Search results for: machine resistance training

Authors: Jairo Alejandro Fernandez Ortega

Abstract:

Objective: Regarding effects of training velocity on strength in the functional condition of older adults controversy exists. The purpose of this study was to examine the effects of a twelve-week strength training program (PE) performed at high speed (GAV) versus a traditionally executed program (GBV), on functional performance, maximum strength and muscle power in a group of older adult women. Methodology: 86 women aged between 60-81 years participated voluntarily in the study and were assigned randomly to the GAV (three series at 40% 1RM at maximum speed, with maximum losses of 10% speed) or to the GBV (three series with three sets at 70% of 1RM). Both groups performed three weekly trainings. The maximum strength of upper and lower limbs (1RM), prehensile strength, walking speed, maximum power, mean propulsive velocity (MPV) and functional performance (senior fitness test) were evaluated before and after the PE. Results: Significant improvements were observed (p < 0.05) in all the tests in the two groups after the twelve weeks of training. However, the results of GAV were significantly (P < 0.05) higher than those of the GBV, in the tests of agility and dynamic equilibrium, stationary walking, sitting and standing, walking speed over 4 and 6 meters, MPV and peak power. In the tests of maximum strength and prehensile force, the differences were not significant. Conclusion: Strength training performed at high speeds seems to have a better effect on functional performance and muscle power than strength training performed at low speed.

Keywords: power training, resistance exercise, aging, strength, physical performance, high-velocity, resistance training

Procedia PDF Downloads 114

Authors: Obinna Afamefuna Echi

Abstract:

Background: The global increase in the elderly population is anticipated to reach significant levels by 2050, presenting extensive economic, social, and healthcare challenges. Age-related cognitive decline, alterations in brain anatomy, and systemic inflammation are profound concerns that diminish the quality of life and increase susceptibility to diseases like Alzheimer's and cardiovascular diseases. Resistance training is presently studied for its potential neuroprotective and anti-inflammatory benefits in older adults. Objectives: This study aimed to explore the effects of different resistance training modalities on neurotrophic factors, inflammatory markers, and cognitive functions in the elderly. Methods: A controlled trial was conducted with 60 male participants aged 60-75, assigned to either 12 weeks of high-intensity blood flow restriction training (BFRT), muscle damaging resistance training (MDRT), or a non-exercising control group. Cognitive function, neurotrophic factors such as BDNF, and inflammatory markers including IL-6 and TNF were measured before and after the intervention period. Setting: Participants were recruited from Kaunas, Lithuania, with sessions facilitated at the Lithuanian Sports University and health assessments conducted at the Lithuanian University of Health Sciences. Results: Preliminary data suggested did not show significant improvements in BDNF levels and cognitive functions in the BFRT and MDRT groups compared to controls. However, there was a notable reduction in inflammatory markers, indicating potential health benefits beyond cognitive enhancement. Conclusion: The incorporation of resistance training can be a strategic intervention to mitigate age-associated cognitive decline and systemic inflammation, thereby enhancing overall health and quality of life in older adults. The results advocate for wider adoption and further study of resistance training as a preventive measure in ageing populations. Funding: The Lithuanian Sports University, the Research Council of Lithuania and the Lithuanian University of Health Sciences.

Keywords: ageing, resistance training, BDNF, cognitive function

Procedia PDF Downloads 46

Authors: U. Borasi, Amit Kr. Jain, Rakesh, Piyush Jain

Abstract:

Data collection, data preparation, model training, model evaluation, and deployment are all processes in a typical machine learning workflow. Training data needs to be gathered and organised. This often entails collecting a sizable dataset and cleaning it to remove or correct any inaccurate or missing information. Preparing the data for use in the machine learning model requires pre-processing it after it has been acquired. This often entails actions like scaling or normalising the data, handling outliers, selecting appropriate features, reducing dimensionality, etc. This pre-processed data is then used to train a model on some machine learning algorithm. After the model has been trained, it needs to be assessed by determining metrics like accuracy, precision, and recall, utilising a test dataset. Every time a new model is built, both data pre-processing and model training—two crucial processes in the Machine learning (ML) workflow—must be carried out. Thus, there are various Machine Learning algorithms that can be employed for every single approach to data pre-processing, generating a large set of combinations to choose from. Example: for every method to handle missing values (dropping records, replacing with mean, etc.), for every scaling technique, and for every combination of features selected, a different algorithm can be used. As a result, in order to get the optimum outcomes, these tasks are frequently repeated in different combinations. This paper suggests a simple architecture for organizing this largely produced “combination set of pre-processing steps and algorithms” into an automated workflow which simplifies the task of carrying out all possibilities.

Keywords: machine learning, automation, AUTOML, architecture, operator pool, configuration, scheduler

Procedia PDF Downloads 58

Authors: Rasoul Eslami, Reza Gharakhanlou

Abstract:

NT-4/5 and TrkB have been proposed to be involved in the coordinated adaptations of the neuromuscular system to elevated level of activity. Despite the persistence of this neurotrophin and its receptor expression in adult skeletal muscle, little attention has been paid to the functional significance of this complex in the mature neuromuscular system. Therefore, the purpose of this research was to study the effect of one session of resistance exercise on mRNA expression of NT4/5 and TrkB proteins in slow and fast muscles of Wistar Rats. Male Wistar rats (10 mo of age, preparation of Pasteur Institute) were housed under similar living conditions in cages (in groups of four) at room temperature under a controlled light/dark (12-h) cycle with ad libitum access to food and water. A number of sixteen rats were randomly divided to two groups (resistance exercise (T) and control (C); n=8 for each group). The resistance training protocol consisted of climbing a 1-meter–long ladder, with a weight attached to a tail sleeve. Twenty-four hours following the main training session, rats of T and C groups were anaesthetized and the right soleus and flexor hallucis longus (FHL) muscles were removed under sterile conditions via an incision on the dorsolateral aspect of the hind limb. For NT-4/5 and TrkB expression, quantitative real time RT-PCR was used. SPSS software and independent-samples t-test were used for data analysis. The level of significance was set at P < 0.05. Data indicate that resistance training significantly (P<0.05) decreased mRNA expression of NT4/5 in soleus muscle. However, no significant alteration was detected in FHL muscle (P>0.05). Our results also indicate that no significant alterations were detected for TrkB mRNA expression in soleus and FHL muscles (P>0.05). Decrease in mRNA expression of NT4/5 in soleus muscle may be as result of post-translation regulation following resistance training. Also, non-alteration in TrkB mRNA expression was indicated in probable roll of P75 receptor.

Keywords: neurotrophin-4/5 (NT-4/5), TrkB receptor, resistance training, slow and fast muscles

Procedia PDF Downloads 444

Authors: Fernanda Bravo Cornejo, Camilo Cerda Sarabia, Belén Díaz Díaz, Diego Santibañez Oyarce, Esteban Gómez Terán, Hugo Osses Prado, Raúl Caulier-Cisterna, Jorge Vergara-Quezada, Ana Moya-Beltrán

Abstract:

Streptococcus pyogenes is a gram-positive bacteria involved in a wide range of diseases and is a major-human-specific bacterial pathogen. In Chile, this year the 'Ministerio de Salud' declared an alert due to the increase in strains throughout the year. This increase can be attributed to the multitude of factors including antimicrobial resistance (AMR) and Virulence Factors (VF). Understanding these VF and AMR is crucial for developing effective strategies and improving public health responses. Moreover, experimental identification and characterization of these pathogenic mechanisms are labor-intensive and time-consuming. Therefore, new computational methods are required to provide robust techniques for accelerating this identification. Advances in Machine Learning (ML) algorithms represent the opportunity to refine and accelerate the discovery of VF associated with Streptococcus pyogenes. In this work, we evaluate the accuracy of various machine learning models in predicting the virulence factors and antimicrobial resistance of Streptococcus pyogenes, with the objective of providing new methods for identifying the pathogenic mechanisms of this organism.Our comprehensive approach involved the download of 32,798 genbank files of S. pyogenes from NCBI dataset, coupled with the incorporation of data from Virulence Factor Database (VFDB) and Antibiotic Resistance Database (CARD) which contains sequences of AMR gene sequence and resistance profiles. These datasets provided labeled examples of both virulent and non-virulent genes, enabling a robust foundation for feature extraction and model training. We employed preprocessing, characterization and feature extraction techniques on primary nucleotide/amino acid sequences and selected the optimal more for model training. The feature set was constructed using sequence-based descriptors (e.g., k-mers and One-hot encoding), and functional annotations based on database prediction. The ML models compared are logistic regression, decision trees, support vector machines, neural networks among others. The results of this work show some differences in accuracy between the algorithms, these differences allow us to identify different aspects that represent unique opportunities for a more precise and efficient characterization and identification of VF and AMR. This comparative analysis underscores the value of integrating machine learning techniques in predicting S. pyogenes virulence and AMR, offering potential pathways for more effective diagnostic and therapeutic strategies. Future work will focus on incorporating additional omics data, such as transcriptomics, and exploring advanced deep learning models to further enhance predictive capabilities.

Keywords: antibiotic resistance, streptococcus pyogenes, virulence factors., machine learning

Procedia PDF Downloads 31

Authors: Leyla Sattarzadeh, Maghsoud Peeri, Mohammadali Azarbaijani, Hasan Matin Homaee

Abstract:

Inflammation by various mechanisms may cause atherosclerosis. Systemic circulating inflammatory markers such as C-reactive protein (CRP), pro-inflammatory cytokines such as Interleukin-6 (IL-6) and adhesion molecules like Intracellular Adhesion Molecule-1 (ICAM-1) are the predictors of cardiovascular diseases. Regarding the conflicting results about the effect of resistance exercise training on these inflammatory markers, the present study aimed to examine the effect of eight week different patterns of resistance exercise training on CRP, IL-6 and ICAM-1 levels in healthy untrained women. 40 volunteered and healthy untrained female university students (aged: 21+ 3 yr., Body Mass Index: 21.5+ 3.5 kg/m2) were selected purposefully and divided into three groups. At the end of training protocol and after subjects drop during the protocol in upper body exercise training (n=11), lower body (n=12) completed the eight week of training period although the control group (n=7) did anything. Blood samples gathered pre and post experimental period and CRP, IL-6 and ICAM-1 levels were evaluated using special laboratory kits, then the difference of pre and post values of each indices analyzed using one way Analysis of Variance (α < 0.05). The results of one way ANOVA for difference of pre and post values of CRP and ICAM-1 showed no significant changes due to the exercise training. But there were significant differences between groups about IL-6. Tukey post- hoc test indicated that there is significant difference between the differences of pre and post values of IL-6 between lower body exercise training group and control group, and eight weeks of lower body exercise training lead to significant changes in IL-6 values. There were no changes in anthropometric indices. The findings show that the different patterns of upper and lower body exercise training by involving the different amount of muscles altered the IL-6 values in lower body exercise training group probably because of engaging the bigger amount of muscles, but showed any significant changes about CRP and ICAM-1 probably due to intensity and duration of exercise or the lower levels of these markers at baseline of healthy people.

