Search results for: Computer based training

Authors: Wojciech P. Gajewski

Abstract:

The problem of spam has been seriously troubling the Internet community during the last few years and currently reached an alarming scale. Observations made at CERN (European Organization for Nuclear Research located in Geneva, Switzerland) show that spam mails can constitute up to 75% of daily SMTP traffic. A naïve Bayesian classifier based on a Bag Of Words representation of an email is widely used to stop this unwanted flood as it combines good performance with simplicity of the training and classification processes. However, facing the constantly changing patterns of spam, it is necessary to assure online adaptability of the classifier. This work proposes combining such a classifier with another NBC (naïve Bayesian classifier) based on pairs of adjacent words. Only the latter will be retrained with examples of spam reported by users. Tests are performed on considerable sets of mails both from public spam archives and CERN mailboxes. They suggest that this architecture can increase spam recall without affecting the classifier precision as it happens when only the NBC based on single words is retrained.

Keywords: Text classification, naïve Bayesian classification, spam, email.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4401

Authors: M. Antonelli, G. Frosini, B. Lazzerini, F. Marcelloni

Abstract:

In this paper we describe a computer-aided diagnosis (CAD) system for automated detection of pulmonary nodules in computed-tomography (CT) images. After extracting the pulmonary parenchyma using a combination of image processing techniques, a region growing method is applied to detect nodules based on 3D geometric features. We applied the CAD system to CT scans collected in a screening program for lung cancer detection. Each scan consists of a sequence of about 300 slices stored in DICOM (Digital Imaging and Communications in Medicine) format. All malignant nodules were detected and a low false-positive detection rate was achieved.

Keywords: computer assisted diagnosis, medical imagesegmentation, shape recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1806

Authors: Anjin Park, Sungju Yun, Jungwhan Kim, Seungk Min, Keechul Jung

Abstract:

Finger spelling is an art of communicating by signs made with fingers, and has been introduced into sign language to serve as a bridge between the sign language and the verbal language. Previous approaches to finger spelling recognition are classified into two categories: glove-based and vision-based approaches. The glove-based approach is simpler and more accurate recognizing work of hand posture than vision-based, yet the interfaces require the user to wear a cumbersome and carry a load of cables that connected the device to a computer. In contrast, the vision-based approaches provide an attractive alternative to the cumbersome interface, and promise more natural and unobtrusive human-computer interaction. The vision-based approaches generally consist of two steps: hand extraction and recognition, and two steps are processed independently. This paper proposes real-time vision-based Korean finger spelling recognition system by integrating hand extraction into recognition. First, we tentatively detect a hand region using CAMShift algorithm. Then fill factor and aspect ratio estimated by width and height estimated by CAMShift are used to choose candidate from database, which can reduce the number of matching in recognition step. To recognize the finger spelling, we use DTW(dynamic time warping) based on modified chain codes, to be robust to scale and orientation variations. In this procedure, since accurate hand regions, without holes and noises, should be extracted to improve the precision, we use graph cuts algorithm that globally minimize the energy function elegantly expressed by Markov random fields (MRFs). In the experiments, the computational times are less than 130ms, and the times are not related to the number of templates of finger spellings in database, as candidate templates are selected in extraction step.

Keywords: CAMShift, DTW, Graph Cuts, MRF.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1618

Authors: L. Petrosyan

Abstract:

