Search results for: trained athletes

Authors: Amy Matharu

Abstract:

Existing literature on older athletes in competitive sports is often male-dominated and limited. This study explores how age and gender impact the experiences of older female bodybuilders in Canada using the social theories of deviance and intersectionality. Qualitative, semi-structured interviews were conducted with 11 Canadian female bodybuilders over the age of 45. Interviews were transcribed, coded, and thematically analysed. This study was approached from a phenomenological perspective. The participants deviated from their perceived social norms of women their age. They exhibited deviance with their actions, such as prioritising themselves and following extreme dieting practices, and with their aesthetics, such as maintaining a muscular appearance. Participants received both positive and negative reactions from society resulting in both admiration and stigmatisation. These reactions varied based on the environment, audience, and context of the situation. Overall, the intersection of age and gender results in a unique position for older female bodybuilders within society and within the sport.

Keywords: age, bodybuilding, gender, females

Procedia PDF Downloads 99

Authors: Elham Bagheri, Yalda Mohsenzadeh

Abstract:

Image memorability refers to the phenomenon where certain images are more likely to be remembered by humans than others. It is a quantifiable and intrinsic attribute of an image. Understanding how visual perception and memory interact is important in both cognitive science and artificial intelligence. It reveals the complex processes that support human cognition and helps to improve machine learning algorithms by mimicking the brain's efficient data processing and storage mechanisms. To explore the computational underpinnings of image memorability, this study examines the relationship between an image's reconstruction error, distinctiveness in latent space, and its memorability score. A trained autoencoder is used to replicate human-like memorability assessment inspired by the visual memory game employed in memorability estimations. This study leverages a VGG-based autoencoder that is pre-trained on the vast ImageNet dataset, enabling it to recognize patterns and features that are common to a wide and diverse range of images. An empirical analysis is conducted using the MemCat dataset, which includes 10,000 images from five broad categories: animals, sports, food, landscapes, and vehicles, along with their corresponding memorability scores. The memorability score assigned to each image represents the probability of that image being remembered by participants after a single exposure. The autoencoder is finetuned for one epoch with a batch size of one, attempting to create a scenario similar to human memorability experiments where memorability is quantified by the likelihood of an image being remembered after being seen only once. The reconstruction error, which is quantified as the difference between the original and reconstructed images, serves as a measure of how well the autoencoder has learned to represent the data. The reconstruction error of each image, the error reduction, and its distinctiveness in latent space are calculated and correlated with the memorability score. Distinctiveness is measured as the Euclidean distance between each image's latent representation and its nearest neighbor within the autoencoder's latent space. Different structural and perceptual loss functions are considered to quantify the reconstruction error. The results indicate that there is a strong correlation between the reconstruction error and the distinctiveness of images and their memorability scores. This suggests that images with more unique distinct features that challenge the autoencoder's compressive capacities are inherently more memorable. There is also a negative correlation between the reduction in reconstruction error compared to the autoencoder pre-trained on ImageNet, which suggests that highly memorable images are harder to reconstruct, probably due to having features that are more difficult to learn by the autoencoder. These insights suggest a new pathway for evaluating image memorability, which could potentially impact industries reliant on visual content and mark a step forward in merging the fields of artificial intelligence and cognitive science. The current research opens avenues for utilizing neural representations as instruments for understanding and predicting visual memory.

Keywords: autoencoder, computational vision, image memorability, image reconstruction, memory retention, reconstruction error, visual perception

Procedia PDF Downloads 48

Authors: Saseyi Olaitan Olaoluwa, Osifeko Olalekan Remigious

Abstract:

The study was meant to identify the impediments to female sports management and participation in the selected colleges. Seven colleges of education in the south west parts of the country were selected for the study. A total of one hundred and five subjects were sampled to supply data. Only one hundred adequately completed and returned, copies of the questionnaire were used for data analysis. The collected data were analysed descriptively. The result of the study showed that inadequate fund, personnel, facilities equipment, supplies, management of sports, supervision and coaching were some of the impediments to female sports management and participation. Athletes were not encouraged to participate. Based on the findings, it was recommended that the government should come to the aid of the colleges by providing fund and other needs that will make sports attractive for enhanced participation.

Keywords: female sports, impediments, management, Nigeria, south west, colleges

Procedia PDF Downloads 388

Authors: Gholba Niranjan Dilip, Anil Kumar

Abstract:

Conduct of accurate reliable mapping of oil palm plantations and census of individual palm trees is a huge challenge. This study addresses this challenge and developed an optimized solution implemented deep learning techniques on remote sensing data. The oil palm is a very important tropical crop. To improve its productivity and land management, it is imperative to have accurate census over large areas. Since, manual census is costly and prone to approximations, a methodology for automated census using panchromatic images from Cartosat-2, SkySat and World View-3 satellites is demonstrated. It is selected two different study sites in Indonesia. The customized set of training data and ground-truth data are created for this study from Cartosat-2 images. The pre-trained model of Single Shot MultiBox Detector (SSD) Lite MobileNet V2 Convolutional Neural Network (CNN) from the TensorFlow Object Detection API is subjected to transfer learning on this customized dataset. The SSD model is able to generate the bounding boxes for each oil palm and also do the counting of palms with good accuracy on the panchromatic images. The detection yielded an F-Score of 83.16 % on seven different images. The detections are buffered and dissolved to generate polygons demarcating the boundaries of the oil palm plantations. This provided the area under the plantations and also gave maps of their location, thereby completing the automated census, with a fairly high accuracy (≈100%). The trained CNN was found competent enough to detect oil palm crowns from images obtained from multiple satellite sensors and of varying temporal vintage. It helped to estimate the increase in oil palm plantations from 2014 to 2021 in the study area. The study proved that high-resolution panchromatic satellite image can successfully be used to undertake census of oil palm plantations using CNNs.

Keywords: object detection, oil palm tree census, panchromatic images, single shot multibox detector

Procedia PDF Downloads 141

Authors: Nancy Retzlaff, Sarah J. Berkemer, Trudie Strauss

Abstract:

In the last couple of decades, the advent of digitalization of any kind of data was probably one of the major advances in all fields of study. This paves the way for also analysing these data even though they might come from disciplines where there was no initial computational necessity to do so. Especially in linguistics, one can find a rather manual tradition. Still when considering studies that involve the history of language families it is hard to overlook the striking similarities to bioinformatics (phylogenetic) approaches. Alignments of words are such a fairly well studied example of an application of bioinformatics methods to historical linguistics. In this paper we will not only consider alignments of strings, i.e., words in this case, but also alignments of syntax trees of selected Indo-European languages. Based on initial, crude alignments, a sophisticated scoring model is trained on both letters and syntactic features. The aim is to gain a better understanding on which features in two languages are related, i.e., most likely to have the same root. Initially, all words in two languages are pre-aligned with a basic scoring model that primarily selects consonants and adjusts them before fitting in the vowels. Mixture models are subsequently used to filter ‘good’ alignments depending on the alignment length and the number of inserted gaps. Using these selected word alignments it is possible to perform tree alignments of the given syntax trees and consequently find sentences that correspond rather well to each other across languages. The syntax alignments are then filtered for meaningful scores—’good’ scores contain evolutionary information and are therefore used to train the sophisticated scoring model. Further iterations of alignments and training steps are performed until the scoring model saturates, i.e., barely changes anymore. A better evaluation of the trained scoring model and its function in containing evolutionary meaningful information will be given. An assessment of sentence alignment compared to possible phrase structure will also be provided. The method described here may have its flaws because of limited prior information. This, however, may offer a good starting point to study languages where only little prior knowledge is available and a detailed, unbiased study is needed.

Keywords: alignments, bioinformatics, comparative linguistics, historical linguistics, statistical methods

Procedia PDF Downloads 133

Authors: Massimo Miccoli, Luca Marangoni, Alberto Aniello Scaringi, Alessandro Marceddu, Alessandro Amicone

Abstract:

The susceptibility of deep neural networks (DNNs) to adversarial manipulations is a recognized challenge within the computer vision domain. Adversarial examples, crafted by adding subtle yet malicious alterations to benign images, exploit this vulnerability. Various defense strategies have been proposed to safeguard DNNs against such attacks, stemming from diverse research hypotheses. Building upon prior work, our approach involves the utilization of autoencoder models. Autoencoders, a type of neural network, are trained to learn representations of training data and reconstruct inputs from these representations, typically minimizing reconstruction errors like mean squared error (MSE). Our autoencoder was trained on a dataset of benign examples; learning features specific to them. Consequently, when presented with significantly perturbed adversarial examples, the autoencoder exhibited high reconstruction errors. The architecture of the autoencoder was tailored to the dimensions of the images under evaluation. We considered various image sizes, constructing models differently for 256x256 and 512x512 images. Moreover, the choice of the computer vision model is crucial, as most adversarial attacks are designed with specific AI structures in mind. To mitigate this, we proposed a method to replace image-specific dimensions with a structure independent of both dimensions and neural network models, thereby enhancing robustness. Our multi-modal autoencoder reconstructs the spectral representation of images across the red-green-blue (RGB) color channels. To validate our approach, we conducted experiments using diverse datasets and subjected them to adversarial attacks using models such as ResNet50 and ViT_L_16 from the torch vision library. The autoencoder extracted features used in a classification model, resulting in an MSE (RGB) of 0.014, a classification accuracy of 97.33%, and a precision of 99%.

Keywords: adversarial attacks, malicious images detector, binary classifier, multimodal transformer autoencoder

Procedia PDF Downloads 48

Authors: Alfred M. Caronia

Abstract:

The aim of this pilot study was to explore an NCAA Division 1 female volleyball players’ experience of a strength and conditioning program and the result this has on self-efficacy of sport skill performance. This phenomenological study comprised of 10 college aged participants that have strength training program experience. Data was collected using semi-structured interviews and a reflective journal; the transcribed interviews were analyzed using qualitative content analysis. From the analysis, four themes emerged: performance enhancement, injury prevention, motivational experience, and learning experience. From the players’ perspective, care needs to be taken to explain the purpose of an exercise and the benefit it will have for a play performance. Other factors that play an important role in a strength training program are team motivation, individual goal setting, bonding, and communication with the strength coach, as all these items appear to be fundamentals of coaching.

Keywords: self-efficacy, skill performance, sports performance, strength training

Procedia PDF Downloads 73

Authors: Alex S. Talan

Abstract:

The introduction of scientific terms for esports can directly affect the quality of the training process. This is a critically important scientific task since esports is a rapidly developing global sport that has only recently begun to receive scientific and methodological consideration. In this report, we evaluate esports from a biomechanical perspective. First, we examine the relationship between physical performance and esports gaming techniques, with consideration toward engineering more effective physical and in-game training methodologies for amateur and professional esports competitors. In addition, we advocate that applying biomechanical research methodologies has the added potential to improve physical performance and endurance in esports athletes. With the budding attention on the esports enterprise globally, scientific research into esports would benefit from standardizing terminologies and methodological approaches that are specifically tailored to assess esports training efficacy to enhance individual and team performance within the esports community.

Keywords: cybersport, esports, biomechanics, sports technique, training standards, dental occlusion, sports engineering, sitting pose

Procedia PDF Downloads 58

Authors: Vivek Mahadev, Manoj Kumar, Neelu Mathur, Brahm Dutt Pandey

Abstract:

Perimeter guarding and protection of critical installations require prompt intrusion detection and assessment to take effective countermeasures. Currently, visual and electronic surveillance are the primary methods used for perimeter guarding. These methods can be costly and complicated, requiring careful planning according to the location and terrain. Moreover, these methods often struggle to detect stealthy and camouflaged insurgents. The object of the present work is to devise a surveillance technique using seismic sensors that overcomes the limitations of existing systems. The aim is to improve intrusion detection, assessment, and characterization by utilizing seismic sensors. Most of the similar systems have only two types of intrusion detection capability viz., human or vehicle. In our work we could even categorize further to identify types of intrusion activity such as walking, running, group walking, fence jumping, tunnel digging and vehicular movements. A virtual fence of 60 meters at GCNEP, Bahadurgarh, Haryana, India, was created by installing four underground geophones at a distance of 15 meters each. The signals received from these geophones are then processed to find unique seismic signatures called features. Various feature optimization and selection methodologies, such as LightGBM, Boruta, Random Forest, Logistics, Recursive Feature Elimination, Chi-2 and Pearson Ratio were used to identify the best features for training the machine learning models. The trained models were developed using algorithms such as supervised support vector machine (SVM) classifier, kNN, Decision Tree, Logistic Regression, Naïve Bayes, and Artificial Neural Networks. These models were then used to predict the category of events, employing weighted ensemble voting to analyze and combine their results. The models were trained with 1940 training events and results were evaluated with 831 test events. It was observed that using the weighted ensemble voting increased the efficiency of predictions. In this study we successfully developed and deployed the virtual fence using geophones. Since these sensors are passive, do not radiate any energy and are installed underground, it is impossible for intruders to locate and nullify them. Their flexibility, quick and easy installation, low costs, hidden deployment and unattended surveillance make such systems especially suitable for critical installations and remote facilities with difficult terrain. This work demonstrates the potential of utilizing seismic sensors for creating better perimeter guarding and protection systems using multiple machine learning models in weighted ensemble voting. In this study the virtual fence achieved an intruder detection efficiency of over 97%.

Keywords: geophone, seismic perimeter surveillance, machine learning, weighted ensemble method

Procedia PDF Downloads 47

Authors: Z. Wochyński, K. A. Sobiech, Z. Kobos

Abstract:

To C-Reactive Proteins include ferritin, transferrin, and ceruloplasmin- metalloproteins. The study aimed at assessing an effect of training on the Special Aerial Gymnastics Instruments (SAGI) on changes of serum ferritin, transferrin, and ceruloplasmin and cadets’ physical fitness in comparison with a control group. Fifty-five cadets in the mean age 20 years were included into this study. They were divided into two groups: Group A (N=41) trained on SAGI and Group B (N=14) trained according the standard program of physical education (control group). In both groups, blood was a material for assays. Samples were collected twice before and after training at the start of the program (training I), during (training II), and after education program completion (training III). Commercially available kits were used to assay blood serum ferritin, transferrin, and ceruloplasmin. Cadets’ physical fitness was evaluated with exercise tests before and after education program completion. In Group A, serum post-exercise ferritin decreased statistically insignificantly in training I and II and increased in training III in comparison with pre-exercise values. In Group B, post-exercise serum ferritin decreased statistically insignificantly in training I and III and significantly increased in training II in comparison with the pre-exercise values. In Group A, serum transferrin decreased statistically insignificantly in training I, and significantly increased in training II, whereas in training III it increased insignificantly in comparison with pre-exercise values. In Group B, post-exercise serum transferrin increased statistically significantly in training I, II, and III in comparison with pre-exercise values. I n Group A, serum ceruloplasmin decreased in all three series in comparison with pre-exercise values. In Group B, serum ceruloplasmin increased significantly in training II. It was showed that the training on SAGI significantly decreased serum ceruloplasmin in Group A in all three series of assays and did not produce significant changes in serum ferritin also was showed significant increase in serum transferrin.

Keywords: special aerial gymnastics instruments, ferritin, ceruloplasmin, transferrin

Procedia PDF Downloads 444

Authors: Nadia Zahra Karimi Khiavi, Amir Ghiami Rad

Abstract:

Due to the high likelihood of injuries in karate, karatekas' injuries warrant special treatment. This study explores the prevalence of karate injuries in East Azerbaijan, Iran and provides a model for karatekas to use in the prevention of such injuries. This study employs a descriptive approach. Male and female participants with a brown belt or above in either control or non-control styles in East Azerbaijan province are included in the study's statistical population. A statistical sample size of 100 people was computed using the tools employed (smartpls), and the samples were drawn at random from all clubs in the province with the assistance of the Karate Board in order to give a model for the prevention of karate injuries. Information was gathered by means of a survey that made use of the Standard Questionnaire for Australian Sports Medicine Injury Reports. The information is presented in the form of tables and samples, and descriptive statistics were used to organise and summarise the data. Control and non-control independent t-tests were conducted using SPSS version 20, and structural equation modelling (pls) was utilised for injury prevention modelling at a 0.05 level of significance. The results showed that the most common areas of injury among the control groups were the upper limbs (46.15%), lower limbs (34.61%), trunk (15.38%), and head and neck (3.84%). The most common types of injuries were broken bones (34.61%), sprain or strain (23.13%), bruising and contusions (23.13%), trauma to the face and mouth (11.53%), and damage to the nerves (69.69%). Uncontrolled committees are most likely to sustain injuries to the head and neck (33.33%), trunk (25.92%), upper limbs (22.22%), and lower limbs (18.51%). The most common injuries were to the mouth and face (33.33%), dislocations and fractures (22.22%), aspirin and strain (22.22%), bruises and contusions (18.51%), and nerves (70%), in that order. Among those who practice control kata, injuries to the upper limb account for 45.83%, the lower limb for 41.666%, the trunk for 8.33%, and the head and neck for 4.166%. The most common types of injuries are dislocations and fractures (41.66 per cent), aspirin and strain (29.16 per cent), bruising and bruises (16.66 per cent), and nerves (12.5%). Injuries to the face and mouth were not reported among those practising the control kata. By far, the most common sites of injury for those practising uncontrolled kata were the lower limb (43.74%), upper limb (39.13%), trunk (13.14%), and head and neck (4.34%). The most common types of injuries were dislocations and fractures (34.82%), aspirin and strain (26.08%), bruises and contusions (21.73%), mouth and face (13.14%), and nerves. Teaching the concepts of cooling and warming (0.591) and enhancing the degree of safety in the sports environment (0.413) were shown to play the most essential roles in reducing sports injuries among karate practitioners of controlling and uncontrolled styles, respectively. Use of common sports gear (0.390), Modification of training programme principles (0.341), Formulation of an effective diet plan for athletes (0.284), Evaluation of athletes' physical anatomy, physiology, chemistry, and physics (0.247).

Keywords: sports injuries, karate, prevention, cooling and warming

Procedia PDF Downloads 77

Authors: Luis Alvarado, Victor Poblete, Isaac Gonzalez, Yetzabeth Gonzalez

Abstract:

In MIREX 2016 (http://www.music-ir.org/mirex), the deep neural network (DNN)-Deep Chroma Extractor, proposed by Korzeniowski and Wiedmer, reached the highest score in an audio chord recognition task. In the present paper, this tool is assessed under acoustic reverberant environments and distinct source-microphone distances. The evaluation dataset comprises The Beatles and Queen datasets. These datasets are sequentially re-recorded with a single microphone in a real reverberant chamber at four reverberation times (0 -anechoic-, 1, 2, and 3 s, approximately), as well as four source-microphone distances (32, 64, 128, and 256 cm). It is expected that the performance of the trained DNN will dramatically decrease under these acoustic conditions with signals degraded by room reverberation and distance to the source. Recently, the effect of the bio-inspired Locally-Normalized Cepstral Coefficients (LNCC), has been assessed in a text independent speaker verification task using speech signals degraded by additive noise at different signal-to-noise ratios with variations of recording distance, and it has also been assessed under reverberant conditions with variations of recording distance. LNCC showed a performance so high as the state-of-the-art Mel Frequency Cepstral Coefficient filters. Based on these results, this paper proposes a variation of locally-normalized triangular filters called Locally-Normalized Quarter Tone (LNQT) filters. By using the LNQT spectrogram, robustness improvements of the trained Deep Chroma Extractor are expected, compared with classical triangular filters, and thus compensating the music signal degradation improving the accuracy of the chord recognition system.

Keywords: chord recognition, deep neural networks, feature extraction, music information retrieval

Procedia PDF Downloads 206

Authors: Robert Ogbanje Okwori

Abstract:

The research studied expository and simulation method of teaching woodwork at Federal University of Technology, Minna, Niger State, Nigeria. The purpose of the study was to compare expository and simulation method of teaching woodwork and determine the method that is more effective in improving performance of students in woodwork. Two research questions and two hypotheses were formulated to guide the study. Fifteen objective questions and two theory questions were used for data collection. The questions set were on structure of timber. The study used the quasi experimental design. The population of the study consisted of 25 woodwork students of Federal University of Technology, Minna, Niger State, Nigeria and three hundred (300) level students were used for the study. The lesson plans for expository method and questions were validated by three lecturers in the Department of Industrial and Technology Education, Federal University of Technology, Minna, Nigeria. The validators checked the appropriates of test items and all the corrections and inputs were effected before administration of the instrument. Data obtained were analyzed using mean, standard deviation and t-test statistical tool. The null hypotheses were formulated and tested using t-test statistics at 0.05 level of significance. The findings of the study showed that simulation method of teaching has improved students’ performance in woodwork and the performance of the students was not influenced by gender. Based on the findings of the study, it was concluded that there was a significant difference in the mean achievement scores of students taught woodwork using simulation method. This implies that simulation method is more effective than expository method of teaching woodwork. Therefore, woodwork teachers should adopt simulation method of teaching woodwork towards better performance. It was recommended that simulation method should be used by woodwork lecturers to teach woodwork since students perform better using the method and also the teachers needs to be trained and re-trained in using simulation method for teaching woodwork. Teachers should be encouraged to use simulation method for their instructional delivery because it will allow them to identify their areas of strength and weakness when imparting knowledge to woodwork students. Government and different agencies should assist in procuring materials and equipment for wood workshops to enable students effectively practice what they have been taught using simulation method.

Keywords: comparative, expository, simulation, woodwork

Procedia PDF Downloads 396

Authors: David Dean Hampton, William Morrison, Mary Rizza, Jan Osborn

Abstract:

This evaluation examined the effects of a supplemental reading intervThis evaluation examined the effects of a supplemental reading intervention for students with specific learning disabilities in reading who were presented with below grade level on fall benchmark scores on DIBELS 6th ed. Revised. Participants consisted of a condition group, those who received supplemental reading instruction in addition to core + special education services and a comparison group of students who were at grade level in their fall benchmark scores. The students in the condition group received 26 weeks of Project MORE instruction delivered multiple times each week from trained volunteer tutors. Using a regression-discontinuity design, condition and comparison groups were compared on reading development growth using DIBELS ORF. Significant findings were reported for grade 2, 3, and 4. ntion for students with specific learning disabilities in reading who presented with below grade level on fall benchmark scores on DIBELS 6th ed. Revised. Participants consisted of a condition group, those who received supplemental reading instruction in addition to core + special education services and a comparison group of students who were at grade level in their fall benchmark scores. The students in the condition group received 26 weeks of Project MORE instruction delivered multiple times each week from trained volunteer tutors. Using a regression-discontinuity design, condition and comparison groups were compared on reading development growth using DIBELS ORF. Significant findings were reported for grade 2, 3, and 4.

Keywords: special education, evidence-based practices, curriculum, tutoring

Procedia PDF Downloads 46

Authors: C. S. Subhashini, H. L. Premaratne

Abstract:

Landslides are the most recurrent and prominent disaster in Sri Lanka. Sri Lanka has been subjected to a number of extreme landslide disasters that resulted in a significant loss of life, material damage, and distress. It is required to explore a solution towards preparedness and mitigation to reduce recurrent losses associated with landslides. Artificial Neural Networks (ANNs) and Hidden Markov Model (HMMs) are now widely used in many computer applications spanning multiple domains. This research examines the effectiveness of using Artificial Neural Networks and Hidden Markov Model in landslides predictions and the possibility of applying the modern technology to predict landslides in a prominent geographical area in Sri Lanka. A thorough survey was conducted with the participation of resource persons from several national universities in Sri Lanka to identify and rank the influencing factors for landslides. A landslide database was created using existing topographic; soil, drainage, land cover maps and historical data. The landslide related factors which include external factors (Rainfall and Number of Previous Occurrences) and internal factors (Soil Material, Geology, Land Use, Curvature, Soil Texture, Slope, Aspect, Soil Drainage, and Soil Effective Thickness) are extracted from the landslide database. These factors are used to recognize the possibility to occur landslides by using an ANN and HMM. The model acquires the relationship between the factors of landslide and its hazard index during the training session. These models with landslide related factors as the inputs will be trained to predict three classes namely, ‘landslide occurs’, ‘landslide does not occur’ and ‘landslide likely to occur’. Once trained, the models will be able to predict the most likely class for the prevailing data. Finally compared two models with regards to prediction accuracy, False Acceptance Rates and False Rejection rates and This research indicates that the Artificial Neural Network could be used as a strong decision support system to predict landslides efficiently and effectively than Hidden Markov Model.

Keywords: landslides, influencing factors, neural network model, hidden markov model

Procedia PDF Downloads 362

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 122

Authors: Madushani Rodrigo, Banuka Athuraliya

Abstract:

In today's world of medical diagnosis and prediction, machine learning stands out as a strong tool, transforming old ways of caring for health. This study analyzes the use of machine learning in the specialized domain of sports medicine, with a focus on the timely and accurate detection of bone fractures in cricket athletes. Failure to identify bone fractures in real time can result in malunion or non-union conditions. To ensure proper treatment and enhance the bone healing process, accurately identifying fracture locations and types is necessary. When interpreting X-ray images, it relies on the expertise and experience of medical professionals in the identification process. Sometimes, radiographic images are of low quality, leading to potential issues. Therefore, it is necessary to have a proper approach to accurately localize and classify fractures in real time. The research has revealed that the optimal approach needs to address the stated problem and employ appropriate radiographic image processing techniques and object detection algorithms. These algorithms should effectively localize and accurately classify all types of fractures with high precision and in a timely manner. In order to overcome the challenges of misidentifying fractures, a distinct model for fracture localization and classification has been implemented. The research also incorporates radiographic image enhancement and preprocessing techniques to overcome the limitations posed by low-quality images. A classification ensemble model has been implemented using ResNet18 and VGG16. In parallel, a fracture segmentation model has been implemented using the enhanced U-Net architecture. Combining the results of these two implemented models, the FracXpert system can accurately localize exact fracture locations along with fracture types from the available 12 different types of fracture patterns, which include avulsion, comminuted, compressed, dislocation, greenstick, hairline, impacted, intraarticular, longitudinal, oblique, pathological, and spiral. This system will generate a confidence score level indicating the degree of confidence in the predicted result. Using ResNet18 and VGG16 architectures, the implemented fracture segmentation model, based on the U-Net architecture, achieved a high accuracy level of 99.94%, demonstrating its precision in identifying fracture locations. Simultaneously, the classification ensemble model achieved an accuracy of 81.0%, showcasing its ability to categorize various fracture patterns, which is instrumental in the fracture treatment process. In conclusion, FracXpert has become a promising ML application in sports medicine, demonstrating its potential to revolutionize fracture detection processes. By leveraging the power of ML algorithms, this study contributes to the advancement of diagnostic capabilities in cricket athlete healthcare, ensuring timely and accurate identification of bone fractures for the best treatment outcomes.

Keywords: multiclass classification, object detection, ResNet18, U-Net, VGG16

Procedia PDF Downloads 52

Authors: Amirul Adlan, Robert McCulloch, Scott Evans, Michael Parry, Jonathan Stevenson, Lee Jeys

Abstract:

Background and Objectives: The gastrocnemius myofascial flap is used to manage soft-tissue defects over the anterior aspect of the knee in the context of a patient presenting with a sinus and periprosthetic joint infection (PJI) or extensor mechanism failure. The aim of this study was twofold: firstly, to evaluate the outcomes of gastrocnemius flaps performed by appropriately trained orthopaedic surgeons in the context of PJI and, secondly, to evaluate the infection-free survival of this patient group. Methods: We retrospectively reviewed 30 patients who underwent gastrocnemius flap reconstruction during staged revision total knee arthroplasty for prosthetic joint infection (PJI). All flaps were performed by an orthopaedic surgeon with orthoplastics training. Patients had a mean age of 68.9 years (range 50–84) and were followed up for a mean of 50.4 months (range 2–128 months). A total of 29 patients (97 %) were categorized into Musculoskeletal Infection Society (MSIS) local extremity grade 3 (greater than two compromising factors), and 52 % of PJIs were polymicrobial. The primary outcome measure was flap failure, and the secondary outcome measure was a recurrent infection. Results: Flap survival was 100% with no failures or early returns to theatre for flap problems such as necrosis or haematoma. Overall infection-free survival during the study period was 48% (13 of 27 infected cases). Using limb salvage as the outcome, 77% (23 of 30 patients) retained the limb. Infection recurrence occurred in 48% (10 patients) in the type B3 cohort and 67% (4 patients) in the type C3 cohort (p = 0.65). Conclusion: The surgical technique for a gastrocnemius myofascial flap is reliable and reproducible when performed by appropriately trained orthopaedic surgeons, even in high-risk groups. However, the risks of recurrent infection and amputation remain high within our series due to poor host and extremity factors.

Keywords: gastrocnemius flap, limb salvage, revision arthroplasty, outcomes

Procedia PDF Downloads 91

Authors: Yilin Liao, Hewen Li, Paula McConvey

Abstract:

Concussion for speed skaters often occurs when skaters fall on the ice and impact the crash mats during practices and competition races. Gaining insight into the impact of interactions is of essential interest as it is directly related to skaters’ potential health risks and injuries. Precise concussion measurements are challenging and very difficult, making computer simulation the only reliable way to analyze accidents. This research aims to create the crash mat and skater’s multi-body model using Solidworks, develop a computer simulation model for skater-mat impact using ANSYS software, and predict the skater’s concussion degree by evaluating the “head injury criteria” (HIC) through the resulting accelerations. The developed method and results help understand the relationship between impact parameters and concussion risk for speed skaters and inform the design of crash mats and skating rink layouts more specifically by considering athletes’ health risks.

Keywords: computer simulation modeling, concussion, impact, speed skater

Procedia PDF Downloads 111

Authors: Joy Cao, Min Zhou

Abstract:

Purpose: Acute Type A aortic dissection is a well-known cause of extremely high mortality rate. A highly accurate and cost-effective non-invasive predictor is critically needed so that the patient can be treated at earlier stage. Although various CFD approaches have been tried to establish some prediction frameworks, they are sensitive to uncertainty in both image segmentation and boundary conditions. Tedious pre-processing and demanding calibration procedures requirement further compound the issue, thus hampering their clinical applicability. Using the latest physics informed deep learning methods to establish an accurate and cost-effective predictor framework are amongst the main goals for a better Type A aortic dissection treatment. Methods: Via training a novel physics-informed deep residual network, with non-invasive 4D MRI displacement vectors as inputs, the trained model can cost-effectively calculate all these biomarkers: aortic blood pressure, WSS, and OSI, which are used to predict potential type A aortic dissection to avoid the high mortality events down the road. Results: The proposed deep learning method has been successfully trained and tested with both synthetic 3D aneurysm dataset and a clinical dataset in the aortic dissection context using Google colab environment. In both cases, the model has generated aortic blood pressure, WSS, and OSI results matching the expected patient’s health status. Conclusion: The proposed novel physics-informed deep residual network shows great potential to create a cost-effective, non-invasive predictor framework. Additional physics-based de-noising algorithm will be added to make the model more robust to clinical data noises. Further studies will be conducted in collaboration with big institutions such as Cleveland Clinic with more clinical samples to further improve the model’s clinical applicability.

Keywords: type-a aortic dissection, deep residual networks, blood flow modeling, data-driven modeling, non-invasive diagnostics, deep learning, artificial intelligence.

Procedia PDF Downloads 62

Authors: Leszek Szpakowski, Daniel Celiński, Sławomir Pilip, Grzegorz Michalak

Abstract:

The aim of the study was to analyse the usefulness of the 'E-rescuer' pilot project planned to be implemented in a chosen area of Eastern Poland in the cases of suspected sudden cardiac arrests in the extra-urban areas. Inventing an application allowing to dispatch simultaneously both Medical Emergency Teams and the E-rescuer to the place of the accident is the crucial assumption of the mentioned pilot project. The E-rescuer is defined to be the trained person able to take effective basic life support and to use automated external defibrillator. Having logged in using a smartphone, the E-rescuer's readiness is reported online to provide cardiopulmonary resuscitation exactly at the given location. Due to the accurately defined location of the E-rescuer, his arrival time is possible to be precisely fixed, and the substantive support through the displayed algorithms is capable of being provided as well. Having analysed the medical records in the years 2015-2016, cardiopulmonary resuscitation was considered to be effective when an early indication of circulation was provided, and the patient was taken to hospital. In the mentioned term, there were 2.291 cases of a sudden cardiac arrest. Cardiopulmonary resuscitation was taken in 621 patients in total including 205 people in the urban area and 416 in the extra-urban areas. The effectiveness of cardiopulmonary resuscitation in the extra-urban areas was much lower (33,8%) than in the urban (50,7%). The average ambulance arrival time was respectively longer in the extra-urban areas, and it was 12,3 minutes while in the urban area 3,3 minutes. There was no significant difference in the average age of studied patients - 62,5 and 64,8 years old. However, the average ambulance arrival time was 7,6 minutes for effective resuscitations and 10,5 minutes for ineffective ones. Hence, the ambulance arrival time is a crucial factor influencing on the effectiveness of cardiopulmonary resuscitation, especially in the extra-urban areas where it is much longer than in the urban. The key role of trained E-rescuers being nearby taking basic life support before the ambulance arrival can effectively support Emergency Medical Services System in Poland.

Keywords: basic life support, bystander, effectiveness, resuscitation

Procedia PDF Downloads 177

Authors: Sara Nasiri Semnani, Alireza Ramzani

Abstract:

Background and Aims: Sodium bicarbonate is a supplementation that used to reduce fatigue and increase power output in short-term training. On the other hand, the Ischemic Reperfusion Preconditioning (IRPC) is an appropriate stimulus to increase the submaximal contractile response. Materials and methods: 9 female student-athletes in double-blind randomized crossover design were three mode, sodium bicarbonate + IRPC, sodium bicarbonate and placebo+ IRPC. Participants moved forward single arm dumbbell hand with a weight of 2 kg can be carried out most frequently. Results: The results showed that plasma lactate concentration and records of sodium bicarbonate + IRPC and sodium bicarbonate conditions were significantly different compared to placebo + IRPC (Respectively p=0.001, p=0/02). Conclusion: According to the research findings, bicarbonate supplementation in IRPC training condition increased force and delay fatigue in submaximal dynamic contraction.

Keywords: ischemic reperfusion, preconditioning, sodium bicarbonate, submaximal dynamic force

Procedia PDF Downloads 273

Authors: Yanting Cao, Kazumitsu Nawata

Abstract:

As smartphones upgrading, their software and hardware are getting smarter, so the smartphone-based human activity recognition will be described as more refined, complex, and detailed. In this context, we analyzed a set of experimental data obtained by observing and measuring 30 volunteers with six activities of daily living (ADL). Due to the large sample size, especially a 561-feature vector with time and frequency domain variables, cleaning these intractable features and training a proper model becomes extremely challenging. After a series of feature selection and parameters adjustment, a well-performed SVM classifier has been trained.

Keywords: smart sensors, human activity recognition, artificial intelligence, SVM

Procedia PDF Downloads 122

Authors: Xabier Olaz Moratinos

Abstract:

Drone navigation is critical, particularly during the initial phases, such as the initial ascension, where pilots may fail due to strong external interferences that could potentially lead to a crash. In this ongoing work, a drone has been successfully trained to perform an ascent of up to 6 meters at speeds with external disturbances pushing it up to 24 mph, with the DQN algorithm managing external forces affecting the system. It has been demonstrated that the system can control its height, position, and stability in all three axes (roll, pitch, and yaw) throughout the process. The learning process is carried out in the Gazebo simulator, which emulates interferences, while ROS is used to communicate with the agent.

Keywords: machine learning, DQN, gazebo, navigation

Procedia PDF Downloads 81

Authors: Chiedu C. Ifekandu, Olusegun Sangowawa, Jean E. Njab

Abstract:

Background: Health care providers (HCPs) in Nigeria receive little or no training of the healthcare needs of men who have sex with men (MSM) limiting the quality and effectiveness of comprehensive HIV prevention and treatment services. Consequently, most MSM disguise themselves to access services which limit the quality of care provided partly due to challenges related to stigma and discrimination, and breach of confidentiality. Objective: To assess the knowledge of healthcare providers on effective intervention for MSM. Methods: We trained 122 HIV focal persons drawn from 60 health facilities from twelve Nigerian states. , the participants were requested to complete a pre-training questionnaire to assess their level of working experience with key populations as a baseline. Participants included male and female doctors, nurses and counselors/testers. A test was administered to measure their knowledge on MSM sexual risk practices, HIV prevention and healthcare needs and also to assess their attitudes (including homophobia) and beliefs and how it affects service uptake by key populations particularly MSM prior and immediately after the training to ascertain the impact of the training. Results: The mean age of the HCP was 38 years +/- SD Of the 122 HCPs (45 % female, 55 % male; 85 % counsellor/testers; 15 % doctors and nurses; 92 % working in government facilities) from 42 health facilities were trained, of which 105 attempted the test questions. At the baseline, few HCPs reported any prior sensitivity training on MSM. Most of the HCPs had limited knowledge of MSM sexual health needs. Over 90% of the HCPs believed that homosexuality is a mental illness. 8 % do not consider MSM, FSW and PWID as key populations for HIV infection. 45 % lacked knowledge on MSM anal sexual practices. The post-test showed that homophobic attitudes had decreased significantly by the end of the training; the health care providers have acquired basic knowledge compared to the pre-test. Conclusions: Scaling up MSM sensitivity training for Nigerian HCPs is likely to be a timely and effective means to improve their understanding of MSM-related health issues, reduce homophobic sentiments and enhance their capacity to provide responsive HIV prevention, treatment and care services in a supportive and non-stigmatizing environment.

Keywords: healthcare providers, key population, men who have sex with men, HCT

Procedia PDF Downloads 326

Authors: Nelson Lay, Felipe Vallejo

Abstract:

The objective of this study is to determine the psychometric properties of a questionnaire to measure Fluid Experience in the practical sport shooting. Also, associate this variable with the performance levels of a group of athletes who are competitors in the discipline. The study included the participation of 18 shooters belonging to sports shooting clubs. Initially semi-structured interviews were conducted to observe the manifestation of the dimensions of the Fluid Experience. Based on these interviews, a self-report sheet was elaborated (feedback sheet). Then, through a correlational design, the association between the elaborated Fluid Experience Psychometric Questionnaire, the score assigned to the responses of the feedback sheet and the scores of the round of shots made by the participants was evaluated. The data were collected, on two different occasions, which implied a variation in the score of the Fluid Experience Questionnaire for each subject in both executions. The results showed a positive association between variations in sports performance and those of the Fluid Experience level.

Keywords: flow psychology, sports psychology, states of conscience, sports performance

Procedia PDF Downloads 229

Authors: Sunethra Jayathilake, Vathsala Jayasuriya-Illesinghe, Kerstin Samarasinghe, Himani Molligoda, Rasika Perera

Abstract:

In Sri Lanka, postnatal care in the state hospitals is provided by different professional categories: Midwifery trained registered nurses (MTRNs), Registered Nurses (RNs) who do not have midwifery training, doctors and midwives. Even though four professional categories provide postnatal care to mothers and newborn babies, they are not aware of their own tasks and responsibilities in postnatal care. Particularly MTRN’s role in the postnatal unit is unclear. The current study aimed to identify nurses’ (both MTRN and RNs) perception on MTRN’s tasks and responsibilities in postnatal care. This is a descriptive cross sectional study using postal survey. All nurses who were currently working in postnatal units at five selected tertiary care hospitals in the Western Province at that time were invited to participate in the study. Accordingly, the pre evaluated self-administered questionnaire was sent to 201 nurses (53 MTRNs and 148 RNs) in the study setting. The number of valid return questionnaire was 166; response rate was 83%. Respondents rated the responsibility of four professional categories: MTRN, RN, doctor and midwife whether they are 'primarily responsible', 'responsible in absence' and 'not responsible', for each of 15 postnatal (PN) tasks which were previously identified from focus group discussions with care providers during the first phase of the study. Data were analyzed using SPSS version 20; descriptive statistics were calculated. Out of the 15 PN tasks, 13 were identified as MTRNs’ primary responsibilities by 71%-93% of respondents. The respondents also considered six (6) tasks out of 15 as primary responsibility of both MTRN and RN, seven (7) tasks as primary responsibility of MTRN, RN and doctor and the remaining two (2) tasks were identified as the primary responsibility of MTRN, RN and midwife. All 15 PN tasks overlapped with other professional categories. Overlapping tasks may create role confusion leading to conflicts among professional categories which affect the quality of care they provide, eventually, threaten the safety of the client. It is recommended that an official job description for each care provider is needed to recognize their own professional boundaries for ensuring safe, quality care delivery in Sri Lanka.

Keywords: overlapping, postnatal, responsibilities, tasks

Procedia PDF Downloads 126

Authors: Lancer Scott

Abstract:

Purpose: High quality clinical disaster medicine requires providers working collaboratively to care for multiple patients in chaotic environments; however, many providers lack adequate training. To address this deficit, we created a competency-based, 5-hour Emergency Preparedness Training (EPT) curriculum using didactics, small-group discussion, and kinetic learning. The goal was to evaluate the effect of a short course on improving provider knowledge, confidence and skills in disaster scenarios. Methods: Diverse groups of medical university students, health care professionals, and community members were enrolled between 2011 and 2014. The course consisted of didactic lectures, small group exercises, and two live, multi-patient mass casualty incident (MCI) scenarios. The outcome measures were based on core competencies and performance objectives developed by a curriculum task force and assessed via trained facilitator observation, pre- and post-testing, and a course evaluation. Results: 708 participants completed were trained between November 2011 and August 2014, including 49.9% physicians, 31.9% medical students, 7.2% nurses, and 11% various other healthcare professions. 100% of participants completed the pre-test and 71.9% completed the post-test, with average correct answers increasing from 39% to 60%. Following didactics, trainees met 73% and 96% of performance objectives for the two small group exercises and 68.5% and 61.1% of performance objectives for the two MCI scenarios. Average trainee self-assessment of both overall knowledge and skill with clinical disasters improved from 33/100 to 74/100 (overall knowledge) and 33/100 to 77/100 (overall skill). The course assessment was completed by 34.3% participants, of whom 91.5% highly recommended the course. Conclusion: A relatively short, intensive EPT course can improve the ability of a diverse group of disaster care providers to respond effectively to mass casualty scenarios.

Keywords: clinical disaster medicine, training, hospital preparedness, surge capacity, education, curriculum, research, performance, training, student, physicians, nurses, health care providers, health care

Procedia PDF Downloads 173

Authors: Xabier Olaz Moratinos

Abstract:

Drone navigation is critical, particularly during the initial phases, such as the initial ascension, where pilots may fail due to strong external interferences that could potentially lead to a crash. In this ongoing work, a drone has been successfully trained to perform an ascent of up to 6 meters at speeds with external disturbances pushing it up to 24 mph, with the DQN algorithm managing external forces affecting the system. It has been demonstrated that the system can control its height, position, and stability in all three axes (roll, pitch, and yaw) throughout the process. The learning process is carried out in the Gazebo simulator, which emulates interferences, while ROS is used to communicate with the agent.

Keywords: machine learning, DQN, Gazebo, navigation

Procedia PDF Downloads 50

Authors: Alireza Barari, Saeed Shirali, Ahmad Abdi

Abstract:

Abstract: Introduction: Physical activity may be related to male reproductive function by affecting on thehypothalamic-pituitary-gonadal(HPG) axis. Our aim was to determine the effects of 6 weeks resistance exercise on reproductive hormones, HPG axis. The hypothalamic-pituitary-gonadal (HPG) axis refers tothe effects of endocrine glands in three-level including (i) the hypothalamic releasing hormone GnRH, which is synthesized in in a small heterogenous neuronal population and released in a pulsatile fashion, (ii) the anterior pituitary hormones, follicle-stimulating hormone(FSH) and luteinizing hormone (LH) and (iii) the gonadal hormones, which include both steroid such as testosterone (T), estradiol and progesterone and peptide hormones (such as inhibin). Hormonal changes that create a more anabolic environment have been suggested to contribute to the adaptation to strength exercise. Physical activity has an extensive impact on male reproductive function depending upon the intensity and duration of the exercise and the fitness level of the individual. However, strenuous exercise represents a physical stress and inflammation changed that challenges homeostasis. Materials and methods: Sixteen male volunteered were included in a 6-week control period followed by 6 weeks of resistance training (leg press, lat pull, chest press, squat, seatedrow, abdominal crunch, shoulder press, biceps curl and triceps press down) four times per week. intensity of training loading was 60%-75% of one maximum repetition. Participants performed 3 sets of 10 repetitions. Rest periods were two min between exercises and sets. Start with warm up exercises include: The muscles relax and stretch the body, which was for 10 minutes. Body composition, VO2max and the circulating level of free testosterone (fT), luteinizing hormone (LH), follicle-stimulating hormone (FSH), sex hormone binding globulin (SHBG) and inhibin B measured prior and post 6-week intervention. The hormonal levels of each serum sample were measured using commercially available ELISA kits. Analysis of anthropometrical data and hormonal level were compared using the independent samples t- test in both groups and using SPSS (version 19). P ≤ 0.05 was considered statistically significant. Results: For muscle strength, both lower- and upper-body strength were increased significantly. Aerobic fitness level improved in trained participant from 39.4 ± 5.6 to 41.9 ± 5.3 (P = 0.002). fT concentration rise progressively in the trained group and was significantly greater than those in the control group (P = 0.000). By the end of the 6-week resistance training, serum SHBG significantly increased in the trained group compared with the control group (P = 0.013). In response to resistance training, LH, FSH and inhibin B were not significantly changed. Discussion: According to our finfings, 6 weeks of resistance training induce fat loss without any changes in body weight and BMI. A decline of 25.3% in percentage of body fat with statiscally same weight was due to increase in muscle mass that happened during resistance exercise periods . Six weeks of resistance training resulted in significant improvement in BF%, VO2max and increasing strength and the level of fT and SHBG.

Keywords: resistance, hypothalamic, pituitary, gonadal axis

Procedia PDF Downloads 382