Keywords: C-reactive protein, interleukin-6, intracellular adhesion molecule-1, resistance training

Procedia PDF Downloads 255

Authors: Leyla Sattarzadeh, Shahin Fathi Molk Kian, Maghsoud Peeri, Mohammadali Azarbaijani, Hasan Matin Homaee

Abstract:

Inflammation by various mechanisms may cause atherosclerosis. Systemic circulating inflammatory markers such as C-reactive protein (CRP), pro-inflammatory cytokines such as Interleukin-6 (IL-6), vascular inflammatory markers as adhesion molecules like Intracellular Adhesion Molecule-1 (ICAM-1) and Vascular Cell Adhesion Molecule-1 (VCAM-1) are the predictors of cardiovascular diseases. Regarding the conflicting results about the effect of different patterns of resistance exercise training on these inflammatory markers, present study aimed to examine the effect of different patterns of eight week resistance exercise training on CRP, IL-6, ICAM-1 and VCAM-1 levels in healthy untrained women. 56 healthy volunteered untrained female university students (aged: 21 ± 3 yr., Body Mass Index: 21.5 ± 3.5 kg/m²) were selected purposefully and divided into four groups. At the end of training protocol and after subject drop during the protocol, upper body exercise training (n=11), lower body (n=12) and whole body resistance exercise training group (n=11) completed the eight weeks of training period although the control group (n=7) did anything. Blood samples gathered pre and post-experimental period and CRP, IL-6, ICAM-1 and VCAM-1 levels were evaluated using special laboratory kits, then the difference of pre and post values of each indices analyzed using one-way analysis of variance (α < 0.05). The results of one way ANOVA for difference of pre and post values of CRP, ICAM-1 and VCAM-1 showed no significant changes due to the exercise training, but there were significant differences between groups about IL-6. Tukey post- hoc test indicated that there is significant difference between the differences of pre and post values of IL-6 between lower body exercise training group and control group, and eight weeks of lower body exercise training lead to significant changes in IL-6 values. There were no changes in anthropometric indices. The findings show that the different patterns of upper, lower and whole body exercise training by involving the different amounts of muscles altered the IL-6 values in lower body exercise training group probably because of engaging the bigger amount of muscles, but showed any significant changes about CRP, ICAM-1 and VCAM-1 probably due to intensity and duration of exercise or the lower levels of these markers at baseline of healthy people.

Keywords: resistance training, C-reactive protein, interleukin-6, intracellular adhesion molecule-1, vascular cell adhesion molecule-1

Procedia PDF Downloads 138

Authors: Yan Cheng, Yijun Shao, James Rudolph, Charlene R. Weir, Beth Sahlmann, Qing Zeng-Treitler

Abstract:

Supervised predictive models require labeled data for training purposes. Complete and accurate labeled data, i.e., a ‘gold standard’, is not always available, and imperfectly labeled data may need to serve as an alternative. An important question is if the accuracy of the labeled data creates a performance ceiling for the trained model. In this study, we trained several models to recognize the presence of delirium in clinical documents using data with annotations that are not completely accurate (i.e., weakly-supervised learning). In the external evaluation, the support vector machine model with a linear kernel performed best, achieving an area under the curve of 89.3% and accuracy of 88%, surpassing the 80% accuracy of the training sample. We then generated a set of simulated data and carried out a series of experiments which demonstrated that models trained on imperfect data can (but do not always) outperform the accuracy of the training data, e.g., the area under the curve for some models is higher than 80% when trained on the data with an error rate of 40%. Our experiments also showed that the error resistance of linear modeling is associated with larger sample size, error type, and linearity of the data (all p-values < 0.001). In conclusion, this study sheds light on the usefulness of imperfect data in clinical research via weakly-supervised learning.

Keywords: weakly-supervised learning, support vector machine, prediction, delirium, simulation

Procedia PDF Downloads 199

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: artificial intelligence, machine learning, deep learning, convolutional neural networks

Procedia PDF Downloads 211

Authors: Chen-Chi An, Jun-Yi He, Cheng-Han Hsieh, Chen-Ching Ting

Abstract:

This research has successfully developed an intelligent table tennis ball machine with human play simulate all situations of human play to take the service. It is well known; an excellent ball machine can help the table tennis coach to provide more efficient teaching, also give players the good technical training and entertainment. An excellent ball machine should be able to service all balls based on human play simulation due to the conventional competitions are today all taken place for people. In this work, two counter-rotating wheels are used to service the balls, where changing the absolute rotating speeds of the two wheels and the differences of rotating speeds between the two wheels can adjust the struck forces and the rotating speeds of the ball. The relationships between the absolute rotating speed of the two wheels and the struck forces of the ball as well as the differences rotating speeds between the two wheels and the rotating speeds of the ball are experimentally determined for technical development. The outlet speed, the ejected distance, and the rotating speed of the ball were measured by changing the absolute rotating speeds of the two wheels in terms of a series of differences in rotating speed between the two wheels for calibration of the ball machine; where the outlet speed and the ejected distance of the ball were further converted to the struck forces of the ball. In process, the balls serviced by the intelligent ball machine were based on the received calibration curves with help of the computer. Experiments technically used photosensitive devices to detect the outlet and rotating speed of the ball. Finally, this research developed some teaching programs for technical training using three ball machines and received more efficient training.