The problem of psychologist training remains a key priority in Armenia. During the Soviet period, the notion of a psychologist was obscure not only in Armenia but also in other Soviet republics. The breakup of the Soviet Union triggered a gradual change in this area activating the cooperation with specialists from other countries. The need for recovery from the psychological trauma caused by the 1988 earthquake pushed forward the development of practical psychology in Armenia. This phenomenon led to positive changes in perception of and interest to a psychologist profession.Armenian universities started designing special programs for psychologists’ preparation. Armenian psychologists combined their efforts in the field of training relevant specialists. During the recent years, the Bologna educational system was introduced in Armenia which led to implementation of education quality improvement programs. Nevertheless, even today the issue of psychologists’ training is not yet settled in Armenian universities. So far graduate psychologists haven’t got a clear idea of personal and professional qualities of a psychologist. Recently, as a result of educational reforms, the psychology curricula underwent changes, but so far they have not led to a desired outcome. Almost all curricula in certain specialties are aimed to form professional competencies and strengthen practical skills. A survey conducted in Armenia aimed to identify what are the ideas of young psychology specialists on the image of a psychologist. The survey respondents were 45 specialists holding bachelor’s degree as well as 30 master degree graduates, who have not been working yet. The research reveals that we need to change the approach of preparing psychology practitioners in the universities of Armenia. Such an approach to psychologist training will make it possible to train qualified specialists for enhancement of modern psychology theory and practice.

Keywords: Practitioners, Psychology Degree, study, professional competencies.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2051

Authors: Janusz Bobulski, Kamila Pasternak

Abstract:

Despite many years of effort and research, the problem of waste management is still current. There is a lack of fast and effective algorithms for classifying individual waste fractions. Many programs and projects improve statistics on the percentage of waste recycled every year. In these efforts, it is worth using modern Computer Vision techniques supported by artificial intelligence. In the article, we present a method of identifying plastic waste based on the asymmetry analysis of the histogram of the image containing the waste. The method is simple but effective (94%), which allows it to be implemented on devices with low computing power, in particular on microcomputers. Such de-vices will be used both at home and in waste sorting plants.

Keywords: Computer vision, environmental protection, image processing, waste management.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 263

Authors: Ibrahim S AlNomay, Alaa Jaber, Ghada AlNasser

Abstract:

A learning management system (commonly abbreviated as LMS) is a software application for the administration, documentation, tracking, and reporting of training programs, classroom and online events, e-learning programs, and training content (Ellis 2009). (Hall 2003) defines an LMS as \"software that automates the administration of training events. All Learning Management Systems manage the log-in of registered users, manage course catalogs, record data from learners, and provide reports to management\". Evidence of the worldwide spread of e-learning in recent years is easy to obtain. In April 2003, no fewer than 66,000 fully online courses and 1,200 complete online programs were listed on the TeleCampus portal from TeleEducation (Paulsen 2003). In the report \" The US market in the Self-paced eLearning Products and Services:2010-2015 Forecast and Analysis\" The number of student taken classes exclusively online will be nearly equal (1% less) to the number taken classes exclusively in physical campuses. Number of student taken online course will increase from 1.37 million in 2010 to 3.86 million in 2015 in USA. In another report by The Sloan Consortium three-quarters of institutions report that the economic downturn has increased demand for online courses and programs.

Keywords: LMS, Interactive Materials, Exam Centers, Learning Outcomes

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1564

Authors: Gulzar A. Khuwaja, Mohammad S. Laghari

Abstract:

Biometrics, which refers to identifying an individual based on his or her physiological or behavioral characteristics, has the capability to reliably distinguish between an authorized person and an imposter. Signature verification systems can be categorized as offline (static) and online (dynamic). This paper presents a neural network based recognition of offline handwritten signatures system that is trained with low-resolution scanned signature images.

Keywords: Pattern Recognition, Computer Vision, AdaptiveClassification, Handwritten Signature Recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2886

Authors: Abdenour Bounsiar, Edith Grall, Pierre Beauseroy

Abstract:

In this paper we are interested in classification problems with a performance constraint on error probability. In such problems if the constraint cannot be satisfied, then a rejection option is introduced. For binary labelled classification, a number of SVM based methods with rejection option have been proposed over the past few years. All of these methods use two thresholds on the SVM output. However, in previous works, we have shown on synthetic data that using thresholds on the output of the optimal SVM may lead to poor results for classification tasks with performance constraint. In this paper a new method for supervised classification with rejection option is proposed. It consists in two different classifiers jointly optimized to minimize the rejection probability subject to a given constraint on error rate. This method uses a new kernel based linear learning machine that we have recently presented. This learning machine is characterized by its simplicity and high training speed which makes the simultaneous optimization of the two classifiers computationally reasonable. The proposed classification method with rejection option is compared to a SVM based rejection method proposed in recent literature. Experiments show the superiority of the proposed method.

Keywords: rejection, Chow's rule, error-reject tradeoff, SupportVector Machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1435

Authors: Somorjeet Sharma Shamurailatpam, Rabindra Das, A. Suchitra Devi

Abstract:

Computer and video display users might complain about Asthenopia, burning, dry eyes etc. The management of dry eyes is often not in the lines of severity. Following systematic evaluation and grading, dry eye disease is one condition that can be practiced at all levels of ophthalmic care. In the present study, different spectrum causing dry eye and prevalence of dry eye disease in computer users of Manipur, India are determined with 600 individuals (300 cases and 300 control). Individuals between 15 and 50 years who used computers for more than 3 hrs a day for 1 year or more were included. Tear break up time (TBUT) and Schirmer’s test were conducted. It shows that 33 (20.4%) out of 164 males and 47 (30.3%) out of 136 females have dry eye. Possible explanation for the observed result is discussed.

Keywords: Asthenopia, computer vision syndrome, dry eyes, Schirmer’s test, tear breakup time.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1062

Authors: Bruce X. B. Yu, Yan Liu, Keith C. C. Chan

Abstract:

We propose to record Activities of Daily Living (ADLs) of elderly people using a vision-based system so as to provide better assistive and personalization technologies. Current ADL-related research is based on data collected with help from non-elderly subjects in laboratory environments and the activities performed are predetermined for the sole purpose of data collection. To obtain more realistic datasets for the application, we recorded ADLs for the elderly with data collected from real-world environment involving real elderly subjects. Motivated by the need to collect data for more effective research related to elderly care, we chose to collect data in the room of an elderly person. Specifically, we installed Kinect, a vision-based sensor on the ceiling, to capture the activities that the elderly subject performs in the morning every day. Based on the data, we identified 12 morning activities that the elderly person performs daily. To recognize these activities, we created a HARELCARE framework to investigate into the effectiveness of existing Human Activity Recognition (HAR) algorithms and propose the use of a transfer learning algorithm for HAR. We compared the performance, in terms of accuracy, and training progress. Although the collected dataset is relatively small, the proposed algorithm has a good potential to be applied to all daily routine activities for healthcare purposes such as evidence-based diagnosis and treatment.

Keywords: Daily activity recognition, healthcare, IoT sensors, transfer learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 862

Authors: Fereidoon Nowshiravan Rahatabad, Mohammad Hassan Moradi, Vahid Reza Nafisi

Abstract:

Nothing that an effective cure for infertility happens when we can find a unique solution, a great deal of study has been done in this field and this is a hot research subject for to days study. So we could analyze the men-s seaman and find out about fertility and infertility and from this find a true cure for this, since this will be a non invasive and low risk procedure, it will be greatly welcomed. In this research, the procedure has been based on few Algorithms enhancement and segmentation of images which has been done on the images taken from microscope in different fertility institution and have obtained a suitable result from the computer images which in turn help us to distinguish these sperms from fluids and its surroundings.

Keywords: Computer-Assisted Sperm Analysis (CASA), Spermidentification, Segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1617

Authors: P. Meesuk, T. Kulworawanichpong, P. Pao-la-or

Abstract:

This paper proposes a set of quasi-static mathematical model of magnetic fields caused by high voltage conductors of distribution transformer by using a set of second-order partial differential equation. The modification for complex magnetic field analysis and time-harmonic simulation are also utilized. In this research, transformers were study in both balanced and unbalanced loading conditions. Computer-based simulation utilizing the threedimensional finite element method (3-D FEM) is exploited as a tool for visualizing magnetic fields distribution volume a distribution transformer. Finite Element Method (FEM) is one among popular numerical methods that is able to handle problem complexity in various forms. At present, the FEM has been widely applied in most engineering fields. Even for problems of magnetic field distribution, the FEM is able to estimate solutions of Maxwell-s equations governing the power transmission systems. The computer simulation based on the use of the FEM has been developed in MATLAB programming environment.

Keywords: Distribution Transformer, Magnetic Field, Load Unbalance, 3-D Finite Element Method (3-D FEM)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2670

Authors: Xiaoshu Lu, Esa-Pekka Takala, Risto Toivonen

Abstract:

This paper systematically investigates the timedependent health outcomes for office staff during computer work using the developed mathematical model. The model describes timedependent health outcomes in multiple body regions associated with computer usage. The association is explicitly presented with a doseresponse relationship which is parametrized by body region parameters. Using the developed model we perform extensive investigations of the health outcomes statically and dynamically. We compare the risk body regions and provide various severity rankings of the discomfort rate changes with respect to computer-related workload dynamically for the study population. Application of the developed model reveals a wide range of findings. Such broad spectrum of investigations in a single report literature is lacking. Based upon the model analysis, it is discovered that the highest average severity level of the discomfort exists in neck, shoulder, eyes, shoulder joint/upper arm, upper back, low back and head etc. The biggest weekly changes of discomfort rates are in eyes, neck, head, shoulder, shoulder joint/upper arm and upper back etc. The fastest discomfort rate is found in neck, followed by shoulder, eyes, head, shoulder joint/upper arm and upper back etc. Most of our findings are consistent with the literature, which demonstrates that the developed model and results are applicable and valuable and can be utilized to assess correlation between the amount of computer-related workload and health risk.

Keywords: Computer-related workload, health outcomes, dynamic association, dose-response relationship, systematic analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1272

Authors: Erika Pigliapoco, Valerio Freschi, Alessandro Bogliolo

Abstract:

This work presents a new phonetic transcription system based on a tree of hierarchical pronunciation rules expressed as context-specific grapheme-phoneme correspondences. The tree is automatically inferred from a phonetic dictionary by incrementally analyzing deeper context levels, eventually representing a minimum set of exhaustive rules that pronounce without errors all the words in the training dictionary and that can be applied to out-of-vocabulary words. The proposed approach improves upon existing rule-tree-based techniques in that it makes use of graphemes, rather than letters, as elementary orthographic units. A new linear algorithm for the segmentation of a word in graphemes is introduced to enable outof- vocabulary grapheme-based phonetic transcription. Exhaustive rule trees provide a canonical representation of the pronunciation rules of a language that can be used not only to pronounce out-of-vocabulary words, but also to analyze and compare the pronunciation rules inferred from different dictionaries. The proposed approach has been implemented in C and tested on Oxford British English and Basic English. Experimental results show that grapheme-based rule trees represent phonetically sound rules and provide better performance than letter-based rule trees.

Keywords: Automatic phonetic transcription, pronunciation rules, hierarchical tree inference.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1909

Authors: Dasom Kim, Chen Liu, Myungsu Lim, Soo-Hyeon Jeon, Byeoung Kug Jeon, Kee-Young Kwahk, Namgyu Kim

Abstract:

Recently, numerous documents including large volumes of unstructured data and text have been created because of the rapid increase in the use of social media and the Internet. Usually, these documents are categorized for the convenience of users. Because the accuracy of manual categorization is not guaranteed, and such categorization requires a large amount of time and incurs huge costs. Many studies on automatic categorization have been conducted to help mitigate the limitations of manual categorization. Unfortunately, most of these methods cannot be applied to categorize complex documents with multiple topics because they work on the assumption that individual documents can be categorized into single categories only. Therefore, to overcome this limitation, some studies have attempted to categorize each document into multiple categories. However, the learning process employed in these studies involves training using a multi-categorized document set. These methods therefore cannot be applied to the multi-categorization of most documents unless multi-categorized training sets using traditional multi-categorization algorithms are provided. To overcome this limitation, in this study, we review our novel methodology for extending the category of a single-categorized document to multiple categorizes, and then introduce a survey-based verification scenario for estimating the accuracy of our automatic categorization methodology.

