Search results for: task replication

Authors: Ashish James, Anusha James

Abstract:

The impressive predictive performance of deep learning techniques on a wide range of tasks has led to its widespread use. Estimating the confidence of these predictions is paramount for improving the safety and reliability of such systems. However, the uncertainty estimates provided by neural networks (NNs) tend to be overconfident and unreasonable. Ensemble of NNs typically produce good predictions but uncertainty estimates tend to be inconsistent. Inspired by these, this paper presents a framework that can quantitatively estimate the uncertainties by leveraging the advances in transfer learning through slight modification to the existing training pipelines. This promising algorithm is developed with an intention of deployment in real world problems which already boast a good predictive performance by reusing those pretrained models. The idea is to capture the behavior of the trained NNs for the base task by augmenting it with the uncertainty estimates from a supplementary network. A series of experiments with known and unknown distributions show that the proposed approach produces well calibrated uncertainty estimates with high quality predictions.

Keywords: uncertainty estimation, neural networks, transfer learning, regression

Procedia PDF Downloads 137

Authors: Ghada S. Moussa

Abstract:

Vehicle classification is an important task in traffic surveillance and intelligent transportation systems. Classification of vehicle images is facing several problems such as: high intra-class vehicle variations, occlusion, shadow, illumination. These problems and others must be considered to develop a reliable vehicle classification system. In this study, a reliable multi-type vehicle classification system based on Bag-of-Words (BoW) paradigm is developed. Our proposed system used and compared four well-known classifiers; Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), k-Nearest Neighbour (KNN), and Decision Tree to classify vehicles into four categories: motorcycles, small, medium and large. Experiments on a large dataset show that our approach is efficient and reliable in classifying vehicles with accuracy of 95.7%. The SVM outperforms other classification algorithms in terms of both accuracy and robustness alongside considerable reduction in execution time. The innovativeness of developed system is it can serve as a framework for many vehicle classification systems.

Keywords: vehicle classification, bag-of-words technique, SVM classifier, LDA classifier, KNN classifier, decision tree classifier, SIFT algorithm

Procedia PDF Downloads 359

Authors: Ryan A. Black, Stacey A. McCaffrey

Abstract:

Over the past few decades, great strides have been made towards improving the science in the measurement of psychological constructs. Item Response Theory (IRT) has been the foundation upon which statistical models have been derived to increase both precision and accuracy in psychological measurement. These models are now being used widely to develop and refine tests intended to measure an individual's level of academic achievement, aptitude, and intelligence. Recently, the field of clinical psychology has adopted IRT models to measure psychopathological phenomena such as depression, anxiety, and addiction. Because advances in IRT measurement models are being made so rapidly across various fields, it has become quite challenging for psychologists and other behavioral scientists to keep abreast of the most recent developments, much less learn how to employ and decide which models are the most appropriate to use in their line of work. In the same vein, IRT measurement models vary greatly in complexity in several interrelated ways including but not limited to the number of item-specific parameters estimated in a given model, the function which links the expected response and the predictor, response option formats, as well as dimensionality. As a result, inferior methods (a.k.a. Classical Test Theory methods) continue to be employed in efforts to measure psychological constructs, despite evidence showing that IRT methods yield more precise and accurate measurement. To increase the use of IRT methods, this study endeavors to provide a comprehensive overview of binary IRT models; that is, measurement models employed on test data consisting of binary response options (e.g., correct/incorrect, true/false, agree/disagree). Specifically, this study will cover the most basic binary IRT model, known as the 1-parameter logistic (1-PL) model dating back to over 50 years ago, up until the most recent complex, 4-parameter logistic (4-PL) model. Binary IRT models will be defined mathematically and the interpretation of each parameter will be provided. Next, all four binary IRT models will be employed on two sets of data: 1. Simulated data of N=500,000 subjects who responded to four dichotomous items and 2. A pilot analysis of real-world data collected from a sample of approximately 770 subjects who responded to four self-report dichotomous items pertaining to emotional consequences to alcohol use. Real-world data were based on responses collected on items administered to subjects as part of a scale-development study (NIDA Grant No. R44 DA023322). IRT analyses conducted on both the simulated data and analyses of real-world pilot will provide a clear demonstration of how to construct, evaluate, and compare binary IRT measurement models. All analyses will be performed using the new IRT procedure in SAS 9.4. SAS code to generate simulated data and analyses will be available upon request to allow for replication of results.

