifier, an average pooling strategy is employed to merge the 3D representations from audio into 2D representations, and a linear layer is added. The pre-trained model used is ‘hubert-large-ls960-ft’. Empirically, the number of epochs selected is 5, and the batch size defined is 1. Experiments show that our proposed method reaches a 69% balanced accuracy. This suggests that the linguistic and speech information encoded in the self-supervised ASR-based model is able to learn acoustic cues of AD and MCI.Keywords: automatic speech recognition, early Alzheimer’s recognition, mild cognitive impairment, speech impairment
Procedia PDF Downloads 12026502 A Novel Method for Face Detection
Authors: H. Abas Nejad, A. R. Teymoori
Abstract:
Facial expression recognition is one of the open problems in computer vision. Robust neutral face recognition in real time is a major challenge for various supervised learning based facial expression recognition methods. This is due to the fact that supervised methods cannot accommodate all appearance variability across the faces with respect to race, pose, lighting, facial biases, etc. in the limited amount of training data. Moreover, processing each and every frame to classify emotions is not required, as the user stays neutral for the majority of the time in usual applications like video chat or photo album/web browsing. Detecting neutral state at an early stage, thereby bypassing those frames from emotion classification would save the computational power. In this work, we propose a light-weight neutral vs. emotion classification engine, which acts as a preprocessor to the traditional supervised emotion classification approaches. It dynamically learns neutral appearance at Key Emotion (KE) points using a textural statistical model, constructed by a set of reference neutral frames for each user. The proposed method is made robust to various types of user head motions by accounting for affine distortions based on a textural statistical model. Robustness to dynamic shift of KE points is achieved by evaluating the similarities on a subset of neighborhood patches around each KE point using the prior information regarding the directionality of specific facial action units acting on the respective KE point. The proposed method, as a result, improves ER accuracy and simultaneously reduces the computational complexity of ER system, as validated on multiple databases.Keywords: neutral vs. emotion classification, Constrained Local Model, procrustes analysis, Local Binary Pattern Histogram, statistical model
Procedia PDF Downloads 33326501 Multi-Level Air Quality Classification in China Using Information Gain and Support Vector Machine
Authors: Bingchun Liu, Pei-Chann Chang, Natasha Huang, Dun Li
Abstract:
Machine Learning and Data Mining are the two important tools for extracting useful information and knowledge from large datasets. In machine learning, classification is a wildly used technique to predict qualitative variables and is generally preferred over regression from an operational point of view. Due to the enormous increase in air pollution in various countries especially China, Air Quality Classification has become one of the most important topics in air quality research and modelling. This study aims at introducing a hybrid classification model based on information theory and Support Vector Machine (SVM) using the air quality data of four cities in China namely Beijing, Guangzhou, Shanghai and Tianjin from Jan 1, 2014 to April 30, 2016. China's Ministry of Environmental Protection has classified the daily air quality into 6 levels namely Serious Pollution, Severe Pollution, Moderate Pollution, Light Pollution, Good and Excellent based on their respective Air Quality Index (AQI) values. Using the information theory, information gain (IG) is calculated and feature selection is done for both categorical features and continuous numeric features. Then SVM Machine Learning algorithm is implemented on the selected features with cross-validation. The final evaluation reveals that the IG and SVM hybrid model performs better than SVM (alone), Artificial Neural Network (ANN) and K-Nearest Neighbours (KNN) models in terms of accuracy as well as complexity.Keywords: machine learning, air quality classification, air quality index, information gain, support vector machine, cross-validation
Procedia PDF Downloads 23126500 Catchment Yield Prediction in an Ungauged Basin Using PyTOPKAPI
Authors: B. S. Fatoyinbo, D. Stretch, O. T. Amoo, D. Allopi
Abstract:
This study extends the use of the Drainage Area Regionalization (DAR) method in generating synthetic data and calibrating PyTOPKAPI stream yield for an ungauged basin at a daily time scale. The generation of runoff in determining a river yield has been subjected to various topographic and spatial meteorological variables, which integers form the Catchment Characteristics Model (CCM). Many of the conventional CCM models adapted in Africa have been challenged with a paucity of adequate, relevance and accurate data to parameterize and validate the potential. The purpose of generating synthetic flow is to test a hydrological model, which will not suffer from the impact of very low flows or very high flows, thus allowing to check whether the model is structurally sound enough or not. The employed physically-based, watershed-scale hydrologic model (PyTOPKAPI) was parameterized with GIS-pre-processing parameters and remote sensing hydro-meteorological variables. The validation with mean annual runoff ratio proposes a decent graphical understanding between observed and the simulated discharge. The Nash-Sutcliffe efficiency and coefficient of determination (R²) values of 0.704 and 0.739 proves strong model efficiency. Given the current climate variability impact, water planner can now assert a tool for flow quantification and sustainable planning purposes.Keywords: catchment characteristics model, GIS, synthetic data, ungauged basin
