Search results for: learning orientation
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 7953

Search results for: learning orientation

2673 On Improving Breast Cancer Prediction Using GRNN-CP

Authors: Kefaya Qaddoum

Abstract:

The aim of this study is to predict breast cancer and to construct a supportive model that will stimulate a more reliable prediction as a factor that is fundamental for public health. In this study, we utilize general regression neural networks (GRNN) to replace the normal predictions with prediction periods to achieve a reasonable percentage of confidence. The mechanism employed here utilises a machine learning system called conformal prediction (CP), in order to assign consistent confidence measures to predictions, which are combined with GRNN. We apply the resulting algorithm to the problem of breast cancer diagnosis. The results show that the prediction constructed by this method is reasonable and could be useful in practice.

Keywords: neural network, conformal prediction, cancer classification, regression

Procedia PDF Downloads 271
2672 Knowledge Creation and Diffusion Dynamics under Stable and Turbulent Environment for Organizational Performance Optimization

Authors: Jessica Gu, Yu Chen

Abstract:

Knowledge Management (KM) is undoubtable crucial to organizational value creation, learning, and adaptation. Although the rapidly growing KM domain has been fueled with full-fledged methodologies and technologies, studies on KM evolution that bridge the organizational performance and adaptation to the organizational environment are still rarely attempted. In particular, creation (or generation) and diffusion (or share/exchange) of knowledge are of the organizational primary concerns on the problem-solving perspective, however, the optimized distribution of knowledge creation and diffusion endeavors are still unknown to knowledge workers. This research proposed an agent-based model of knowledge creation and diffusion in an organization, aiming at elucidating how the intertwining knowledge flows at microscopic level lead to optimized organizational performance at macroscopic level through evolution, and exploring what exogenous interventions by the policy maker and endogenous adjustments of the knowledge workers can better cope with different environmental conditions. With the developed model, a series of simulation experiments are conducted. Both long-term steady-state and time-dependent developmental results on organizational performance, network and structure, social interaction and learning among individuals, knowledge audit and stocktaking, and the likelihood of choosing knowledge creation and diffusion by the knowledge workers are obtained. One of the interesting findings reveals a non-monotonic phenomenon on organizational performance under turbulent environment while a monotonic phenomenon on organizational performance under a stable environment. Hence, whether the environmental condition is turbulence or stable, the most suitable exogenous KM policy and endogenous knowledge creation and diffusion choice adjustments can be identified for achieving the optimized organizational performance. Additional influential variables are further discussed and future work directions are finally elaborated. The proposed agent-based model generates evidence on how knowledge worker strategically allocates efforts on knowledge creation and diffusion, how the bottom-up interactions among individuals lead to emerged structure and optimized performance, and how environmental conditions bring in challenges to the organization system. Meanwhile, it serves as a roadmap and offers great macro and long-term insights to policy makers without interrupting the real organizational operation, sacrificing huge overhead cost, or introducing undesired panic to employees.

Keywords: knowledge creation, knowledge diffusion, agent-based modeling, organizational performance, decision making evolution

Procedia PDF Downloads 229
2671 Survey on Big Data Stream Classification by Decision Tree

Authors: Mansoureh Ghiasabadi Farahani, Samira Kalantary, Sara Taghi-Pour, Mahboubeh Shamsi

Abstract:

Nowadays, the development of computers technology and its recent applications provide access to new types of data, which have not been considered by the traditional data analysts. Two particularly interesting characteristics of such data sets include their huge size and streaming nature .Incremental learning techniques have been used extensively to address the data stream classification problem. This paper presents a concise survey on the obstacles and the requirements issues classifying data streams with using decision tree. The most important issue is to maintain a balance between accuracy and efficiency, the algorithm should provide good classification performance with a reasonable time response.

Keywords: big data, data streams, classification, decision tree

Procedia PDF Downloads 505
2670 Effective Use of Visuals in Teaching Mathematics

Authors: Gohar Marikyan

Abstract:

This article is about investigating how to effectively use visuals in teaching introductory mathematics. The analysis showed the use of visuals in teaching introductory mathematics can be an effective tool for enhancing students’ learning and engagement in mathematics. The use of visuals was particularly effective for teaching concepts of numbers, operations with whole numbers, and properties of operations. The analysis also provides strong evidence that the effectiveness of visuals varied depending on the way the visuals are used. Furthermore, the analysis revealed that the use of visuals in mathematics instruction had a positive impact on student’s attitudes toward mathematics, with students showing higher levels of motivation and enjoyment in mathematics classes.

Keywords: analytical thinking skills, instructional strategies with visuals, introductory mathematics, student engagement and motivation

Procedia PDF Downloads 110
2669 Synthesis and Characterization of Highly Oriented Bismuth Oxyiodide Thin Films for the Photocatalytical Degradation of Pharmaceuticals Compounds in Water

Authors: Juan C. Duran-Alvarez, Daniel Mejia, Rodolfo Zanella

Abstract:

Heterogeneous photocatalysis is a promising method to achieve the complete degradation and mineralization of organic pollutants in water via their exhaustive oxidation. In order to take this advanced oxidation process towards sustainability, it is necessary to reduce the energy consumption, referred as the light sources and the post-treatment operations. For this, the synthesis of new nanostructures of low band gap semiconductors in the form of thin films is in continuous development. In this work, thin films of the low band gap semiconductor bismuth oxyiodide (BiOI) were synthesized via the Successive Ionic Layer Adsorption and Reaction (SILAR) method. For this, Bi(NO3)3 and KI solutions were prepared, and glass supports were immersed in each solution under strict rate and time immersion conditions. Synthesis was performed at room temperature and a washing step was set prior to each immersion. Thin films with an average thickness below 100 nm were obtained upon a cycle of 30 immersions, as determined by AFM and profilometry measurements. Cubic BiOI nanocrystals with average size of 17 nm and a high orientation to the 001 plane were observed by XRD. In order to optimize the synthesis method, several Bi/I ratios were tested, namely 1/1, 1/5, 1/10, 1/20 and 1/50. The highest crystallinity of the BiOI films was observed when the 1/5 ratio was used in the synthesis. Non-stoichiometric conditions also resulted in the highest uniformity of the thin layers. PVP was used as an additive to improve the adherence of the BiOI thin films to the support. The addition of 0.1 mg/mL of PVP during the washing step resulted in the highest adherence of the thin films. In photocatalysis tests, degradation rate of the antibiotic ciprofloxacin as high as 75% was achieved using visible light (380 to 700 nm) irradiation for 5 h in batch tests. Mineralization of the antibiotic was also observed, although in a lower extent; ~ 30% of the total organic carbon was removed upon 5 h of visible light irradiation. Some ciprofloxacin by-products were identified throughout the reaction; and some of these molecules displayed residual antibiotic activity. In conclusion, it is possible to obtain highly oriented BiOI thin films under ambient conditions via the SILAR method. Non-stoichiometric conditions using PVP additive are necessary to increase the crystallinity and adherence of the films, which are photocatalytically active to remove recalcitrant organic pollutants under visible light irradiation.

Keywords: bismuth oxyhalides, photocatalysis, thin films, water treatment

Procedia PDF Downloads 108
2668 The Differential Impacts of Shame and Guilt on Father Involvement in Families with Special Needs Children

Authors: Lo Kai Chung

Abstract:

Fathers in the family of disabled children play a crucial role in fostering child development. Previous studies addressing emotions of father involvement in rearing children with special needs have been rare. With reference to the cultural orientation and masculine idea of Chinese fathers, shame and guilt are probable causal emotions that affect fathers’ psycho-behavioral reactions and, thus, father involvement. Based on the findings of our earlier qualitative studies, the current study aims to develop and validate a multi-item scale of guilt or shame and explore their relations with and fatherhood in families with children with special needs. A model is proposed to understand the roles that shame and guilt play in affecting fathers’ involvement in their family system. The severity and type of the child’s special needs are regarded as independent variables affecting the father’s emotional responses – shame and guilt. It is hypothesized that shame and guilt, under the influence of masculinity, lead to avoidance and compensation, respectively, which subsequently decrease and increase father involvement with children with special needs. A cross-sectional online questionnaire survey of fathers with children with special needs recruited by convenience sampling was conducted. Potential participants were reached by bulk emails, related groups on the Internet and education/social services providers. Totally 537 valid sets of online questionnaires were collected from fathers of children with special needs. EFA on the items pool of shame and guilt was performed, resulting in an x-item single-factor solution and y-item single-factor solution, respectively. Further path model analysis revealed that shame and guilt, under the influence of masculinity, showed differential avoidance and compensation responses and resulted in a decrease and increase in father involvement with special needs children. Demographic and key confounding variables were controlled in the analysis. The shame and guilt scales developed show good psychometric properties. Furthermore, they showed significant differential impacts, under the influence of masculinity, on avoidance and compensation behaviours, consequently resulting in a decrease/increase in father involvement in the expected directions. The findings have important theoretical and practical implications. At the community and policy level, the findings inform the design of strategies for strengthening the role of men in families with special needs children.

Keywords: emotions, father involvement, guilt, shame, special needs

Procedia PDF Downloads 52
2667 The Impact of Entrepreneurship Education on the Entrepreneurial Tendencies of Students: A Quasi-Experimental Design

Authors: Lamia Emam

Abstract:

The attractiveness of entrepreneurship education stems from its perceived value as a venue through which students can develop an entrepreneurial mindset, skill set, and practice, which may not necessarily lead to them starting a new business, but could, more importantly, be manifested as a life skill that could be applied to all types of organizations and career endeavors. This, in turn, raises important questions about what happens in our classrooms; our role as educators, the role of students, center of learning, and the instructional approach; all of which eventually contribute to achieving the desired EE outcomes. With application to an undergraduate entrepreneurship course -Entrepreneurship as Practice- the current paper aims to explore the effect of entrepreneurship education on the development of students’ general entrepreneurial tendencies. Towards that purpose, the researcher herein uses a pre-test and post-test quasi-experimental research design where the Durham University General Enterprising Tendency Test (GET2) is administered to the same group of students before and after course delivery. As designed and delivered, the Entrepreneurship as Practice module is a highly applied and experiential course where students are required to develop an idea for a start-up while practicing the entrepreneurship-related knowledge, mindset, and skills that are taught in class, both individually and in groups. The course is delivered using a combination of short lectures, readings, group discussions, case analysis, guest speakers, and, more importantly, actively engaging in a series of activities that are inspired by diverse methods for developing successful and innovative business ideas, including design thinking, lean-start up and business feasibility analysis. The instructional approach of the course particularly aims at developing the students' critical thinking, reflective, analytical, and creativity-based problem-solving skills that are needed to launch one’s own start-up. The analysis and interpretation of the experiment’s outcomes shall simultaneously incorporate the views of both the educator and students. As presented, the study responds to the rising call for the application of experimental designs in entrepreneurship in general and EE in particular. While doing so, the paper presents an educator’s perspective of EE to complement the dominant stream of research which is constrained to the students’ point of view. Finally, the study sheds light on EE in the MENA region, where the study is applied.

Keywords: entrepreneurship education, andragogy and heutagogy, scholarship of teaching and learning, experiment

Procedia PDF Downloads 109
2666 Computational Modelling of pH-Responsive Nanovalves in Controlled-Release System

Authors: Tomilola J. Ajayi

Abstract:

A category of nanovalves system containing the α-cyclodextrin (α-CD) ring on a stalk tethered to the pores of mesoporous silica nanoparticles (MSN) is theoretically and computationally modelled. This functions to control opening and blocking of the MSN pores for efficient targeted drug release system. Modeling of the nanovalves is based on the interaction between α-CD and the stalk (p-anisidine) in relation to pH variation. Conformational analysis was carried out prior to the formation of the inclusion complex, to find the global minimum of both neutral and protonated stalk. B3LYP/6-311G**(d, p) basis set was employed to attain all theoretically possible conformers of the stalk. Six conformers were taken into considerations, and the dihedral angle (θ) around the reference atom (N17) of the p-anisidine stalk was scanned from 0° to 360° at 5° intervals. The most stable conformer was obtained at a dihedral angle of 85.3° and was fully optimized at B3LYP/6-311G**(d, p) level of theory. The most stable conformer obtained from conformational analysis was used as the starting structure to create the inclusion complexes. 9 complexes were formed by moving the neutral guest into the α-CD cavity along the Z-axis in 1 Å stepwise while keeping the distance between dummy atom and OMe oxygen atom on the stalk restricted. The dummy atom and the carbon atoms on α-CD structure were equally restricted for orientation A (see Scheme 1). The generated structures at each step were optimized with B3LYP/6-311G**(d, p) methods to determine their energy minima. Protonation of the nitrogen atom on the stalk occurs at acidic pH, leading to unsatisfactory host-guest interaction in the nanogate; hence there is dethreading. High required interaction energy and conformational change are theoretically established to drive the release of α-CD at a certain pH. The release was found to occur between pH 5-7 which agreed with reported experimental results. In this study, we applied the theoretical model for the prediction of the experimentally observed pH-responsive nanovalves which enables blocking, and opening of mesoporous silica nanoparticles pores for targeted drug release system. Our results show that two major factors are responsible for the cargo release at acidic pH. The higher interaction energy needed for the complex/nanovalve formation to exist after protonation as well as conformational change upon protonation are driving the release due to slight pH change from 5 to 7.

Keywords: nanovalves, nanogate, mesoporous silica nanoparticles, cargo

Procedia PDF Downloads 110
2665 Genome-Wide Mining of Potential Guide RNAs for Streptococcus pyogenes and Neisseria meningitides CRISPR-Cas Systems for Genome Engineering

Authors: Farahnaz Sadat Golestan Hashemi, Mohd Razi Ismail, Mohd Y. Rafii

Abstract:

Clustered regularly interspaced short palindromic repeats (CRISPR) and CRISPR-associated protein (Cas) system can facilitate targeted genome editing in organisms. Dual or single guide RNA (gRNA) can program the Cas9 nuclease to cut target DNA in particular areas; thus, introducing concise mutations either via error-prone non-homologous end-joining repairing or via incorporating foreign DNAs by homologous recombination between donor DNA and target area. In spite of high demand of such promising technology, developing a well-organized procedure in order for reliable mining of potential target sites for gRNAs in large genomic data is still challenging. Hence, we aimed to perform high-throughput detection of target sites by specific PAMs for not only common Streptococcus pyogenes (SpCas9) but also for Neisseria meningitides (NmCas9) CRISPR-Cas systems. Previous research confirmed the successful application of such RNA-guided Cas9 orthologs for effective gene targeting and subsequently genome manipulation. However, Cas9 orthologs need their particular PAM sequence for DNA cleavage activity. Activity levels are based on the sequence of the protospacer and specific combinations of favorable PAM bases. Therefore, based on the specific length and sequence of PAM followed by a constant length of the target site for the two orthogonals of Cas9 protein, we created a reliable procedure to explore possible gRNA sequences. To mine CRISPR target sites, four different searching modes of sgRNA binding to target DNA strand were applied. These searching modes are as follows i) coding strand searching, ii) anti-coding strand searching, iii) both strand searching, and iv) paired-gRNA searching. Finally, a complete list of all potential gRNAs along with their locations, strands, and PAMs sequence orientation can be provided for both SpCas9 as well as another potential Cas9 ortholog (NmCas9). The artificial design of potential gRNAs in a genome of interest can accelerate functional genomic studies. Consequently, the application of such novel genome editing tool (CRISPR/Cas technology) will enhance by presenting increased versatility and efficiency.

Keywords: CRISPR/Cas9 genome editing, gRNA mining, SpCas9, NmCas9

Procedia PDF Downloads 245
2664 Transition from Early Education to Pre-School Education in Children with Hearing Loss in Turkey: Problems and Recommendations

Authors: Şule Yanık, Emel Ertürk-Mustul, Zerrin Turan, Hasan Gürgür

Abstract:

It is known that there are policies that will support the early special education (ESE) for children requiring special care including the children with hearing loss (CHL) in many countries that give importance to early childhood (0-6 years) education, accordingly ESE services have been gradually increasing and these services provide positive contributions to the child and family. These services begin with medical diagnostics, provision of the use of assistive technologies for hearing and the orientation of children towards early education program (EEP) for the CHL. In 0-3 years of age EEP, education and support services are provided to the children and their families. In 3-6 years of age, children are supported in a pre-school education program (PSE) in which their peers and teachers are present. Therefore, the children with hearing loss and their families are going through a series of medical, educational and social transition process after diagnosed with hearing loss. Depending on their age and development, CHL also go through a transition period from hospital to home, from home to EEP and from EEP to PSE. It is seen that there is no legal regulation regarding the transition process in Turkey and hence different processes have been carried out in the transition process from EEP to PSE. The aim of this study is to reveal the problems confronted by the CHL during the transition period from EEP to PSE and the solution proposals for these problems. In this study, a document review was made by reviewing the national and international studies about transition processes of the CHL in Turkey from EEP to PSE. Accordingly, in the study carried out in two stages, firstly, a review of the body of literature was performed by creating key words related to the subject. Secondly, the problems confronted by the CHL in Turkey during the transition period from EEP to PSE and the solution proposals for these problems were demonstrated by analyzing the obtained data. According to the body of literature, it is seen that there are no laws concerning the transition processes of the children who require special care including the CHL in Turkey from EEP (sending) to PSE (receiving), and correspondingly numerous problems have been experienced during the transition period. It seems that the EEP adopts family-centered approaches for strengthening the families of the CHL. However, PSE program aims to prepare the children to school life by focusing on their social and academical development rather with the adoption of children-centered approaches. Therefore, while the families feel an inseparable part of the team in EEP, they indicated that they felt like a stranger in the school team after their children have started to PSE. Therefore, families find the transition processes worrisome and state that they are not satisfied with the process. We discovered that in the process of transition from EEP to PSE, families are not informed, there is a limited number of PSE options available, children cannot adapt to the new educational environment and cannot benefit from the existing PSE.

Keywords: early education program, early special education, children with hearing loss, transition

Procedia PDF Downloads 129
2663 Acceptability and Challenges Experienced by Homosexual Indigenous Peoples in Southern Palawan

Authors: Crisanto H. Ecaldre

Abstract:

Gender perception represents how an individual perceives the gender identity of a person. Since this is a subjective assessment, it paves the way to various social reactions, either in the form of acceptance or discrimination. Reports across the world show that lesbian, gay, bisexual, or transgender (LGBT) people often face discrimination, stigmatization, and targeted violence because of their sexual orientation or gender identity. However, the challenges faced by those who belong to both a sexual minority and a marginalized ethnic, religious, linguistic, or indigenous community are even more complex. Specifically, in Palaw’an community, members own those who identify themselves as gays or lesbians and use “bantut” to identify them. There was also the introduction of various scholarly works to facilitate dialogues that promote visibility and inclusivity across sectors in terms of gender preferences; however, there are still gaps that need to be addressed in terms of recognition and visibility. Though local research initiatives are slowly increasing in terms of numbers, culturally situating gender studies appropriately within the context of indigenous cultural communities is still lacking. Indigenous community-based discourses on gender or indigenizing gender discourses remain a challenge; hence, this study aimed to contribute to addressing these identified gaps. These research objectives were realized through a qualitative approach following an exploratory design. Findings revealed that the Palaw’an indigenous cultural community has an existing concept of homosexuality, which they termed “bantut.” This notion was culturally defined by the participants as (a) kaloob ng diwata; (b) a manifestation of physical inferiority; (c) hindi nakapag-asawa or hindi nagka-anak; and (d) based on the ascribed roles by the community. These were recognized and valued by the community. However, despite the recognition and visibility within the community, the outside people view them otherwise. The challenges experienced by the Palaw’an homosexuals are imposed by the people outside their community, and these include prejudice, discrimination, and double marginalization. Because of these struggles, they are forced to cope. They deal with these imposed limitations, biases, and burdens by non-Palaw’an through self-acceptance, strong self-perception, and the option to leave the community to seek a more open and progressive environment for LGBTs. While these are indications of their ‘resilience’ amidst difficult situations, this reality poses an important concern -how the recognition and visibility of indigenous homosexuals from the mainstream perspective can be attained.

Keywords: gender preference, acceptability, challenge, recognition, visibility, coping

Procedia PDF Downloads 43
2662 Quasi-Photon Monte Carlo on Radiative Heat Transfer: An Importance Sampling and Learning Approach

Authors: Utkarsh A. Mishra, Ankit Bansal

Abstract:

At high temperature, radiative heat transfer is the dominant mode of heat transfer. It is governed by various phenomena such as photon emission, absorption, and scattering. The solution of the governing integrodifferential equation of radiative transfer is a complex process, more when the effect of participating medium and wavelength properties are taken into consideration. Although a generic formulation of such radiative transport problem can be modeled for a wide variety of problems with non-gray, non-diffusive surfaces, there is always a trade-off between simplicity and accuracy of the problem. Recently, solutions of complicated mathematical problems with statistical methods based on randomization of naturally occurring phenomena have gained significant importance. Photon bundles with discrete energy can be replicated with random numbers describing the emission, absorption, and scattering processes. Photon Monte Carlo (PMC) is a simple, yet powerful technique, to solve radiative transfer problems in complicated geometries with arbitrary participating medium. The method, on the one hand, increases the accuracy of estimation, and on the other hand, increases the computational cost. The participating media -generally a gas, such as CO₂, CO, and H₂O- present complex emission and absorption spectra. To model the emission/absorption accurately with random numbers requires a weighted sampling as different sections of the spectrum carries different importance. Importance sampling (IS) was implemented to sample random photon of arbitrary wavelength, and the sampled data provided unbiased training of MC estimators for better results. A better replacement to uniform random numbers is using deterministic, quasi-random sequences. Halton, Sobol, and Faure Low-Discrepancy Sequences are used in this study. They possess better space-filling performance than the uniform random number generator and gives rise to a low variance, stable Quasi-Monte Carlo (QMC) estimators with faster convergence. An optimal supervised learning scheme was further considered to reduce the computation costs of the PMC simulation. A one-dimensional plane-parallel slab problem with participating media was formulated. The history of some randomly sampled photon bundles is recorded to train an Artificial Neural Network (ANN), back-propagation model. The flux was calculated using the standard quasi PMC and was considered to be the training target. Results obtained with the proposed model for the one-dimensional problem are compared with the exact analytical and PMC model with the Line by Line (LBL) spectral model. The approximate variance obtained was around 3.14%. Results were analyzed with respect to time and the total flux in both cases. A significant reduction in variance as well a faster rate of convergence was observed in the case of the QMC method over the standard PMC method. However, the results obtained with the ANN method resulted in greater variance (around 25-28%) as compared to the other cases. There is a great scope of machine learning models to help in further reduction of computation cost once trained successfully. Multiple ways of selecting the input data as well as various architectures will be tried such that the concerned environment can be fully addressed to the ANN model. Better results can be achieved in this unexplored domain.

Keywords: radiative heat transfer, Monte Carlo Method, pseudo-random numbers, low discrepancy sequences, artificial neural networks

Procedia PDF Downloads 211
2661 A Challenge of the 3ʳᵈ Millenium: The Emotional Intelligence Development

Authors: Florentina Hahaianu, Mihaela Negrescu

Abstract:

The analysis of the positive and negative effects of technology use and abuse in Generation Z comes as a necessity in order to understand their ever-changing emotional development needs. The article quantitatively analyzes the findings of a sociological questionnaire on a group of students in social sciences. It aimed to identify the changes generated by the use of digital resources in the emotional intelligence development. Among the outcomes of our study we include a predilection for IT related activities – be they social, learning, entertainment, etc. which undermines the manifestation of emotional intelligence, especially the reluctance to face-to-face interaction. In this context, the issue of emotional intelligence development comes into focus as a solution to compensate for the undesirable effects that contact with technology has on this generation.

Keywords: digital resources, emotional intelligence, generation Z, students

Procedia PDF Downloads 188
2660 Depth Estimation in DNN Using Stereo Thermal Image Pairs

Authors: Ahmet Faruk Akyuz, Hasan Sakir Bilge

Abstract:

Depth estimation using stereo images is a challenging problem in computer vision. Many different studies have been carried out to solve this problem. With advancing machine learning, tackling this problem is often done with neural network-based solutions. The images used in these studies are mostly in the visible spectrum. However, the need to use the Infrared (IR) spectrum for depth estimation has emerged because it gives better results than visible spectra in some conditions. At this point, we recommend using thermal-thermal (IR) image pairs for depth estimation. In this study, we used two well-known networks (PSMNet, FADNet) with minor modifications to demonstrate the viability of this idea.

Keywords: thermal stereo matching, deep neural networks, CNN, Depth estimation

Procedia PDF Downloads 262
2659 Neurocognitive and Executive Function in Cocaine Addicted Females

Authors: Gwendolyn Royal-Smith

Abstract:

Cocaine ranks as one of the world’s most addictive and commonly abused stimulant drugs. Recent evidence indicates that the abuse of cocaine has risen so quickly among females that this group now accounts for about 40 percent of all users in the United States. Neuropsychological studies have demonstrated that specific neural activation patterns carry higher risks for neurocognitive and executive function in cocaine addicted females thereby increasing their vulnerability for poorer treatment outcomes and more frequent post-treatment relapse when compared to males. This study examined secondary data with a convenience sample of 164 cocaine addicted male and females to assess neurocognitive and executive function. The principal objective of this study was to assess whether individual performance on the Stroop Word Color Task is predictive of treatment success by gender. A second objective of the study evaluated whether individual performance employing neurocognitive measures including the Stroop Word-Color task, the Rey Auditory Verbal Learning Test (RALVT), the Iowa Gambling Task, the Wisconsin Card Sorting Task (WISCT), the total score from the Barratte Impulsiveness Scale (Version 11) (BIS-11) and the total score from the Frontal Systems Behavioral Scale (FrSBE) test demonstrated differences in neurocognitive and executive function performance by gender. Logistic regression models were employed utilizing a covariate adjusted model application. Initial analyses of the Stroop Word color tasks indicated significant differences in the performance of males and females, with females experiencing more challenges in derived interference reaction time and associate recall ability. In early testing including the Rey Auditory Verbal Learning Test (RALVT), the number of advantageous vs disadvantageous cards from the Iowa Gambling Task, the number of perseverance errors from the Wisconsin Card Sorting Task (WISCT), the total score from the Barratte Impulsiveness Scale (Version 11) (BIS-11) and the total score from the Frontal Systems Behavioral Scale, results were mixed with women scoring lower in multiple indicators in both neurocognitive and executive function.

Keywords: cocaine addiction, gender, neuropsychology, neurocognitive, executive function

Procedia PDF Downloads 386
2658 Artificial Intelligence for All: Artificial Intelligence Education for K-12

Authors: Yiqiao Yin

Abstract:

Many scholars and educators have dedicated their lives in K12 education system and there has been an exploding amount of attention to implement technical foundations for Artificial Intelligence Education for high school and precollege level students. This paper focuses on the development and use of resources to support K-12 education in Artificial Intelligence (AI). The author and his team have more than three years of experience coaching students from pre-college level age from 15 to 18. This paper is a culmination of the experience and proposed online tools, software demos, and structured activities for high school students. The paper also addresses a portfolio of AI concepts as well as the expected learning outcomes. All resources are provided with online videos and Github repositories for immediate use.

Keywords: K12 education, AI4ALL, pre-college education, pre-college AI

Procedia PDF Downloads 120
2657 Understand and Redefine Lean Product Development

Authors: Alemu Moges Belay, Torgeir Welo, Jan Ola Strandhagen

Abstract:

Lean has long been linked with manufacturing, but its application claimed also by other functions such as product development and services. However, there is a challenge on understanding and defining lean in each function context. This paper aims to investigate the literature that focus mainly on PD process improvement, obtain better understanding and redefine LPD in systematic way. In addition to that, the paper attempts to summarize various proposed transformation strategies, definitions, identifying features of manufacturing and product development that would help to redefining lean in product development context. Finally we redefine LPD in organized way that encompasses different steps such as stage gate, communication and information, events, learning, innovation, knowledge and value creation.

Keywords: lean, lean manufacturing, lean product development, transformation, strategies

Procedia PDF Downloads 459
2656 Investigation of Mechanical and Tribological Property of Graphene Reinforced SS-316L Matrix Composite Prepared by Selective Laser Melting

Authors: Ajay Mandal, Jitendar Kumar Tiwari, N. Sathish, A. K. Srivastava

Abstract:

A fundamental investigation is performed on the development of graphene (Gr) reinforced stainless steel 316L (SS 316L) metal matrix composite via selective laser melting (SLM) in order to improve specific strength and wear resistance property of SS 316L. Firstly, SS 316L powder and graphene were mixed in a fixed ratio using low energy planetary ball milling. The milled powder is then subjected to the SLM process to fabricate composite samples at a laser power of 320 W and exposure time of 100 µs. The prepared composite was mechanically tested (hardness and tensile test) at ambient temperature, and obtained results indicate that the properties of the composite increased significantly with the addition of 0.2 wt. % Gr. Increment of about 25% (from 194 to 242 HV) and 70% (from 502 to 850 MPa) is obtained in hardness and yield strength of composite, respectively. Raman mapping and XRD were performed to see the distribution of Gr in the matrix and its effect on the formation of carbide, respectively. Results of Raman mapping show the uniform distribution of graphene inside the matrix. Electron back scatter diffraction (EBSD) map of the prepared composite was analyzed under FESEM in order to understand the microstructure and grain orientation. Due to thermal gradient, elongated grains were observed along the building direction, and grains get finer with the addition of Gr. Most of the mechanical components are subjected to several types of wear conditions. Therefore, it is very necessary to improve the wear property of the component, and hence apart from strength and hardness, a tribological property of composite was also measured under dry sliding condition. Solid lubrication property of Gr plays an important role during the sliding process due to which the wear rate of composite reduces up to 58%. Also, the surface roughness of worn surface reduces up to 70% as measured by 3D surface profilometry. Finally, it can be concluded that SLM is an efficient method of fabricating cutting edge metal matrix nano-composite having Gr like reinforcement, which was very difficult to fabricate through conventional manufacturing techniques. Prepared composite has superior mechanical and tribological properties and can be used for a wide variety of engineering applications. However, due to the unavailability of a considerable amount of literature in a similar domain, more experimental works need to perform, such as thermal property analysis, and is a part of ongoing study.

Keywords: selective laser melting, graphene, composite, mechanical property, tribological property

Procedia PDF Downloads 128
2655 Supports for Student Learning Program: Exploring the Educational Terrain of Newcomer and Refugee Students in Canada

Authors: Edward Shizha, Edward Makwarimba

Abstract:

This literature review explores current research on the educational strengths and barriers of newcomer and refugee youth in Canada. Canada’s shift in immigration policy in the past three decades, from Europe to Asian and African countries as source continents of recent immigrants to Canada, has tremendously increased the ethnic, linguistic, cultural and religious diversity of the population, including that of students in its education system. Over 18% of the country’s population was born in another country, of which 70% are visible minorities. There has been an increase in admitted immigrants and refugees, with a total of 226,203 between July 2020 and June 2021. Newcomer parents and their children in all major destination countries, including Canada, face tremendous challenges, including racism and discrimination, lack of English language skills, poverty, income inequality, unemployment, and underemployment. They face additional challenges, including discrimination against those who cannot speak the official languages, English or French. The severity of the challenges depends on several intersectional factors, including immigrant status (asylum seeker, refugee, or immigrant), age, gender, level of education and others. Through the lens of intersectionality as an explanatory perspective, this literature review examines the educational attainment and outcomes of newcomer and refugee youth in Canada in order to understand their educational needs, educational barriers and strengths. Newcomer youths’ experiences are shaped by numerous intersectional and interconnected sociocultural, sociopolitical, and socioeconomic factors—including gender, migration status, racialized status, ethnicity, socioeconomic class, sexual minority status, age, race—that produce and perpetuate their disadvantage. According to research, immigrants and refugees from visible minority ethnic backgrounds experience exclusions more than newcomers from other backgrounds and groups from the mainstream population. For many immigrant parents, migration provides financial and educational opportunities for their children. Yet, when attending school, newcomer and refugee youth face unique challenges related to racism and discrimination, negative attitudes and stereotypes from teachers and other school authorities, language learning and proficiency, differing levels of acculturation, and different cultural views of the role of parents in relation to teachers and school, and unfamiliarity with the social or school context in Canada. Recognizing discrepancies in educational attainment of newcomer and refugee youth based on their race and immigrant status, the paper develops insights into existing research and data gaps related to educational strengths and challenges for visible minority newcomer youth in Canada. The paper concludes that the educational successes or failures of the newcomer and refugee youth and their settlement and integration into the school system in Canada may depend on where their families settle, the attitudes of the host community and the school officials (teachers, guidance counsellors and school administrators) after-school support programs and their own set of coping mechanisms. Conceivably a unique approach to after-school programming should provide learning supports and opportunities that consider newcomer and refugee youth’s needs, experiences, backgrounds and circumstances. This support is likely to translate into significant academic and psychological well-being of newcomer students.

Keywords: deficit discourse, discrimination, educational outcomes, newcomer and refugee youth, racism, strength-based approach, whiteness

Procedia PDF Downloads 51
2654 Application of Vector Representation for Revealing the Richness of Meaning of Facial Expressions

Authors: Carmel Sofer, Dan Vilenchik, Ron Dotsch, Galia Avidan

Abstract:

Studies investigating emotional facial expressions typically reveal consensus among observes regarding the meaning of basic expressions, whose number ranges between 6 to 15 emotional states. Given this limited number of discrete expressions, how is it that the human vocabulary of emotional states is so rich? The present study argues that perceivers use sequences of these discrete expressions as the basis for a much richer vocabulary of emotional states. Such mechanisms, in which a relatively small number of basic components is expanded to a much larger number of possible combinations of meanings, exist in other human communications modalities, such as spoken language and music. In these modalities, letters and notes, which serve as basic components of spoken language and music respectively, are temporally linked, resulting in the richness of expressions. In the current study, in each trial participants were presented with sequences of two images containing facial expression in different combinations sampled out of the eight static basic expressions (total 64; 8X8). In each trial, using single word participants were required to judge the 'state of mind' portrayed by the person whose face was presented. Utilizing word embedding methods (Global Vectors for Word Representation), employed in the field of Natural Language Processing, and relying on machine learning computational methods, it was found that the perceived meanings of the sequences of facial expressions were a weighted average of the single expressions comprising them, resulting in 22 new emotional states, in addition to the eight, classic basic expressions. An interaction between the first and the second expression in each sequence indicated that every single facial expression modulated the effect of the other facial expression thus leading to a different interpretation ascribed to the sequence as a whole. These findings suggest that the vocabulary of emotional states conveyed by facial expressions is not restricted to the (small) number of discrete facial expressions. Rather, the vocabulary is rich, as it results from combinations of these expressions. In addition, present research suggests that using word embedding in social perception studies, can be a powerful, accurate and efficient tool, to capture explicit and implicit perceptions and intentions. Acknowledgment: The study was supported by a grant from the Ministry of Defense in Israel to GA and CS. CS is also supported by the ABC initiative in Ben-Gurion University of the Negev.

Keywords: Glove, face perception, facial expression perception. , facial expression production, machine learning, word embedding, word2vec

Procedia PDF Downloads 170
2653 Music Listening in Dementia: Current Developments and the Potential for Automated Systems in the Home: Scoping Review and Discussion

Authors: Alexander Street, Nina Wollersberger, Paul Fernie, Leonardo Muller, Ming Hung HSU, Helen Odell-Miller, Jorg Fachner, Patrizia Di Campli San Vito, Stephen Brewster, Hari Shaji, Satvik Venkatesh, Paolo Itaborai, Nicolas Farina, Alexis Kirke, Sube Banerjee, Eduardo Reck Miranda

Abstract:

Escalating neuropsychiatric symptoms (NPS) in people with dementia may lead to earlier care home admission. Music listening has been reported to stimulate cognitive function, potentially reducing agitation in this population. We present a scoping review, reporting on current developments and discussing the potential for music listening with related technology in managing agitation in dementia care. Of two searches for music listening studies, one focused on older people or people living with dementia where music listening interventions, including technology, were delivered in participants’ homes or in institutions to address neuropsychiatric symptoms, quality of life and independence. The second included any population focusing on the use of music technology for health and wellbeing. In search one 70/251 full texts were included. The majority reported either statistical significance (6, 8.5%), significance (17, 24.2%) or improvements (26, 37.1%). Agitation was specifically reported in 36 (51.4%). The second search included 51/99 full texts, reporting improvement (28, 54.9%), significance (11, 21.5%), statistical significance (1, 1.9%) and no difference compared to the control (6, 11.7%). The majority in the first focused on mood and agitation, and the second on mood and psychophysiological responses. Five studies used AI or machine learning systems to select music, all involving healthy controls and reporting benefits. Most studies in both reviews were not conducted in a home environment (review 1 = 12; 17.1%; review 2 = 11; 21.5%). Preferred music listening may help manage NPS in the care home settings. Based on these and other data extracted in the review, a reasonable progression would be to co-design and test music listening systems and protocols for NPS in all settings, including people’s homes. Machine learning and automated technology for music selection and arousal adjustment, driven by live biodata, have not been explored in dementia care. Such approaches may help deliver the right music at the appropriate time in the required dosage, reducing the use of medication and improving quality of life.

Keywords: music listening, dementia, agitation, scoping review, technology

Procedia PDF Downloads 96
2652 An Analytical Review of Tourism Management in India with Special Reference to Maharashtra State

Authors: Anilkumar L. Rathod

Abstract:

This paper examines event tourism as a field of study and area of professional practice updating the previous review article published in 2015. In this substantially extended review, a deeper analysis of the field's evolution and development is presented, charting the growth of the literature, focusing both chronologically and thematically. A framework for understanding and creating knowledge about events and tourism is presented, forming the basis which signposts established research themes and concepts and outlines future directions for research. In addition, the review article focuses on constraining and propelling forces, ontological advances, contributions from key journals, and emerging themes and issues. It also presents a roadmap for research activity in event tourism. Published scholarly studies within this period are examined through content analysis, using such keywords as knowledge management, organizational learning, hospitality, tourism, tourist destinations, travel industry, hotels, lodging, motels, hotel industry, gaming, casino hotel and convention to search scholarly research journals. All contributions found are then screened for a hospitality and tourism theme. Researchers mostly discuss knowledge management approach in improving information technology, marketing and strategic planning in order to gain competitive advantage. Overall, knowledge management research is still limited. Planned events in tourism are created for a purpose, and what was once the realm of individual and community initiatives has largely become the realm of professionals and entrepreneurs provides a typology of the four main categories of planned events within an event-tourism context, including the main venues associated with each. It also assesses whether differences exist between socio-demographic groupings. An analysis using primarily descriptive statistics indicated both sub-samples had similar viewpoints although Maharashtra residents tended to have higher scores pertaining to the consequences of gambling. It is suggested that the differences arise due to the greater exposure of Maharashtra residents to the influences of casino development.

Keywords: organizational learning, hospitality, tourism, tourist destinations, travel industry, hotels, lodging, motels, hotel industry, gaming, casino hotel and convention to search scholarly research journals

Procedia PDF Downloads 226
2651 HTML5 Online Learning Application with Offline Web, Location Based, Animated Web, Multithread, and Real-Time Features

Authors: Sheetal R. Jadhwani, Daisy Sang, Chang-Shyh Peng

Abstract:

Web applications are an integral part of modem life. They are mostly based upon the HyperText Markup Language (HTML). While HTML meets the basic needs, there are some shortcomings. For example, applications can cease to work once user goes offline, real-time updates may be lagging, and user interface can freeze on computationally intensive tasks. The latest language specification HTML5 attempts to rectify the situation with new tools and protocols. This paper studies the new Web Storage, Geolocation, Web Worker, Canvas, and Web Socket APIs, and presents applications to test their features and efficiencies.

Keywords: HTML5, web worker, canvas, web socket

Procedia PDF Downloads 287
2650 Use of Hierarchical Temporal Memory Algorithm in Heart Attack Detection

Authors: Tesnim Charrad, Kaouther Nouira, Ahmed Ferchichi

Abstract:

In order to reduce the number of deaths due to heart problems, we propose the use of Hierarchical Temporal Memory Algorithm (HTM) which is a real time anomaly detection algorithm. HTM is a cortical learning algorithm based on neocortex used for anomaly detection. In other words, it is based on a conceptual theory of how the human brain can work. It is powerful in predicting unusual patterns, anomaly detection and classification. In this paper, HTM have been implemented and tested on ECG datasets in order to detect cardiac anomalies. Experiments showed good performance in terms of specificity, sensitivity and execution time.

Keywords: cardiac anomalies, ECG, HTM, real time anomaly detection

Procedia PDF Downloads 207
2649 Integrating a Six Thinking Hats Approach Into the Prewriting Stage of Argumentative Writing In English as a Foreign Language: A Chinese Case Study of Generating Ideas in Action

Authors: Mei Lin, Chang Liu

Abstract:

Argumentative writing is the most prevalent genre in diverse writing tests. How to construct academic arguments is often regarded as a difficult task by most English as a foreign language (EFL) learners. A failure to generate enough ideas and organise them coherently and logically as well as a lack of competence in supporting their arguments with relevant evidence are frequent problems faced by EFL learners when approaching an English argumentative writing task. Overall, these problems are closely related to planning, and planning an argumentative writing at pre-writing stage plays a vital role in a good academic essay. However, how teachers can effectively guide students to generate ideas is rarely discussed in planning English argumentative writing, apart from brainstorming. Brainstorming has been a common practice used by teachers to help students generate ideas. However, some limitations of brainstorming suggest that it can help students generate many ideas, but ideas might not necessarily be coherent and logic, and could sometimes impede production. It calls for a need to explore effective instructional strategies at pre-writing stage of English argumentative writing. This paper will first examine how a Six Thinking Hats approach can be used to provide a dialogic space for EFL learners to experience and collaboratively generate ideas from multiple perspectives at pre-writing stage. Part of the findings of the impact of a twelve-week intervention (from March to July 2021) on students learning to generate ideas through engaging in group discussions of using Six Thinking Hats will then be reported. The research design is based on the sociocultural theory. The findings present evidence from a mixed-methods approach and fifty-nine participants from two first-year undergraduate natural classes in a Chinese university. Analysis of pre- and post- questionnaires suggests that participants had a positive attitude toward the Six Thinking Hats approach. It fosters their understanding of prewriting and argumentative writing, helps them to generate more ideas not only from multiple perspectives but also in a systematic way. A comparison of participants writing plans confirms an improvement in generating counterarguments and rebuttals to support their arguments. Above all, visual and transcripts data of group discussion collected from different weeks throughout the intervention enable teachers and researchers to ‘see’ the hidden process of learning to generate ideas in action.

Keywords: argumentative writing, innovative pedagogy, six thinking hats, dialogic space, prewriting, higher education

Procedia PDF Downloads 76
2648 Proposed Anticipating Learning Classifier System for Cloud Intrusion Detection (ALCS-CID)

Authors: Wafa' Slaibi Alsharafat

Abstract:

Cloud computing is a modern approach in network environment. According to increased number of network users and online systems, there is a need to help these systems to be away from unauthorized resource access and detect any attempts for privacy contravention. For that purpose, Intrusion Detection System is an effective security mechanism to detect any attempts of attacks for cloud resources and their information. In this paper, Cloud Intrusion Detection System has been proposed in term of reducing or eliminating any attacks. This model concerns about achieving high detection rate after conducting a set of experiments using benchmarks dataset called KDD'99.

Keywords: IDS, cloud computing, anticipating classifier system, intrusion detection

Procedia PDF Downloads 460
2647 People Management, Knowledge Sharing and Intermediary Variables

Authors: Nizar Mansour, Chiha Gaha, Emna Gara

Abstract:

The present research investigates the relationship among HRM practices, knowledge sharing behavior and a certain number of intermediary variables in the context of Tunisian knowledge-intensive firms. Results suggest that five HR practices influence either directly or indirectly the knowledge sharing behavior through enhancing the value of human capital and fostering a learning-oriented organizational climate. Results have strong theoretical implications for both the fields of knowledge management and strategic human resource management. Managerial implications are also derived.

Keywords: human capital, knowledge intensive firms, knowledge sharing, organizational climate, Tunisia

Procedia PDF Downloads 321
2646 Digital Image Correlation: Metrological Characterization in Mechanical Analysis

Authors: D. Signore, M. Ferraiuolo, P. Caramuta, O. Petrella, C. Toscano

Abstract:

The Digital Image Correlation (DIC) is a newly developed optical technique that is spreading in all engineering sectors because it allows the non-destructive estimation of the entire surface deformation without any contact with the component under analysis. These characteristics make the DIC very appealing in all the cases the global deformation state is to be known without using strain gages, which are the most used measuring device. The DIC is applicable to any material subjected to distortion caused by either thermal or mechanical load, allowing to obtain high-definition mapping of displacements and deformations. That is why in the civil and the transportation industry, DIC is very useful for studying the behavior of metallic materials as well as of composite materials. DIC is also used in the medical field for the characterization of the local strain field of the vascular tissues surface subjected to uniaxial tensile loading. DIC can be carried out in the two dimension mode (2D DIC) if a single camera is used or in a three dimension mode (3D DIC) if two cameras are involved. Each point of the test surface framed by the cameras can be associated with a specific pixel of the image, and the coordinates of each point are calculated knowing the relative distance between the two cameras together with their orientation. In both arrangements, when a component is subjected to a load, several images related to different deformation states can be are acquired through the cameras. A specific software analyzes the images via the mutual correlation between the reference image (obtained without any applied load) and those acquired during the deformation giving the relative displacements. In this paper, a metrological characterization of the digital image correlation is performed on aluminum and composite targets both in static and dynamic loading conditions by comparison between DIC and strain gauges measures. In the static test, interesting results have been obtained thanks to an excellent agreement between the two measuring techniques. In addition, the deformation detected by the DIC is compliant with the result of a FEM simulation. In the dynamic test, the DIC was able to follow with a good accuracy the periodic deformation of the specimen giving results coherent with the ones given by FEM simulation. In both situations, it was seen that the DIC measurement accuracy depends on several parameters such as the optical focusing, the parameters chosen to perform the mutual correlation between the images and, finally, the reference points on image to be analyzed. In the future, the influence of these parameters will be studied, and a method to increase the accuracy of the measurements will be developed in accordance with the requirements of the industries especially of the aerospace one.

Keywords: accuracy, deformation, image correlation, mechanical analysis

Procedia PDF Downloads 300
2645 A Case Study on Experiences of Clinical Preceptors in the Undergraduate Nursing Program

Authors: Jacqueline M. Dias, Amina A Khowaja

Abstract:

Clinical education is one of the most important components of a nursing curriculum as it develops the students’ cognitive, psychomotor and affective skills. Clinical teaching ensures the integration of knowledge into practice. As the numbers of students increase in the field of nursing coupled with the faculty shortage, clinical preceptors are the best choice to ensure student learning in the clinical settings. The clinical preceptor role has been introduced in the undergraduate nursing programme. In Pakistan, this role emerged due to a faculty shortage. Initially, two clinical preceptors were hired. This study will explore clinical preceptors views and experiences of precepting Bachelor of Science in Nursing (BScN) students in an undergraduate program. A case study design was used. As case studies explore a single unit of study such as a person or very small number of subjects; the two clinical preceptors were fundamental to the study and served as a single case. Qualitative data were obtained through an iterative process using in depth interviews and written accounts from reflective journals that were kept by the clinical preceptors. The findings revealed that the clinical preceptors were dedicated to their roles and responsibilities. Another, key finding was that clinical preceptors’ prior knowledge and clinical experience were valuable assets to perform their role effectively. The clinical preceptors found their new role innovative and challenging; it was stressful at the same time. Findings also revealed that in the clinical agencies there were unclear expectations and role ambiguity. Furthermore, clinical preceptors had difficulty integrating theory into practice in the clinical area and they had difficulty in giving feedback to the students. Although this study is localized to one university, generalizations can be drawn from the results. The key findings indicate that the role of a clinical preceptor is demanding and stressful. Clinical preceptors need preparation prior to precepting students on clinicals. Also, institutional support is fundamental for their acceptance. This paper focuses on the views and experiences of clinical preceptors undertaking a newly established role and resonates with the literature. The following recommendations are drawn to strengthen the role of the clinical preceptors: A structured program for clinical preceptors is needed along with mentorship. Clinical preceptors should be provided with formal training in teaching and learning with emphasis on clinical teaching and giving feedback to students. Additionally, for improving integration of theory into practice, clinical modules should be provided ahead of the clinical. In spite of all the challenges, ten more clinical preceptors have been hired as the faculty shortage continues to persist.

Keywords: baccalaureate nursing education, clinical education, clinical preceptors, nursing curriculum

Procedia PDF Downloads 162
2644 High Resolution Satellite Imagery and Lidar Data for Object-Based Tree Species Classification in Quebec, Canada

Authors: Bilel Chalghaf, Mathieu Varin

Abstract:

Forest characterization in Quebec, Canada, is usually assessed based on photo-interpretation at the stand level. For species identification, this often results in a lack of precision. Very high spatial resolution imagery, such as DigitalGlobe, and Light Detection and Ranging (LiDAR), have the potential to overcome the limitations of aerial imagery. To date, few studies have used that data to map a large number of species at the tree level using machine learning techniques. The main objective of this study is to map 11 individual high tree species ( > 17m) at the tree level using an object-based approach in the broadleaf forest of Kenauk Nature, Quebec. For the individual tree crown segmentation, three canopy-height models (CHMs) from LiDAR data were assessed: 1) the original, 2) a filtered, and 3) a corrected model. The corrected CHM gave the best accuracy and was then coupled with imagery to refine tree species crown identification. When compared with photo-interpretation, 90% of the objects represented a single species. For modeling, 313 variables were derived from 16-band WorldView-3 imagery and LiDAR data, using radiance, reflectance, pixel, and object-based calculation techniques. Variable selection procedures were employed to reduce their number from 313 to 16, using only 11 bands to aid reproducibility. For classification, a global approach using all 11 species was compared to a semi-hierarchical hybrid classification approach at two levels: (1) tree type (broadleaf/conifer) and (2) individual broadleaf (five) and conifer (six) species. Five different model techniques were used: (1) support vector machine (SVM), (2) classification and regression tree (CART), (3) random forest (RF), (4) k-nearest neighbors (k-NN), and (5) linear discriminant analysis (LDA). Each model was tuned separately for all approaches and levels. For the global approach, the best model was the SVM using eight variables (overall accuracy (OA): 80%, Kappa: 0.77). With the semi-hierarchical hybrid approach, at the tree type level, the best model was the k-NN using six variables (OA: 100% and Kappa: 1.00). At the level of identifying broadleaf and conifer species, the best model was the SVM, with OA of 80% and 97% and Kappa values of 0.74 and 0.97, respectively, using seven variables for both models. This paper demonstrates that a hybrid classification approach gives better results and that using 16-band WorldView-3 with LiDAR data leads to more precise predictions for tree segmentation and classification, especially when the number of tree species is large.

Keywords: tree species, object-based, classification, multispectral, machine learning, WorldView-3, LiDAR

Procedia PDF Downloads 120