Keywords: table tennis, ball machine, human play simulation, counter-rotating wheels

Procedia PDF Downloads 429

Authors: Jennifer Leach, Umashanger Thayasivam

Abstract:

The use of technology has benefited society in more ways than one ever thought possible. Unfortunately, though, as society’s knowledge of technology has advanced, so has its knowledge of ways to use technology to manipulate people. This has led to a simultaneous advancement in the world of fraud. Machine learning techniques can offer a possible solution to help decrease this advancement. This research explores how the use of various machine learning techniques can aid in detecting fraudulent activity across two different types of fraudulent data, and the accuracy, precision, recall, and F1 were recorded for each method. Each machine learning model was also tested across five different training and testing splits in order to discover which testing split and technique would lead to the most optimal results.

Keywords: data science, fraud detection, machine learning, supervised learning

Procedia PDF Downloads 196

Authors: Hailyie Tekleselase

Abstract:

Deep learning is increasingly used as a building block of security systems. However, neural networks are hard to interpret and typically solid to the practitioner. This paper presents a detail survey of computing methods in cyber security, and analyzes the prospects of enhancing the cyber security capabilities by suggests that of accelerating the intelligence of the security systems. There are many AI-based applications used in industrial scenarios such as Internet of Things (IoT), smart grids, and edge computing. Machine learning technologies require a training process which introduces the protection problems in the training data and algorithms. We present machine learning techniques currently applied to the detection of intrusion, malware, and spam. Our conclusions are based on an extensive review of the literature as well as on experiments performed on real enterprise systems and network traffic. We conclude that problems can be solved successfully only when methods of artificial intelligence are being used besides human experts or operators.

Keywords: artificial intelligence, machine learning, deep learning, cyber security, big data

Procedia PDF Downloads 126

Authors: S. M. Mahdi Niktabara, K. Seshagiri Raob, Amit Kumar Shrivastavac, Jiří Ščučkaa

Abstract:

The presence of the discontinuity in the form of joints is one of the most significant factors causing instability in the rock mass. On the other hand, dynamic loads, including earthquake and blasting induce cyclic shear loads along the joints in rock masses; therefore, failure of rock mass exacerbates along the joints due to changing shear resistance. Joints are under constant normal load (CNL) and constant normal stiffness (CNS) conditions. Normal stiffness increases on the joints with increasing depth, and it can affect shear resistance. For correct assessment of joint shear resistance under varying normal stiffness and number of cycles, advanced laboratory shear machine is essential for the shear test. Conventional direct shear equipment has limitations such as boundary conditions, working under monotonic movements only, or cyclic shear loads with constant frequency and amplitude of shear loads. Hence, a large-scale servo-controlled direct shear testing machine was designed and fabricated to perform shear test under the both CNL and CNS conditions with varying normal stiffness at different frequencies and amplitudes of shear loads. In this study, laboratory cyclic shear tests were conducted on non-planar joints under varying normal stiffness. In addition, the effects of different frequencies and amplitudes of shear loads were investigated. The test results indicate that shear resistance increases with increasing normal stiffness at the first cycle, but the influence of normal stiffness significantly decreases with an increase in the number of shear cycles. The frequency of shear load influences on shear resistance, i.e. shear resistance increases with increasing frequency. However, at low shear amplitude the number of cycles does not affect shear resistance on the joints, but it decreases with higher amplitude.

Keywords: cyclic shear load, frequency of load, amplitude of displacement, normal stiffness

Procedia PDF Downloads 151

Authors: Goodarzvand Fatemeh, Soori Rahman, Effatpanah Mohammad, Ajbarnejad Ali

Abstract:

Attention deficit hyperactivity disorder (ADHD) is characterized by a pervasive pattern of developmentally inappropriate inattentive, impulsive and hyperactive behaviors that typically begin during the preschool ages and often persist into adulthood. This disorder is related to autism and schizophrenia and other psychological disorders and clinical conditions such as insulin resistance and they may operate through common pathways, and treatments used exclusively for one of these conditions may prove beneficial for the others. While ADHD is not fully understood as developmental disorder with an etiopathogeny, but studies show that core symptom of disorder was associated with and increased by the interleukins IL-13, where relation of IL-13 with inattention was notable. Regular exercise improves functions associated with attention deficit hyperactivity disorder (ADHD). However, the impact of exercise on cytokines associated with the disease activity remains relatively unexplored. The aim of this study was to examine the effects of 6 weeks high intensity by intervals training (HIIT) on IL-13 levels and insulin resistance in boys with ADHD. Twenty eight boys with ADHD disease in a range of 12-18 year of old participated in this study as the subject. Subjects were divided into control group (n=10) and training group (n=18) randomly. The training group performed progressive HIIT program, 3 days a week for 6 weeks. The control group was in absolute rest at the same time. The results showed that after six weeks of HIIT, IL-13 decreased in the exercise group and these changes achieved (p= 0.002) statistical significance (p < 0.005). The results suggest HIIT with specific intensity and duration utilized in this study had not significant effect on insulin resistance levels in female patients with ADHD (p=0.39), while the difference in the average control and case group was decreased.

