Search results for: trained athletes

Authors: Niklas Panten, Eberhard Abele

Abstract:

This paper presents a novel approach for real-time and near-optimal control of industrial smart grids by deep reinforcement learning (DRL). To achieve highly energy-efficient factory systems, the energetic linkage of machines, technical building equipment and the building itself is desirable. However, the increased complexity of the interacting sub-systems, multiple time-variant target values and stochastic influences by the production environment, weather and energy markets make it difficult to efficiently control the energy production, storage and consumption in the hybrid industrial smart grids. The studied deep reinforcement learning approach allows to explore the solution space for proper control policies which minimize a cost function. The deep neural network of the DRL agent is based on a multilayer perceptron (MLP), Long Short-Term Memory (LSTM) and convolutional layers. The agent is trained within multiple Modelica-based factory simulation environments by the Advantage Actor Critic algorithm (A2C). The DRL controller is evaluated by means of the simulation and then compared to a conventional, rule-based approach. Finally, the results indicate that the DRL approach is able to improve the control performance and significantly reduce energy respectively operating costs of industrial smart grids.

Keywords: industrial smart grids, energy efficiency, deep reinforcement learning, optimal control

Procedia PDF Downloads 195

Authors: Claire Xu, Welton Wang, Manasvi Pinnaka, Anqi Pan, Michael Han

Abstract:

Hospitalizations account for one-third of the total health care spending in the US. Early risk detection and intervention can reduce this high cost and increase the satisfaction of both patients and physicians. Due to the lack of awareness of the potential arising risks in home environment, the opportunities for patients to seek early actions of clinical visits are dramatically reduced. This research aims to offer a highly personalized remote patients monitoring and risk assessment AI framework to identify the potentially preventable hospitalization for both acute as well as chronic diseases. A hybrid-AI framework is trained with data from clinical setting, patients surveys, as well as online databases. 20+ risk factors are analyzed ranging from activities, biometric info, demographic info, socio-economic info, hospitalization history, medication info, lifestyle info, etc. The AI model yields high performance of 87% accuracy and 88 sensitivity with 20+ features. This hybrid-AI framework is proven to be effective in identifying the potentially preventable hospitalization. Further, the high indicative features are identified by the models which guide us to a healthy lifestyle and early intervention suggestions.

Keywords: hospitalization prevention, machine learning, remote patient monitoring, risk prediction

Procedia PDF Downloads 231

Authors: Shaode Yu, Jiajian Meng, Bing Zhu, Hang Yu, Qiurui Sun

Abstract:

Speech emotion recognition (SER) is for recognizing human subjective emotions through audio data in-depth analysis. From speech audios, how to comprehensively extract emotional information and how to effectively fuse extracted features remain challenging. This paper presents a dual-stream SER framework that embraces both full training and transfer learning of different networks for thorough feature encoding. Besides, a plug-and-play cross-attention fusion (CAF) module is implemented for the valid integration of the dual-stream encoder output. The effectiveness of the proposed CAF module is compared to the other three fusion modules (feature summation, feature concatenation, and feature-wise linear modulation) on two databases (RAVDESS and IEMO-CAP) using different dual-stream encoders (full training network, DPCNN or TextRCNN; transfer learning network, HuBERT or Wav2Vec2). Experimental results suggest that the CAF module can effectively reconcile conflicts between features from different encoders and outperform the other three feature fusion modules on the SER task. In the future, the plug-and-play CAF module can be extended for multi-branch feature fusion, and the dual-stream SER framework can be widened for multi-stream data representation to improve the recognition performance and generalization capacity.

Keywords: speech emotion recognition, cross-attention fusion, dual-stream, pre-trained

Procedia PDF Downloads 76

Authors: Salieg L. Munestri

Abstract:

War on Terror became a principal war after the 9/11 attacks on U.S. homeland. Instead of helping to build up worldwide efforts to condemn terror and suicide bombings, the U.S.-led war on terror has given opportunities for the vast spread of terror. In much of Muslim world recently, the Bush’s Doctrine pushing all nations to choose sides in a war that is not truly a war has resulted worse effects. In the world’s most populous Muslim nation, Indonesia, more terror occurred since then. Instead of reinforcing the well-trained anti-terror military forces, Indonesian government established US-funded Special Detachment 88 to guarantee the accomplishment of war on terror in Indonesia and significantly to bring impact on regional security atmosphere. Indonesia is a potential power in Asia but it lacked off sophisticated military equipments. Consequently, Indonesia agrees to become a U.S. mutual partner in combating terrorism managed by Defense Security Cooperation Agency. The formation of elite anti-terror forces and U.S. partnerships perform Indonesia’s commitment to take a position beside the U.S. in coping with terrorism issue. However, this undeniably brings consequences on Indonesian political athmosphere, which encourages the writer to dig deep the consequences on the domestic environment of Indonesian political system. The establishment of the elite forces has aroused fluctuations within government, chiefly Indonesian House, concerning the establishment urgency, the large amount of funding, and the unpleasant performances, particularly the treatment toward suspected terrorists. Hence, evaluation process upon the Detachment 88 is highly demanding.

Keywords: anti-terror forces, Indonesia, political system, war on terror

Procedia PDF Downloads 346

Authors: Carlette Groome

Abstract:

This paper examined the role of drama in the lives of four women. The researcher concluded that drama can be an avenue of healing and could be an effective means of social work intervention in the communities as well as female empowerment. The participants in the study were able to, through the dramatic process; re-write their life’s scripts by resolving paradoxes and conflicts related to the themes unearthed. The research conducted examined the role of drama in the lives of four women living in volatile communities in Jamaica, who were each exposed to violence in one, or multiple, forms. The women were trained by Sistren Theatre Collective in the use of drama for education (edutainment), and were actresses in Sistren's street theatre drama group. Using their own personal and collective experiences, they used drama to raise social consciousness at the community level, about violence and other issues affecting women. The study employed a narrative case study approach and was grounded in a constructivist paradigm. This paradigm was coupled with a basic interpretive qualitative method and the concept of the reflective practitioner provided the foundation for the analysis. Through individual conversations with the women, themes of abuse, resilience, self- esteem, and empowerment arose sharply. The women explored drama and understood it to be instrumental in healing different aspects of their lives. Also, through the dramatic process; they were able to re-write their life’s scripts by resolving paradoxes and conflicts related to the themes unearthed.

Keywords: women, drama, healing, community

Procedia PDF Downloads 340

Authors: Naghmeh Moradpoor Sheykhkanloo

Abstract:

Structured Query Language Injection (SQLI) attack is a code injection technique in which malicious SQL statements are inserted into a given SQL database by simply using a web browser. Losing data, disclosing confidential information or even changing the value of data are the severe damages that SQLI attack can cause on a given database. SQLI attack has also been rated as the number-one attack among top ten web application threats on Open Web Application Security Project (OWASP). OWASP is an open community dedicated to enabling organisations to consider, develop, obtain, function, and preserve applications that can be trusted. In this paper, we propose an effective pattern recognition neural network model for detection and classification of SQLI attacks. The proposed model is built from three main elements of: a Uniform Resource Locator (URL) generator in order to generate thousands of malicious and benign URLs, a URL classifier in order to: 1) classify each generated URL to either a benign URL or a malicious URL and 2) classify the malicious URLs into different SQLI attack categories, and an NN model in order to: 1) detect either a given URL is a malicious URL or a benign URL and 2) identify the type of SQLI attack for each malicious URL. The model is first trained and then evaluated by employing thousands of benign and malicious URLs. The results of the experiments are presented in order to demonstrate the effectiveness of the proposed approach.

Keywords: neural networks, pattern recognition, SQL injection attacks, SQL injection attack classification, SQL injection attack detection

Procedia PDF Downloads 469

Authors: Suresh Sharma, Neeti Goutam

Abstract:

In India abortions are legal and with the exceedingly liberal and broadened law that was passed in 1971, “Medical Termination of Pregnancy Act” had opened a new window to Women’s’ freedom and choice over their fertility. This paper would like to focus on the factors responsible for or leading to unsafe abortion as well as such high incidence of abortion in India which can help in understanding the ways in which we can prevent this apathy. To study the intricacies involved in delivering safety to womanhood in terms of safe abortion practice which includes more trained personnel, detailed explanation and consequences of conducting an abortion, fine reporting, awareness regarding family planning measures and not only pressurizing them to sterilize immediately after an abortion but also prior to that informing them and lastly easy accessibility of Contraceptives with a educated and brief information on that. Data has been drawn from various sources such as National Family Household Survey (1, 2, 3), Health Management Information System and Annual Health Survey. To safeguard the interest of women when it comes to complications resulting from unsafe abortions, Reproductive Health laid its strict adherence to it in its guidelines. The Government could induce more measures in terms of family planning measures and increase in the number of skilled medical health force, chiefly in rural areas to prevent the illegality of abortions. But before that fine reporting on the number of abortions performed will give an insight to this very issue only then policies and programs will work much better in favor of women.

Keywords: abortion, MTP act, India, women

Procedia PDF Downloads 358

Authors: Hannah Wamaitha Irungu

Abstract:

Educational reforms have been made from time to time since independence in Kenya. Kenya previously had a curriculum system coined as 8.4.4, where learners go through 8 years of primary, 4 years of secondary, and 4 years of tertiary or college education. The 8.4.4 system was very theoretical, examinational oriented, lacked career guidance, lacked I.C.T. infrastructure and had the pressure for exam grading results to move to the next level. Kenya is now implementing a Competency Based Curriculum (C.B.C) system of education. C.B.C, on the other hand, is learner based. It focuses mainly on the ability of the learners, their strengths/likings, not what they are systematically trained to pass exams only for progression. The academic pressure will be eased, which gives a chance to all learners to pursue their fields of strength and not only those endowed academically/theoretically. With C.B.C., each learner’s progress is nurtured and monitored over a period of 14 years that are divided into four major levels (2-6-3-3): 1. Pre-primary education [pp1 and pp2]-2 years; 2. Lower-primary [grades 1 - 6]-6 years; 3. Junior-secondary [grades 7 - 9]-3 years; 4. Senior secondary [grades 10 - 12]-3 years. In this paper, we look at these aspects with regards to C.B.C.: What necessitates it, its key strengths/benefits and application in a developing country; Implementation, what has worked and what is not working with the approach taken by Kenya education stakeholders during this process; Stakeholders, who should be involved/own the process; Conclusion, lessons learned, current status and recommendations going forward.