Keywords: instrument development, item response theory, latent trait theory, psychometrics

Procedia PDF Downloads 358

Authors: Khalak Bin Khair, Saqib Jahir, Mohammed Ibrahim, Fahad Bin, Debajyoti Karmaker

Abstract:

Object detection is a computer technology that deals with searching through digital images and videos for occurrences of semantic elements of a particular class. It is associated with image processing and computer vision. On top of object detection, we detect camouflage objects within an image using Deep Learning techniques. Deep learning may be a subset of machine learning that's essentially a three-layer neural network Over 6500 images that possess camouflage properties are gathered from various internet sources and divided into 4 categories to compare the result. Those images are labeled and then trained and tested using vgg16 architecture on the jupyter notebook using the TensorFlow platform. The architecture is further customized using Transfer Learning. Methods for transferring information from one or more of these source tasks to increase learning in a related target task are created through transfer learning. The purpose of this transfer of learning methodologies is to aid in the evolution of machine learning to the point where it is as efficient as human learning.

Keywords: deep learning, transfer learning, TensorFlow, camouflage, object detection, architecture, accuracy, model, VGG16

Procedia PDF Downloads 152

Authors: Thorsten Prante, Robert Schöch, Ruth Fleisch, Vaheh Khachatouri, Alexander Walch

Abstract:

The development of industrial plant control software is a complex and often very expensive task. One of the core problems is that a lot of the implementation and adaptation work can only be done after the plant hardware has been installed. In this paper, we present our approach to virtually developing and validating plant-level control software of production plants. This way, plant control software can be virtually commissioned before actual ramp-up of a plant, reducing actual commissioning costs and time. Technically, this is achieved by linking the actual plant-wide process control software (often called plant server) and an elaborate virtual plant model together to form an emulation system. Method-wise, we are suggesting a four-step iterative process with well-defined increments and time frame. Our work is based on practical experiences from planning to commissioning and start-up of several cut-to-size plants.

Keywords: iterative system design, virtual plant engineering, plant control software, simulation and emulation, virtual commissioning

Procedia PDF Downloads 490

Authors: Reza Yadollahi, Arash Hejazi, Dante Savasta

Abstract:

Building Information Modeling (BIM) is growing so fast in construction projects around the world. Considering BIM's weaknesses in implementing existing heritage and historical buildings, it is critical to facilitate BIM application for such structures. One of the pieces of information to build a model in BIM is to import material and its characteristics. Material library is essential to speed up the entry of project information. To save time and prevent cost overrun, a BIM object material library should be provided. However, historical buildings' lack of information and documents is typically a challenge in renovation and retrofitting projects. Due to the lack of case documents for historic buildings, importing data is a time-consuming task, which can be improved by creating BIM libraries. Based on previous research, this paper reviews the complexities and challenges in BIM modeling for heritage, historic, and architectural buildings. Through identifying the strengths and weaknesses of the standard BIM systems, recommendations are provided to enhance the modeling platform.

Keywords: building Information modeling, historic, heritage buildings, material library

Procedia PDF Downloads 120

Authors: Alhadi Bustaman, Soeganda Formalidin, Titin Siswantining

Abstract:

DNA microarray technology is used to analyze thousand gene expression data simultaneously and a very important task for drug development and test, function annotation, and cancer diagnosis. Various clustering methods have been used for analyzing gene expression data. However, when analyzing very large and heterogeneous collections of gene expression data, conventional clustering methods often cannot produce a satisfactory solution. Biclustering algorithm has been used as an alternative approach to identifying structures from gene expression data. In this paper, we introduce a transform technique based on singular value decomposition to identify normalized matrix of gene expression data followed by Mixed-Clustering algorithm and the Lift algorithm, inspired in the node-deletion and node-addition phases proposed by Cheng and Church based on Agglomerative Hierarchical Clustering (AHC). Experimental study on standard datasets demonstrated the effectiveness of the algorithm in gene expression data.

Keywords: agglomerative hierarchical clustering (AHC), biclustering, gene expression data, lymphoma, singular value decomposition (SVD)

Procedia PDF Downloads 279

Authors: Amdouni Hamida, Gammoudi Mohamed Mohsen

Abstract:

In order to help the expert to validate association rules extracted from data, some quality measures are proposed in the literature. We distinguish two categories: objective and subjective measures. The first one depends on a fixed threshold and on data quality from which the rules are extracted. The second one consists on providing to the expert some tools in the objective to explore and visualize rules during the evaluation step. However, the number of extracted rules to validate remains high. Thus, the manually mining rules task is very hard. To solve this problem, we propose, in this paper, a semi-automatic method to assist the expert during the association rule's validation. Our method uses rule-based classification as follow: (i) We transform association rules into classification rules (classifiers), (ii) We use the generated classifiers for data classification. (iii) We visualize association rules with their quality classification to give an idea to the expert and to assist him during validation process.

Keywords: association rules, rule-based classification, classification quality, validation

Procedia PDF Downloads 440

Authors: Baoshan Wei, Shuai Han, Xing Zhang

Abstract:

Local obstacle avoidance is critical for mobile robot navigation. It is a challenging task to ensure path optimality and safety in cluttered environments. We proposed an Environment Aware Dynamic Window Approach in this paper to cope with the issue. The method integrates environment characterization into Dynamic Window Approach (DWA). Two strategies are proposed in order to achieve the integration. The local goal strategy guides the robot to move through openings before approaching the final goal, which solves the local minima problem in DWA. The adaptive control strategy endows the robot to adjust its state according to the environment, which addresses path safety compared with DWA. Besides, the evaluation shows that the path generated from the proposed algorithm is safer and smoother compared with state-of-the-art algorithms.

Keywords: adaptive control, dynamic window approach, environment aware, local obstacle avoidance, mobile robots

Procedia PDF Downloads 159

Authors: Jesus Carretero, Mario Vasile, Guillermo Izquierdo, Javier Garcia-Blas

Abstract:

Currently, there is a so called ‘identity crisis’ in cybersecurity caused by the substantial security, privacy and usability shortcomings encountered in existing systems for identity management. Federated Identity Management (FIM) could be solution for this crisis, as it is a method that facilitates management of identity processes and policies among collaborating entities without enforcing a global consistency, that is difficult to achieve when there are ID legacy systems. To cope with this problem, the Connecting Europe Facility (CEF) initiative proposed in 2014 a federated solution in anticipation of the adoption of the Regulation (EU) N°910/2014, the so-called eIDAS Regulation. At present, a network of eIDAS Nodes is being deployed at European level to allow that every citizen recognized by a member state is to be recognized within the trust network at European level, enabling the consumption of services in other member states that, until now were not allowed, or whose concession was tedious. This is a very ambitious approach, since it tends to enable cross-border authentication of Member States citizens without the need to unify the authentication method (eID Scheme) of the member state in question. However, this federation is currently managed by member states and it is initially applied only to citizens and public organizations. The goal of this paper is to present the results of a European Project, named eID@Cloud, that focuses on the integration of eID in 5 cloud platforms belonging to authentication service providers of different EU Member States to act as Service Providers (SP) for private entities. We propose an initiative based on a private eID Scheme both for natural and legal persons. The methodology followed in the eID@Cloud project is that each Identity Provider (IdP) is subscribed to an eIDAS Node Connector, requesting for authentication, that is subscribed to an eIDAS Node Proxy Service, issuing authentication assertions. To cope with high loads, load balancing is supported in the eIDAS Node. The eID@Cloud project is still going on, but we already have some important outcomes. First, we have deployed the federation identity nodes and tested it from the security and performance point of view. The pilot prototype has shown the feasibility of deploying this kind of systems, ensuring good performance due to the replication of the eIDAS nodes and the load balance mechanism. Second, our solution avoids the propagation of identity data out of the native domain of the user or entity being identified, which avoids problems well known in cybersecurity due to network interception, man in the middle attack, etc. Last, but not least, this system allows to connect any country or collectivity easily, providing incremental development of the network and avoiding difficult political negotiations to agree on a single authentication format (which would be a major stopper).

Keywords: cybersecurity, identity federation, trust, user authentication

Procedia PDF Downloads 167

Authors: S. Meziane, H. I. Faraoun, C. Esling

Abstract:

Transition metal dichalcogenides have potential applications in power generation devices that convert waste heat into electric current by the so-called Seebeck and Hall effects thus providing an alternative energy technology to reduce the dependence on traditional fossil fuels. In this study, the thermoelectric properties of 1T and 2HTaX2 (X= S or Se) dichalcogenide superconductors have been computed using the semi-classical Boltzmann theory. Technologically, the task is to fabricate suitable materials with high efficiency. It is found that 2HTaS2 possesses the largest value of figure of merit ZT= 1.27 at 175 K. From a scientific point of view, we aim to model the underlying materials properties and in particular the transport phenomena as mediated by electrons and lattice vibrations responsible for superconductivity, Charge Density Waves (CDW) and metal/insulator transitions as function of temperature. The goal of the present work is to develop an understanding of the superconductivity of these selected materials using the transport properties at the fundamental level.

Keywords: Ab initio, High efficiency, Power generation devices, Transition metal dichalcogenides

Procedia PDF Downloads 199

Authors: Chibuzor Dalmeida

Abstract:

This paper shall discuss the factors affecting English Language Acquisition and Learning for Primary School in Nigeria. Learning English language is a difficult task mostly those at the primary school level. Pupils find it more difficult on vocabulary, grammar and sentence structure, idioms, pronunciation etc. Researchers have discovered the reasons behind these discrepancies and have formulated theories that could be of utmost assistance to English language teachers and students. This paper further looked at the following factors that include Learner Characteristics and Personal Traits, Situational and Environmental Factors, Prior Language Development and Competence and Age and Brain Development. It further recommended that pupils must learn new vocabulary, rules for grammar and sentence structure, idioms, pronunciation. Pupils whose families and communities set high standards for language acquisition learn more quickly than those who do not. Exposure to high-quality programs also essential. Pupils do best when they are allowed to speak their native language.

Keywords: acquisition, affecting, factors, learning

Procedia PDF Downloads 633

Authors: Bharatendra Rai

Abstract:

The sequence of words in text data has long-term dependencies and is known to suffer from vanishing gradient problems when developing deep learning models. Although recurrent networks such as long short-term memory networks help to overcome this problem, achieving high text classification performance is a challenging problem. Convolutional recurrent networks that combine the advantages of long short-term memory networks and convolutional neural networks can be useful for text classification performance improvements. However, arriving at suitable hyperparameter values for convolutional recurrent networks is still a challenging task where fitting a model requires significant computing resources. This paper illustrates the advantages of using convolutional recurrent networks for text classification with the help of statistically planned computer experiments for hyperparameter tuning.

Keywords: long short-term memory networks, convolutional recurrent networks, text classification, hyperparameter tuning, Tukey honest significant differences

Procedia PDF Downloads 131

Authors: Aryana Collins Jackson, Elisabetta Bevacqua, Pierre De Loor, Ronan Querrec

Abstract:

This paper presents a taxonomy of non-technical skills, communicative intentions, and behavior for an individual acting as a medical coordinator. In medical emergency situations, a leader among the group is imperative to both patient health and team emotional and mental health. Situational Leadership is used to make clear and easy-to-follow guidelines for behavior depending on circumstantial factors. Low-level leadership behaviors belonging to two different styles, directive and supporting, are identified from literature and are included in the proposed taxonomy. The high-level information in the taxonomy consists of the necessary non-technical skills belonging to a medical coordinator: situation awareness, decision making, task management, and teamwork. Finally, communicative intentions, dimensions, and functions are included. Thus this work brings high-level and low-level information - medical non-technical skills, communication capabilities, and leadership behavior - into a single versatile taxonomy of behavior.

Keywords: human behavior, leadership styles, medical, taxonomy

Procedia PDF Downloads 161

Authors: G. Prakash, L. Mohamed Aasiq, N. Dhivya, M. Jothi Mani, R. Mounika, B. Gomathi

Abstract:

In our day to day life, many people met with an accident due to various reasons like over speed, overload in the vehicle, violation of the traffic rules, etc. Driving license system is difficult task for the government to monitor. To prevent non-licensees from driving who are causing most of the accidents, a new system is proposed. The proposed system consists of a smart card capable of storing the license details of a particular person. Vehicles such as cars, bikes etc., should have a card reader capable of reading the particular license. A person, who wishes to drive the vehicle, should insert the card (license) in the vehicle and then enter the password in the keypad. If the license data stored in the card and database about the entire license holders in the microcontroller matches, he/she can proceed for ignition after the automated opening of the fuel tank valve, otherwise the user is restricted to use the vehicle. Moreover, overload detector in our proposed system verifies and then prompts the user to avoid overload before driving. This increases the security of vehicles and also ensures safe driving by preventing accidents.