Procedia PDF Downloads 31826499 A Corpus-Based Study on the Lexical, Syntactic and Sequential Features across Interpreting Types
Authors: Qianxi Lv, Junying Liang
Abstract:
Among the various modes of interpreting, simultaneous interpreting (SI) is regarded as a ‘complex’ and ‘extreme condition’ of cognitive tasks while consecutive interpreters (CI) do not have to share processing capacity between tasks. Given that SI exerts great cognitive demand, it makes sense to posit that the output of SI may be more compromised than that of CI in the linguistic features. The bulk of the research has stressed the varying cognitive demand and processes involved in different modes of interpreting; however, related empirical research is sparse. In keeping with our interest in investigating the quantitative linguistic factors discriminating between SI and CI, the current study seeks to examine the potential lexical simplification, syntactic complexity and sequential organization mechanism with a self-made inter-model corpus of transcribed simultaneous and consecutive interpretation, translated speech and original speech texts with a total running word of 321960. The lexical features are extracted in terms of the lexical density, list head coverage, hapax legomena, and type-token ratio, as well as core vocabulary percentage. Dependency distance, an index for syntactic complexity and reflective of processing demand is employed. Frequency motif is a non-grammatically-bound sequential unit and is also used to visualize the local function distribution of interpreting the output. While SI is generally regarded as multitasking with high cognitive load, our findings evidently show that CI may impose heavier or taxing cognitive resource differently and hence yields more lexically and syntactically simplified output. In addition, the sequential features manifest that SI and CI organize the sequences from the source text in different ways into the output, to minimize the cognitive load respectively. We reasoned the results in the framework that cognitive demand is exerted both on maintaining and coordinating component of Working Memory. On the one hand, the information maintained in CI is inherently larger in volume compared to SI. On the other hand, time constraints directly influence the sentence reformulation process. The temporal pressure from the input in SI makes the interpreters only keep a small chunk of information in the focus of attention. Thus, SI interpreters usually produce the output by largely retaining the source structure so as to relieve the information from the working memory immediately after formulated in the target language. Conversely, CI interpreters receive at least a few sentences before reformulation, when they are more self-paced. CI interpreters may thus tend to retain and generate the information in a way to lessen the demand. In other words, interpreters cope with the high demand in the reformulation phase of CI by generating output with densely distributed function words, more content words of higher frequency values and fewer variations, simpler structures and more frequently used language sequences. We consequently propose a revised effort model based on the result for a better illustration of cognitive demand during both interpreting types.Keywords: cognitive demand, corpus-based, dependency distance, frequency motif, interpreting types, lexical simplification, sequential units distribution, syntactic complexity
Procedia PDF Downloads 16826498 Information Communication Technology (ICT) Using Management in Nursing College under the Praboromarajchanok Institute
Authors: Suphaphon Udomluck, Pannathorn Chachvarat
Abstract:
Information Communication Technology (ICT) using management is essential for effective decision making in organization. The Concerns Based Adoption Model (CBAM) was employed as the conceptual framework. The purposes of the study were to assess the situation of Information Communication Technology (ICT) using management in College of Nursing under the Praboromarajchanok Institute. The samples were multi – stage sampling of 10 colleges of nursing that participated include directors, vice directors, head of learning groups, teachers, system administrator and responsible for ICT. The total participants were 280; the instrument used were questionnaires that include 4 parts, general information, Information Communication Technology (ICT) using management, the Stage of concern Questionnaires (SoC), and the Levels of Use (LoU) ICT Questionnaires respectively. Reliability coefficients were tested; alpha coefficients were 0.967for Information Communication Technology (ICT) using management, 0.884 for SoC and 0.945 for LoU. The data were analyzed by frequency, percentage, mean, standard deviation, Pearson Product Moment Correlation and Multiple Regression. They were founded as follows: The high level overall score of Information Communication Technology (ICT) using management and issue were administration, hardware, software, and people. The overall score of the Stage of concern (SoC)ICTis at high level and the overall score of the Levels of Use (LoU) ICTis at moderate. The Information Communication Technology (ICT) using management had the positive relationship with the Stage of concern (SoC)ICTand the Levels of Use (LoU) ICT(p < .01). The results of Multiple Regression revealed that administration hardwear, software and people ware could predict SoC of ICT (18.5%) and LoU of ICT (20.8%).The factors that were significantly influenced by SoCs were people ware. The factors that were significantly influenced by LoU of ICT were administration hardware and people ware.Keywords: information communication technology (ICT), management, the concerns-based adoption model (CBAM), stage of concern(SoC), the levels of use(LoU)