Keywords: attention deficit hyperactivity disorder, interleukin 13, insulin resistance, high intensity by intervals training

Procedia PDF Downloads 511

Authors: Humberto Miranda, Haroldo G. Santana, Gabriel A. Paz, Vicente P. Lima, Jeffrey M. Willardson

Abstract:

Foam rolling is a practice that has increased in popularity before and after strength training. The purpose of this study was to compare the acute effects of different foam rolling periods for the lower body muscles on subsequent performance (total repetitions and training volume), myoelectric activity and rating of perceived exertion in trained men. Fourteen trained men (26.2 ± 3.2 years, 178 ± 0.04 cm height, 82.2 ± 10 kg weight and body mass index 25.9 ± 3.3kg/m2) volunteered for this study. Four repetition maximum (4-RM) loads were determined for hexagonal bar deadlift and 45º angled leg press during test and retest sessions over two nonconsecutive days. Five experimental protocols were applied in a randomized design, which included: a traditional protocol (control)—a resistance training session without prior foam rolling; or resistance training sessions performed following one (P1), two (P2), three (P3), or four (P4) sets of 30 sec. foam rolling for the lower extremity musculature. Subjects were asked to roll over the medial and lateral aspects of each muscle group with as much pressure as possible. All foam rolling was completed at a cadence of 50 bpm. These procedures were performed on both sides unilaterally as described below. Quadriceps: between the apex of the patella and the ASIS; Hamstring: between the gluteal fold and popliteal fossa; Triceps surae: between popliteal fossa and calcaneus tendon. The resistance training consisted of five sets with 4-RM loads and two-minute rest intervals between sets, and a four-minute rest interval between the hexagonal bar deadlift and the 45º angled leg press. The number of repetitions completed, the myoelectric activity of vastus lateralis (VL), vastus medialis oblique (VMO), semitendinosus (SM) and medial gastrocnemius (GM) were recorded, as well as the rating of perceived exertion for each protocol. There were no differences between the protocols in the total repetitions for the hexagonal bar deadlift (Control - 16.2 ± 5.9; P1 - 16.9 ± 5.5; P2 - 19.2 ± 5.7; P3 - 19.4 ± 5.2; P4 - 17.2 ± 8.2) (p > 0.05) and 45º angled leg press (Control - 23.3 ± 9.7; P1 - 25.9 ± 9.5; P2 - 29.1 ± 13.8; P3 - 28.0 ± 11.7; P4 - 30.2 ± 11.2) exercises. Similar results between protocols were also noted for myoelectric activity (p > 0.05) and rating of perceived exertion (p > 0.05). Therefore, the results of the present study indicated no deleterious effects on performance, myoelectric activity and rating of perceived exertion responses during lower body resistance training.

Keywords: self myofascial release, foam rolling, electromyography, resistance training

Procedia PDF Downloads 226

Authors: Yi Huang, Clemens Guehmann

Abstract:

In order to monitor the thermal behavior of an asynchronous machine with squirrel cage rotor, a 9th-order extended Kalman filter (EKF) algorithm is implemented to estimate the temperatures of the stator windings, the rotor cage and the stator core. The state-space equations of EKF are established based on the electrical, mechanical and the simplified thermal models of an asynchronous machine. The asynchronous machine with simplified thermal model in Dymola is compiled as DymolaBlock, a physical model in MATLAB/Simulink. The coolant air temperature, three-phase voltages and currents are exported from the physical model and are processed by EKF estimator as inputs. Compared to the temperatures exported from the physical model of the machine, three parts of temperatures can be estimated quite accurately by the EKF estimator. The online EKF estimator is independent from the machine control algorithm and can work under any speed and load condition if the stator current is nonzero current system.

Keywords: asynchronous machine, extended Kalman filter, resistance, simulation, temperature estimation, thermal model

Procedia PDF Downloads 285

Authors: Masoomeh Alsadat Mirshafaei

Abstract:

The present study aims to explore the effect of an 8-week aerobic training regimen combined with cinnamon extract on serum irisin and leptin levels in insulin-resistant rats. Additionally, this research leverages various machine learning (ML) and deep learning (DL) algorithms to model the complex interdependencies between exercise, nutrition, and metabolic markers, offering a groundbreaking approach to obesity and diabetes research. Forty-eight Wistar rats were selected and randomly divided into four groups: control, training, cinnamon, and training cinnamon. The training protocol was conducted over 8 weeks, with sessions 5 days a week at 75-80% VO2 max. The cinnamon and training-cinnamon groups were injected with 200 ml/kg/day of cinnamon extract. Data analysis included serum data, dietary intake, exercise intensity, and metabolic response variables, with blood samples collected 72 hours after the final training session. The dataset was analyzed using one-way ANOVA (P<0.05) and fed into various ML and DL models, including Support Vector Machines (SVM), Random Forest (RF), and Convolutional Neural Networks (CNN). Traditional statistical methods indicated that aerobic training, with and without cinnamon extract, significantly increased serum irisin and decreased leptin levels. Among the algorithms, the CNN model provided superior performance in identifying specific interactions between cinnamon extract concentration and exercise intensity, optimizing the increase in irisin and the decrease in leptin. The CNN model achieved an accuracy of 92%, outperforming the SVM (85%) and RF (88%) models in predicting the optimal conditions for metabolic marker improvements. The study demonstrated that advanced ML and DL techniques could uncover nuanced relationships and potential cellular responses to exercise and dietary supplements, which is not evident through traditional methods. These findings advocate for the integration of advanced analytical techniques in nutritional science and exercise physiology, paving the way for personalized health interventions in managing obesity and diabetes.