Keywords: Big Data Analysis, Document Classification, Text Mining, Topic Analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1735

Authors: Kang Huang, Wanting Zhou, Shiwei Yuan, Lei Li

Abstract:

Since information technology develops rapidly, the security issue has become an increasingly critical for computer system. In particular, as cloud computing and the Internet of Things (IoT) continue to gain widespread adoption, computer systems need to new security threats and attacks. The Root of Trust (RoT) is the foundation for providing basic trusted computing, which is used to verify the security and trustworthiness of other components. Designing a reliable RoT and guaranteeing its own security are essential for improving the overall security and credibility of computer systems. In this paper, we discuss the implementation of self-security technology based on the RISC-V RoT at the hardware level. To effectively safeguard the security of the RoT, researches on security safeguard technology on the RoT have been studied. At first, a lightweight and secure boot framework is proposed as a secure mechanism. Secondly, two kinds of memory protection mechanism are built to against memory attacks. Moreover, hardware implementation of proposed method has been also investigated. A series of experiments and tests have been carried on to verify to effectiveness of the proposed method. The experimental results demonstrated that the proposed approach is effective in verifying the integrity of the RoT’s own boot rom, user instructions, and data, ensuring authenticity and enabling the secure boot of the RoT’s own system. Additionally, our approach provides memory protection against certain types of memory attacks, such as cache leaks and tampering, and ensures the security of root-of-trust sensitive information, including keys.

Keywords: Root of Trust, secure boot, memory protection, hardware security.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4

Authors: Okan Özgönenel

Abstract:

This paper presents the development of a wavelet based algorithm, for distinguishing between magnetizing inrush currents and power system fault currents, which is quite adequate, reliable, fast and computationally efficient tool. The proposed technique consists of a preprocessing unit based on discrete wavelet transform (DWT) in combination with an artificial neural network (ANN) for detecting and classifying fault currents. The DWT acts as an extractor of distinctive features in the input signals at the relay location. This information is then fed into an ANN for classifying fault and magnetizing inrush conditions. A 220/55/55 V, 50Hz laboratory transformer connected to a 380 V power system were simulated using ATP-EMTP. The DWT was implemented by using Matlab and Coiflet mother wavelet was used to analyze primary currents and generate training data. The simulated results presented clearly show that the proposed technique can accurately discriminate between magnetizing inrush and fault currents in transformer protection.

Keywords: Artificial neural network, discrete wavelet transform, fault detection, magnetizing inrush current.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1828

Authors: Yehjune Heo

Abstract:

As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.

Keywords: Anti-spoofing, CNN, fingerprint recognition, loss function, optimizer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 393

Authors: Khairul Akram Zainol Ariffin, Ahmad Kamil Mahmood, Jafreezal Jaafar, Solahuddin Shamsuddin

Abstract:

Random Access Memory (RAM) is an important device in computer system. It can represent the snapshot on how the computer has been used by the user. With the growth of its importance, the computer memory has been an issue that has been discussed in digital forensics. A number of tools have been developed to retrieve the information from the memory. However, most of the tools have their limitation in the ability of retrieving the important information from the computer memory. Hence, this paper is aimed to discuss the limitation and the setback for two main techniques such as process signature search and process enumeration. Then, a new hybrid approach will be presented to minimize the setback in both individual techniques. This new approach combines both techniques with the purpose to retrieve the information from the process block and other objects in the computer memory. Nevertheless, the basic theory in address translation for x86 platforms will be demonstrated in this paper.

Keywords: Algorithms, Digital Forensics, Memory Analysis, Signature Search.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1975

Authors: Arslan Qamar Malik, Jehanzeb Ahmad

Abstract:

The paper presents a novel idea to control computer mouse cursor movement with human eyes. In this paper, a working of the product has been described as to how it helps the special people share their knowledge with the world. Number of traditional techniques such as Head and Eye Movement Tracking Systems etc. exist for cursor control by making use of image processing in which light is the primary source. Electro-oculography (EOG) is a new technology to sense eye signals with which the mouse cursor can be controlled. The signals captured using sensors, are first amplified, then noise is removed and then digitized, before being transferred to PC for software interfacing.

