Search results for: Lecturers’ Training.

Authors: Hadi Veisi, Mansour Jamzad

Abstract:

In this paper we present an adaptive method for image compression that is based on complexity level of the image. The basic compressor/de-compressor structure of this method is a multilayer perceptron artificial neural network. In adaptive approach different Back-Propagation artificial neural networks are used as compressor and de-compressor and this is done by dividing the image into blocks, computing the complexity of each block and then selecting one network for each block according to its complexity value. Three complexity measure methods, called Entropy, Activity and Pattern-based are used to determine the level of complexity in image blocks and their ability in complexity estimation are evaluated and compared. In training and evaluation, each image block is assigned to a network based on its complexity value. Best-SNR is another alternative in selecting compressor network for image blocks in evolution phase which chooses one of the trained networks such that results best SNR in compressing the input image block. In our evaluations, best results are obtained when overlapping the blocks is allowed and choosing the networks in compressor is based on the Best-SNR. In this case, the results demonstrate superiority of this method comparing with previous similar works and JPEG standard coding.

Keywords: Adaptive image compression, Image complexity, Multi-layer perceptron neural network, JPEG Standard, PSNR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2222

Authors: Getaye F. Gelaw

Abstract:

The purpose of this study was to investigate the key physical and physiological characteristics of 16 elite male Ethiopian national team distance runners, who have an average age of 28.1 ± 4.3 years, a height of 175.0 ± 5.6 cm, a weight of 59.1 ± 3.9 kg, a BMI of 19.6 ± 1.5, and training age of 10.1 ± 5.1 yrs. The average weekly distance is 196.3 ± 13.8 km, the average 10,000 m time is 27:14 ± 0.5 min sec, the average half marathon time is 59:30 ± 0.6 min sec, the average marathon time is 2:04:20 ± 2.7 hr min ss. In addition, the average Cooper test (12-minute run test) is 4525.4 ± 139.7 meters, and the average VO2 max is 90.8 ± 3.1 ml/kg/m. All athletes have a high profile and compete on the international label, and according to the World Athletics athletes' ranking system in 2021, 56.3% of the 16 participants were platinum label status, while the remaining 43.7% were gold label status-completed an incremental treadmill test for the assessment of VO2peak, submaximal running, lactate threshold and test during which they ran continuously at 21 km/h. The laboratory determined VO2peak was 91.4 ± 1.7 mL/kg/min with anaerobic threshold of 74.2 ± 1.6 mL/min/kg and VO2 max 81%. The speed at the Anaerobic Threshold (AT) is 15.9 ± 0.6 kmh and the altitude is 4.0%. The Respiratory Compensation Point (RCP) was reached at 88.7 ± 1.1 mL/min/kg and 97% of VO2 max. On RCP, the speed is 17.6 ± 0.4 km/h and the altitude/slope are 5.5%, and the speed at Maximum effort is 19.5 ± 1.5 and the elevation is 6.0%. The data also suggest that Ethiopian distance top athletes have considerably higher VO2 max values than those found in earlier research.

Keywords: Long-distance running, Ethiopians, VO2 max, World Athletics, Anthropometric.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 274

Authors: Shashank N. Mathur, Anil K. Ahlawat, Virendra P. Vishwakarma

Abstract:

In this paper, a comparative study of application of supervised and unsupervised learning algorithms on illumination invariant face recognition has been carried out. The supervised learning has been carried out with the help of using a bi-layered artificial neural network having one input, two hidden and one output layer. The gradient descent with momentum and adaptive learning rate back propagation learning algorithm has been used to implement the supervised learning in a way that both the inputs and corresponding outputs are provided at the time of training the network, thus here is an inherent clustering and optimized learning of weights which provide us with efficient results.. The unsupervised learning has been implemented with the help of a modified Counterpropagation network. The Counterpropagation network involves the process of clustering followed by application of Outstar rule to obtain the recognized face. The face recognition system has been developed for recognizing faces which have varying illumination intensities, where the database images vary in lighting with respect to angle of illumination with horizontal and vertical planes. The supervised and unsupervised learning algorithms have been implemented and have been tested exhaustively, with and without application of histogram equalization to get efficient results.