Keywords: aerobic training, cinnamon extract, insulin resistance, irisin, leptin, convolutional neural networks, exercise physiology, support vector machines, random forest

Procedia PDF Downloads 38

Authors: Elham Serkani, Hossein Gharaee Garakani, Naser Mohammadzadeh, Elaheh Vaezpour

Abstract:

Intrusion detection systems (IDS) are the main components of network security. These systems analyze the network events for intrusion detection. The design of an IDS is through the training of normal traffic data or attack. The methods of machine learning are the best ways to design IDSs. In the method presented in this article, the pruning algorithm of C5.0 decision tree is being used to reduce the features of traffic data used and training IDS by the least square vector algorithm (LS-SVM). Then, the remaining features are arranged according to the predictor importance criterion. The least important features are eliminated in the order. The remaining features of this stage, which have created the highest level of accuracy in LS-SVM, are selected as the final features. The features obtained, compared to other similar articles which have examined the selected features in the least squared support vector machine model, are better in the accuracy, true positive rate, and false positive. The results are tested by the UNSW-NB15 dataset.

Keywords: decision tree, feature selection, intrusion detection system, support vector machine

Procedia PDF Downloads 265

Authors: Matteo Calabrese, Martin Cimmino, Dimos Kapetis, Martina Manfrin, Donato Concilio, Giuseppe Toscano, Giovanni Ciandrini, Giancarlo Paccapeli, Gianluca Giarratana, Marco Siciliano, Andrea Forlani, Alberto Carrotta

Abstract:

In this paper we describe a machine learning methodology for Predictive Maintenance (PdM) applied on woodworking industrial machines. PdM is a prominent strategy consisting of all the operational techniques and actions required to ensure machine availability and to prevent a machine-down failure. One of the challenges with PdM approach is to design and develop of an embedded smart system to enable the health status of the machine. The proposed approach allows screening simultaneously multiple connected machines, thus providing real-time monitoring that can be adopted with maintenance management. This is achieved by applying temporal feature engineering techniques and training an ensemble of classification algorithms to predict Remaining Useful Lifetime of woodworking machines. The effectiveness of the methodology is demonstrated by testing an independent sample of additional woodworking machines without presenting machine down event.

Keywords: predictive maintenance, machine learning, connected machines, artificial intelligence

Procedia PDF Downloads 226

Authors: Jay L. Fu

Abstract:

Patients with Alzheimer's disease progressively lose their memory and thinking skills and, eventually, the ability to carry out simple daily tasks. The disease is irreversible, but early detection and treatment can slow down the disease progression. In this research, publicly available MRI data and demographic data from 373 MRI imaging sessions were utilized to build models to predict dementia. Various machine learning models, including logistic regression, k-nearest neighbor, support vector machine, random forest, and neural network, were developed. Data were divided into training and testing sets, where training sets were used to build the predictive model, and testing sets were used to assess the accuracy of prediction. Key risk factors were identified, and various models were compared to come forward with the best prediction model. Among these models, the random forest model appeared to be the best model with an accuracy of 90.34%. MMSE, nWBV, and gender were the three most important contributing factors to the detection of Alzheimer’s. Among all the models used, the percent in which at least 4 of the 5 models shared the same diagnosis for a testing input was 90.42%. These machine learning models allow early detection of Alzheimer’s with good accuracy, which ultimately leads to early treatment of these patients.

Keywords: Alzheimer's disease, clinical diagnosis, magnetic resonance imaging, machine learning prediction

Procedia PDF Downloads 143

Authors: Lizhi Ma, Chengcheng Hu, Fuxian Wong

Abstract:

Partial reduce (P-Reduce) has set a state-of-the-art performance on distributed machine learning in the heterogeneous environment over the All-Reduce architecture. The dynamic P-Reduce based on the exponential moving average (EMA) approach predicts all the intermediate model parameters, which raises unreliability. It is noticed that the approximation trick leads the wrong way to obtaining model parameters in all the nodes. In this paper, SAP-Reduce is proposed, which is a variant of the All-Reduce distributed training model with staleness-aware dynamic P-Reduce. SAP-Reduce directly utilizes the EMA-like algorithm to generate the normalized weights. To demonstrate the effectiveness of the algorithm, the experiments are set based on a number of deep learning models, comparing the single-step training acceleration ratio and convergence time. It is found that SAP-Reduce simplifying dynamic P-Reduce outperforms the intermediate approximation one. The empirical results show SAP-Reduce is 1.3× −2.1× faster than existing baselines.

Keywords: collective communication, decentralized distributed training, machine learning, P-Reduce

Procedia PDF Downloads 33

Authors: Chaima Babi, Said Gadri

Abstract:

The rapid increase in fake news continues to grow at a very fast rate; this requires implementing efficient techniques that allow testing the re-liability of online content. For that, the current research strives to illuminate the fake news problem using deep learning DL and machine learning ML ap-proaches. We have developed the traditional LSTM (Long short-term memory), and the bidirectional BiLSTM model. A such process is to perform a training task on almost of samples of the dataset, validate the model on a subset called the test set to provide an unbiased evaluation of the final model fit on the training dataset, then compute the accuracy of detecting classifica-tion and comparing the results. For the programming stage, we used Tensor-Flow and Keras libraries on Python to support Graphical Processing Units (GPUs) that are being used for developing deep learning applications.

Keywords: machine learning, deep learning, natural language, fake news, Bi-LSTM, LSTM, multiclass classification

Procedia PDF Downloads 95

Authors: Feng Yang

Abstract:

Machine learning (ML), especially deep learning (DL), has been extensively applied to many applications in recently years and gained great success in solving different problems, including scientific problems. However, conventional ML/DL methodologies are purely data-driven which have the limitations, such as need of ample amount of labelled training data, lack of consistency to physical principles, and lack of generalizability to new problems/domains. Recently, there is a growing consensus that ML models need to further take advantage of prior knowledge to deal with these limitations. Physics-informed machine learning, aiming at integration of physics/domain knowledge into ML, has been recognized as an emerging area of research, especially in the recent 2 to 3 years. In this work, physics-informed ML, specifically physics-informed neural network (NN), is employed and implemented to estimate the displacements at x, y, z directions in a solid mechanics problem that is controlled by equilibrium equations with boundary conditions. By incorporating the physics (i.e. the equilibrium equations) into the learning process of NN, it is showed that the NN can be trained very efficiently with a small set of labelled training data. Experiments with different settings of the NN model and the amount of labelled training data were conducted, and the results show that very high accuracy can be achieved in fulfilling the equilibrium equations as well as in predicting the displacements, e.g. in setting the overall displacement of 0.1, a root mean square error (RMSE) of 2.09 × 10−4 was achieved.

Keywords: deep learning, neural network, physics-informed machine learning, solid mechanics

Procedia PDF Downloads 150

Authors: Abishek Rajkumar

Abstract:

Antibiotic resistance can occur naturally given the selective pressure placed on antibiotics. Within a large population of bacteria, there is a significant chance that some of those bacteria can develop resistance via mutations or genetic recombination. However, a growing public health concern has arisen over the fact that antibiotic resistance has increased significantly over the past few decades. This is because humans have been over-consuming and producing antibiotics, which has ultimately accelerated the antibiotic resistance seen in these bacteria. The product of all of this is an ongoing race between scientists and the bacteria as bacteria continue to develop resistance, which creates even more demand for an antibiotic that can still terminate the newly resistant strain of bacteria. This paper will focus on a myriad of aspects of antibiotic resistance in bacteria starting with how it occurs on a molecular level and then focusing on the antibiotic concentrations and how they affect the resistance and fitness seen in bacteria.

Keywords: antibiotic, molecular, mutation, resistance

Procedia PDF Downloads 323

Authors: Carlos Roncero-Parra, Alfonso Parreño-Torres, Jorge Mateo Sotos, Alejandro L. Borja

Abstract:

In this research, different methods based on machine/deep learning algorithms are presented for the classification and diagnosis of patients with mental disorders such as alzheimer. For this purpose, the signals obtained from 32 unipolar electrodes identified by non-invasive EEG were examined, and their basic properties were obtained. More specifically, different well-known machine learning based classifiers have been used, i.e., support vector machine (SVM), Bayesian linear discriminant analysis (BLDA), decision tree (DT), Gaussian Naïve Bayes (GNB), K-nearest neighbor (KNN) and Convolutional Neural Network (CNN). A total of 668 patients from five different hospitals have been studied in the period from 2011 to 2021. The best accuracy is obtained was around 93 % in both ADM and ADA classifications. It can be concluded that such a classification will enable the training of algorithms that can be used to identify and classify different mental disorders with high accuracy.

Keywords: alzheimer, machine learning, deep learning, EEG

Procedia PDF Downloads 126

Authors: Camilo Cerda Sarabia, Fernanda Bravo Cornejo, Diego Santibanez Oyarce, Hugo Osses Prado, Esteban Gómez Terán, Belén Diaz Diaz, Raúl Caulier-Cisterna, Jorge Vergara-Quezada, Ana Moya-Beltrán

Abstract:

Antimicrobial resistance (AMR) represents a significant and rapidly escalating global health threat. Projections estimate that by 2050, AMR infections could claim up to 10 million lives annually. Respiratory infections, in particular, pose a severe risk not only to individual patients but also to the broader public health system. Despite the alarming rise in resistant respiratory infections, AMR within the lung microbiome (microbial community) remains underexplored and poorly characterized. The lungs, as a complex and dynamic microbial environment, host diverse communities of microorganisms whose interactions and resistance mechanisms are not fully understood. Unlike studies that focus on individual genomes, analyzing the entire microbiome provides a comprehensive perspective on microbial interactions, resistance gene transfer, and community dynamics, which are crucial for understanding AMR. However, this holistic approach introduces significant computational challenges and exposes the limitations of traditional analytical methods such as the difficulty of identifying the AMR. Machine learning has emerged as a powerful tool to overcome these challenges, offering the ability to analyze complex genomic data and uncover novel insights into AMR that might be overlooked by conventional approaches. This study investigates microbial resistance within the lung microbiome using unsupervised machine learning approaches to uncover resistance patterns and potential clinical associations. it downloaded and selected lung microbiome data from HumanMetagenomeDB based on metadata characteristics such as relevant clinical information, patient demographics, environmental factors, and sample collection methods. The metadata was further complemented by details on antibiotic usage, disease status, and other relevant descriptions. The sequencing data underwent stringent quality control, followed by a functional profiling focus on identifying resistance genes through specialized databases like Antibiotic Resistance Database (CARD) which contains sequences of AMR gene sequence and resistance profiles. Subsequent analyses employed unsupervised machine learning techniques to unravel the structure and diversity of resistomes in the microbial community. Some of the methods employed were clustering methods such as K-Means and Hierarchical Clustering enabled the identification of sample groups based on their resistance gene profiles. The work was implemented in python, leveraging a range of libraries such as biopython for biological sequence manipulation, NumPy for numerical operations, Scikit-learn for machine learning, Matplotlib for data visualization and Pandas for data manipulation. The findings from this study provide insights into the distribution and dynamics of antimicrobial resistance within the lung microbiome. By leveraging unsupervised machine learning, we identified novel resistance patterns and potential drivers within the microbial community.

