Search results for: deep brain stimulation (DBS)

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

Abstract:

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

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

Procedia PDF Downloads 331

Authors: Ben Khayut, Lina Fabri, Maya Avikhana

Abstract:

The models of the modern Artificial Narrow Intelligence (ANI) cannot: a) independently and continuously function without of human intelligence, used for retraining and reprogramming the ANI’s models, and b) think, understand, be conscious, cognize, infer, and more in state of Uncertainty, and changes in situations, and environmental objects. To eliminate these shortcomings and build a new generation of Artificial Intelligence systems, the paper proposes a Conception, Model, and Method of Computational Psycholinguistic Cognitive Situational-Fuzzy Self-Controlled Brain and Mind System (CPCSFSCBMSUU) using a neural network as its computational memory, operating under uncertainty, and activating its functions by perception, identification of real objects, fuzzy situational control, forming images of these objects, modeling their psychological, linguistic, cognitive, and neural values of properties and features, the meanings of which are identified, interpreted, generated, and formed taking into account the identified subject area, using the data, information, knowledge, and images, accumulated in the Memory. The functioning of the CPCSFSCBMSUU is carried out by its subsystems of the: fuzzy situational control of all processes, computational perception, identifying of reactions and actions, Psycholinguistic Cognitive Fuzzy Logical Inference, Decision making, Reasoning, Systems Thinking, Planning, Awareness, Consciousness, Cognition, Intuition, Wisdom, analysis and processing of the psycholinguistic, subject, visual, signal, sound and other objects, accumulation and using the data, information and knowledge in the Memory, communication, and interaction with other computing systems, robots and humans in order of solving the joint tasks. To investigate the functional processes of the proposed system, the principles of Situational Control, Fuzzy Logic, Psycholinguistics, Informatics, and modern possibilities of Data Science were applied. The proposed self-controlled System of Brain and Mind is oriented on use as a plug-in in multilingual subject Applications.

Keywords: computational brain, mind, psycholinguistic, system, under uncertainty

Procedia PDF Downloads 177

Authors: Noriyoshi Yamauchi, Etsuo Horikawa, Takunori Tsuji

Abstract:

Training by exoskeleton robot is drawing attention as a rehabilitation method for body paralysis seen in many cases, and there are many forms that assist with the myoelectric signal generated by exercise commands from the brain. Rehabilitation requires more frequent training, but it is one of the reasons that the technology is required for the identification of the myoelectric potential derivation site and attachment of the device is preventing the spread of paralysis. In this research, we focus on improving the efficiency of gait training by exoskeleton type robots, improvement of myoelectric acquisition and analysis method using active matrix sensing method, and improvement of walking rehabilitation and walking by optimization of robot control.

Keywords: active matrix sensing, brain machine interface (BMI), the central pattern generator (CPG), myoelectric signal processing, robot rehabilitation

Procedia PDF Downloads 385

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

Selecting appropriate patients for surgery is one of the main issues in thoracic surgery (TS). Both short-term and long-term risks and benefits of surgery must be considered in the patient selection criteria. There are some limitations in the existing datasets of TS patients because of missing values of attributes and imbalanced distribution of survival classes. In this study, a novel ensemble architecture of deep learning networks is proposed based on stacking different linear and non-linear layers to deal with imbalance datasets. The categorical and numerical features are split using different layers with ability to shrink the unnecessary features. Then, after extracting the insight from the raw features, a novel biased-kernel layer is applied to reinforce the gradient of the minority class and cause the network to be trained better comparing the current methods. Finally, the performance and advantages of our proposed model over the existing models are examined for predicting patient survival after thoracic surgery using a real-life clinical data for lung cancer patients.

Keywords: deep learning, ensemble models, imbalanced classification, lung cancer, TS patient selection

Procedia PDF Downloads 145

Authors: Carolina Beltran, Carlos De Los Reyes

Abstract:

Acquired brain injury (ABI) is any physical and functional injury secondary to events that affect the brain tissue. It is one of the biggest causes of disability in the world and it has a high annual incidence in the pediatric population. There are several causes of ABI such as traumatic brain injury, central nervous system infection, stroke, hypoxia, tumors and others. The consequences can be cognitive, behavioral, emotional and functional. The cognitive rehabilitation is necessary to achieve the best outcomes for pediatric people with ABI. Cognitive orientation to daily occupational performance (CO-OP) is an individualized client-centered, performance-based, problem-solving approach that focuses on the strategy used to support the acquisition of three client-chosen goals. It has demonstrated improvements in the pediatric population with other neurological disorder but not in Spanish speakers with ABI. Aim: The main objective of this study was to determine the efficacy of cognitive orientation to daily occupational performances (CO-OP) adapted to Spanish speakers, in the level of independence and behavior in a pediatric population with ABI. Methods: Case studies with measure pre/post-treatment were used in three children with ABI, sustained at least before 6 months assessment, in school, aged 8 to 16 years, age ABI after 6 years old and above average intellectual ability. Twelve sessions of CO-OP adapted to Spanish speakers were used and videotaped. The outcomes were based on cognitive, behavior and functional independence measurements such as Child Behavior Checklist (CBCL), