Search results for: machine learning approach for neurological disorder assessment

Authors: Darlington Mapiye, Mpho Mokoatle, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on k-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0 %, 80.5 %, 80.5 %, 63.6 %, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 145

Authors: Bernd Engel, Sara Salman Hassan Al-Maeeni

Abstract:

A substantial amount of natural resources are nowadays consumed at a growing rate, as humans all over the world used materials obtained from the Earth. Machinery manufacturing industry is one of the major resource consumers on a global scale. Even though the incessant finding out of the new material, metals, and resources, it is urgent for the industry to develop methods to use the Earth's resources intelligently and more sustainable than before. Re-engineering of machine tools regarding design and failure analysis is an approach whereby out-of-date machines are upgraded and returned to useful life. To ensure the reliable future performance of the used machine components, it is essential to investigate the machine component failure through the material, design, and surface examinations. This paper presents an experimental approach aimed at inspecting the shaft of the rotary draw bending machine as a case to study. The testing methodology, which is based on the principle of the three-point bending test, allows assessing the shaft elastic behavior under loading. Furthermore, the shaft elastic characteristics include the maximum linear deflection, and maximum bending stress was determined by using an analytical approach and finite element (FE) analysis approach. In the end, the results were compared with the ones obtained by the experimental approach. In conclusion, it is seen that the measured bending deflection and bending stress were well close to the permissible design value. Therefore, the shaft can work in the second life cycle. However, based on previous surface tests conducted, the shaft needs surface treatments include re-carburizing and refining processes to ensure the reliable surface performance.

Keywords: deflection, FE analysis, shaft, stress, three-point bending

Procedia PDF Downloads 149

Authors: Rahul Paul, Kedar Nath Das

Abstract:

The field of machine learning (ML) is experiencing rapid development, resulting in a multitude of theoretical advancements and extensive practical implementations across various disciplines. The objective of ML is to facilitate the ability of machines to perform cognitive tasks by leveraging knowledge gained from prior experiences and effectively addressing complex problems, even in situations that deviate from previously encountered instances. Reinforcement Learning (RL) has emerged as a prominent subfield within ML and has gained considerable attention in recent times from researchers. This surge in interest can be attributed to the practical applications of RL, the increasing availability of data, and the rapid advancements in computing power. At the same time, optimization algorithms play a pivotal role in the field of ML and have attracted considerable interest from researchers. A multitude of proposals have been put forth to address optimization problems or improve optimization techniques within the domain of ML. The necessity of a thorough examination and implementation of optimization algorithms within the context of ML is of utmost importance in order to provide guidance for the advancement of research in both optimization and ML. This article provides a comprehensive overview of the application of metaheuristic evolutionary optimization algorithms in conjunction with RL to address a diverse range of scientific challenges. Furthermore, this article delves into the various challenges and unresolved issues pertaining to the optimization of RL models.

Keywords: machine learning, reinforcement learning, loss function, evolutionary optimization techniques

Procedia PDF Downloads 64

Authors: Akshay Paranjape, Nils Plettenberg, Robert Schmitt

Abstract:

Producing faulty products can be costly for manufacturing companies and wastes resources. To reduce scrap rates in manufacturing, process parameters can be optimized using machine learning. Thus far, research mainly focused on optimizing specific processes using traditional algorithms. To develop a framework that enables real-time optimization based on a predictive model for an arbitrary production process, this study explores the application of reinforcement learning (RL) in this field. Based on a thorough review of literature about RL and process parameter optimization, a model based on maximum a posteriori policy optimization that can handle both numerical and categorical parameters is proposed. A case study compares the model to state–of–the–art traditional algorithms and shows that RL can find optima of similar quality while requiring significantly less time. These results are confirmed in a large-scale validation study on data sets from both production and other fields. Finally, multiple ways to improve the model are discussed.

Keywords: reinforcement learning, production process optimization, evolutionary algorithms, policy optimization, actor critic approach

Procedia PDF Downloads 86

Authors: Alev Atak

Abstract:

In this paper, we aim to create a financial sentiment index by investigating the company’s voluntary information disclosures. We retrieve structured content from BIST 100 companies’ financial reports for the period 1998-2018 and extract relevant financial information for sentiment analysis through Natural Language Processing. We measure strategy-related disclosures and their cross-sectional variation and classify report content into generic sections using synonym lists divided into four main categories according to their liquidity risk profile, risk positions, intra-annual information, and exposure to risk. We use Word Error Rate and Cosin Similarity for comparing and measuring text similarity and derivation in sets of texts. In addition to performing text extraction, we will provide a range of text analysis options, such as the readability metrics, word counts using pre-determined lists (e.g., forward-looking, uncertainty, tone, etc.), and comparison with reference corpus (word, parts of speech and semantic level). Therefore, we create an adequate analytical tool and a financial dictionary to depict the importance of granular financial disclosure for investors to identify correctly the risk-taking behavior and hence make the aggregated effects traceable.

Keywords: financial sentiment, machine learning, information disclosure, risk

Procedia PDF Downloads 87

Authors: E. Verduci, I. Aguglia, A. Filocamo, I. Macrì, R. Scala, A. Vinci

Abstract:

One of the first indicator of autism spectrum disorder (ASD) is a decreasing tendency or failure to respond to name (RTN) call. Despite RTN is important for social and language developmentand it’s a common target for early interventions for children with ASD, research on specific treatments is insufficient and does not consider the importance of the discrimination between the own name and other names. The purpose of the current study was to replicate an assessment and treatment model proposed by Conine et al. (2020) to teach children with ASD to respond to their own name and to not respond to other names (RTO). The model includes three different phases (baseline/screening, treatment, and generalization), and itgradually introduces the different treatment components, starting with the most naturalistic ones (such as social interaction) and adding more intrusive components (such as tangible reinforcements, prompt and fading procedures) if necessary. The participants of this study were three children with ASD diagnosis: D. (5 years old) with a low frequency of RTN, M. (7 years old) with a RTN unstable and no ability of discrimination between his name and other names, S. (3 years old) with a strong RTN but a constant response to other names. Moreover, the treatment for D. and M. consisted of social and tangible reinforcements (treatment T1), for S. the purpose of the treatment was to teach the discrimination between his name and the others. For all participants, results suggest the efficacy of the model to acquire the ability to selectively respond to the own name and the generalization of the behavior with other people and settings.

Keywords: response to name, autism spectrum disorder, progressive training, ABA

Procedia PDF Downloads 74

Authors: Thirumila Muthukamaru

Abstract:

The objective of a Health Risk Assessment (HRA) is to achieve a quality evaluation of risk assessments in a timely manner where adequate controls can be in place to protect workers health, especially during turnarounds where the exposure to health hazards is expected to rise during the performance of the many activities that take place, exposing workers to health risk. HRA development requires a competent team comprising experienced subject matter experts in the field, such as Industrial hygienists, Occupational Health Doctors, Turnaround Coordinators, Operation / Maintenance personnel, etc. The conventional way of conducting HRA is not only tedious and time-consuming but also less appreciated when it is not interpreted correctly, which may contribute to inadequate operationalization of it. Simplification can be the essence of timely intervention in managing health risks. This paper is intended as a sharing of the approach taken to simplify the methodology of developing the HRA report and operationalizing it. The approach includes developing a Generic HRA for turnaround activities to be used as a reference document and the empowerment of identified personnel through upskilling sessions to take up the role of facilitating HRA sessions. This empowerment is one of the key approaches towards the successful translation of the HRA into specific turnaround Job Hazard Analysis (JHA) that embed it in the Permit to Work (PTW) process. The approach used here increases awareness and compliance on HRA for turnaround activities through better interpretation and operationalization of the HRA report, adding value to the risk assessment for turnaround activities.

Keywords: industrial hygiene, health risk assessment, HRA, risk assessment

Procedia PDF Downloads 33

Authors: Mingming Jiang

Abstract:

This literature review aims to offer an overview of existing research on learning analytics and learning design, the alignment between the two, and how learning analytics has been leveraged to inform learning design in higher education. Current research suggests a need to create more alignment and integration between learning analytics and learning design in order to not only ground learning analytics on learning sciences but also enable data-driven decisions in learning design to improve learning outcomes. In addition, multiple conceptual frameworks have been proposed to enhance the synergy and alignment between learning analytics and learning design. Future research should explore this synergy further in the unique context of higher education, identifying learning analytics metrics in higher education that can offer insight into learning processes, evaluating the effect of learning analytics outcomes on learning design decision-making in higher education, and designing learning environments in higher education that make the capturing and deployment of learning analytics outcomes more efficient.

Keywords: learning analytics, learning design, big data in higher education, online learning environments

Procedia PDF Downloads 148

Authors: Kemal Polat

Abstract:

In this paper, three feature weighting methods have been used to improve the classification performance of diabetic retinopathy (DR). To classify the diabetic retinopathy, features extracted from the output of several retinal image processing algorithms, such as image-level, lesion-specific and anatomical components, have been used and fed them into the classifier algorithms. The dataset used in this study has been taken from University of California, Irvine (UCI) machine learning repository. Feature weighting methods including the fuzzy c-means clustering based feature weighting, subtractive clustering based feature weighting, and Gaussian mixture clustering based feature weighting, have been used and compered with each other in the classification of DR. After feature weighting, five different classifier algorithms comprising multi-layer perceptron (MLP), k- nearest neighbor (k-NN), decision tree, support vector machine (SVM), and Naïve Bayes have been used. The hybrid method based on combination of subtractive clustering based feature weighting and decision tree classifier has been obtained the classification accuracy of 100% in the screening of DR. These results have demonstrated that the proposed hybrid scheme is very promising in the medical data set classification.

Keywords: machine learning, data weighting, classification, data mining

Procedia PDF Downloads 319

Authors: Salina Budin, Shaira Ismail

Abstract:

Students learn effectively in a learning environment with a suitable teaching approach that matches their learning preferences. The main objective of the study is to examine the learning preferences amongst the students in the Science and Technology (S&T), and Social Science (SS) fields of study at the Universiti Teknologi Mara (UiTM), Pulau Pinang. The measurement instrument is based on the Dunn and Dunn Learning Styles which measure five elements of learning styles; environmental, sociological, emotional, physiological and psychological. Questionnaires are distributed amongst undergraduates in the Faculty of Mechanical Engineering and Faculty of Business Management. The respondents comprise of 131 diploma students of the Faculty of Mechanical Engineering and 111 degree students of the Faculty of Business Management. The results indicate that, both S&T and SS students share a similar learning preferences on the environmental aspect, emotional preferences, motivational level, learning responsibility, persistent level in learning and learning structure. Most of the S&T students are concluded as analytical learners and the majority of SS students are global learners. Both S&T and SS students are concluded as visual learners, preferred to be in an active mobility in a relaxing and enjoying mode with some light of refreshments during the learning process and exhibited reflective characteristics in learning. Obviously, the S&T students are considered as left brain dominant, whereas the SS students are right brain dominant. The findings highlighted that both categories of students exhibited similar learning preferences except on psychological preferences.

Keywords: learning preferences, Dunn and Dunn learning style, teaching approach, science and technology, social science

Procedia PDF Downloads 232

Authors: Krongthong Khairiree

Abstract:

The purpose of this research study is to explore mathematics project-based learning approach and the use of technology in the context of school mathematics in Thailand. Data of the study were collected from 6 sample secondary schools and the students were 6-14 years old. Research findings show that through mathematics project-based learning approach and the use of GSP, students were able to make mathematics learning fun and challenging. Based on the students’ interviews they revealed that, with GSP, they were able to visualize and create graphical representations, which will enable them to develop their mathematical thinking skills, concepts and understanding. The students had fun in creating variety of graphs of functions which they can not do by drawing on graph paper. In addition, there are evidences to show the students’ abilities in connecting mathematics to real life outside the classroom and commercial products, such as weaving, patterning of broomstick, and ceramics design.

Keywords: mathematics, project-based learning, Geometer’s Sketchpad (GSP), commercial products

Procedia PDF Downloads 329

Authors: Hira Lal Gope, Hidekazu Fukai

Abstract:

The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.

Keywords: convolutional neural networks, coffee bean, peaberry, sorting, support vector machine

Procedia PDF Downloads 138

Authors: Shervin Alaei, Reza Moradi

Abstract:

Trading in financial markets is subject to risks due to their high volatilities. Here, using an LSTM neural network, and by doing some risk-based feature engineering tasks, we developed a method that can accurately predict trends of the Tehran stock exchange market index from a few days ago. Our test results have shown that the proposed method with an average prediction accuracy of more than 94% is superior to the other common machine learning algorithms. To the best of our knowledge, this is the first work incorporating deep learning and risk factors to accurately predict market trends.

Keywords: deep learning, LSTM, trend prediction, risk management, artificial neural networks

Procedia PDF Downloads 139

Authors: Darshana Sharma

Abstract:

Distance Education has emerged as a viable alternative to serve the higher educational needs of the socially and economically disadvantaged people of the remote, rural areas of Jammu region. The University of Jammu is a National Accreditation, and Assessment Council accredited, A+ university and has been accorded graded autonomy by the University Grants Commission. It is a dual mode university offering academic programmes through the regular departments and through the Directorate of Distance Education. The Directorate of Distance Education, University of Jammu still uses printed study material as a mode of instructional delivery. The development of technologies has assured increased interaction and communication for distance learners throughout the distance open learning institutions. Though it is tempting and convenient to adopt technology already being used by others, it may not prove effective for the simple reason that two institutions may be unlike in some respect. The use of technology must be conceived in view of the needs of the learners; geographical socio-economic-cultural and technological contexts and financial, administrative and academic resources of the institution. Mobile learning (m-learning) is a novel approach to knowledge acquisition and dissemination and is gaining global attention. It has evolved as one of the useful channels of distance learning promoting interaction between learners and teachers. It is felt that the Directorate of Distance Education, University of Jammu also needs to adopt new technologies to provide more effective academic and information support to distance learners in order to keep them motivated and also to develop self-learning skills. The chief objective of the research on which this paper is based was to measure the opinion of the distance learners of the DDE, the University of Jammu about the merits of mobile learning. It also explores their preferences for implementing mobile learning. The survey research design of descriptive research has been used. The data was collected from 400 distance learners enrolled with undergraduate and post-graduate programmes using self-constructed questionnaire containing five-point Likert scale items arranging from strongly agree, agree, indifferent, disagree and strongly disagree. Percentages were used to analyze the data. The findings lead to conclude that mobile learning has a great potential for the DDE for reaching out to the rural, remotely located distance learners of the Jammu region and also to improve the teaching-learning environment. The paper also finds out the challenges in the implementation of mobile learning in the region and further makes suggestions for effective implementation of mobile learning in DDE, University of Jammu.

Keywords: directorate of distance education, mobile learning, national accreditation and assessment council, university of Jammu

Procedia PDF Downloads 116

Authors: Merve Colak, Gizem Donmez Yalcin

Abstract:

Glutamate has many neurological functions in the central nervous system and is found at high concentrations in the brain. Increased levels of glutamate in the neuronal space are toxic, causing neuron damage and death. This is called glutamate-induced excitotoxicity. Excitotoxicity is among the causes of many neurological diseases such as trauma, cerebral ischemia, epilepsy, Parkinson's Disease, Alzheimer's Disease. Since neuroblastoma cells are known to be excitotoxic, we propose that excitotoxicity can be studied in neuroblastoma cells. Excitotoxicity can be induced using kainic acid in neuroblastoma cells. Measuring the secretion of glutamate, excitotoxicity can be analyzed in neuroblastoma cells.

Keywords: glutamate, excitotoxicity, kainic acid, Sirt4

Procedia PDF Downloads 153

Authors: Mohaned G. Abed

Abstract:

Attention Deficit Hyperactivity Disorder (ADHD) is considered one of the most frequently diagnosed psychiatric childhood disorders. It has an effect on 3–5% of school-aged children, and brings about difficulties in academic and social interaction. This study explored the knowledge and beliefs of parents in Saudi Arabia about children with ADHD. The Knowledge about Attention Deficit Disorder Questionnaire (KADD-Q) was administered to a sample of parents, followed by interviews with a subset of the total respondents. The results indicated that the parents knew more about the characteristics of ADHD than they knew about its related causes and treatment. Overall, the findings indicated that these parents had some knowledge about general characteristics of ADHD, but they had little understanding of causes and possible interventions. These results suggest an important need for more formal parents training regarding all aspects of ADHD in school age children.

Keywords: attention deficit hyperactivity disorder, childhood disorders, school-aged children, difficulties in academic, social interaction

Procedia PDF Downloads 105

Authors: M. Touhidul Islam Sarker, Mohammod Abul Kashem

Abstract:

The purpose of this paper is to improve the e-learning system and digitize the learning method in the educational sector. The learner will login into e-learning platform and easily access the digital content, the content can be downloaded and take an assessment for evaluation. Learner can get access to these digital resources by using tablet, computer, and smart phone also. E-learning system can be defined as teaching and learning with the help of multimedia technologies and the internet by access to digital content. E-learning replacing the traditional education system through information and communication technology-based learning. This paper has designed and implemented integrated e-learning system architecture with University Management System. Moodle (Modular Object-Oriented Dynamic Learning Environment) is the best e-learning system, but the problem of Moodle has no school or university management system. In this research, we have not considered the school’s student because they are out of internet facilities. That’s why we considered the university students because they have the internet access and used technologies. The University Management System has different types of activities such as student registration, account management, teacher information, semester registration, staff information, etc. If we integrated these types of activity or module with Moodle, then we can overcome the problem of Moodle, and it will enhance the e-learning system architecture which makes effective use of technology. This architecture will give the learner to easily access the resources of e-learning platform anytime or anywhere which digitizes the learning method.

Keywords: database, e-learning, LMS, Moodle

Procedia PDF Downloads 175

Authors: Amrane Meriem, Oukid Salyha

Abstract:

The presence of defects or bugs in software can lead to costly setbacks, operational inefficiencies, and compromised user experiences. The integration of Machine Learning(ML) techniques has emerged to predict and preemptively address software defects. ML represents a proactive strategy aimed at identifying potential anomalies, errors, or vulnerabilities within code before they manifest as operational issues. By analyzing historical data, such as code changes, feature im- plementations, and defect occurrences. This en- ables development teams to anticipate and mitigate these issues, thus enhancing software quality, reducing maintenance costs, and ensuring smoother user interactions. In this work, we used a recommendation system to improve the performance of ML models in terms of predicting the code severity and effort estimation.

Keywords: software engineering, machine learning, bugs detection, effort estimation

Procedia PDF Downloads 75

Authors: F. Ghazalnaz Sharifonnasabi, Iman Makhdoom

Abstract:

Breast cancer is a serious health concern that affects many people around the world. According to a study published in the Breast journal, the global burden of breast cancer is expected to increase significantly over the next few decades. The number of deaths from breast cancer has been increasing over the years, but the age-standardized mortality rate has decreased in some countries. It’s important to be aware of the risk factors for breast cancer and to get regular check- ups to catch it early if it does occur. Machin learning techniques have been used to aid in the early detection and diagnosis of breast cancer. These techniques, that have been shown to be effective in predicting and diagnosing the disease, have become a research hotspot. In this study, we consider two deep learning approaches including: Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN). We also considered the five-machine learning algorithm titled: Decision Tree (C4.5), Naïve Bayesian (NB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN) Algorithm and XGBoost (eXtreme Gradient Boosting) on the Breast Cancer Wisconsin Diagnostic dataset. We have carried out the process of evaluating and comparing classifiers involving selecting appropriate metrics to evaluate classifier performance and selecting an appropriate tool to quantify this performance. The main purpose of the study is predicting and diagnosis breast cancer, applying the mentioned algorithms and also discovering of the most effective with respect to confusion matrix, accuracy and precision. It is realized that CNN outperformed all other classifiers and achieved the highest accuracy (0.982456). The work is implemented in the Anaconda environment based on Python programing language.

Keywords: breast cancer, multi-layer perceptron, Naïve Bayesian, SVM, decision tree, convolutional neural network, XGBoost, KNN

Procedia PDF Downloads 62

Authors: Reza Khani, Ziba Hosseini

Abstract:

Ever since the importance of language learning strategy instruction (LLS) has been distinguished, there has been growing interest on how to teach LLS in language learning classrooms. So thus this study attempted to implement language strategy instruction based on CALLA approach for Iranian EFL learners in a real classroom setting. The study was testing the hypothesis that strategy instruction result in improved linguistic strategy of students. The participant of the study were 240 EFL learners who received language learning instruction for four months. The data collected using Oxford strategy inventory for language learning. The results indicated the instruction had statistically significant effect on language strategy use of intervention group who received instruction.

Keywords: CALLA, language learning strategy, language learning strategy instruction, Iranian EFL language strategy

Procedia PDF Downloads 557

Authors: Qisheng Hu, Jianglei Han, Yue Yang, My Hoa Ha

Abstract:

When a company is considering purchasing software for commercial use, contract risk assessment is critical to identify risks to mitigate the potential adverse business impact, e.g., security, financial and regulatory risks. Contract risk assessment requires reviewers with specialized knowledge and time to evaluate the legal documents manually. Specifically, validating contracts for a software vendor requires the following steps: manual screening, interpreting legal documents, and extracting risk-prone segments. To automate the process, we proposed a framework to assist legal contract document risk identification, leveraging pre-trained deep learning models and natural language processing techniques. Given a set of pre-defined risk evaluation problems, our framework utilizes the pre-trained transformer-based models for question-answering to identify risk-prone sections in a contract. Furthermore, the question-answering model encodes the concatenated question-contract text and predicts the start and end position for clause extraction. Due to the limited labelled dataset for training, we leveraged transfer learning by fine-tuning the models with the CUAD dataset to enhance the model. On a dataset comprising 287 contract documents and 2000 labelled samples, our best model achieved an F1 score of 0.687.

Keywords: contract risk assessment, NLP, transfer learning, question answering

Procedia PDF Downloads 122

Authors: Isabel Moscol, Carlos J. Díaz, Ciro Rodríguez

Abstract:

Hip replacement becomes necessary when a person suffers severe pain or considerable functional limitations and the best option to enhance their quality of life is through the replacement of the damaged joint. One of the main components in femoral prostheses is the stem which distributes the loads from the joint to the proximal femur. To preserve more bone stock and avoid weakening of the diaphysis, a short starting stem was selected, generated from the intramedullary morphology of the patient's femur. It ensures the implantability of the design and leads to geometric delimitation for personalized optimization with machine learning (ML) and metaheuristic algorithms. The present study attempts to design a cementless short stem to make the strain deviation before and after implantation close to zero, promoting its fixation and durability. Regression models developed to estimate the percentage change of maximum principal stresses were used as objective optimization functions by the metaheuristic algorithm. The latter evaluated different geometries of the short stem with the modification of certain parameters in oblique sections from the osteotomy plane. The optimized geometry reached a global stress shielding (SS) of 18.37% with a determination factor (R²) of 0.667. The predicted results favour implantability integration in the short stem optimization to effectively reduce SS in the proximal femur.

Keywords: machine learning techniques, metaheuristic algorithms, short-stem design, stress shielding, hip replacement

Procedia PDF Downloads 187

Authors: Nidhal K. Azawi, John M. Gauch

Abstract:

Colorectal cancer is one of the leading causes of cancer death in the US and the world, which is why millions of colonoscopy examinations are performed annually. Unfortunately, noise, specular highlights, and motion artifacts corrupt many images in a typical colonoscopy exam. The goal of our research is to produce automated techniques to detect and correct or remove these noninformative images from colonoscopy videos, so physicians can focus their attention on informative images. In this research, we first automatically extract features from images. Then we use machine learning and deep neural network to classify colonoscopy images as either informative or noninformative. Our results show that we achieve image classification accuracy between 92-98%. We also show how the removal of noninformative images together with image alignment can aid in the creation of image panoramas and other visualizations of colonoscopy images.

Keywords: colonoscopy classification, feature extraction, image alignment, machine learning

Procedia PDF Downloads 245

Authors: Hans Schumann, Colin Domnauer, Louis Rosenberg

Abstract:

In this study, machine learning techniques were deployed on real-time human swarm data to forecast the likelihood of outcomes for English Premier League matches in the 2020/21 season. These techniques included ensemble models in combination with neural networks and were tested against an industry standard of Vegas Oddsmakers. Predictions made from the collective intelligence of human swarm participants managed to achieve a positive return on investment over a full season on matches, empirically proving the usefulness of a new artificial intelligence valuing human instinct and intelligence.

Keywords: artificial intelligence, data science, English Premier League, human swarming, machine learning, sports betting, swarm intelligence

Procedia PDF Downloads 200

Authors: Julius Onyancha, Valentina Plekhanova

Abstract:

One of the significant issues facing web users is the amount of noise in web data which hinders the process of finding useful information in relation to their dynamic interests. Current research works consider noise as any data that does not form part of the main web page and propose noise web data reduction tools which mainly focus on eliminating noise in relation to the content and layout of web data. This paper argues that not all data that form part of the main web page is of a user interest and not all noise data is actually noise to a given user. Therefore, learning of noise web data allocated to the user requests ensures not only reduction of noisiness level in a web user profile, but also a decrease in the loss of useful information hence improves the quality of a web user profile. Noise Web Data Learning (NWDL) tool/algorithm capable of learning noise web data in web user profile is proposed. The proposed work considers elimination of noise data in relation to dynamic user interest. In order to validate the performance of the proposed work, an experimental design setup is presented. The results obtained are compared with the current algorithms applied in noise web data reduction process. The experimental results show that the proposed work considers the dynamic change of user interest prior to elimination of noise data. The proposed work contributes towards improving the quality of a web user profile by reducing the amount of useful information eliminated as noise.

Keywords: web log data, web user profile, user interest, noise web data learning, machine learning

Procedia PDF Downloads 256

Authors: Lu Xi, Li Pan, Wen Mengmeng

Abstract:

The stiffness of each component has different influences on the stiffness of the machine tool. Taking the five-axis gantry machining center as an example, we made the modal analysis of the machine tool, followed by raising and lowering the stiffness of the pillar, slide plate, beam, ram and saddle so as to study the stiffness matching among these components on the standard of whether the stiffness of the modified machine tool changes more than 50% relative to the stiffness of the original machine tool. The structural optimization of the machine tool can be realized by changing the stiffness of the components whose stiffness is mismatched. For example, the stiffness of the beam is mismatching. The natural frequencies of the first six orders of the beam increased by 7.70%, 0.38%, 6.82%, 7.96%, 18.72% and 23.13%, with the weight increased by 28Kg, leading to the natural frequencies of several orders which had a great influence on the dynamic performance of the whole machine increased by 1.44%, 0.43%, 0.065%, which verified the correctness of the optimization method based on stiffness matching proposed in this paper.

Keywords: machine tool, optimization, modal analysis, stiffness matching

Procedia PDF Downloads 92

Authors: Chana Pavneet

Abstract:

Background: In more recent years in dentistry, a greater emphasis has been placed on competency-based education (CBE) programmes. Undergraduate and postgraduate curriculums have been reformed to reflect these changes, and adopting a CBE approach has shown to be beneficial to trainees and places an emphasis on continuous lifelong learning. The literature is vast; however, very little work has been done specifically to the assessment of competence in dentistry and even less so in oral surgery. The majority of the literature tends to opinion pieces. Some small-scale studies have been undertaken in this area researching assessment tools which can be used to assess competence in oral surgery. However, there is a lack of general consensus on the preferable assessment methods. The aim of this review is to identify the assessment methods available and their usefulness. Methods: Electronic databases (Medline, Embase, and the Cochrane Database of systematic reviews) were searched. PRISMA guidelines were followed to identify relevant papers. Abstracts of studies were reviewed, and if they met the inclusion criteria, they were included in the review. Papers were reviewed against the critical appraisal skills programme (CASP) checklist and medical education research quality instrument (MERQSI) to assess their quality and identify any bias in a systematic manner. The validity and reliability of each assessment method or tool were assessed. Results: A number of assessment methods were identified, including self-assessment, peer assessment, and direct observation of skills by someone senior. Senior assessment tended to be the preferred method, followed by self-assessment and, finally, peer assessment. The level of training was shown to affect the preferred assessment method, with one study finding peer assessment more useful in postgraduate trainees as opposed to undergraduate trainees. Numerous tools for assessment were identified, including a checklist scale and a global rating scale. Both had their strengths and weaknesses, but the evidence was more favourable for global rating scales in terms of reliability, applicability to more clinical situations, and easier to use for examiners. Studies also looked into trainees’ opinions on assessment tools. Logbooks were not found to be significant in measuring the competence of trainees. Conclusion: There is limited literature exploring the methods and tools which assess the competence of oral surgery trainees. Current evidence shows that the most favourable assessment method and tool may differ depending on the stage of training. More research is required in this area to streamline assessment methods and tools.

Keywords: competence, oral surgery, assessment, trainees, education

Procedia PDF Downloads 121

Authors: Shahrzad Yektatalab, Agrin Mohammadi, Ladan Zarshenas

Abstract:

Background: Misophonia is a severe emotional response to repetitive sounds. This disorder may limit a person's communication, reduce their ability, or disrupt their social and personal life. This study aims to determine the prevalence of Misophonia and its relationship with obsessive-compulsive disorder, anxiety, and depression in undergraduate students of XXX University of Medical Sciences. Methods: The present study is an analytical descriptive study conducted in October 2020. The study samples are 390 undergraduate students of XXX University of medical sciences. A relative and systematic sampling method was used. In this study, a demographic questionnaire, misophonia questionnaire (A score of 7 or higher is considered as misophonia), Beck anxiety questionnaire, Beck depression questionnaire, and Maudsley questionnaire were used, and the data were analyzed using SPSS 24 software. Due to the non-normality of the data, the Spearman correlation coefficient was used for analyzing data. The significance level was considered less than 0.05. Results: 23.8% of students have misophonia. Of the 390 participants in the study, 93 had experienced misophonia. Among these 93 students, 37 (39.8%) had obsessive-compulsive disorder, 8 (8.6%) had anxiety and 9 (9.7%) had depression. There was a significant and direct relationship between all variables (p <0.001), which means that with the increase of each disorder, the probability of an increase in other disorders increases. Conclusion: Due to the high prevalence of misophonia in students and its direct relationship with obsessive-compulsive disorder, anxiety, and depression, It is recommended that future studies be conducted to identify ways to prevent and reduce the incidence of misophonia.

Keywords: misophonia, obsessive-compulsive disorder, anxiety, depression

Procedia PDF Downloads 53

Authors: Rong Wang, Sandra Hasanefendic, Elizabeth von Hauff, Bart Bossink

Abstract:

Technological learning and learning curve models have been continuously used to estimate the photovoltaics (PV) cost development over time for the climate mitigation targets. They can integrate a number of technological learning sources which influence the learning process. Yet the accuracy and realistic predictions for cost estimations of PV development are still difficult to achieve. This paper develops four hypothetical-alternative learning curve models by proposing different combinations of technological learning sources, including both local and global technology experience and the knowledge stock. This paper specifically focuses on the non-linear relationship between the costs and technological learning source and their dynamic interaction and uses the system dynamics approach to predict a more accurate PV cost estimation for future development. As the case study, the data from China is gathered and drawn to illustrate that the learning curve model that incorporates both the global and local experience is more accurate and realistic than the other three models for PV cost estimation. Further, absorbing and integrating the global experience into the local industry has a positive impact on PV cost reduction. Although the learning curve model incorporating knowledge stock is not realistic for current PV cost deployment in China, it still plays an effective positive role in future PV cost reduction.

Keywords: photovoltaic, system dynamics, technological learning, learning curve

Procedia PDF Downloads 88

Authors: Helen Coronel, Will Brewer, Peggy Bergeron, Clarissa Hall, Victoria Casson

Abstract:

Simulation-based training provides the nurse practitioner (NP) student with a safe and controlled environment in which they can practice a real-life scenario. This type of learning fosters critical thinking skills essential to practice. The expectation of this study was that students would have an increase in their competency and confidence after performing the simulation. Approximately 8.4% of Americans suffer from depression. The state of Alabama is ranked 47th out of 50 for access to mental health care. As a result of this significant shortage of mental health providers, primary care providers are frequently put in the position of screening for and treating mental health conditions, such as depression. Family nurse practitioners are often utilized as primary care providers, making their ability to assess, diagnose and treat these disorders a necessary skill. The expected outcome of this simulation is an increase in confidence, competency and the empowerment of the nurse practitioner student’s ability to assess, diagnose and treat a common mood disorder they may encounter in practice. The Kirkpatrick Module was applied for this study. A non-experimental design using descriptive statistical analysis was utilized. The simulation was based on a common psychiatric mood disorder frequently observed in primary care and mental health clinics. Students were asked to watch a voiceover power point presentation prior to their on-campus simulation. The presentation included training on the assessment, diagnosis, and treatment of a patient with depression. Prior to the simulation, the students completed a pre-test, then participated in the simulation, and completed a post-test when done. Apple iPads were utilized to access a simulated health record. Major findings of the study support an increase in students’ competency and confidence when assessing, diagnosing, and treating an adult patient with depression.

Keywords: advanced practice, nurse practitioner, simulation, primary care, depression

Procedia PDF Downloads 89