Keywords: Artificial Neural Networks, back propagation, Counterpropagation networks, face recognition, learning algorithms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1686

Authors: Wenguang Ding, Yang Wu, Xia Wang, Yayu Gao

Abstract:

Biogas, a clean renewable energy, is attracting a growing concern of researchers and professionals in many fields. Based on the natural and climatic conditions in semi-arid regions of northwestern China, the present study introduces a specifically-designed family-size biogas plant (with a digester of 10m3) with manure and urine of animals and humanity as raw materials. The biogas plant is applicable to areas with altitudes of more than 2000 meters in northwestern China. In addition to the installation cost, a little operational expenditure, structure, characteristics, benefits of this small-scale biogas plant, this article introduces a wide range of specific popularization methods such as training, financial support, guided tour to the biogas plant, community-based group study and delivery of operational manuals. The feasibility of the biogas plant is explored on the basis of the availability of the raw materials. Simple operations contained in the current work increase the possibility of the wide use of this small-scale biogas plant in similar regions of the world.

Keywords: biogas, family-size biogas plant, northwestern China, popularization

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2773

Authors: L. Parisi

Abstract:

In this research work, neural networks were applied to classify two types of hip joint implants based on the relative hip joint implant side speed and three components of each ground reaction force. The condition of walking gait at normal velocity was used and carried out with each of the two hip joint implants assessed. Ground reaction forces’ kinetic temporal changes were considered in the first approach followed but discarded in the second one. Ground reaction force components were obtained from eighteen patients under such gait condition, half of which had a hip implant type I-II, whilst the other half had the hip implant, defined as type III by Orthoload®. After pre-processing raw gait kinetic data and selecting the time frames needed for the analysis, the ground reaction force components were used to train a MLP neural network, which learnt to distinguish the two hip joint implants in the abovementioned condition. Further to training, unknown hip implant side and ground reaction force components were presented to the neural networks, which assigned those features into the right class with a reasonably high accuracy for the hip implant type I-II and the type III. The results suggest that neural networks could be successfully applied in the performance assessment of hip joint implants.

Keywords: Kinemic gait data, Neural networks, Hip joint implant, Hip arthroplasty, Rehabilitation Engineering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1798

Authors: Yang Meng, James L. Patnao

Abstract:

With the rapid development of information technology and the impact of the epidemic environment, the traditional teaching model can no longer meet the requirements of the development of the times. The development of teaching mechanisms is the inevitable trend of the future development of higher education. We must further promote the informatization of higher education in teaching practice, let modern information technology penetrate and practice in classroom teaching, and provide promising opportunities for the high-quality development of higher education. This article, mainly through the distribution of questionnaires to teachers of colleges and universities, aims to understand the degree of informatization in the teaching of colleges and universities. And on the basis of domestic and foreign scholars' research on higher education informatization, it analyzes the existing problems, and finds the optimal solution based on the needs of education and teaching development. According to the survey results, most college teachers will use information technology in teaching practice, but the information technology teaching tools used by teachers are relatively simple, and most of them use only slides. In addition, backward informatization infrastructure and less informatization training are the main challenges facing the current teaching informatization construction. If colleges and universities can make good use of information technology and multimedia technology and combine it with traditional teaching, it will definitely promote the development of college education and further promote the modernization and informatization of higher education.

Keywords: Higher education, teaching practice, informatization construction, e-education.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 230

Authors: Yi-Shiang Shiu, Meng-Lung Lin, Kang-Tsung Chang, Tzu-How Chu

Abstract:

Most paddy rice fields in East Asia are small parcels, and the weather conditions during the growing season are usually cloudy. FORMOSAT-2 multi-spectral images have an 8-meter resolution and one-day recurrence, ideal for mapping paddy rice fields in East Asia. To map rice fields, this study first determined the transplanting and the most active tillering stages of paddy rice and then used multi-temporal images to distinguish different growing characteristics between paddy rice and other ground covers. The unsupervised ISODATA (iterative self-organizing data analysis techniques) and supervised maximum likelihood were both used to discriminate paddy rice fields, with training areas automatically derived from ten-year cultivation parcels in Taiwan. Besides original bands in multi-spectral images, we also generated normalized difference vegetation index and experimented with object-based pre-classification and post-classification. This paper discusses results of different image classification methods in an attempt to find a precise and automatic solution to mapping paddy rice in Taiwan.