Keywords: benefits, challenges, competency, curricula, Kenya, successes

Procedia PDF Downloads 106

Authors: T. Hari Prasath, P. Ithaya Rani

Abstract:

In the world of visual technology, recognizing emotions from the face images is a challenging task. Several related methods have not utilized the dynamic facial features effectively for high performance. This paper proposes a method for emotions recognition using dynamic facial features with high performance. Initially, local features are captured by Gabor filter with different scale and orientations in each frame for finding the position and scale of face part from different backgrounds. The Gabor features are sent to the ensemble classifier for detecting Gabor facial features. The region of dynamic features is captured from the Gabor facial features in the consecutive frames which represent the dynamic variations of facial appearances. In each region of dynamic features is normalized using Z-score normalization method which is further encoded into binary pattern features with the help of threshold values. The binary features are passed to Multi-class AdaBoost classifier algorithm with the well-trained database contain happiness, sadness, surprise, fear, anger, disgust, and neutral expressions to classify the discriminative dynamic features for emotions recognition. The developed method is deployed on the Ryerson Multimedia Research Lab and Cohn-Kanade databases and they show significant performance improvement owing to their dynamic features when compared with the existing methods.

Keywords: detecting face, Gabor filter, multi-class AdaBoost classifier, Z-score normalization

Procedia PDF Downloads 278

Authors: Gaetano Zazzaro, Angelo Martone, Roberto V. Montaquila, Luigi Pavone

Abstract:

Seizure is the main factor that affects the quality of life of epileptic patients. The diagnosis of epilepsy, and hence the identification of epileptogenic zone, is commonly made by using continuous Electroencephalogram (EEG) signal monitoring. Seizure identification on EEG signals is made manually by epileptologists and this process is usually very long and error prone. The aim of this paper is to describe an automated method able to detect seizures in EEG signals, using knowledge discovery in database process and data mining methods and algorithms, which can support physicians during the seizure detection process. Our detection method is based on Artificial Neural Network classifier, trained by applying the multilayer perceptron algorithm, and by using a software application, called Training Builder that has been developed for the massive extraction of features from EEG signals. This tool is able to cover all the data preparation steps ranging from signal processing to data analysis techniques, including the sliding window paradigm, the dimensionality reduction algorithms, information theory, and feature selection measures. The final model shows excellent performances, reaching an accuracy of over 99% during tests on data of a single patient retrieved from a publicly available EEG dataset.

Keywords: artificial neural network, data mining, electroencephalogram, epilepsy, feature extraction, seizure detection, signal processing

Procedia PDF Downloads 188

Authors: Melody Yin

Abstract:

Concussions impact a large amount of adolescents; they make up as much as half of the diagnosed concussions in America. This research proposes a hybrid machine learning model based on the combination of human/knowledge-based domains and computer-generated feature rankings to improve the accuracy of diagnosing sports related concussion (SRC). Using a data set of symptoms collected on the sideline post-SRC events, the symptom selection criteria method has been developed by using Google AutoML's important score function to identify the top 10 symptom features. In addition, symptom domains have been introduced as another parameter, categorizing the symptoms into physical, cognitive, sleep, and emotional domains. The hybrid machine learning model has been trained with a combination of the top 10 symptoms and 4 domains. From the results, the hybrid model was the best performer for symptom resolution time prediction in 2 and 4-week thresholds. This research is a proof of concept study in the use of domains along with machine learning in order to improve concussion prediction accuracy. It is also possible that the use of domains can make the model more efficient due to reduced training time. This research examines the use of a hybrid method in predicting sports-related concussion. This achievement is based on data preprocessing, using a hybrid method to select criteria to achieve high performance.

Keywords: hybrid model, machine learning, sports related concussion, symptom resolution time

Procedia PDF Downloads 168

Authors: Caroline Provost, Francois Dumont

Abstract:

Production of insects for human and animal consumption is an increasingly important activity in Canada. Protein production is more efficient and less harmful to the environment using insect rearing compared to the impact of traditional livestock, poultry and fish farms. Insects are rich in essential amino acids, essential fatty acids and trace elements. Thus, insect-based products could be used as a food supplement for livestock and domestic animals and may even find their way into the diets of high performing athletes or fine dining. Nevertheless, several parameters remain to be determined to ensure efficient and profitable production that meet the potential of these sectors. This project proposes to improve the production processes, rearing diets and processing methods for three species with valuable gastronomic and nutritional potential: the common mealworms (Tenebrio molitor), the small mealworm (Alphitobius diaperinus), and the giant mealworm (Zophobas morio). The general objective of the project is to acquire specific knowledge for mass rearing of insects dedicated to animal and human consumption in order to respond to current market opportunities and meet a growing demand for these products. Mass rearing of the three species of mealworm was produced to provide the individuals needed for the experiments. Mealworms eat flour from different cereals (e.g. wheat, barley, buckwheat). These cereals vary in their composition (protein, carbohydrates, fiber, vitamins, antioxidant, etc.), but also in their purchase cost. Seven different diets were compared to optimize the yield of the rearing. Diets were composed of cereal flour (e.g. wheat, barley) and were either mixed or left alone. Female fecundity, larvae mortality and growing curves were observed. Some flour diets have positive effects on female fecundity and larvae performance while each mealworm was found to have specific diet requirements. Trade-offs between mealworm performance and costs need to be considered. Experiments on the effect of flour composition on several parameters related to performance and nutritional and gastronomic value led to the identification of a more appropriate diet for each mealworm.

Keywords: mass rearing, mealworm, human consumption, diet

Procedia PDF Downloads 147

Authors: Qiang Wang, Hongyang Yu

Abstract:

Multi-human 3D pose estimation is a challenging task in computer vision, which aims to recover the 3D joint locations of multiple people from multi-view images. In contrast to traditional methods, which typically only use color (RGB) images as input, our approach utilizes both color and depth (D) information contained in RGB-D images. We also employ a transformer-based model as the backbone of our approach, which is able to capture long-range dependencies and has been shown to perform well on various sequence modeling tasks. Our method is trained and tested on the Carnegie Mellon University (CMU) Panoptic dataset, which contains a diverse set of indoor and outdoor scenes with multiple people in varying poses and clothing. We evaluate the performance of our model on the standard 3D pose estimation metrics of mean per-joint position error (MPJPE). Our results show that the transformer-based approach outperforms traditional methods and achieves competitive results on the CMU Panoptic dataset. We also perform an ablation study to understand the impact of different design choices on the overall performance of the model. In summary, our work demonstrates the effectiveness of using a transformer-based approach with RGB-D images for multi-human 3D pose estimation and has potential applications in real-world scenarios such as human-computer interaction, robotics, and augmented reality.

Keywords: multi-human 3D pose estimation, RGB-D images, transformer, 3D joint locations

Procedia PDF Downloads 80

Authors: Mayowa Adeyeye, Kehinde Adeyemo

Abstract:

The direct free kick is considered a great opportunity to score a goal but this is not always the case amidst Nigerian and other elite footballers. This study, therefore, examined the extent to which an 8 weeks mental skill training programme is effective for improving accuracy in direct free kick in football. Sixty (n-60) students of Pepsi Football Academy participated in the study. They were randomly distributed into two groups of positive self-talk group (intervention n-30) and control group (n-30). The instrument used in the collection of data include a standard football goal post while the research materials include a dummy soccer wall, a cord, an improvised vanishing spray, a clipboard, writing materials, a recording sheet, a self-talk log book, six standard 5 football, cones, an audiotape and a compact disc. The Weinberge and Gould (2011) mental skills training manual was used. The reliability coefficient of the apparatus following a pilot study stood at 0.72. Before the commencement of the mental skills training programme, the participants were asked to take six simulated direct free kick. At the end of each physical skills training session after the pre-test, the researcher spent at least 15 minutes with the groups exposing them to the intervention. The mental skills training programme alongside physical skills training took place in two different locations for the different groups under study, these included Agege Stadium Main bowl Football Pitch (Imagery Group), and Ogba Ijaye (Control Group). The mental skills training programme lasted for eight weeks. After the completion of the mental skills training programme, all the participants were asked to take another six simulated direct free kick attempts using the same field used for the pre-test to determine the efficacy of the treatments. The pre-test and post-test data were analysed using inferential statistics of t-test, while the alpha level was set at 0.05. The result revealed significant differences in t-test for positive self-talk and control group. Based on the findings, it is recommended that athletes should be exposed to positive self-talk alongside their normal physical skills training for quality delivery of accurate direct free kick during training and competition.

Keywords: accuracy, direct free kick, pepsi football academy, positive self-talk

Procedia PDF Downloads 348

Authors: Rodolfo Lorbieski, Silvia Modesto Nassar

Abstract:

Many supervised machine learning tasks require decision making across numerous different classes. Multi-class classification has several applications, such as face recognition, text recognition and medical diagnostics. The objective of this article is to analyze an adapted method of Stacking in multi-class problems, which combines ensembles within the ensemble itself. For this purpose, a training similar to Stacking was used, but with three levels, where the final decision-maker (level 2) performs its training by combining outputs from the tree-based pair of meta-classifiers (level 1) from Bayesian families. These are in turn trained by pairs of base classifiers (level 0) of the same family. This strategy seeks to promote diversity among the ensembles forming the meta-classifier level 2. Three performance measures were used: (1) accuracy, (2) area under the ROC curve, and (3) time for three factors: (a) datasets, (b) experiments and (c) levels. To compare the factors, ANOVA three-way test was executed for each performance measure, considering 5 datasets by 25 experiments by 3 levels. A triple interaction between factors was observed only in time. The accuracy and area under the ROC curve presented similar results, showing a double interaction between level and experiment, as well as for the dataset factor. It was concluded that level 2 had an average performance above the other levels and that the proposed method is especially efficient for multi-class problems when compared to binary problems.

Keywords: stacking, multi-layers, ensemble, multi-class

Procedia PDF Downloads 269

Authors: Sifen Abreham

Abstract:

Employees are resources in organizations; as such, they need to be trained and developed properly to achieve an organization's goals and expectations. The initial development of the human resource management concept is based on the effective utilization of people to treat them as resources, leading to the realization of business strategies and organizational objectives. The study aimed to assess the effect of training and development practices on employee performance. The researcher used an explanatory research design, which helps to explain, understand, and predict the relationship between variables. To collect the data from the respondents, the study used probability sampling. From the probability, the researcher used stratified random sampling, which can branch off the entire population into homogenous groups. The result was analyzed and presented by using the statistical package for the social science (SPSS) version 26. The major finding of the study was that the training has an impact on employees' job performance to achieve organizational objectives. The district has a policy and procedure for training and development, but it doesn’t apply actively, and it’s not suitable for district-advised reform this policy and procedure and applied actively; the district gives training for the majority of its employees, but most of the time, the training is theoretical the district advised to use practical training method to see positive change, the district gives evaluation after the employees take training and development, but the result is not encouraging the district advised to assess employees skill gap and feel that gap, the district has a budget, but it’s not adequate the district advised to strengthen its financial ground.

Keywords: training, development, employees, performance, policy

Procedia PDF Downloads 58

Authors: Muhandiram Rallage Ruvini Nisansala Yatigammana, Anuruddhika Kumudu Kumari Rajakaruna Jayathilaka

Abstract:

Sports injuries are common among teenagers and children engaged in organized sports. While most sports injuries are typical, some rare occurrences involve conditions such as eye, dental, cervical, and rare internal organ injuries, such as pancreatic injuries. These injuries, especially traumatic pancreatitis, require prompt attention due to their potential for severe and sometimes fatal complications. This case revolves around a real accident involving a 12-year-old girl, Piyumi, who suffered a face-to-face collision during netball practice, resulting in severe abdominal pain. After a medical examination, she was diagnosed with a rare pancreatic injury, uncommon in children compared to adults. In Piyumi’s case, she had a grade 3 pancreatic injury and underwent non-surgical management, successfully healing her wound without surgery. The study attempts to fill empirical and population gaps, addressing a rarely discussed injury experienced by a 12-year-old female netball player. The paper will also provide an in-depth understanding of pancreatic injury, which is a rare sports injury. The study’s main objective was to investigate the incidence and characteristics of pancreatic injury, particularly focusing on pancreatic trauma, among children and adolescents engaged in high-impact sports, such as netball. This research adopted a case study strategy, employing interviews as the primary data collection method. Interviews were conducted with Piyumi, her parents, and the two specialist doctors directly involved in her treatment, providing firsthand accounts and insights. By examining the case, the paper arrives at three main conclusions. Firstly, pancreatic damage is uncommon, especially in the sports world, and proper diagnosis is essential to avoiding health concerns, particularly for minors. Secondly, CT (Computed Tomography) was useful in locating the injury, as injuries can be diagnosed very well with Computed Tomography (CT) images. Finally, and most importantly, pancreatic injuries are infrequent, but trauma can still occur, particularly in high-impact sports or accidents involving extreme force or falls. These injuries should be accurately diagnosed and treated promptly.

Keywords: child athlete, pancreatic injury, rare sports injuries, sportswoman

Procedia PDF Downloads 73

Authors: Raymond Xu, Cindy Jingru Wang

Abstract:

Social media has become a globally connected and influencing platform. Social media data, such as tweets, can help predict the spread of pandemics and provide individuals and healthcare providers early warnings. Public psychological reactions and opinions can be efficiently monitored by AI models on the progression of dominant topics on Twitter. However, statistics show that as the coronavirus spreads, so does an infodemic of misinformation due to pandemic-related factors such as unemployment and lockdowns. Social media algorithms are often biased toward outrage by promoting content that people have an emotional reaction to and are likely to engage with. This can influence users’ attitudes and cause confusion. Therefore, social media is a double-edged sword. Combating fake news and biased content has become one of the essential tasks. This research analyzes the variety of methods used for fake news detection covering random forest, logistic regression, support vector machines, decision tree, naive Bayes, BoW, TF-IDF, LDA, CNN, RNN, LSTM, DeepFake, and hierarchical attention network. The performance of each method is analyzed. Based on these models’ achievements and limitations, a multi-dimensional AI framework is proposed to achieve higher accuracy in infodemic detection, especially pandemic-related news. The model is trained on contextual content, images, and news metadata.

Keywords: artificial intelligence, fake news detection, infodemic detection, image recognition, sentiment analysis

Procedia PDF Downloads 254

Authors: Auni Idi Muhire

Abstract:

Background: Prior to April 2012, resuscitations were often ineffective resulting in poor patient outcomes. An initiative was implemented at Rwanda Military Hospital (RMH) to review root causes and plan strategies to improve patient outcomes. An interdisciplinary committee was developed to review this problem. Purpose: Analyze the frequency, obstacles, and outcome of patient resuscitation following cardiac and/or respiratory arrest. Methods: A form was developed to allow recording of all actions taken during resuscitation including response times, staff present, and equipment and medications used. Results:-The patient population requiring the most resuscitation effort are the intensive care patients, most frequently the neonatal the intensive care patients (42.8%) -Despite having trained staff representatives, not all resuscitations follow protocol -Lack of compliance with drug administration guidelines was noted, particularly in initiating use of drugs despite the drug being available (59%). Lesson Learned: Basic Life Support training for interdisciplinary staff resulted in more effective response to cardiac and/or respiratory arrest at RMH. Obstacles to effective resuscitation included number of staff, knowledge and skill level of staff, availability of appropriate equipment and medications, staff communication, and patient Do not Attempt Resuscitation (DNR) status.

Keywords: resuscitation, case analysis of knowledge versus practice, intensive care, critical care

Procedia PDF Downloads 278

Authors: Alvaro Javier Ortega

Abstract:

A large number of companies face the challenge of matching highly-skilled professionals to high-end positions by human resource deployment professionals. However, when the professional list and tasks to be matched are larger than a few dozens, this process result is far from optimal and takes a long time to be made. Therefore, an automated assignment algorithm for this workforce management problem is needed. The majority of companies are divided into several sectors or departments, where trained employees with different experience levels deal with a large number of tasks daily. Also, the execution order of all tasks is of mater consequence, due to some of these tasks just can be run it if the result of another task is provided. Thus, a wrong execution order leads to large waiting times between consecutive tasks. The desired goal is, therefore, creating accurate matches and a near-optimal execution order that maximizes the number of tasks performed and minimizes the idle time of the expensive skilled employees. The problem described before can be model as a mixed-integer non-linear programming (MINLP) as it will be shown in detail through this paper. A large number of MINLP algorithms have been proposed in the literature. Here, genetic algorithm solutions are considered and a comparison between two different mutation approaches is presented. The simulated results considering different complexity levels of assignment decisions show the appropriateness of the proposed model.

Keywords: employees, genetic algorithm, industry management, workforce

Procedia PDF Downloads 168

Authors: Che Jusoh, Mohd Rahimi, Toby Mundel

Abstract:

This study was designed to investigate the physiological and performance effects of a local Malaysian native starch (Metroxylin sago) on cycling in a hot (30°C) and humid (78% RH) environment. Eight male, non-heat acclimated, well-trained club cyclists (VO2max 65 ± 10 ml kg-1 min-1, peak aerobic power 397 ± 71 W) completed one familiarization and three experimental trials in our laboratory simulating cycling in environmental conditions of heat and humidity. Each trial consisted of 45 minutes at a fixed workload (55% VO2max) followed by a 15 minute time-trial (~75% VO2max). Sago in porridge form was consumed 1h before exercise (Pre), in gel form during exercise (Dur) and compared to a control trial (Con), using a random, cross-over design. Plasma glucose concentration did not differ between trials (P = 0.06) with an increase from 4.1 ± 0.6 to 6.1 ± 1.6 mmol-1 (Con), 4.8 ± 1.7 to 5.7 ± 0.4 mmol-1 (Pre) and 4.7 ± 0.8 to 6.9 ± 1.4 mmol-1 (Dur) from start to end of exercise. Plasma lactate increased (P = 0.02) from 1.6 ± 0.3 to 7.6 ± 2.2 mmol-1 (Con), 1.7 ± 0.5 to 7.3 ± 2.9 mmol-1 (Pre) and 1.6 ± 0.2 to 7.3 ± 1.8 mmol-1 (Dur) with no effect of trial (P = 0.74). No differences were found between trials for RER (P = 0.328) with values of 0.93 ± 0.05 (Con), 0.94 ± 0.04 (Pre) and 0.92 ± 0.04 (Dur). There were no differences between trials in rectal (P = 0.64) and skin (P = 0.56) temperatures; values reaching 39.1 ± 0.5°C (Con), 38.9 ± 0.4°C (Pre) and 39.1 ± 0.4°C (Dur) for rectal and 32.7 ± 1.2°C (Con), 32.8 ± 1.4°C (Pre) and 32.8 ± 1.8°C (Dur) for skin temperature, respectively. Heart rate (P = 0.07) also did not differ between trials but reached maximal values by the end of time-trial for all trials. Performance was unaffected by trial (P = 0.98) with the average work completed in 15 minutes being 221 ± 33 kJ (Con), 222 ± 31 kJ (Pre) and 219 ± 32 kJ (Dur), respectively. Therefore, the results of this investigation do not support consumption of sago, either before or during exercise, in altering the thermoregulatory, metabolic or performance responses in a hot and humid environment.

Keywords: hot and humid, physiology, time trial performance, thermoregulatory

Procedia PDF Downloads 409

Authors: Sagri Sharma

Abstract:

Analysis of diseases integrating multi-factors increases the complexity of the problem and therefore, development of frameworks for the analysis of diseases is an issue that is currently a topic of intense research. Due to the inter-dependence of the various parameters, the use of traditional methodologies has not been very effective. Consequently, newer methodologies are being sought to deal with the problem. Supervised Learning Algorithms are commonly used for performing the prediction on previously unseen data. These algorithms are commonly used for applications in fields ranging from image analysis to protein structure and function prediction and they get trained using a known dataset to come up with a predictor model that generates reasonable predictions for the response to new data. Gene expression profiles generated by DNA analysis experiments can be quite complex since these experiments can involve hypotheses involving entire genomes. The application of well-known machine learning algorithm - Support Vector Machine - to analyze the expression levels of thousands of genes simultaneously in a timely, automated and cost effective way is thus used. The objectives to undertake the presented work are development of a methodology to identify genes relevant to Hepatocellular Carcinoma (HCC) from gene expression dataset utilizing supervised learning algorithms and statistical evaluations along with development of a predictive framework that can perform classification tasks on new, unseen data.

Keywords: artificial intelligence, biomarker, gene expression datasets, hepatocellular carcinoma, machine learning, supervised learning algorithms, support vector machine

Procedia PDF Downloads 429

Authors: Anna Tokajuk, Agnieszka Zakrzeska, Ewa Chabielska, Halina Car

Abstract:

Whey is a by-product generated mainly in the production of cheese and casein. Powder forms of whey are used widely in the food industry as well as a high-protein food for infants, for convalescents, by athletes and especially by bodybuilders to increase muscle mass during exercise. Whey protein concentrate-80 (WPC-80) is a source of bioactive peptides with beneficial effects on the cardiovascular system. It is known that whey proteins health beneficial properties include antidiabetic, blood pressure lowering, improving cardiovascular system function, antibacterial, antiviral and other effects. To study its influence on the development of thrombosis, venous thrombosis model was performed according to the protocol featured by Reyers with modification by Chabielska and Gromotowicz. Male Wistar-Crl: WI (Han) rats from researched groups were supplemented with two doses of WPC-80 (0.3 or 0.5 g/kg) for 7, 14 or 21 days and after these periods, one-hour venous thrombosis model was performed. Control group received 0.9 % NaCl solution and was sham operated. The statistical significance of results was computed by Mann – Whitney’s test. We observed that thrombus weight was decreased in animals obtaining WPC-8080 and that was statistically significant in 14 and 21-day supplemented groups. Blood count parameters did not differ significantly in rats with and without thrombosis induction whether they were fed with WPC-80 or not. Moreover, the number of platelets (PLT) was within the normal range in each group. The examined coagulation parameters in rats of the control groups were within normal limits. After WPC-80 supplementation there was the tendency to prolonged activated partial thromboplastin time (aPTT), but in comparison, the results did not turn out significant. In animals that received WPC-80 0.3 g·kg-1 for 21 days with and without induced thrombosis, prothrombin time (PT) and an international normalized ratio (INR) was somewhat decreased, remaining within the normal range, but the nature and significance of this observation are beyond the framework of the current study. Additionally, fibrinogen and thrombin time (TT) did not differ significantly between groups. Therefore the exact effect of WPC-80 on coagulation system is still elusive and requires further thorough research including mechanisms of action. Determining the potential clinical application of WPC-80 requires the selection of the optimal dose and duration of supplementation.

Keywords: antithrombotic, rats, venous thrombosis, WPC-80

Procedia PDF Downloads 118

Authors: Teng Zhang, Shenshi Huang, Gang Xu, Xuelin Zhang, Shouxiang Lu

Abstract:

With the acceleration of urbanization and the increasing of the population in the city, the evacuation of pedestrians suffering from disaster environments such as fire in a room or other limited space becomes a vital issue in modern society. Mice have been used in experimental crowd evacuation in recent years for its good similarities to human in physical structure and stress reaction. In this study, the effect of experience or memory on the collective behavior of mice was explored. To help mice familiarize themselves with the design of the space and the stimulus caused by smoke, we trained them repeatedly for 2 days so that they can escape from the emergency conditions as soon as possible. The escape pattern, trajectories, walking speed, turning angle and mean individual escape time of mice in each training trail were analyzed. We found that mice can build memory quickly after the first trial on the first day. On the second day, the evacuation of mice was maintained in a stable and efficient state. Meanwhile, the group with size of 30 (G30) had a shorter mean individual escape time compared with G12. Furthermore, we tested the experience of evacuation skill of mice after several days. The results showed that the mice can hold the experience or memory over 3 weeks. We proposed the importance of experience of evacuation skill and the research of training methods in experimental evacuation of mice. The results can deepen our understanding of collective behavior of mice and conduce to the establishment of animal models in the study of pedestrian crowd dynamics in emergency conditions.

Keywords: experience, evacuation, mice, group size, behavior

Procedia PDF Downloads 268

Authors: Kalat P. Duniya

Abstract:

A number of technologies expected to increase maize productivity have been introduced by several research programs at national and international level. To this end, the study sought to identify the factors influencing adoption intensity of certified maize varieties. The data used were obtained from a sample household survey of 406 maize farmers, conducted in the northern guinea savannah of Nigeria through multistage stratified sampling, structured questionnaire. A triple hurdle model was adopted to estimate the determinants of adoption intensity; considering awareness, adoption, and intensity as three separate stages. The result showed that the drivers of farmers’ awareness, adoption, and intensity of usage may not necessarily be the same, and where they are, not of the same magnitude and direction. However, factors which were found to be statistically significant were age, education, membership of association and frequency of extension advice. In addition, awareness and adoption of the technologies were likely to be increased with male respondents. Farmers that were members of either community organizations or cooperative organizations had a higher tendency of being aware and adopting certified maize seed varieties. It was also discovered that though some of the farmers were fully aware of the existence of some certified maize varieties, majority lacked detailed knowledge and technical know-how. There is a need for creation of awareness through an excellent trained extension and restructuring of the educational sector to improve on the adoption process as well as improve maize productivity in the country.

Keywords: adoption, awareness, maize farmers, Nigeria, regression

Procedia PDF Downloads 174

Authors: Thanura Randula Abeywardena

Abstract:

This study recognized the effectiveness of cold-water immersion recovery post exhaustive short-term exercise. The purpose of this study was to understand if 16- 20°C of cold-water immersion would be beneficial in a tropical environment to achieve optimal recovery in sprint swim performance in comparison to 10-15°C of water immersion. Two 100m-sprint swim performance times were measured along with blood lactate (BLa), heart rate (HR) and rate of perceived exertion (RPE) in a 25m swimming pool with full body head out horizontal water immersions of 10-15°C, 16-20°C and 29-32°C (pool temperature) for 10 minutes followed by 5 minutes of seated passive rest outside; in between the two swim performances. Twelve well-trained adult swimmers (5 male and 5 female) within the top twenty in the Sri Lankan national swimming championships in 100m Butterfly and Freestyle in the years 2020 & 2021 volunteered for this study. One-way ANOVA analysis (p<0.05) suggested performance time, Bla and HR had no significant differences between the 3 conditions after the second sprint; however, RPE was significantly different with p=0.034 between 10-15°C and 16-20°C immersion conditions. The study suggested that the recovery post the two cold-water immersion conditions were similar in terms of performance and physiological factors; however, the 16-20°C temperature had a better “feel good” factor post sprint 2. Further study is recommended as there was participant bias with the swimmers not reaching optimal levels in sprint 1. Therefore, they might have possibly fully recovered before sprint 2, invalidating the physiological effect of recovery.

Keywords: hydrotherapy, blood lactate, fatigue, recovery, sprint-performance, sprint-swimming

Procedia PDF Downloads 102

Authors: Maryam Zarra-Nezhad, Ali Moazami-Goodarzi, Joona Muotka, Nina Sajaniemi

Abstract:

This study examines the extent to which the impact of a universal intervention program, i.e., POMPedaSens, on children’s early social-emotional learning (SEL) is different depending on early childhood education (ECE) teaches stress at work. The POMPedaSens program aims to promote children’s (5–6-year-olds) SEL by supporting ECE teachers’ engagement and emotional availability. The intervention effectiveness has been monitored using an 8-month randomized controlled trial design with an intervention (IG; 26 teachers and 195 children) and a waiting control group (CG; 36 teachers and 198 children) that provided the data before and after the program implementation. The ECE teachers in the IG are trained to implement the intervention program in their early childhood education and care groups. Latent change score analysis suggests that the program increases children’s prosocial behavior in the IG when teachers show a low level of stress. No significant results were found for the IG regarding a change in antisocial behavior. However, when teachers showed a high level of stress, an increase in prosocial behavior and a decrease in antisocial behavior were only found for children in the CG. The results suggest a promising application of the POMPedaSens program for promoting prosocial behavior in early childhood when teachers have low stress. The intervention will likely need a longer time to display the moderating effect of ECE teachers’ well-being on children’s antisocial behavior change.

Keywords: early childhood, social-emotional learning, universal intervention program, professional development, teachers' stress

Procedia PDF Downloads 89

Authors: Fatima Muhammad Shitu

Abstract:

This study seeks to investigate the effect of the keyword strategy on lexico–semantic acquisition, recognition, retention and comprehension in an ESL context. The aim of the study is to determine whether the keyword strategy can be used to enhance acquisition. As a quasi- experimental research, the objectives of the study include: To determine the extent to which the scores obtained by the subjects, who were trained on the use of the keyword strategy for acquisition, differ at the pre-tests and the post–tests and also to find out the relationship in the scores obtained at these tests levels. The sample for the study consists of 300 hundred undergraduate ESL Students in the Federal College of Education, Kano. The seventy-five lexical items for acquisition belong to the lexical field category known as register, and they include Medical, Agriculture and Photography registers (MAP). These were divided in the ratio twenty-five (25) lexical items in each lexical field. The testing technique was used to collect the data while the descriptive and inferential statistics were employed for data analysis. For the purpose of testing, the two kinds of tests administered at each test level include the WARRT (Word Acquisition, Recognition, and Retention Test) and the CCPT (Cloze Comprehension Passage Test). The results of the study revealed that there are significant differences in the scores obtained between the pre-tests, and the post–tests and there are no correlations in the scores obtained as well. This implies that the keyword strategy has effectively enhanced the acquisition of the lexical items studied.

Keywords: keyword, lexical, semantics, strategy

Procedia PDF Downloads 311

Authors: A. Degale Desta, Cheng Jian

Abstract:

Deep learning application in computer vision is rapidly advancing, giving it the ability to monitor the public and quickly identify potentially anomalous behaviour from crowd scenes. Therefore, the purpose of the current work is to improve the performance of safety of people in crowd events from panic behaviour through introducing the innovative idea of Aggregation of Ensembles (AOE), which makes use of the pre-trained ConvNets and a pool of classifiers to find anomalies in video data with packed scenes. According to the theory of algorithms that applied K-means, KNN, CNN, SVD, and Faster-CNN, YOLOv5 architectures learn different levels of semantic representation from crowd videos; the proposed approach leverages an ensemble of various fine-tuned convolutional neural networks (CNN), allowing for the extraction of enriched feature sets. In addition to the above algorithms, a long short-term memory neural network to forecast future feature values and a handmade feature that takes into consideration the peculiarities of the crowd to understand human behavior. On well-known datasets of panic situations, experiments are run to assess the effectiveness and precision of the suggested method. Results reveal that, compared to state-of-the-art methodologies, the system produces better and more promising results in terms of accuracy and processing speed.

Keywords: action recognition, computer vision, crowd detecting and tracking, deep learning

Procedia PDF Downloads 161

Authors: Judith Mwakalonge, Geophrey Mbatta, Saidi Siuhi, Gurcan Comert, Cuthbert Ruseruka

Abstract:

Transportation agencies worldwide continuously monitor their roads' conditions to minimize road maintenance costs and maintain public safety and rideability quality. Existing methods for carrying out road condition surveys involve manual observations of roads using standard survey forms done by qualified road condition surveyors or engineers either on foot or by vehicle. Automated road condition survey vehicles exist; however, they are very expensive since they require special vehicles equipped with sensors for data collection together with data processing and computing devices. The manual methods are expensive, time-consuming, infrequent, and can hardly provide real-time information for road conditions. This study contributes to this arena by utilizing built-in vehicle technologies, drones, and deep learning to automate road condition surveys while using low-cost technology. A single model is trained to capture flexible pavement distresses (Potholes, Rutting, Cracking, and raveling), thereby providing a more cost-effective and efficient road condition monitoring approach that can also provide real-time road conditions. Additionally, data fusion is employed to enhance the road condition assessment with data from vehicles and drones.

Keywords: road conditions, built-in vehicle technology, deep learning, drones

Procedia PDF Downloads 124