Keywords: license, verifier, EEPROM, secure, overload detection

Procedia PDF Downloads 242

Authors: Amine Alaoui Sanae, Tagjdid Reda, Loutfi Chafiqa, Melloul Merouane, Laloui Aziz, Touil Nadia, El Fahim, E. Mostafa

Abstract:

Background: Rotavirus group A (RVA) strains with G8P[14] specificities are usually detected in calves and goats. However, these strains have been reported globally in humans and have often been characterized as originating from zoonotic transmissions, particularly in area where ruminants and humans live side-by-side. Whether human P[14] genotypes are two-way and can be transmitted to animal species remains to be established. Here we describe VP4 deduced amino-acid relationships of three Moroccan P[14] genotypes originating from different species and the receptiveness of an alpine goat to a human G8P[14] through an experimental infection. Material/methods: the human MA31 RVA strain was originally identified in a four years old girl presenting an acute gastroenteritis hospitalized at the pediatric care unit in Rabat Hospital in 2011. The virus was isolated and propagated in MA104 cells in the presence of trypsin. Ch_10S and 8045_S animal RVA strains were identified in fecal samples of a 2-week-old native goat and 3-week-old calf with diarrhea in 2011 in Bouaarfa and My Bousselham respectively. Genomic RNAs of all strains were subjected to a two-step RT-PCR and sequenced using the consensus primers VP4. The phylogenetic tree for MA31, Ch_10S and 8045_S VP4 and a set of published P[14] genotypes was constructed using MEGA6 software. The receptivity of MA31 strain by an eight month-old alpine goat was assayed. The animal was orally and intraperitonally inoculated with a dose of 8.5 TCID50 of virus stock at passage level 3. The shedding of the virus was tested by a real time RT-PCR assay. Results: The phylogenetic tree showed that the three Moroccan strains MA31, Ch_10S and 8045_S VP4 were highly related to each other (100% similar at the nucleotide level). They were clustered together with the B10925, Sp813, PA77 and P169 strains isolated in Belgium, Spain and Italy respectively. The Belgian strain B10925 was the most closely related to the Moroccan strains. In contrast, the 8045_S and Ch_10S strains were clustered distantly from the Tunisian calf strain B137 and the goat strain cap455 isolated in South Africa respectively. The human MA31 RVA strain was able to induce bloody diarrhea at 2 days post infection (dpi) in the alpine goat kid. RVA virus shedding started by 2 dpi (Ct value of 28) and continued until 5 dpi (Ct value of 25) with a concomitant elevation in the body temperature. Conclusions: Our study while limited to one animal, is the first study proving experimentally that a human P[14] genotype causes diarrhea and virus shedding in the goat. This result reinforce the potential role of inter- species transmission in generating novel and rare rotavirus strains such G8P[14] which infect humans.

Keywords: interspecies transmission, rotavirus, goat, human

Procedia PDF Downloads 291

Authors: Abhishek, Seema Devi, Jyoti Ohri

Abstract:

A mobile ad hoc network (MANET) represents a system of wireless mobile nodes that can self-organize freely and dynamically into arbitrary and temporary network topology. Unlike a wired network, wireless network interface has limited transmission range. Routing is the task of forwarding data packets from source to a given destination. Ad-hoc On Demand Distance Vector (AODV) routing protocol creates a path for a destination only when it required. This paper describes the implementation of AODV routing protocol using MATLAB-based Truetime simulator. In MANET's node movements are not fixed while they are random in nature. Hence intelligent techniques i.e. fuzzy and ANFIS are used to optimize the transmission range. In this paper, we compared the transmission range of AODV, fuzzy AODV and ANFIS AODV. For soft computing AODV, we have taken transmitted power and received threshold as input and transmission range as output. ANFIS gives better results as compared to fuzzy AODV.

Keywords: ANFIS, AODV, fuzzy, MANET, reactive routing protocol, routing protocol, truetime

Procedia PDF Downloads 499

Authors: E. Younsi, H. Andriamboavonjy, A. David, S. Dokou, B. Lemrabet

Abstract:

Software and time optimization are very important factors in financial markets, which are competitive fields, and emergence of new computer tools further stresses the challenge. In this context, any improvement of technical indicators which generate a buy or sell signal is a major issue. Thus, many tools have been created to make them more effective. This worry about efficiency has been leading in present paper to seek best (and most innovative) way giving largest improvement in these indicators. The approach consists in attaching a signature to frequent market configurations by application of frequent patterns extraction method which is here most appropriate to optimize investment strategies. The goal of proposed trading algorithm is to find most accurate signatures using back testing procedure applied to technical indicators for improving their performance. The problem is then to determine the signatures which, combined with an indicator, outperform this indicator alone. To do this, the FP-Tree algorithm has been preferred, as it appears to be the most efficient algorithm to perform this task.