Keywords: antibiotic resistance, microbial community, unsupervised machine learning., sequences of AMR gene

Procedia PDF Downloads 23

Authors: Dominika Collett

Abstract:

AI applications, such as machine learning, require access to a vast amount of data in the training phase, which can often be the subject of copyright protection. During later usage, the various content with which the application works can be recorded or made available on the basis of which it produces the resulting output. The EU has recently adopted new legislation to secure machine access to protected works under the DSM Directive; but, the issue of machine use of copyright works is not clearly addressed. However, such clarity is needed regarding the increasing importance of AI and its development. Therefore, this paper provides a basic background of the technology used in the development of applications in the field of computer creativity. The second part of the paper then will focus on a legal analysis of machine use of the authors' works from the perspective of existing European and Czech legislation. The main results of the paper discuss the potential collision of existing legislation in regards to machine use of works with special focus on exceptions and limitations. The legal regulation of machine use of copyright work will impact the development of AI technology.

Keywords: copyright, artificial intelligence, legal use, infringement, Czech law, EU law, text and data mining

Procedia PDF Downloads 124

Authors: James Purnama, Riri Fitri Sari

Abstract:

We investigate the machine learning algorithm selection problem in the term of a depth image based eye gaze estimation, with respect to its essential difficulty in reducing the number of required training samples and duration time of training. Statistics based prediction accuracy are increasingly used to assess and evaluate prediction or estimation in gaze estimation. This article evaluates Root Mean Squared Error (RMSE) and R-Squared statistical analysis to assess machine learning methods on depth camera data for gaze estimation. There are 4 machines learning methods have been evaluated: Random Forest Regression, Regression Tree, Support Vector Machine (SVM), and Linear Regression. The experiment results show that the Random Forest Regression has the lowest RMSE and the highest R-Squared, which means that it is the best among other methods.

Keywords: gaze estimation, gaze tracking, eye tracking, kinect, regression model, orange python

Procedia PDF Downloads 538

Authors: Cyril Mae B. Mationg, Alexa T. Belizar, Vethany B. Bellen

Abstract:

This study aims to determine the use of coconut husks and sugarcane bagasse as natural components in making water-resistant tote bags. The study consists of three concentrations: 70% Coconut Husk - 30% Sugarcane Bagasse, 70% cellulose, and 30% cellulose. The results of these tests revealed that, out of the three concentration concentrations, the one consisting of 70% Coconut Husk and 30% sugarcane bagasse exhibited superior performance in breaking capacity and water penetration. During tensile strength testing, the coconut husk and sugarcane bagasse withstood a force of 207.7 Newtons (N) in the machine direction and 216.5 N in the cross-machine direction.

Keywords: coconut husk, sugarcane bagasse, tote bags, water resistance

Procedia PDF Downloads 72

Authors: Donna-Marie Phyllis Lanton

Abstract:

Sarcopenia is a well-known geriatric syndrome characterized by the progressive and generalized loss of muscle quantity or quality. The incidence of sarcopenia increases with age and is associated with adverse outcomes such as the increased risk of falls, cognitive impairment, loss of independence, diminished quality of life, increased health costs, need for care in a skilled nursing facility, and increased mortality. Physical activity, including resistance training, is the most prevalent recommendation for treating and preventing sarcopenia. Residents (N = 23) of a skilled nursing facility in East Orlando, Florida, participated in a 90-day strength training program designed using the PARIHS framework to improve measures of muscle mass, muscle strength, physical performance, and quality of life. Residents engaged in both resistance and balance exercises for 1 hour two times a week. Baseline data were collected and compared to data at Days 30, 60, and 90. T tests indicated significant gains on all measures from baseline to 90 days: muscle mass increased by 1.2 (t[22] = 2.85, p = .009), grip strength increased by 4.02 (t[22] = 8.15, p < .001), balance increased by 2.13 (t[22] = 18.64, p < .001), gait speed increased by 1.83 (t[22] = 17.84, p < .001), chair speed increased 1.87 (t[22] = 16.36, p < .001), and quality of life score increased by 17.5 (t[22] = 19.26, p < .001). For residents with sarcopenia in skilled nursing facilities, a 90-day strength training program with resistance and balance exercises may provide an option for decreasing the incidence of sarcopenia among that population

Keywords: muscle mass, muscle strength, older adults, PARIHS framework

Procedia PDF Downloads 88