Keywords: Human Computer Interaction, Real-Time System, Electro-oculography, Signal Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4219

Authors: Eric Jiang

Abstract:

As a popular rank-reduced vector space approach, Latent Semantic Indexing (LSI) has been used in information retrieval and other applications. In this paper, an LSI-based content vector model for text classification is presented, which constructs multiple augmented category LSI spaces and classifies text by their content. The model integrates the class discriminative information from the training data and is equipped with several pertinent feature selection and text classification algorithms. The proposed classifier has been applied to email classification and its experiments on a benchmark spam testing corpus (PU1) have shown that the approach represents a competitive alternative to other email classifiers based on the well-known SVM and naïve Bayes algorithms.

Keywords: Feature Selection, Latent Semantic Indexing, Text Classification, Vector Space Model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1868

Authors: Iliana Marinova, Valentin Mateev

Abstract:

In this paper a computer system for electromagnetic properties measurements is designed. The system employs Agilent 4294A precision impedance analyzer to measure the amplitude and the phase of a signal applied over a tested biological tissue sample. Measured by the developed computer system data could be used for tissue characterization in wide frequency range from 40Hz to 110MHz. The computer system can interface with output devices acquiring flexible testing process.

Keywords: Electromagnetic properties, human tissue, bioimpedance, measurement system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2413

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: Artificial Intelligence, machine learning, deep learning, convolutional neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1225

Authors: Kadyrzhan Smagulov, Beken Makhmutov, Abai Kurmankulov

Abstract:

The concept of the new government should focus on forming a new relationship between public servants and citizens of the state, formed on the principles of transparency, accountability, protection of citizens' rights. These principles are laid down in the problem of administrative reform in the Republic of Kazakhstan. Also, this wish arises, contributing to the improvement of the system of political management in our country. For the full realization of the goals is necessary to develop a special state program designed to improve the regulatory framework for public service, improving training, retraining and advanced training of civil servants, forming a system of incentives in public service and other activities aimed at achieving the efficiency of the entire system government.

Keywords: Kazakhstan, political management, independence

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1446

Authors: Hsin-Chang Yang, Chung-Hong Lee, Kuo-Lung Ke

Abstract:

The self-organizing map (SOM) model is a well-known neural network model with wide spread of applications. The main characteristics of SOM are two-fold, namely dimension reduction and topology preservation. Using SOM, a high-dimensional data space will be mapped to some low-dimensional space. Meanwhile, the topological relations among data will be preserved. With such characteristics, the SOM was usually applied on data clustering and visualization tasks. However, the SOM has main disadvantage of the need to know the number and structure of neurons prior to training, which are difficult to be determined. Several schemes have been proposed to tackle such deficiency. Examples are growing/expandable SOM, hierarchical SOM, and growing hierarchical SOM. These schemes could dynamically expand the map, even generate hierarchical maps, during training. Encouraging results were reported. Basically, these schemes adapt the size and structure of the map according to the distribution of training data. That is, they are data-driven or dataoriented SOM schemes. In this work, a topic-oriented SOM scheme which is suitable for document clustering and organization will be developed. The proposed SOM will automatically adapt the number as well as the structure of the map according to identified topics. Unlike other data-oriented SOMs, our approach expands the map and generates the hierarchies both according to the topics and their characteristics of the neurons. The preliminary experiments give promising result and demonstrate the plausibility of the method.

Keywords: Self-organizing map, topic identification, learning algorithm, text clustering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2010

Authors: R. Rajeswari, N. Kamaraj

Abstract:

In this paper, Wavelet based ANFIS for finding inter turn fault of generator is proposed. The detector uniquely responds to the winding inter turn fault with remarkably high sensitivity. Discrimination of different percentage of winding affected by inter turn fault is provided via ANFIS having an Eight dimensional input vector. This input vector is obtained from features extracted from DWT of inter turn faulty current leaving the generator phase winding. Training data for ANFIS are generated via a simulation of generator with inter turn fault using MATLAB. The proposed algorithm using ANFIS is giving satisfied performance than ANN with selected statistical data of decomposed levels of faulty current.