Keywords: quantitative analysis, back-testing, computational models, apriori algorithm, pattern recognition, data mining, FP-tree

Procedia PDF Downloads 363

Authors: Amani Hamdan

Abstract:

A post-workshop of higher-order thinking skills (HOTS), for faculty from diverse academic disciplines, was conducted and the researcher surveyed the participants’ intentions and plans to include HOTS as a goal, as learning and teaching task in their practices. Follow-up interviews with a random sample of participants were used to determine if they fulfilled their intentions three 3 months after the workshop. The degree of planned and enacted HOTS then was analyzed against the post-workshop HOT ability and knowledge. This is one topic that has not been adequately explored in faculty professional development literature where measuring the effect of learning on their ability to use what they learned. This qualitative method study explored a group of male and female faculty members (n=85) enrolled in HOTS 2 day workshop. The results showed that 89% of faculty members although were mostly enthused to apply what they learned after a 3 months period they were caught up with routine presentations and lecturing.

Keywords: higher education, faculty development, Saudi Arabia, higher order thinking skills

Procedia PDF Downloads 458

Authors: Sijia Guo

Abstract:

The development of new technologies and the falling cost of high-speed Internet access have made it easier for institutes and language teachers to opt different ways to communicate with students at distance. The emergence of web-conferencing applications, which integrate text, chat, audio / video and graphic facilities, offers great opportunities for language learning to through the multimodal environment. This paper reports on data elicited from a Ph.D. study of using web-conferencing in the teaching of first-year Chinese class in order to promote learners’ collaborative learning. Firstly, a comparison of four desktop videoconferencing (DVC) tools was conducted to determine the pedagogical value of the videoconferencing tool-Blackboard Collaborate. Secondly, the evaluation of 14 campus-based Chinese learners who conducted five one-hour online sessions via the multimodal environment reveals the users’ choice of modes and their learning preference. The findings show that the tasks designed for the web-conferencing environment contributed to the learners’ collaborative learning and second language acquisition.

Keywords: computer-mediated communication (CMC), CALL evaluation, TBLT, web-conferencing, online Chinese teaching

Procedia PDF Downloads 310

Authors: Lakshmi Prayaga, Chandra Prayaga. Aaron Wade, Gopi Shankar Mallu, Harsha Satya Pola

Abstract:

Synthetic data generated by Generative Adversarial Networks and Autoencoders is becoming more common to combat the problem of insufficient data for research purposes. However, generating synthetic data is a tedious task requiring extensive mathematical and programming background. Open-source platforms such as the Synthetic Data Vault (SDV) and Mostly AI have offered a platform that is user-friendly and accessible to non-technical professionals to generate synthetic data to augment existing data for further analysis. The SDV also provides for additions to the generic GAN, such as the Gaussian copula. We present the results from two synthetic data sets (CTGAN data and CTGAN with Gaussian Copula) generated by the SDV and report the findings. The results indicate that the ROC and AUC curves for the data generated by adding the layer of Gaussian copula are much higher than the data generated by the CTGAN.

Keywords: synthetic data generation, generative adversarial networks, conditional tabular GAN, Gaussian copula

Procedia PDF Downloads 84

Authors: Mansouri Nabila, Ben Jemaa Yousra, Motamed Cina, Watelain Eric

Abstract:

Research and development efforts in intelligent Advanced Driver Assistance Systems (ADAS) seek to save lives and reduce the number of on-road fatalities. For traffic and emergency monitoring, the essential but challenging task is vehicle detection and tracking in reasonably short time. This purpose needs first of all a powerful dynamic car detector model. In fact, this paper presents an optimized HOG process based on shape and motion parameters fusion. Our proposed approach mains to compute HOG by bloc feature from foreground blobs using configurable research window and pathway in order to overcome the shortcoming in term of computing time of HOG descriptor and improve their dynamic application performance. Indeed we prove in this paper that HOG by bloc descriptor combined with motion parameters is a very suitable car detector which reaches in record time a satisfactory recognition rate in dynamic outside area and bypasses several popular works without using sophisticated and expensive architectures such as GPU and FPGA.

Keywords: car-detector, HOG, motion, computing time

Procedia PDF Downloads 323

Authors: Hyon I. Paek, Sang Rim Kim, Hyon A. Ryu

Abstract:

In functional linear regression, one typical problem is to reduce dimension. Compared with multivariate linear regression, functional linear regression is regarded as an infinite-dimensional case, and the main task is to reduce dimensions of functional response and functional predictors. One common approach is to adapt functional principal component analysis (FPCA) on functional predictors and then use a few leading functional principal components (FPC) to predict the functional model. The leading FPCs estimated by the typical FPCA explain a major variation of the functional predictor, but these leading FPCs may not be mostly correlated with the functional response, so they may not be significant in the prediction for response. In this paper, we propose a supervised functional principal component analysis method for a functional response model with FPCs obtained by considering the correlation of the functional response. Our method would have a better prediction accuracy than the typical FPCA method.