Keywords: paddy rice fields; multi-temporal; FORMOSAT-2images, normalized difference vegetation index, object-basedclassification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1796

Authors: Lo Kar Yin, Law Ka Mei

Abstract:

Architectural, engineering, construction and operations (AECO) industry practitioners have been well adapting to the dynamic construction market from the fundamental training of its disciplines. As further triggered by the pandemic since 2019, great steps are taken in virtual environment and the best collaboration is strived with project teams without boundaries. With adoption of Building Information Modeling-based approach and qualitative analysis, this paper is to review quantity take-off (QTO) and cost estimation process through modeling techniques in liaison with suppliers, fabricators, subcontractors, contractors, designers, consultants and services providers in the construction industry value chain for automatic project cost budgeting, project cost control and cost evaluation on design options of in-situ reinforced-concrete construction and Modular Integrated Construction (MiC) at design stage, variation of works and cash flow/spending analysis at construction stage as far as practicable, with a view to sharing the findings for enhancing mutual trust and co-operation among AECO industry practitioners. It is to foster development through a common prototype of design and build project delivery method in NEC4 Engineering and Construction Contract (ECC) Options A and C.

Keywords: Building Information Modeling, cost estimation, quantity take-off, modeling techniques.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 709

Authors: Konstantinos Perifanos, Eirini Florou, Dionysis Goutsos

Abstract:

This paper presents and benchmarks a number of end-to-end Deep Learning based models for metaphor detection in Greek. We combine Convolutional Neural Networks and Recurrent Neural Networks with representation learning to bear on the metaphor detection problem for the Greek language. The models presented achieve exceptional accuracy scores, significantly improving the previous state-of-the-art results, which had already achieved accuracy 0.82. Furthermore, no special preprocessing, feature engineering or linguistic knowledge is used in this work. The methods presented achieve accuracy of 0.92 and F-score 0.92 with Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory networks (LSTMs). Comparable results of 0.91 accuracy and 0.91 F-score are also achieved with bidirectional Gated Recurrent Units (GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The models are trained and evaluated only on the basis of training tuples, the related sentences and their labels. The outcome is a state-of-the-art collection of metaphor detection models, trained on limited labelled resources, which can be extended to other languages and similar tasks.

Keywords: Metaphor detection, deep learning, representation learning, embeddings.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 553

Authors: Paolo Pilloni, Fabrizio Mulas, Salvatore Carta

Abstract:

Nowadays, several research studies point up that an active lifestyle is essential for physical and mental health benefits. Mobile phones have greatly influenced people’s habits and attitudes also in the way they exercise. Our research work is mainly focused on investigating how to exploit mobile technologies to favour people’s exertion experience. To this end, we developed an exertion framework users can exploit through a real world mobile application, called EverywhereSport Run (EWRun), designed to act as a virtual personal trainer to support runners during their trainings. In this work, inspired by both previous findings in the field of interaction design for people with visual impairments, feedback gathered from real users of our framework, and positive results obtained from two experimentations, we present some new interaction facilities we designed to enhance the interaction experience during a training. The positive obtained results helped us to derive some interaction design recommendations we believe will be a valid support for designers of future mobile systems conceived to be used in circumstances where there are limited possibilities of interaction.

Keywords: Human Computer Interaction, Interaction Design Guidelines, Persuasive Mobile Technologies for Sport and Health.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1946

Authors: Sarah K. Taylor, Miratun M. Saharuddin, Zabri A. Talib

Abstract:

Cybercrime is on the rise, and yet many Law Enforcement Agencies (LEAs) in Malaysia have no Digital Forensics Laboratory (DFL) to assist them in the attrition and analysis of digital evidence. From the estimated number of 30 LEAs in Malaysia, sadly, only eight of them owned a DFL. All of the DFLs are concentrated in the capital of Malaysia and none at the state level. LEAs are still depending on the national DFL (CyberSecurity Malaysia) even for simple and straightforward cases. A survey was conducted among LEAs in Malaysia owning a DFL to understand their history of establishing the DFL, the challenges that they faced and the significance of the DFL to their case investigation. The results showed that the while some LEAs faced no challenge in establishing a DFL, some of them took seven to 10 years to do so. The reason was due to the difficulty in convincing their management because of the high costs involved. The results also revealed that with the establishment of a DFL, LEAs were better able to get faster forensic result and to meet agency’s timeline expectation. It is also found that LEAs were also able to get more meaningful forensic results on cases that require niche expertise, compared to sending off cases to the national DFL. Other than that, cases are getting more complex, and hence, a continuous stream of budget for equipment and training is inevitable. The result derived from the study is hoped to be used by other LEAs in justifying to their management the benefits of establishing an in-house DFL.

Keywords: Digital forensics, digital forensics laboratory, digital evidence, law enforcement agency.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1497

Authors: Sarah Beaver, Renee Bryce

Abstract:

Audiograms detect hearing impairment, but missing values pose problems. This work explores imputations in an attempt to improve accuracy. This work implements Linear Regression, Lasso, Linear Support Vector Regression, Bayesian Ridge, K Nearest Neighbors (KNN), and Random Forest machine learning techniques to impute audiogram frequencies ranging from 125 Hz to 8000 Hz. The data contain patients who had or were candidates for cochlear implants. Accuracy is compared across two different Nested Cross-Validation k values. Over 4000 audiograms were used from 800 unique patients. Additionally, training on data combines and compares left and right ear audiograms versus single ear side audiograms. The accuracy achieved using Root Mean Square Error (RMSE) values for the best models for Random Forest ranges from 4.74 to 6.37. The R2 values for the best models for Random Forest ranges from .91 to .96. The accuracy achieved using RMSE values for the best models for KNN ranges from 5.00 to 7.72. The R2 values for the best models for KNN ranges from .89 to .95. The best imputation models received R2 between .89 to .96 and RMSE values less than 8dB. We also show that the accuracy of classification predictive models performed better with our imputation models versus constant imputations by a two percent increase.

Keywords: Machine Learning, audiograms, data imputations, single imputations.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 160

Authors: G. Meyer, M. Klewer, P. Nyhuis

Abstract:

Constantly changing economic conditions require companies to design their production to be more economical, innovative, and flexible. Since workers have a decisive influence on cost, time, and quality, e.g. by monitoring indicators that determine quality, by developing processes more resistant to disturbances, or by monitoring environmental standards, a focus on personnel as a production factor is needed. This presupposes the efficient use and systematic enhancement of employees’ existing competences since greater consideration of these aspects in work planning will help to enhance competitiveness. The aim of the research project ‘Integrated Technology- and Competence-based Work Planning in Socio-Technical Systems’ is to develop a new work planning method that combines technology with work science by incorporating employees’ skills as a quality indicator. For employee competences to increase competitiveness, it is first of all necessary to assess how competences affect cost, time, and quality. A model for deriving predictions about the effects of competence-based parameters on these strategic business objectives is developed in this paper.

Keywords: Competence management, education and training, employee competences, one-factor-at-a-time method, work planning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1542

Authors: Eric P. Jiang

Abstract:

As the Internet continues to grow at a rapid pace as the primary medium for communications and commerce and as telecommunication networks and systems continue to expand their global reach, digital information has become the most popular and important information resource and our dependence upon the underlying cyber infrastructure has been increasing significantly. Unfortunately, as our dependency has grown, so has the threat to the cyber infrastructure from spammers, attackers and criminal enterprises. In this paper, we propose a new machine learning based network intrusion detection framework for cyber security. The detection process of the framework consists of two stages: model construction and intrusion detection. In the model construction stage, a semi-supervised machine learning algorithm is applied to a collected set of network audit data to generate a profile of normal network behavior and in the intrusion detection stage, input network events are analyzed and compared with the patterns gathered in the profile, and some of them are then flagged as anomalies should these events are sufficiently far from the expected normal behavior. The proposed framework is particularly applicable to the situations where there is only a small amount of labeled network training data available, which is very typical in real world network environments.

Keywords: classification, data analysis and mining, network intrusion detection, semi-supervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1795

Authors: Mariyam Arif, Ye Liu, Israr Ul Haq, Ahsan Ashfaq

Abstract:

High cost of fossil fuels and intensifying installations of alternate energy generation sources are intimidating main challenges in power systems. Making accurate load forecasting an important and challenging task for optimal energy planning and management at both distribution and generation side. There are many techniques to forecast load but each technique comes with its own limitation and requires data to accurately predict the forecast load. Artificial Neural Network (ANN) is one such technique to efficiently forecast the load. Comparison between two different ranges of input datasets has been applied to dynamic ANN technique using MATLAB Neural Network Toolbox. It has been observed that selection of input data on training of a network has significant effects on forecasted results. Day-wise input data forecasted the load accurately as compared to year-wise input data. The forecasted load is then distributed among the six generators by using the linear programming to get the optimal point of generation. The algorithm is then verified by comparing the results of each generator with their respective generation limits.