Keywords: Winding InterTurn fault, ANN, ANFIS, and DWT.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2920

Authors: Muhammed Yousoof, Mohd Sapiyan, Khaja Kamaluddin

Abstract:

Learning programming is difficult for many learners. Some researches have found that the main difficulty relates to cognitive load. Cognitive overload happens in programming due to the nature of the subject which is intrinisicly over-bearing on the working memory. It happens due to the complexity of the subject itself. The problem is made worse by the poor instructional design methodology used in the teaching and learning process. Various efforts have been proposed to reduce the cognitive load, e.g. visualization softwares, part-program method etc. Use of many computer based systems have also been tried to tackle the problem. However, little success has been made to alleviate the problem. More has to be done to overcome this hurdle. This research attempts at understanding how cognitive load can be managed so as to reduce the problem of overloading. We propose a mechanism to measure the cognitive load during pre instruction, post instruction and in instructional stages of learning. This mechanism is used to help the instruction. As the load changes the instruction is made to adapt itself to ensure cognitive viability. This mechanism could be incorporated as a sub domain in the student model of various computer based instructional systems to facilitate the learning of programming.

Keywords: Cognitive load, Working memory, Cognitive Loadmeasurement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2546

Authors: Mountassar Maamoun, Abdelhamid Meraghni, Abdelhalim Benbelkacem, Daoud Berkani

Abstract:

This paper describes an efficient hardware implementation of a new technique for interfacing the data exchange between the microprocessor-based systems and the external devices. This technique, based on the use of software/hardware system and a reduced physical address, enlarges the interfacing capacity of the microprocessor-based systems, uses the Direct Memory Access (DMA) to increases the frequency of the new bus, and improves the speed of data exchange. While using this architecture in microprocessor-based system or in computer, the input of the hardware part of our system will be connected to the bus system, and the output, which is a new bus, will be connected to an external device. The new bus is composed of a data bus, a control bus and an address bus. A Xilinx Integrated Software Environment (ISE) 7.1i has been used for the programmable logic implementation.

Keywords: Interfacing, Software/hardware System, CPLD, programmable logic, DMA.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1372

Authors: I. Oloyede

Abstract:

The study investigates the accuracy and loss of deep learning algorithms with the set of coronavirus (COVID-19) images dataset by comparing Bayesian convolutional neural network and traditional convolutional neural network in low dimensional dataset. 50 sets of X-ray images out of which 25 were COVID-19 and the remaining 20 were normal, twenty images were set as training while five were set as validation that were used to ascertained the accuracy of the model. The study found out that Bayesian convolution neural network outperformed conventional neural network at low dimensional dataset that could have exhibited under fitting. The study therefore recommended Bayesian Convolutional neural network (BCNN) for android apps in computer vision for image detection.

Keywords: BCNN, CNN, Images, COVID-19, Deep Learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 843

Authors: Niall J. English, Sylvia Leatham, Maria Isabel Meza Silva, Denis P. Dowling

Abstract:

The training and education of under- and post-graduate students can be promoted by more active learning especially in engineering, overcoming more passive and vicarious experiences and approaches in their documented effectiveness. However, the possibility of outreach to young pupils and school-children in primary and secondary schools is a lesser explored area in terms of Education and Public Engagement (EPE) efforts – as relates to feedback and influence on shaping 3rd-level engineering training and education. Therefore, the outreach and school-visit agenda constitutes an interesting avenue to observe how active learning, careers stimulus and EPE efforts for young children and teenagers can teach the university sector, to improve future engineering-teaching standards and enhance both quality and capabilities of practice. This intervention involved careers-outreach efforts to lead to statistical determinations of motivations towards engineering, manufacturing and training. The aim was to gauge to what extent this intervention would lead to an increased careers awareness in engineering, using the method of the schools-visits programme as the means for so doing. It was found that this led to an increase in engagement by school pupils with engineering as a career option and a greater awareness of the importance of manufacturing. 

Keywords: outreach, education and public engagement, careers, peer interactions

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 476