Keywords: supervised, functional principal component analysis, functional response, functional linear regression

Procedia PDF Downloads 77

Authors: Merve Akca

Abstract:

Retrieval-induced forgetting (RIF) refers to the phenomenon that selective retrieval of some information impairs memory for related, but not previously retrieved information. Despite age differences in retrieval-induced forgetting regarding retrospective memory being documented, this research aimed to highlight age differences in RIF of the prospective memory tasks for the first time. By using retrieval-practice paradigm, this study comparatively examined RIF effects in retrospective memory and event-based prospective memory in young and old adults. In this experimental study, a mixed factorial design with age group (Young, Old) as a between-subject variable, and memory type (Prospective, Retrospective) and item type (Practiced, Non-practiced) as within-subject variables was employed. Retrieval-induced forgetting was observed in the retrospective but not in the prospective memory task. Therefore, the results indicated that selective retrieval of past events led to suppression of other related past events in both age groups but not the suppression of memory for future intentions.

Keywords: prospective memory, retrieval-induced forgetting, retrieval inhibition, retrospective memory

Procedia PDF Downloads 317

Authors: Xiuying Wang, Changliang Li, Bo Xu

Abstract:

A fixed-length feature vector is required for many machine learning algorithms in NLP field. Word embeddings have been very successful at learning lexical information. However, they cannot capture the compositional meaning of sentences, which prevents them from a deeper understanding of language. In this paper, we introduce a novel hierarchical tree long short-term memory (HTLSTM) model that learns vector representations for sentences of arbitrary syntactic type and length. We propose to split one sentence into three hierarchies: short phrase, long phrase and full sentence level. The HTLSTM model gives our algorithm the potential to fully consider the hierarchical information and long-term dependencies of language. We design the experiments on both English and Chinese corpus to evaluate our model on sentiment analysis task. And the results show that our model outperforms several existing state of the art approaches significantly.

Keywords: deep learning, hierarchical tree long short-term memory, sentence representation, sentiment analysis

Procedia PDF Downloads 349

Authors: Jessica To

Abstract:

Feedback is one of the powerful levers for enhancing students’ performance. However, some students are under-engaged with feedback because they lack responsibility for feedback uptake. To resolve this conundrum, recent literature proposes feedback partnerships in which students and teachers share the power and responsibilities to co-construct feedback. During feedback co-construction, students express feedback needs to teachers, and teachers respond to individuals’ needs in return. Though this approach can increase students’ feedback ownership, its application is lagging as the field lacks conceptual clarity and implementation guide. This presentation aims to discuss the conceptual framework of feedback partnerships and feedback co-construction strategies. It identifies the components of feedback partnerships and strategies which could facilitate feedback co-construction. A systematic literature review was conducted to answer the questions. The literature search was performed using ERIC, PsycINFO, and Google Scholar with the keywords “assessment partnership”, “student as partner,” and “feedback engagement”. No time limit was set for the search. The inclusion criteria encompassed (i) student-teacher partnerships in feedback, (ii) feedback engagement in higher education, (iii) peer-reviewed publications, and (iv) English as the language of publication. Those without addressing conceptual understanding and implementation strategies were excluded. Finally, 65 publications were identified and analysed using thematic analysis. For the procedure, the texts relating to the questions were first extracted. Then, codes were assigned to summarise the ideas of the texts. Upon subsuming similar codes into themes, four themes emerged: students’ responsibilities, teachers’ responsibilities, conditions for partnerships development, and strategies. Their interrelationships were examined iteratively for framework development. Establishing feedback partnerships required different responsibilities of students and teachers during feedback co-construction. Students needed to self-evaluate performance against task criteria, identify inadequacies and communicate their needs to teachers. During feedback exchanges, they interpreted teachers’ comments, generated self-feedback through reflection, and co-developed improvement plans with teachers. Teachers had to increase students’ understanding of criteria and evaluation skills and create opportunities for students’ expression of feedback needs. In feedback dialogue, teachers responded to students’ needs and advised on the improvement plans. Feedback partnerships would be best grounded in an environment with trust and psychological safety. Four strategies could facilitate feedback co-construction. First, students’ understanding of task criteria could be increased by rubrics explanation and exemplar analysis. Second, students could sharpen evaluation skills if they participated in peer review and received teacher feedback on the quality of peer feedback. Third, provision of self-evaluation checklists and prompts and teacher modeling of self-assessment process could aid students in articulating feedback needs. Fourth, the trust could be fostered when teachers explained the benefits of feedback co-construction, showed empathy, and provided personalised comments in dialogue. Some strategies were applied in interactive cover sheets in which students performed self-evaluation and made feedback requests on a cover sheet during assignment submission, followed by teachers’ response to individuals’ requests. The significance of this presentation lies in unpacking the conceptual framework of feedback partnerships and outlining feedback co-construction strategies. With a solid foundation in theory and practice, researchers and teachers could better enhance students’ engagement with feedback.