Keywords: Artificial neural networks, demand-side management, economic dispatch, linear programming, power generation dispatch.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 914

Authors: Wang Liguang, Zhang Xueqing

Abstract:

The build-operate-transfer (BOT) project delivery system has provided effective routes to mobilize private sector funds, innovative technologies, management skills and operational efficiencies for public infrastructure development and have been widely used in China during the last 20 years. Many BOT projects in China will be smoothly transferred to the government soon and the transfer stage, which is considered as the last stage, must be studied carefully and handled well to achieve the overall success of BOT projects. There will be many issues faced by both the public sector and private sector in the transfer stage of BOT projects, including project post-assessment, technology and documents transfer, personal training and staff transition, etc. and sometimes additional legislation is needed for future operation and management of facilities. However, most previous studies focused on the bidding, financing, and building and operation stages instead of transfer stage. This research identifies nine key issues in the transfer stage of BOT projects through a comprehensive study on three cases in China, and the expert interview and expert discussion meetings are held to validate the key issues and give detail analysis. A proposed framework of transfer management is prepared based on the experiences derived and lessons drawn from the case studies and expert interview and discussions, which is expected to improve the transfer management of BOT projects in practice.

Keywords: BOT project, key issues, transfer management transfer stage.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1052

Authors: M. F. Yaqub, I. Gondal, J. Kamruzzaman

Abstract:

Wavelet transform has been extensively used in machine fault diagnosis and prognosis owing to its strength to deal with non-stationary signals. The existing Wavelet transform based schemes for fault diagnosis employ wavelet decomposition of the entire vibration frequency which not only involve huge computational overhead in extracting the features but also increases the dimensionality of the feature vector. This increase in the dimensionality has the tendency to 'over-fit' the training data and could mislead the fault diagnostic model. In this paper a novel technique, envelope wavelet packet transform (EWPT) is proposed in which features are extracted based on wavelet packet transform of the filtered envelope signal rather than the overall vibration signal. It not only reduces the computational overhead in terms of reduced number of wavelet decomposition levels and features but also improves the fault detection accuracy. Analytical expressions are provided for the optimal frequency resolution and decomposition level selection in EWPT. Experimental results with both actual and simulated machine fault data demonstrate significant gain in fault detection ability by EWPT at reduced complexity compared to existing techniques.

Keywords: Envelope Detection, Wavelet Transform, Bearing Faults, Machine Health Monitoring.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1958

Authors: Yi Chao Ma, Cheng Siong Chin, Wai Lok Woo

Abstract:

Since the last decade, there has been a rapid growth in digital multimedia, such as high-resolution media files and threedimentional movies. Hence, there is a need for large digital storage such as Hard Disk Drive (HDD). As such, users expect to have a quieter HDD in their laptop. In this paper, a jury test has been conducted on a group of 34 people where 17 of them are students who are the potential consumer, and the remaining are engineers who know the HDD. A total 13 HDD sound samples have been selected from over hundred HDD noise recordings. These samples are selected based on an agreed subjective feeling. The samples are played to the participants using head acoustic playback system, which enabled them to experience as similar as possible the same environment as have been recorded. Analysis has been conducted and the obtained results have indicated different group has different perception over the noises. Two neural network-based acoustic annoyance models are established based on back propagation neural network. Four psychoacoustic metrics, loudness, sharpness, roughness and fluctuation strength, are used as the input of the model, and the subjective evaluation results are taken as the output. The developed models are reasonably accurate in simulating both training and test samples.

Keywords: Hard disk drive noise, jury test, neural network model, psychoacoustic annoyance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1533

Authors: Wen-Chao Tang, Tang-Yi Liu, Ming Gao, Gang Xu, Hua-Yuan Yang

Abstract:

This study developed a method for teaching acupuncture manipulation in small groups optimized with the theory of motor learning. Sixty acupuncture students and their teacher participated in our research. Motion videos were recorded of their manipulations using the lifting-thrusting method. These videos were analyzed using Simi Motion software to acquire the movement parameters of the thumb tip. The parameter velocity curves along Y axis was used to generate small teaching groups clustered by a self-organized map (SOM) and K-means. Ten groups were generated. All the targeted instruction based on the comparative results groups as well as the videos of teacher and student was provided to the members of each group respectively. According to the theory and research of motor learning, the factors or technologies such as video instruction, observational learning, external focus and summary feedback were integrated into this teaching method. Such efforts were desired to improve and enhance the effectiveness of current acupuncture teaching methods in limited classroom teaching time and extracurricular training.

Keywords: Acupuncture, group teaching, video instruction, observational learning, external focus, summary feedback.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 594

Authors: Jin Woong Lee, Kyuman Cho, Taehoon Kim

Abstract:

The application of constructability is increasingly required not only in the construction phase but also in the whole project stage. In particular, the proper application of construction experience and knowledge during the design phase enables the minimization of inefficiencies such as design changes and improvements in constructability during the construction phase. In order to apply knowledge effectively, engineering technology efforts should be implemented with design progress. Among many engineering technologies, engineering for temporary works, including facilities, equipment, and other related construction methods, is important to improve constructability. Therefore, as basic research, this study investigates the applicability of temporary work engineering during the design phase in the building construction industry. As a result, application of temporary work engineering has a greater impact on construction cost reduction and constructability improvement. In contrast to the existing design-bid-build method, the turn-key and CM (construct management) procurement methods currently being implemented in Korea are expected to have a significant impact on the direction of temporary work engineering. To introduce temporary work engineering, expert/professional organization training is first required, and a lack of client awareness should be preferentially improved. The results of this study are expected to be useful as reference material for the development of more effective temporary work engineering tasks and work processes in the future.

Keywords: Temporary work engineering, design phase, constructability, building construction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 972

Authors: Samit Ari, Goutam Saha

Abstract:

Artificial Neural Network (ANN) has been extensively used for classification of heart sounds for its discriminative training ability and easy implementation. However, it suffers from overparameterization if the number of nodes is not chosen properly. In such cases, when the dataset has redundancy within it, ANN is trained along with this redundant information that results in poor validation. Also a larger network means more computational expense resulting more hardware and time related cost. Therefore, an optimum design of neural network is needed towards real-time detection of pathological patterns, if any from heart sound signal. The aims of this work are to (i) select a set of input features that are effective for identification of heart sound signals and (ii) make certain optimum selection of nodes in the hidden layer for a more effective ANN structure. Here, we present an optimization technique that involves Singular Value Decomposition (SVD) and QR factorization with column pivoting (QRcp) methodology to optimize empirically chosen over-parameterized ANN structure. Input nodes present in ANN structure is optimized by SVD followed by QRcp while only SVD is required to prune undesirable hidden nodes. The result is presented for classifying 12 common pathological cases and normal heart sound.

Keywords: ANN, Classification of heart diseases, murmurs, optimization, Phonocardiogram, QRcp, SVD.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2071

Authors: Wanhyun Cho, Soonja Kang, Sangkyoon Kim, Soonyoung Park

Abstract:

In this paper, we present the human action recognition method using the variational Bayesian HMM with the Dirichlet process mixture (DPM) of the Gaussian-Wishart emission model (GWEM). First, we define the Bayesian HMM based on the Dirichlet process, which allows an infinite number of Gaussian-Wishart components to support continuous emission observations. Second, we have considered an efficient variational Bayesian inference method that can be applied to drive the posterior distribution of hidden variables and model parameters for the proposed model based on training data. And then we have derived the predictive distribution that may be used to classify new action. Third, the paper proposes a process of extracting appropriate spatial-temporal feature vectors that can be used to recognize a wide range of human behaviors from input video image. Finally, we have conducted experiments that can evaluate the performance of the proposed method. The experimental results show that the method presented is more efficient with human action recognition than existing methods.

Keywords: Human action recognition, Bayesian HMM, Dirichlet process mixture model, Gaussian-Wishart emission model, Variational Bayesian inference, Prior distribution and approximate posterior distribution, KTH dataset.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1005

Authors: Md. Ashikur Rahman Khan, M. M. Rahman, K. Kadirgama, M.A. Maleque, Rosli A. Bakar

Abstract:

Conventionally the selection of parameters depends intensely on the operator-s experience or conservative technological data provided by the EDM equipment manufacturers that assign inconsistent machining performance. The parameter settings given by the manufacturers are only relevant with common steel grades. A single parameter change influences the process in a complex way. Hence, the present research proposes artificial neural network (ANN) models for the prediction of surface roughness on first commenced Ti-15-3 alloy in electrical discharge machining (EDM) process. The proposed models use peak current, pulse on time, pulse off time and servo voltage as input parameters. Multilayer perceptron (MLP) with three hidden layer feedforward networks are applied. An assessment is carried out with the models of distinct hidden layer. Training of the models is performed with data from an extensive series of experiments utilizing copper electrode as positive polarity. The predictions based on the above developed models have been verified with another set of experiments and are found to be in good agreement with the experimental results. Beside this they can be exercised as precious tools for the process planning for EDM.

Keywords: Ti-15l-3, surface roughness, copper, positive polarity, multi-layered perceptron.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1907

Authors: Parvinder S. Sandhu, Roma Jaswal, Sandeep Khimta, Shailendra Singh

Abstract:

As the majority of faults are found in a few of its modules so there is a need to investigate the modules that are affected severely as compared to other modules and proper maintenance need to be done in time especially for the critical applications. As, Neural networks, which have been already applied in software engineering applications to build reliability growth models predict the gross change or reusability metrics. Neural networks are non-linear sophisticated modeling techniques that are able to model complex functions. Neural network techniques are used when exact nature of input and outputs is not known. A key feature is that they learn the relationship between input and output through training. In this present work, various Neural Network Based techniques are explored and comparative analysis is performed for the prediction of level of need of maintenance by predicting level severity of faults present in NASA-s public domain defect dataset. The comparison of different algorithms is made on the basis of Mean Absolute Error, Root Mean Square Error and Accuracy Values. It is concluded that Generalized Regression Networks is the best algorithm for classification of the software components into different level of severity of impact of the faults. The algorithm can be used to develop model that can be used for identifying modules that are heavily affected by the faults.

Keywords: Neural Network, Software faults, Software Metric.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1575

Authors: Thuy Thi Nguyen, Nguyen Dang Binh, Horst Bischof

Abstract:

In this work, we present a novel active learning approach for learning a visual object detection system. Our system is composed of an active learning mechanism as wrapper around a sub-algorithm which implement an online boosting-based learning object detector. In the core is a combination of a bootstrap procedure and a semi automatic learning process based on the online boosting procedure. The idea is to exploit the availability of classifier during learning to automatically label training samples and increasingly improves the classifier. This addresses the issue of reducing labeling effort meanwhile obtain better performance. In addition, we propose a verification process for further improvement of the classifier. The idea is to allow re-update on seen data during learning for stabilizing the detector. The main contribution of this empirical study is a demonstration that active learning based on an online boosting approach trained in this manner can achieve results comparable or even outperform a framework trained in conventional manner using much more labeling effort. Empirical experiments on challenging data set for specific object deteciton problems show the effectiveness of our approach.

Keywords: Computer vision, object detection, online boosting, active learning, labeling complexity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1784

Authors: Christian Endisch, Christoph Hackl, Dierk Schröder

Abstract:

This paper presents an exact pruning algorithm with adaptive pruning interval for general dynamic neural networks (GDNN). GDNNs are artificial neural networks with internal dynamics. All layers have feedback connections with time delays to the same and to all other layers. The structure of the plant is unknown, so the identification process is started with a larger network architecture than necessary. During parameter optimization with the Levenberg- Marquardt (LM) algorithm irrelevant weights of the dynamic neural network are deleted in order to find a model for the plant as simple as possible. The weights to be pruned are found by direct evaluation of the training data within a sliding time window. The influence of pruning on the identification system depends on the network architecture at pruning time and the selected weight to be deleted. As the architecture of the model is changed drastically during the identification and pruning process, it is suggested to adapt the pruning interval online. Two system identification examples show the architecture selection ability of the proposed pruning approach.

Keywords: System identification, dynamic neural network, recurrentneural network, GDNN, optimization, Levenberg Marquardt, realtime recurrent learning, network pruning, quasi-online learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1937

Authors: Zeineb Deymi-Gheriani

Abstract:

In the last two decades, one can clearly observe a boom of interest for e-learning and web-supported programs. However, one can also notice that many of these programs focus on the accumulation and delivery of content generally as a business industry with no much concern for theoretical underpinnings. The existing research, at least in online English language teaching (ELT), has demonstrated a lack of an effective online teaching pedagogy anchored in a well-defined theoretical framework. Hence, this paper comes as an attempt to present constructivism as one of the theoretical bases for the design of an effective online language teaching pedagogy which is at the same time technologically intelligent and theoretically informed to help envision how education can best take advantage of the information and communication technology (ICT) tools. The present paper discusses the key principles underlying constructivism, its implications for online language teaching design, as well as its limitations that should be avoided in the e-learning instructional design. Although the paper is theoretical in nature, essentially based on an extensive literature survey on constructivism, it does have practical illustrations from an action research conducted by the author both as an e-tutor of English using Moodle online educational platform at the Virtual University of Tunis (VUT) from 2007 up to 2010 and as a face-to-face (F2F) English teaching practitioner in the Professional Certificate of English Language Teaching Training (PCELT) at AMIDEAST, Tunisia (April-May, 2013).

Keywords: Active learning, constructivism, experiential learning, Piaget, Vygotsky.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1469

Authors: Malin Isaksson

Abstract:

Teaching French as a foreign language usually implies teaching French literature, especially in higher education. Training university students in literary reading in a foreign language requires addressing several aspects at the same time: the (foreign) language, the poetic language, the aesthetic aspects of the studied works, and various interpretations of them. A pilot study sought to test a teaching model that would support students in learning to perform competent readings and short analyses of French literary works, in a rather independent manner. This shared practice paper describes the use of a flipped classroom method in two French literature courses, a campus course and an online course, and suggests that the teaching model may provide efficient tools for teaching literary reading and analysis in a foreign language. The teaching model builds on a high level of student activity and focuses on attentive reading, meta-perspectives such as theoretical concepts, individual analyses by students where said concepts are applied, and group discussions of the studied texts and of possible interpretations.

Keywords: Shared practice, flipped classroom, literature in foreign language studies, teaching literature analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 770

Authors: H. Shayeghi, H. A. Shayanfar, G. Azimi

Abstract:

Short-Term Load Forecasting (STLF) plays an important role for the economic and secure operation of power systems. In this paper, Continuous Genetic Algorithm (CGA) is employed to evolve the optimum large neural networks structure and connecting weights for one-day ahead electric load forecasting problem. This study describes the process of developing three layer feed-forward large neural networks for load forecasting and then presents a heuristic search algorithm for performing an important task of this process, i.e. optimal networks structure design. The proposed method is applied to STLF of the local utility. Data are clustered due to the differences in their characteristics. Special days are extracted from the normal training sets and handled separately. In this way, a solution is provided for all load types, including working days and weekends and special days. We find good performance for the large neural networks. The proposed methodology gives lower percent errors all the time. Thus, it can be applied to automatically design an optimal load forecaster based on historical data.

Keywords: Feed-forward Large Neural Network, Short-TermLoad Forecasting, Continuous Genetic Algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1830

Authors: Madhusudan Purohit, Stephen Philip, Bharathkumar Inturi

Abstract:

In this paper we report the quantitative structure activity relationship of novel bis-triazole derivatives for predicting the activity profile. The full model encompassed a dataset of 46 Bis- triazoles. Tripos Sybyl X 2.0 program was used to conduct CoMSIA QSAR modeling. The Partial Least-Squares (PLS) analysis method was used to conduct statistical analysis and to derive a QSAR model based on the field values of CoMSIA descriptor. The compounds were divided into test and training set. The compounds were evaluated by various CoMSIA parameters to predict the best QSAR model. An optimum numbers of components were first determined separately by cross-validation regression for CoMSIA model, which were then applied in the final analysis. A series of parameters were used for the study and the best fit model was obtained using donor, partition coefficient and steric parameters. The CoMSIA models demonstrated good statistical results with regression coefficient (r²) and the cross-validated coefficient (q²) of 0.575 and 0.830 respectively. The standard error for the predicted model was 0.16322. In the CoMSIA model, the steric descriptors make a marginally larger contribution than the electrostatic descriptors. The finding that the steric descriptor is the largest contributor for the CoMSIA QSAR models is consistent with the observation that more than half of the binding site area is occupied by steric regions.

Keywords: 3D QSAR, CoMSIA, Triazoles.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1480