Procedia PDF Downloads 30726497 Performance and Limitations of Likelihood Based Information Criteria and Leave-One-Out Cross-Validation Approximation Methods
Authors: M. A. C. S. Sampath Fernando, James M. Curran, Renate Meyer
Abstract:
Model assessment, in the Bayesian context, involves evaluation of the goodness-of-fit and the comparison of several alternative candidate models for predictive accuracy and improvements. In posterior predictive checks, the data simulated under the fitted model is compared with the actual data. Predictive model accuracy is estimated using information criteria such as the Akaike information criterion (AIC), the Bayesian information criterion (BIC), the Deviance information criterion (DIC), and the Watanabe-Akaike information criterion (WAIC). The goal of an information criterion is to obtain an unbiased measure of out-of-sample prediction error. Since posterior checks use the data twice; once for model estimation and once for testing, a bias correction which penalises the model complexity is incorporated in these criteria. Cross-validation (CV) is another method used for examining out-of-sample prediction accuracy. Leave-one-out cross-validation (LOO-CV) is the most computationally expensive variant among the other CV methods, as it fits as many models as the number of observations. Importance sampling (IS), truncated importance sampling (TIS) and Pareto-smoothed importance sampling (PSIS) are generally used as approximations to the exact LOO-CV and utilise the existing MCMC results avoiding expensive computational issues. The reciprocals of the predictive densities calculated over posterior draws for each observation are treated as the raw importance weights. These are in turn used to calculate the approximate LOO-CV of the observation as a weighted average of posterior densities. In IS-LOO, the raw weights are directly used. In contrast, the larger weights are replaced by their modified truncated weights in calculating TIS-LOO and PSIS-LOO. Although, information criteria and LOO-CV are unable to reflect the goodness-of-fit in absolute sense, the differences can be used to measure the relative performance of the models of interest. However, the use of these measures is only valid under specific circumstances. This study has developed 11 models using normal, log-normal, gamma, and student’s t distributions to improve the PCR stutter prediction with forensic data. These models are comprised of four with profile-wide variances, four with locus specific variances, and three which are two-component mixture models. The mean stutter ratio in each model is modeled as a locus specific simple linear regression against a feature of the alleles under study known as the longest uninterrupted sequence (LUS). The use of AIC, BIC, DIC, and WAIC in model comparison has some practical limitations. Even though, IS-LOO, TIS-LOO, and PSIS-LOO are considered to be approximations of the exact LOO-CV, the study observed some drastic deviations in the results. However, there are some interesting relationships among the logarithms of pointwise predictive densities (lppd) calculated under WAIC and the LOO approximation methods. The estimated overall lppd is a relative measure that reflects the overall goodness-of-fit of the model. Parallel log-likelihood profiles for the models conditional on equal posterior variances in lppds were observed. This study illustrates the limitations of the information criteria in practical model comparison problems. In addition, the relationships among LOO-CV approximation methods and WAIC with their limitations are discussed. Finally, useful recommendations that may help in practical model comparisons with these methods are provided.Keywords: cross-validation, importance sampling, information criteria, predictive accuracy
Procedia PDF Downloads 38526496 Mutual Information Based Image Registration of Satellite Images Using PSO-GA Hybrid Algorithm
Authors: Dipti Patra, Guguloth Uma, Smita Pradhan
Abstract:
Registration is a fundamental task in image processing. It is used to transform different sets of data into one coordinate system, where data are acquired from different times, different viewing angles, and/or different sensors. The registration geometrically aligns two images (the reference and target images). Registration techniques are used in satellite images and it is important in order to be able to compare or integrate the data obtained from these different measurements. In this work, mutual information is considered as a similarity metric for registration of satellite images. The transformation is assumed to be a rigid transformation. An attempt has been made here to optimize the transformation function. The proposed image registration technique hybrid PSO-GA incorporates the notion of Particle Swarm Optimization and Genetic Algorithm and is used for finding the best optimum values of transformation parameters. The performance comparision obtained with the experiments on satellite images found that the proposed hybrid PSO-GA algorithm outperforms the other algorithms in terms of mutual information and registration accuracy.Keywords: image registration, genetic algorithm, particle swarm optimization, hybrid PSO-GA algorithm and mutual information
Procedia PDF Downloads 40326495 Developing Integrated Model for Building Design and Evacuation Planning
Authors: Hao-Hsi Tseng, Hsin-Yun Lee
Abstract:
In the process of building design, the designers have to complete the spatial design and consider the evacuation performance at the same time. It is usually difficult to combine the two planning processes and it results in the gap between spatial design and evacuation performance. Then the designers cannot complete an integrated optimal design solution. In addition, the evacuation routing models proposed by previous researchers is different from the practical evacuation decisions in the real field. On the other hand, more and more building design projects are executed by Building Information Modeling (BIM) in which the design content is formed by the object-oriented framework. Thus, the integration of BIM and evacuation simulation can make a significant contribution for designers. Therefore, this research plan will establish a model that integrates spatial design and evacuation planning. The proposed model will provide the support for the spatial design modifications and optimize the evacuation planning. The designers can complete the integrated design solution in BIM. Besides, this research plan improves the evacuation routing method to make the simulation results more practical. The proposed model will be applied in a building design project for evaluation and validation when it will provide the near-optimal design suggestion. By applying the proposed model, the integration and efficiency of the design process are improved and the evacuation plan is more useful. The quality of building spatial design will be better.Keywords: building information modeling, evacuation, design, floor plan
Procedia PDF Downloads 45026494 A Mixing Matrix Estimation Algorithm for Speech Signals under the Under-Determined Blind Source Separation Model
Authors: Jing Wu, Wei Lv, Yibing Li, Yuanfan You
Abstract:
The separation of speech signals has become a research hotspot in the field of signal processing in recent years. It has many applications and influences in teleconferencing, hearing aids, speech recognition of machines and so on. The sounds received are usually noisy. The issue of identifying the sounds of interest and obtaining clear sounds in such an environment becomes a problem worth exploring, that is, the problem of blind source separation. This paper focuses on the under-determined blind source separation (UBSS). Sparse component analysis is generally used for the problem of under-determined blind source separation. The method is mainly divided into two parts. Firstly, the clustering algorithm is used to estimate the mixing matrix according to the observed signals. Then the signal is separated based on the known mixing matrix. In this paper, the problem of mixing matrix estimation is studied. This paper proposes an improved algorithm to estimate the mixing matrix for speech signals in the UBSS model. The traditional potential algorithm is not accurate for the mixing matrix estimation, especially for low signal-to noise ratio (SNR).In response to this problem, this paper considers the idea of an improved potential function method to estimate the mixing matrix. The algorithm not only avoids the inuence of insufficient prior information in traditional clustering algorithm, but also improves the estimation accuracy of mixing matrix. This paper takes the mixing of four speech signals into two channels as an example. The results of simulations show that the approach in this paper not only improves the accuracy of estimation, but also applies to any mixing matrix.Keywords: DBSCAN, potential function, speech signal, the UBSS model
Procedia PDF Downloads 13026493 Digital Reconstruction of Museum's Statue Using 3D Scanner for Cultural Preservation in Indonesia
Authors: Ahmad Zaini, F. Muhammad Reza Hadafi, Surya Sumpeno, Muhtadin, Mochamad Hariadi
Abstract:
The lack of information about museum’s collection reduces the number of visits of museum. Museum’s revitalization is an urgent activity to increase the number of visits. The research's roadmap is building a web-based application that visualizes museum in the virtual form including museum's statue reconstruction in the form of 3D. This paper describes implementation of three-dimensional model reconstruction method based on light-strip pattern on the museum statue using 3D scanner. Noise removal, alignment, meshing and refinement model's processes is implemented to get a better 3D object reconstruction. Model’s texture derives from surface texture mapping between object's images with reconstructed 3D model. Accuracy test of dimension of the model is measured by calculating relative error of virtual model dimension compared against the original object. The result is realistic three-dimensional model textured with relative error around 4.3% to 5.8%.Keywords: 3D reconstruction, light pattern structure, texture mapping, museum
Procedia PDF Downloads 457