Keywords: conceptual framework, feedback co-construction, feedback partnerships, implementation strategies

Procedia PDF Downloads 91

Authors: Yogendra Sisodia

Abstract:

Researchers are becoming more interested in extracting useful information from legal documents thanks to the development of large-scale language models in natural language processing (NLP), and deep learning has accelerated the creation of powerful text mining models. Legal fields like contracts benefit greatly from semantic text search since it makes it quick and easy to find related clauses. After collecting sentence embeddings, it is relatively simple to locate sentences with a comparable meaning throughout the entire legal corpus. The author of this research investigated two pre-trained language models for this task: MiniLM and Roberta, and further fine-tuned them on Legal Contracts. The author used Multiple Negative Ranking Loss for the creation of sentence transformers. The fine-tuned language models and sentence transformers showed promising results.

Keywords: legal contracts, multiple negative ranking loss, natural language inference, sentence transformers, semantic textual similarity

Procedia PDF Downloads 109

Authors: Misrak Assefa

Abstract:

The Amharic language is the second most widely spoken Semitic language in the world. There are several new overloaded on the web. Searching some useful documents from the web on a specific topic, which is written in the Amharic language, is a challenging task. Hence, document categorization is required for managing and filtering important information. In the classification of Amharic text news, there is still a gap in the domain of information that needs to be launch. This study attempts to design an automatic Amharic news classification using a supervised learning mechanism on four un-touch classes. To achieve this research, 4,182 news articles were used. Naive Bayes (NB) and Decision tree (j48) algorithms were used to classify the given Amharic dataset. In this paper, k-fold cross-validation is used to estimate the accuracy of the classifier. As a result, it shows those algorithms can be applicable in Amharic news categorization. The best average accuracy result is achieved by j48 decision tree and naïve Bayes is 95.2345 %, and 94.6245 % respectively using three categories. This research indicated that a typical decision tree algorithm is more applicable to Amharic news categorization.

Keywords: text categorization, supervised machine learning, naive Bayes, decision tree

Procedia PDF Downloads 211

Authors: S. B. Kerur, B. S. Murgayya

Abstract:

The development of micro and nano particle is challenging task and the study of the behavior of material at the micro level is gaining importance as their behavior at micro/nano level is different. These micro particle are being used as a sensing element to measure and detects the hazardous chemical, gases, explosives and biological agents. In the present study, finite element method is used for static and dynamic analysis of simple and composite cantilever beams of different shapes. The present FE model is validated with available analytical results and various parameters like shape, materials properties, damped and undamped conditions are considered for the numerical study. The results show the effects of shape change on the natural frequency and as these are used with fluid for chemical applications, the effect of damping due to viscous nature of fluid are simulated by considering different damping coefficient effect on the dynamic behavior of cantilever beams. The obtained results show the effect of these parameters can be effectively utilized based on system requirements.

Keywords: micro, FEM, dynamic, cantilever beam

Procedia PDF Downloads 384

Authors: Rafia Rafique, Arifa Khadim

Abstract:

This research investigates the moderating role of job satisfaction between organizational learning and work performance among nurses. Correlation research design was used. Non-probability purposive sampling technique was utilized to recruit a sample of 110 nurses from public hospitals situated in the city of Lahore. The construct of organizational learning was measured using subscale of Integrated Scale for Measuring Organizational Learning. Job satisfaction was measured with the help of Job Satisfaction Survey. Performance of employees (task performance, contextual performance and counterproductive work behavior) was assessed by Individual Work Performance Questionnaire. Job satisfaction negatively moderates the relationship between organizational learning and counterproductive work behavior. Education has a significant positive relationship with organizational learning. Age, current hospital experience, marital satisfaction and salary of the nurses have positive relationship while number of children has significant negative relationship with counterproductive work behavior. These outcomes can be insightful in understanding the dynamics involved in work performance. Based on the result of this study relevant solutions can be proposed to improve the work performance of nurses.

Keywords: counterproductive work behavior, nurses, organizational learning, work performance

Procedia PDF Downloads 446