Search results for: trained athletes

Authors: Constanza A. Barriga, Rafael Bernardi, Amokrane Berdja, Christian D. Guzman

Abstract:

Most image restoration methods in astronomy rely upon probabilistic tools that infer the best solution for a deconvolution problem. They achieve good performances when the point spread function (PSF) is spatially invariable in the image plane. However, this latter condition is not always satisfied with real optical systems. PSF angular variations cannot be evaluated directly from the observations, neither be corrected at a pixel resolution. We have developed a method for the restoration of images affected by static and anisotropic aberrations using deep neural networks that can be directly applied to sky images. The network is trained using simulated sky images corresponding to the T-80 telescope optical system, an 80 cm survey imager at Cerro Tololo (Chile), which are synthesized using a Zernike polynomial representation of the optical system. Once trained, the network can be used directly on sky images, outputting a corrected version of the image, which has a constant and known PSF across its field-of-view. The method was tested with the T-80 telescope, achieving better results than with PSF deconvolution techniques. We present the method and results on this telescope.

Keywords: aberrations, deep neural networks, image restoration, variable point spread function, wide field images

Procedia PDF Downloads 106

Authors: Konstantinos Perifanos, Eirini Florou, Dionysis Goutsos

Abstract:

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

Keywords: metaphor detection, deep learning, representation learning, embeddings

Procedia PDF Downloads 117

Authors: Sandip Sadhukhan, Arpita Sarkar, Debprasad Sinha, Goutam Kumar Ghorai, Gautam Sarkar, Ashis K. Dhara

Abstract:

Accurate segmentation of the optic disc is very important for computer-aided diagnosis of several ocular diseases such as glaucoma, diabetic retinopathy, and hypertensive retinopathy. The paper presents an accurate and fast optic disc detection and segmentation method using an attention based fully convolutional network. The network is trained from scratch using the fundus images of extended MESSIDOR database and the trained model is used for segmentation of optic disc. The false positives are removed based on morphological operation and shape features. The result is evaluated using three-fold cross-validation on six public fundus image databases such as DIARETDB0, DIARETDB1, DRIVE, AV-INSPIRE, CHASE DB1 and MESSIDOR. The attention based fully convolutional network is robust and effective for detection and segmentation of optic disc in the images affected by diabetic retinopathy and it outperforms existing techniques.

Keywords: attention-based fully convolutional network, optic disc detection and segmentation, retinal fundus image, screening of ocular diseases

Procedia PDF Downloads 106

Authors: Hsin Lee, Hsuan Lee

Abstract:

Legal artificial intelligence (LegalAI) has been increasing applications within legal systems, propelled by advancements in natural language processing (NLP). Compared with general documents, legal case documents are typically long text sequences with intrinsic logical structures. Most existing language models have difficulty understanding the long-distance dependencies between different structures. Another unique challenge is that while the Judiciary of Taiwan has released legal judgments from various levels of courts over the years, there remains a significant obstacle in the lack of labeled datasets. This deficiency makes it difficult to train models with strong generalization capabilities, as well as accurately evaluate model performance. To date, models in Taiwan have yet to be specifically trained on judgment data. Given these challenges, this research proposes a Longformer-based pre-trained language model explicitly devised for retrieving similar judgments in Taiwanese legal documents. This model is trained on a self-constructed dataset, which this research has independently labeled to measure judgment similarities, thereby addressing a void left by the lack of an existing labeled dataset for Taiwanese judgments. This research adopts strategies such as early stopping and gradient clipping to prevent overfitting and manage gradient explosion, respectively, thereby enhancing the model's performance. The model in this research is evaluated using both the dataset and the Average Entropy of Offense-charged Clustering (AEOC) metric, which utilizes the notion of similar case scenarios within the same type of legal cases. Our experimental results illustrate our model's significant advancements in handling similarity comparisons within extensive legal judgments. By enabling more efficient retrieval and analysis of legal case documents, our model holds the potential to facilitate legal research, aid legal decision-making, and contribute to the further development of LegalAI in Taiwan.

Keywords: legal artificial intelligence, computation and language, language model, Taiwanese legal cases

Procedia PDF Downloads 45

Authors: Mo-Se Lee, Cheol-Hwi Ahn, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN (Convolutional Neural Network), which is known as effective solution for recognizing and classifying images, has been popularly applied to classification and prediction problems in various fields. In this study, we try to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. In specific, we propose to apply CNN as the binary classifier that predicts stock market direction (up or down) by using a graph as its input. That is, our proposal is to build a machine learning algorithm that mimics a person who looks at the graph and predicts whether the trend will go up or down. Our proposed model consists of four steps. In the first step, it divides the dataset into 5 days, 10 days, 15 days, and 20 days. And then, it creates graphs for each interval in step 2. In the next step, CNN classifiers are trained using the graphs generated in the previous step. In step 4, it optimizes the hyper parameters of the trained model by using the validation dataset. To validate our model, we will apply it to the prediction of KOSPI200 for 1,986 days in eight years (from 2009 to 2016). The experimental dataset will include 14 technical indicators such as CCI, Momentum, ROC and daily closing price of KOSPI200 of Korean stock market.

Keywords: convolutional neural network, deep learning, Korean stock market, stock market prediction

Procedia PDF Downloads 406

Authors: Cheng Fang, Lingwei Quan, Cunyue Lu

Abstract:

Human pose estimation and tracking are to accurately identify and locate the positions of human joints in the video. It is a computer vision task which is of great significance for human motion recognition, behavior understanding and scene analysis. There has been remarkable progress on human pose estimation in recent years. However, more researches are needed for human pose tracking especially for online tracking. In this paper, a framework, called PoseSRPN, is proposed for online single-person pose estimation and tracking. We use Siamese network attaching a pose estimation branch to incorporate Single-person Pose Tracking (SPT) and Visual Object Tracking (VOT) into one framework. The pose estimation branch has a simple network structure that replaces the complex upsampling and convolution network structure with deconvolution. By augmenting the loss of fully convolutional Siamese network with the pose estimation task, pose estimation and tracking can be trained in one stage. Once trained, PoseSRPN only relies on a single bounding box initialization and producing human joints location. The experimental results show that while maintaining the good accuracy of pose estimation on COCO and PoseTrack datasets, the proposed method achieves a speed of 59 frame/s, which is superior to other pose tracking frameworks.

Keywords: computer vision, pose estimation, pose tracking, Siamese network

Procedia PDF Downloads 126

Authors: Iorwase Derek Kaka’an, Peter Smolianov, Steven Dion, Christopher Schoen, Jaclyn Norberg, Charles Gabriel Iortimah

Abstract:

This study examines the current state of football in Nigeria to identify the country's practices, which could be useful internationally, and to determine areas for improvement. Over 200 sources of literature on sport delivery systems in successful sports nations were analyzed to construct a globally applicable model of elite football integrated with mass participation, comprising of the following three levels: macro (socio-economic, cultural, legislative, and organizational), meso (infrastructures, personnel, and services enabling sports programs) and micro level (operations, processes, and methodologies for the development of individual athletes). The model has received scholarly validation and has shown to be a framework for program analysis that is not culturally bound. It has recently been utilized for further understanding such sports systems as US rugby, tennis, soccer, swimming, and volleyball, as well as Dutch and Russian swimming. A questionnaire was developed using the above-mentioned model. Survey questions were validated by 12 experts including academicians, executives from sports governing bodies, football coaches, and administrators. To identify best practices and determine areas for improvement of football in Nigeria, 116 coaches completed the questionnaire. Useful exemplars and possible improvements were further identified through semi-structured discussions with 10 Nigerian football administrators and experts. Finally, a content analysis of the Nigeria Football Federation's website and organizational documentation was conducted. This paper focuses on the micro level of Nigerian football delivery, particularly talent search and development as well as advanced athlete preparation and support. Results suggested that Nigeria could share such progressive practices as the provision of football programs in all schools and full-time coaches paid by governments based on the level of coach education. Nigerian football administrators and coaches could provide better football services affordable for all, where success in mass and elite sports is guided by science focused on athletes' needs. Better implemented could be international best practices such as lifelong guidelines for health and excellence of everyone and integration of fitness tests into player development and ranking as done in best Dutch, English, French, Russian, Spanish, and other European clubs; integration of educational and competitive events for elite and developing athletes as well as fans as done at the 2018 World Cup Russia; and academies with multi-stage athlete nurturing as done by Ajax in Africa as well as Barcelona FC and other top clubs expanding across the world. The methodical integration of these practices into the balanced development of mass and elite football will help contribute to international sports success as well as national health, education, crime control, and social harmony in Nigeria.

Keywords: football, high performance, mass participation, Nigeria, sport development

Procedia PDF Downloads 44

Authors: Jolanta Uszko, Tomasz Wloch, Aneta Pirowska, Roman Nowobilski

Abstract:

Introduction: Phantom phenomena are often reported by subjects who have undergone limb amputation. Mostly, patients feel the amputated part of the limb as if it was still attached to the body. Two types of phantom phenomena: painless (phantom sensation) and painful (phantom pain) were described. Triggers of phantom sensations and phantom pain, as well as fully effective treatment, have not been clearly described yet. Purpose: To assess the influence of psychosocial factors and some clinical conditions on the occurrence of phantom phenomena in amputee athletes. Subjects: 21 men (age: 31 years, SD = 7.5 years) after lower or upper extremity amputation, who regularly performed high-intensity sports (Amp Football Team Players) were included to the study. Method and equipment: In the research, the following method and tools were used: Questionnaire [Pirowska] adapted for athletes with disabilities, Numerical Rating Scale (NRS) - for phantom pain assessment, McGill Pain Assessment Questionnaire (short version), Beck's Depression Inventory (BDI), State Trait Anxiety Inventory (STAI): X-1 and X-2, shortened version of The World Health Organization Quality of Life (WHOQOLBREFF). Results: In the study group, the lower leg amputations with traumatic etiology were predominant. Phantom sensations were present in all subjects. Half of the respondents claimed to experience phantom sensations at least once a day, paroxysmally. There was a prevalence of phantom sensations characterized as incomplete, immobile limb. Phantom pain was reported by over 85% of respondents. The nature of phantom pain was frequently described as stabbing, squeezing, shooting, pulsing, tiring. There was a significant correlation between phantom pain intensity and anxiety, quality of life, depressive tendencies, perception of phantom pain as the obstacle in daily functioning and intensity of the limb pain before amputation. Conclusions: The etiology of phantom phenomena is complex. Psychological factors seem to have a significant influence on the intensity of the phantom pain. Particular attention should be paid to patients who complain about persistent limb pain before the amputation. These are patients with an increased risk of the phantom pain of relatively high intensity.

Keywords: amputation, phantom pain, phantom sensations, adaptive sports

Procedia PDF Downloads 131

Authors: Monica Gonzalez Machorro

Abstract:

Dementia is hard to diagnose because of the lack of early physical symptoms. Early dementia recognition is key to improving the living condition of patients. Speech technology is considered a valuable biomarker for this challenge. Recent works have utilized conventional acoustic features and machine learning methods to detect dementia in speech. BERT-like classifiers have reported the most promising performance. One constraint, nonetheless, is that these studies are either based on human transcripts or on transcripts produced by automatic speech recognition (ASR) systems. This research contribution is to explore a method that does not require transcriptions to detect early Alzheimer’s disease (AD) and mild cognitive impairment (MCI). This is achieved by fine-tuning a pre-trained ASR model for the downstream early AD and MCI tasks. To do so, a subset of the thoroughly studied Pitt Corpus is customized. The subset is balanced for class, age, and gender. Data processing also involves cropping the samples into 10-second segments. For comparison purposes, a baseline model is defined by training and testing a Random Forest with 20 extracted acoustic features using the librosa library implemented in Python. These are: zero-crossing rate, MFCCs, spectral bandwidth, spectral centroid, root mean square, and short-time Fourier transform. The baseline model achieved a 58% accuracy. To fine-tune HuBERT as a classifier, an average pooling strategy is employed to merge the 3D representations from audio into 2D representations, and a linear layer is added. The pre-trained model used is ‘hubert-large-ls960-ft’. Empirically, the number of epochs selected is 5, and the batch size defined is 1. Experiments show that our proposed method reaches a 69% balanced accuracy. This suggests that the linguistic and speech information encoded in the self-supervised ASR-based model is able to learn acoustic cues of AD and MCI.

Keywords: automatic speech recognition, early Alzheimer’s recognition, mild cognitive impairment, speech impairment

Procedia PDF Downloads 98

Authors: Lee Bih Ni, Emily Doreen Lee, Wee Hui Yean

Abstract:

This paper was prepared to see the perceptions of online lectures regarding collaborative learning, in terms of how lecturers view online collaborative learning in the higher learning institution. The purpose of this study was conducted to determine the perceptions of online lectures about collaborative learning, especially how lecturers see online collaborative learning in the university. Adult learning education enhance collaborative learning culture with the target of involving learners in the learning process to make teaching and learning more effective and open at the university. This will finally make students learning that will assist each other. It is also to cut down the pressure of loneliness and isolation might felt among adult learners. Their ways in collaborative online was also determined. In this paper, researchers collect data using questionnaires instruments. The collected data were analyzed and interpreted. By analyzing the data, researchers report the results according the proof taken from the respondents. Results from the study, it is not only dependent on the lecturer but also a student to shape a good collaborative learning practice. Rational concepts and pattern to achieve these targets be clear right from the beginning and may be good seen by a number of proposals submitted and include how the higher learning institution has trained with ongoing lectures online. Advantages of online collaborative learning show that lecturers should be trained effectively. Studies have seen that the lecturer aware of online collaborative learning. This positive attitude will encourage the higher learning institution to continue to give the knowledge and skills required.

Keywords: collaborative online learning, lecturers’ training, learning, online

Procedia PDF Downloads 430

Authors: L. Nathaniel-Wurie

Abstract:

The Sellick manoeuvre a.k.a the application of cricoid force (CF), was first described by Brian Sellick in 1961. CF is the application of digital pressure against the cricoid cartilage with the intention of posterior force causing oesophageal compression against the vertebrae. This is designed to prevent passive regurgitation of gastric contents, which is a major cause of morbidity and mortality during emergency airway management inside and outside of the hospital. To the authors knowledge, there is no universally standardised training modality and, therefore, no reliable way to examine if there are appropriate outcomes. If force is not measured during training, how can one surmise that appropriate, accurate, or precise amounts of force are being used routinely. Poor homogeneity in teaching and untested outcomes will correlate with reduced efficacy and increased adverse effects. For this study, the accuracy of force delivery in trained professionals was tested, and outcomes contrasted against a novice control and a novice study group. In this study, 20 operating department practitioners were tested (with a mean experience of 5.3years of performing CF). Subsequent contrast with 40 novice students who were randomised into one of two arms. ‘Arm A’ were explained the procedure, then shown the procedure then asked to perform CF with the corresponding force measurement being taken three times. Arm B had the same process as arm A then before being tested, they had 10, and 30 Newtons applied to their hands to increase intuitive understanding of what the required force equated to, then were asked to apply the equivalent amount of force against a visible force metre and asked to hold that force for 20 seconds which allowed direct visualisation and correction of any over or under estimation. Following this, Arm B were then asked to perform the manoeuvre, and the force generated measured three times. This study shows that there is a wide distribution of force produced by trained professionals and novices performing the procedure for the first time. Our methodology for teaching the manoeuvre shows an improved accuracy, precision, and homogeneity within the group when compared to novices and even outperforms trained practitioners. In conclusion, if this methodology is adopted, it may correlate with higher clinical outcomes, less adverse events, and more successful airway management in critical medical scenarios.

Keywords: airway, cricoid, medical education, sellick

Procedia PDF Downloads 46

Authors: Jessica Lopez Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri

Abstract:

Pretrained transformer-based models have shown high performance in natural language generation tasks. However, a new wave of interest has surged: automatic programming language code generation. This task consists of translating natural language instructions to a source code. Despite the fact that well-known pre-trained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformer neural network. It aims to generate java source code from natural language text. JaCoText leverages the advantages of both natural language and code generation models. More specifically, we study some findings from state of the art and use them to (1) initialize our model from powerful pre-trained models, (2) explore additional pretraining on our java dataset, (3) lead experiments combining the unimodal and bimodal data in training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

Keywords: java code generation, natural language processing, sequence-to-sequence models, transformer neural networks

Procedia PDF Downloads 237

Authors: Niloofar Zebarjad

Abstract:

This research aims at finding a tool to provide basketball players with real-time audio feedback on their shooting form in free throw shots. Free throws played a pivotal role in taking the lead in fierce competitions. The major problem in performing an accurate free throw seems to be improper training. Since the arm movement during the free throw shot is complex, the coach or the athlete might miss the movement details during practice. Hence, there is a necessity to create a system that measures arm movements' critical characteristics and control for improper kinematics. The proposed setup in this study quantifies arm kinematics and provides real-time feedback as an audio signal consisting of a gyroscope sensor. Spatial shoulder angle data are transmitted in a mobile application in real-time and can be saved and processed for statistical and analysis purposes. The proposed system is easy to use, inexpensive, portable, and real-time applicable. Objectives: This research aims to modify and control the free throw using audio feedback and determine if and to what extent the new setup reduces errors in arm formations during throws and finally assesses the successful throw rate. Methods: One group of elite basketball athletes and two novice athletes (control and study group) participated in this study. Each group contains 5 participants being studied in three separate sessions over a week. Results: Empirical results showed enhancements in the free throw shooting style, shot pocket (SP), and locked position (LP). The mean values of shoulder angle were controlled on 25° and 45° for SP and LP, respectively, recommended by valid FIBA references. Conclusion: Throughout the experiments, the system helped correct and control the shoulder angles toward the targeted pattern of shot pocket (SP) and locked position (LP). According to the desired results for arm motion, adding another sensor to measure and control the elbow angle is recommended.

Keywords: audio-feedback, basketball, free-throw, locked-position, motor-control, shot-pocket

Procedia PDF Downloads 255

Authors: Dorian Audot, Isobel Margaret Thompson, Dominic Hudson, Joseph Banks, Martin Warner

Abstract:

In competitive swimming, after dives and turns, athletes perform underwater undulatory swimming (UUS), copying marine mammals’ method of locomotion. The body, performing this wave-like motion, accelerates the fluid downstream in its vicinity, generating propulsion with minimal resistance. Through this technique, swimmers can maintain greater speeds than surface swimming and take advantage of the overspeed granted by the dive (or push-off). Almost all previous work has considered UUS when performed at maximum effort. Critical parameters to maximize UUS speed are frequently discussed; however, this does not apply to most races. In only 3 out of the 16 individual competitive swimming events are athletes likely to attempt to perform UUS with the greatest speed, without thinking of the cost of locomotion. In the other cases, athletes will want to control the speed of their underwater swimming, attempting to maximise speed whilst considering energy expenditure appropriate to the duration of the event. Hence, there is a need to understand how swimmers adapt their underwater strategies to optimize the speed within the allocated energetic cost. This paper develops a consistent methodology that enables different sets of UUS kinematics to be investigated. These may have different propulsive efficiencies and force generation mechanisms (e.g.: force distribution along with the body and force magnitude). The developed methodology, therefore, needs to: (i) provide an understanding of the UUS propulsive mechanisms at different speeds, (ii) investigate the key performance parameters when UUS is not performed solely for maximizing speed; (iii) consistently determine the propulsive efficiency of a UUS technique. The methodology is separated into two distinct parts: kinematic data acquisition and computational fluid dynamics (CFD) analysis. For the kinematic acquisition, the position of several joints along the body and their sequencing were either obtained by video digitization or by underwater motion capture (Qualisys system). During data acquisition, the swimmers were asked to perform UUS at a constant depth in a prone position (facing the bottom of the pool) at different speeds: maximum effort, 100m pace, 200m pace and 400m pace. The kinematic data were input to a CFD algorithm employing a two-dimensional Large Eddy Simulation (LES). The algorithm adopted was specifically developed in order to perform quick unsteady simulations of deforming bodies and is therefore suitable for swimmers performing UUS. Despite its approximations, the algorithm is applied such that simulations are performed with the inflow velocity updated at every time step. It also enables calculations of the resistive forces (total and applied to each segment) and the power input of the modeled swimmer. Validation of the methodology is achieved by comparing the data obtained from the computations with the original data (e.g.: sustained swimming speed). This method is applied to the different kinematic datasets and provides data on swimmers’ natural responses to pacing instructions. The results show how kinematics affect force generation mechanisms and hence how the propulsive efficiency of UUS varies for different race strategies.

Keywords: CFD, efficiency, human swimming, hydrodynamics, underwater undulatory swimming

Procedia PDF Downloads 187

Authors: Michael McMahon

Abstract:

The use of media (video/animation/graphics) has long been used by athletes, coaches, and sports scientists to analyse and improve performance in technical skills and team tactics. Sports educators are increasingly open to the use of technology to support coach and learner development. However, an overreliance is a concern., This paper is part of a larger Ph.D. study looking into these new challenges for Sports Educators. Most notably, how to exploit the deep-learning potential of Digital Media among expert learners, how to instruct sports educators to create effective media content that fosters deep learning, and finally, how to make the process manageable and cost-effective. Central to the study is Richard Mayers Cognitive Theory of Multimedia Learning. Mayers Multimedia Learning Theory proposes twelve principles that shape the design and organization of multimedia presentations to improve learning and reduce cognitive load. For example, the Prior Knowledge principle suggests and highlights different learning outcomes for Novice and Non-Novice learners, respectively. Little research, however, is available to support this principle in modified domains (e.g., sports tactics and strategy). As a foundation for further research, this paper compares and contrasts a range of contemporary multimedia sports coaching content and assesses how they perform as learning tools for Strategic and Tactical Play Acquisition among elite sports practitioners. The stress tests applied are guided by Mayers's twelve Multimedia Learning Principles. The focus is on the elite athletes and whether current coaching digital media content does foster improved sports learning among this cohort. The sport of Gaelic Football was selected as it has high strategic and tactical play content, a wide range of Practitioner skill levels (Novice to Elite), and also a significant volume of Multimedia Coaching Content available for analysis. It is hoped the resulting data will help identify and inform the future instructional content design and delivery for Sports Practitioners and help promote best design practices optimal for different levels of expertise.

Keywords: multimedia learning, e-learning, design for learning, ICT

Procedia PDF Downloads 76

Authors: Eiman Kattan

Abstract:

This study aims to evaluate the impact of classifying labelled remote sensing images conventional neural network (CNN) architecture, i.e., AlexNet on different land cover scenarios based on two remotely sensed datasets from different point of views such as the computational time and performance. Thus, a set of experiments were conducted to specify the effectiveness of the selected convolutional neural network using two implementing approaches, named fully trained and fine-tuned. For validation purposes, two remote sensing datasets, AID, and RSSCN7 which are publicly available and have different land covers features were used in the experiments. These datasets have a wide diversity of input data, number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in training, validation, and testing. As a result, the fully trained approach has achieved a trivial result for both of the two data sets, AID and RSSCN7 by 73.346% and 71.857% within 24 min, 1 sec and 8 min, 3 sec respectively. However, dramatic improvement of the classification performance using the fine-tuning approach has been recorded by 92.5% and 91% respectively within 24min, 44 secs and 8 min 41 sec respectively. The represented conclusion opens the opportunities for a better classification performance in various applications such as agriculture and crops remote sensing.

Keywords: conventional neural network, remote sensing, land cover, land use

Procedia PDF Downloads 341

Authors: Madhawa Basnayaka, Jouni Paltakari

Abstract:

Fully passive backscattering chipless RFID tags are an emerging wireless technology with low cost, higher reading distance, and fast automatic identification without human interference, unlike already available technologies like optical barcodes. The design optimization of chipless RFID tags is crucial as it requires replacing integrated chips found in conventional RFID tags with printed geometric designs. These designs enable data encoding and decoding through backscattered electromagnetic (EM) signatures. The applications of chipless RFID tags have been limited due to the constraints of data encoding capacity and the ability to design accurate yet efficient configurations. The traditional approach to accomplishing design parameters for a desired EM response involves iterative adjustment of design parameters and simulating until the desired EM spectrum is achieved. However, traditional numerical simulation methods encounter limitations in optimizing design parameters efficiently due to the speed and resource consumption. In this work, a deep learning neural network (DNN) is utilized to establish a correlation between the EM spectrum and the dimensional parameters of nested centric rings, specifically square and octagonal. The proposed bi-directional DNN has two simultaneously running neural networks, namely spectrum prediction and design parameters prediction. First, spectrum prediction DNN was trained to minimize mean square error (MSE). After the training process was completed, the spectrum prediction DNN was able to accurately predict the EM spectrum according to the input design parameters within a few seconds. Then, the trained spectrum prediction DNN was connected to the design parameters prediction DNN and trained two networks simultaneously. For the first time in chipless tag design, design parameters were predicted accurately after training bi-directional DNN for a desired EM spectrum. The model was evaluated using a randomly generated spectrum and the tag was manufactured using the predicted geometrical parameters. The manufactured tags were successfully tested in the laboratory. The amount of iterative computer simulations has been significantly decreased by this approach. Therefore, highly efficient but ultrafast bi-directional DNN models allow rapid and complicated chipless RFID tag designs.

Keywords: artificial intelligence, chipless RFID, deep learning, machine learning

Procedia PDF Downloads 17

Authors: Mehdi Montakhabrazlighi, Ercan Balikci

Abstract:

The neural network (NN) method is applied to alloy development of single crystal Ni-base Superalloys with low density and improved mechanical strength. A set of 1200 dataset which includes chemical composition of the alloys, applied stress and temperature as inputs and density and time to rupture as outputs is used for training and testing the network. Thermodynamic phase diagram modeling of the screened alloys is performed with Thermocalc software to model the equilibrium phases and also microsegregation in solidification processing. The model is first trained by 80% of the data and the 20% rest is used to test it. Comparing the predicted values and the experimental ones showed that a well-trained network is capable of accurately predicting the density and time to rupture strength of the Ni-base superalloys. Modeling results is used to determine the effect of alloying elements, stress, temperature and gamma-prime phase volume fraction on rupture strength of the Ni-base superalloys. This approach is in line with the materials genome initiative and integrated computed materials engineering approaches promoted recently with the aim of reducing the cost and time for development of new alloys for critical aerospace components. This work has been funded by TUBITAK under grant number 112M783.

Keywords: neural network, rupture strength, superalloy, thermocalc

Procedia PDF Downloads 282

Authors: Kelechi Emmanuel, Kyaw Thein Aung, William Burch

Abstract:

Introduction: Although rewarding in more ways than one, rural medicine can be challenging. The factors that lead to the challenges experienced in rural medicine include but are not limited to scarcity of resources, poor patient education inadequately trained professionals. This is the first single center study done on the challenges of and ways to improve diagnosis in rural medicine. Materials and Methods: Questionnaires were given to providers in a single hospital in rural Tennessee USA. In which providers were asked the question ‘In the past six months, what measures have you taken to improve your diagnostic accuracy given limited resources. Results: The questionnaire was passed to ten physicians working in a two hundred and twentyfive hospital bed. Physicians who participated included physicians in hospital medicine, emergency medicine, surgery, cardiology and gastroenterology. The study found that improved physical examination skills, access to specialist especially via telemedicine and affiliation to centers with more experienced professionals improved diagnosis and overall patient outcome in rural medicine. Conclusion: From this single center study, there is evidence to show that in addition to honing physical examination skills and having access to immediate results of testing done; hospital collaborations and access to highly trained specialist via telemedicine does improve diagnosis in rural medicine.

Keywords: rural medicine, diagnostic accuracy, diagnosis, telemedicine

Procedia PDF Downloads 49

Authors: K. Bresilla, L. Manfrini, B. Morandi, A. Boini, G. Perulli, L. C. Grappadelli

Abstract:

Image/video processing for fruit in the tree using hard-coded feature extraction algorithms have shown high accuracy during recent years. While accurate, these approaches even with high-end hardware are computationally intensive and too slow for real-time systems. This paper details the use of deep convolution neural networks (CNNs), specifically an algorithm (YOLO - You Only Look Once) with 24+2 convolution layers. Using deep-learning techniques eliminated the need for hard-code specific features for specific fruit shapes, color and/or other attributes. This CNN is trained on more than 5000 images of apple and pear fruits on 960 cores GPU (Graphical Processing Unit). Testing set showed an accuracy of 90%. After this, trained data were transferred to an embedded device (Raspberry Pi gen.3) with camera for more portability. Based on correlation between number of visible fruits or detected fruits on one frame and the real number of fruits on one tree, a model was created to accommodate this error rate. Speed of processing and detection of the whole platform was higher than 40 frames per second. This speed is fast enough for any grasping/harvesting robotic arm or other real-time applications.

Keywords: artificial intelligence, computer vision, deep learning, fruit recognition, harvesting robot, precision agriculture

Procedia PDF Downloads 386

Authors: Yanjun Chen, Chuanping Hu, Jie Shao, Lin Mei, Chongyang Zhang

Abstract:

Traditional image classification is based on encoding scheme (e.g. Fisher Vector, Vector of Locally Aggregated Descriptor) with low-level image features (e.g. SIFT, HoG). Compared to these low-level local features, deep convolutional features obtained at the mid-level layer of convolutional neural networks (CNN) have richer information but lack of geometric invariance. For scene classification, there are scattered objects with different size, category, layout, number and so on. It is crucial to find the distinctive objects in scene as well as their co-occurrence relationship. In this paper, we propose a method to take advantage of both deep convolutional features and the traditional encoding scheme while taking object-centric and scene-centric information into consideration. First, to exploit the object-centric and scene-centric information, two CNNs that trained on ImageNet and Places dataset separately are used as the pre-trained models to extract deep convolutional features at multiple scales. This produces dense local activations. By analyzing the performance of different CNNs at multiple scales, it is found that each CNN works better in different scale ranges. A scale-wise CNN adaption is reasonable since objects in scene are at its own specific scale. Second, a fisher kernel is applied to aggregate a global representation at each scale and then to merge into a single vector by using a post-processing method called scale-wise normalization. The essence of Fisher Vector lies on the accumulation of the first and second order differences. Hence, the scale-wise normalization followed by average pooling would balance the influence of each scale since different amount of features are extracted. Third, the Fisher vector representation based on the deep convolutional features is followed by a linear Supported Vector Machine, which is a simple yet efficient way to classify the scene categories. Experimental results show that the scale-specific feature extraction and normalization with CNNs trained on object-centric and scene-centric datasets can boost the results from 74.03% up to 79.43% on MIT Indoor67 when only two scales are used (compared to results at single scale). The result is comparable to state-of-art performance which proves that the representation can be applied to other visual recognition tasks.

Keywords: deep convolutional features, Fisher Vector, multiple scales, scale-specific normalization

Procedia PDF Downloads 302

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 100

Authors: Harri Jalonen

Abstract:

Social media has changed the ways we communicate, collaborate and connect with each other. It has also influenced our habits of consuming sports. Social media has allowed direct interaction between sponsoring companies, athletes/players and fans. Drawing on the service dominant logic of value co-creation, the conceptual paper identifies three operant resources which are beneficial for value co-creation: i) social identity and sense of community, ii) congruence and brand personality, and iii) participatory culture and fan activation. The paper contributes to the theoretical discussion on how social can be media used for value co-creation purposes in the sports industry.

Keywords: sports, value co-creation, social media, service

Procedia PDF Downloads 252

Authors: H. S. Niroshani, W. M. Ediri Arachchi, R. Tudugala, U. J. M. A. L. Jayasinghe, U. M. U. J. Jayasekara, P. B. Hewavithana

Abstract:

Mammography is used as a screening tool for early diagnosis of breast cancer. It is also useful in refining the diagnosis of breast cancer either by assessment or work up after a suspicious area in the breast has been detected. In order to detect breast cancer accurately and at the earliest possible stage, the image must have an optimum contrast to reveal mass densities and spiculated fibrous structures radiating from them. In addition, the spatial resolution must be adequate to reveal the suffusion of micro calcifications and their shape. The above factors can be optimized by implementing an effective QA programme to enhance the accurate diagnosis of mammographic imaging. Therefore, the radiographer’s knowledge on QA is greatly instrumental in routine mammographic practice. The aim of this study was to assess the radiographer’s knowledge on Quality Assurance and Quality Control programmes in relation to mammographic procedures. A cross-sectional study was carried out among all radiographers working in each mammography setting in Sri Lanka. Pre-tested, anonymous self-administered questionnaires were circulated among the study population and duly filled questionnaires returned within a period of three months were taken into the account. The data on demographical information, knowledge on QA programme and associated QC tests, overall knowledge on QA and QC programmes were obtained. Data analysis was performed using IBM SPSS statistical software (version 20.0). The total response rate was 59.6% and the average knowledge score was 54.15±11.29 SD out of 100. Knowledge was compared on the basis of education level, special training of mammography, and the years of working experience in a mammographic setting of the individuals. Out of 31 subjects, 64.5% (n=20) were graduate radiographers and 35.5% (n=11) were diploma holders while 83.9% (n=26) of radiographers have been specially trained for mammography and 16.1% (n=5) have not been attended for any special training for mammography. It is also noted that 58.1% (n=18) of individuals possessed their experience of less than one year and rest 41.9% (n=13) of them were greater than that. Further, the results found that there is a significant difference (P < 0.05) in the knowledge of QA and overall knowledge on QA and QC programme in the categories of education level and working experience. Also, results imply that there was a significant difference (P < 0.05) in the knowledge of QC test among the groups of trained and non-trained radiographers. This study reveals that education level, working experience and the training obtained particularly in the field of mammography have a significant impact on their knowledge on QA and QC in mammography.

Keywords: knowledge, mammography, quality assurance, quality control

Procedia PDF Downloads 311

Authors: Karen Chad, Louise Humbert, Kenzie Friesen, Dave Sandomirsky

Abstract:

Background: The pandemic of COVID-19 presented many historical challenges to the sporting community. For organizations and individuals, sport was put on hold resulting in social, economic, physical, and mental health consequences for all involved. High school sports are seen as an effective and accessible pathway for students to receive health, social, and academic benefits. Studies examining sport cessation due to COVID-19 found substantial negative outcomes on the physical and mental well-being of participants in the high school setting. However, the pandemic afforded an opportunity to examine sport participation and the value people place upon their engagement in high school sport. Study objectives: (1) Examine the experiences of students, parents, administrators, officials, and coaches during a year without high school sports; (2) Understand why participants are involved in high school sports; and (3) Learn what supports are needed for future involvement. Methodology: A mixed method design was used, including semi-structured interviews and a survey (SurveyMonkey software), which was disseminated electronically to high school students, coaches, school administrators, parents, and officials. Results: 1222 respondents completed the survey. Findings showed: (1) 100% of students participate in high school sports to improve their mental health, with >95% said it keeps them active and healthy, helps them make friends and teaches teamwork, builds confidence and positive self-perceptions, teaches resiliency, enhances connectivity to their school, and supports academic learning; (2) Top three reasons teachers coach is their desire to make a difference in the lives of students, enjoyment, and love of the sport, and to give back. Teachers said what they enjoy most is contributing to and watching athletes develop, direct involvement with student sport success, and the competitiveatmosphere; (3) 90% of parents believe playing sports is a valuable experience for their child, 95% said it enriches student academic learning and educational experiences, and 97% encouraged their child to play school sports; (4) Officials participate because of their enjoyment and love of the sport, experience, and expertise, desire to make a difference in the lives of children, the competitive/sporting atmosphere and growing the sport. 4% of officials said it was financially motivated; (5) 100% of administrators said high school sports are important for everyone. 80% believed the pandemic will decrease teachers coaching and increase student mental health and well-being. When there was no sport, many athletes got a part-time job and tried to stay active, with limited success. Coaches, officials, and parents spent more time with family. All participants did little physical activity, were bored; and struggled with mental health and poor physical health. Respondents recommended better communication, promotion, and branding of high school sport benefits, equitable funding for all sports, athlete development, compensation and recognition for coaching, and simple processes to strengthen the high school sport model. Conclusions: High school sport is an effective vehicle for athletes, parents, coaches, administrators, and officials to derive many positive outcomes. When it is taken away, serious consequences prevail. Paying attention to important success factors will be important for the effectiveness of high school sports.

Keywords: physical activity, high school, sports, pandemic

Procedia PDF Downloads 106

Authors: Mera Ababneh, Sayer Al-Azzam, Karem Alzoubi, Abeer Rababa'h

Abstract:

Background: Medication errors are among the most common medical errors. Their occurrences result in patient’s mortality, morbidity, and additional healthcare costs. Continuous monitoring and detection is required. Objectives: The aim of this study was to compare medication errors in outpatient’s prescriptions in two different hospitals (paper system vs. electronic system). Methods: This was a cross sectional observational study conducted in two major hospitals; King Abdullah University Hospital (KAUH) and Princess Bassma Teaching Hospital (PBTH) over three months period. Data collection was conducted by two trained pharmacists at each site. During the study period, medication prescriptions and dispensing procedures were screened for medication errors in both participating centers by two trained pharmacist. Results: In the electronic prescription hospital, 2500 prescriptions were screened in which 631 medication errors were detected. Prescription errors were 231 (36.6%), and dispensing errors were 400 (63.4%) of all errors. On the other side, analysis of 2500 prescriptions in paper-based hospital revealed 3714 medication errors, of which 288 (7.8%) were prescription errors, and 3426 (92.2%) were dispensing errors. A significant number of 2496 (67.2%) were inadequately and/or inappropriately labeled. Conclusion: This study provides insight for healthcare policy makers, professionals, and administrators to invest in advanced technology systems, education, and epidemiological surveillance programs to minimize medication errors.

Keywords: medication errors, prescription errors, dispensing errors, electronic prescription, handwritten prescription

Procedia PDF Downloads 250

Authors: Ashi Gautam, Isha Shukla, Akhil Seghal

Abstract:

Biosensors are analytical devices that use a biological sensing element to detect and measure a specific chemical substance or biomolecule in a sample. These devices are widely used in various fields, including medical diagnostics, environmental monitoring, and food analysis, due to their high specificity, sensitivity, and selectivity. In this research paper, a machine learning model is proposed for predicting the suitability of skin care products based on biosensor readings. The proposed model takes in features extracted from biosensor readings, such as biomarker concentration, skin hydration level, inflammation presence, sensitivity, and free radicals, and outputs the most appropriate skin care product for an individual. This model is trained on a dataset of biosensor readings and corresponding skin care product information. The model's performance is evaluated using several metrics, including accuracy, precision, recall, and F1 score. The aim of this research is to develop a personalised skin care product recommendation system using biosensor data. By leveraging the power of machine learning, the proposed model can accurately predict the most suitable skin care product for an individual based on their biosensor readings. This is particularly useful in the skin care industry, where personalised recommendations can lead to better outcomes for consumers. The developed model is based on supervised learning, which means that it is trained on a labeled dataset of biosensor readings and corresponding skin care product information. The model uses these labeled data to learn patterns and relationships between the biosensor readings and skin care products. Once trained, the model can predict the most suitable skin care product for an individual based on their biosensor readings. The results of this study show that the proposed machine learning model can accurately predict the most appropriate skin care product for an individual based on their biosensor readings. The evaluation metrics used in this study demonstrate the effectiveness of the model in predicting skin care products. This model has significant potential for practical use in the skin care industry for personalised skin care product recommendations. The proposed machine learning model for predicting the suitability of skin care products based on biosensor readings is a promising development in the skin care industry. The model's ability to accurately predict the most appropriate skin care product for an individual based on their biosensor readings can lead to better outcomes for consumers. Further research can be done to improve the model's accuracy and effectiveness.

Keywords: biosensors, data model, machine learning, skin care

Procedia PDF Downloads 48

Authors: Shohei Maruyama, Yasuo Matsuyama, Sachiyo Aburatani

Abstract:

The development of the method to annotate unknown gene functions is an important task in bioinformatics. One of the approaches for the annotation is The identification of the metabolic pathway that genes are involved in. Gene expression data have been utilized for the identification, since gene expression data reflect various intracellular phenomena. However, it has been difficult to estimate the gene function with high accuracy. It is considered that the low accuracy of the estimation is caused by the difficulty of accurately measuring a gene expression. Even though they are measured under the same condition, the gene expressions will vary usually. In this study, we proposed a feature extraction method focusing on the variability of gene expressions to estimate the genes' metabolic pathway accurately. First, we estimated the distribution of each gene expression from replicate data. Next, we calculated the similarity between all gene pairs by KL divergence, which is a method for calculating the similarity between distributions. Finally, we utilized the similarity vectors as feature vectors and trained the multiclass SVM for identifying the genes' metabolic pathway. To evaluate our developed method, we applied the method to budding yeast and trained the multiclass SVM for identifying the seven metabolic pathways. As a result, the accuracy that calculated by our developed method was higher than the one that calculated from the raw gene expression data. Thus, our developed method combined with KL divergence is useful for identifying the genes' metabolic pathway.

Keywords: metabolic pathways, gene expression data, microarray, Kullback–Leibler divergence, KL divergence, support vector machines, SVM, machine learning

Procedia PDF Downloads 376

Authors: Oluwaseun Adeleke, Samuel O. Ikani, Simeon Christian Chukwu, Fidelis Edet, Anthony Nwala, Mopelola Raji, Simeon Christian Chukwu

Abstract:

Background: Health service providers are offered in-service training periodically to strengthen their ability to deliver services that are ethical, quality, timely and safe. Not all capacity-building courses have successfully resulted in intended service delivery outcomes because of poor training content, design, approach, and ambiance. The Delivering Innovations in Selfcare (DISC) project developed a Moment of Truth innovation, which is a proven training model focused on improving consumer/provider interaction that leads to an increase in the voluntary uptake of subcutaneous depot medroxyprogesterone acetate (DMPA-SC) self-injection among women who opt for injectable contraception. Methodology: Six months after training on a moment of truth (MoT) training manual, the project conducted two intensive rounds of qualitative data collection and triangulation that included provider, client, and community mobilizer interviews, facility observations, and routine program data collection. Respondents were sampled according to a convenience sampling approach, and data collected was analyzed using a codebook and Atlas-TI. Providers and clients were interviewed to understand their experience, perspective, attitude, and awareness about the DMPA-SC self-inject. Data were collected from 12 health facilities in three states – eight directly trained and four cascades trained. The research team members came together for a participatory analysis workshop to explore and interpret emergent themes. Findings: Quality-of-service delivery and performance outcomes were observed to be significantly better in facilities whose providers were trained directly trained by the DISC project than in sites that received indirect training through master trainers. Facilities that were directly trained recorded SI proportions that were twice more than in cascade-trained sites. Direct training comprised of full-day and standalone didactic and interactive sessions constructed to evoke commitment, passion and conviction as well as eliminate provider bias and misconceptions in providers by utilizing human interest stories and values clarification exercises. Sessions also created compelling arguments using evidence and national guidelines. The training also prioritized demonstration sessions, utilized job aids, particularly videos, strengthened empathetic counseling – allaying client fears and concerns about SI, trained on positioning self-inject first and side effects management. Role plays and practicum was particularly useful to enable providers to retain and internalize new knowledge. These sessions provided experiential learning and the opportunity to apply one's expertise in a supervised environment where supportive feedback is provided in real-time. Cascade Training was often a shorter and abridged form of MoT training that leveraged existing training already planned by master trainers. This training was held over a four-hour period and was less emotive, focusing more on foundational DMPA-SC knowledge such as a reorientation to DMPA-SC, comparison of DMPA-SC variants, counseling framework and skills, data reporting and commodity tracking/requisition – no facility practicums. Training on self-injection was not as robust, presumably because they were not directed at methods in the contraceptive mix that align with state/organizational sponsored objectives – in this instance, fostering LARC services. Conclusion: To achieve better performance outcomes, consideration should be given to providing training that prioritizes practice-based and emotive content. Furthermore, a firm understanding and conviction about the value training offers improve motivation and commitment to accomplish and surpass service-related performance outcomes.

Keywords: training, performance outcomes, innovation, family planning, contraception, DMPA-SC, self-care, self-injection.

Procedia PDF Downloads 53

Authors: Umm-E-Hani, Faiza Babar, Hanif Durad

Abstract:

Malware-detecting approaches suffer many limitations, due to which all anti-malware solutions have failed to be reliable enough for detecting zero-day malware. Signature-based solutions depend upon the signatures that can be generated only when malware surfaces at least once in the cyber world. Another approach that works by detecting the anomalies caused in the environment can easily be defeated by diligently and intelligently written malware. Solutions that have been trained to observe the behavior for detecting malicious files have failed to cater to the malware capable of detecting the sandboxed or protected environment. Machine learning and deep learning-based approaches greatly suffer in training their models with either an imbalanced dataset or an inadequate number of samples. AI-based anti-malware solutions that have been trained with enough samples targeted a selected feature vector, thus ignoring the input of leftover features in the maliciousness of malware just to cope with the lack of underlying hardware processing power. Our research focuses on producing an anti-malware solution for detecting malicious PE files by circumventing the earlier-mentioned shortcomings. Our proposed framework, which is based on automated feature engineering through autoencoders, trains the model over a fairly large dataset. It focuses on the visual patterns of malware samples to automatically extract the meaningful part of the visual pattern. Our experiment has successfully produced a state-of-the-art accuracy of 99.54 % over test data.

Keywords: malware, auto encoders, automated feature engineering, classification

Procedia PDF Downloads 48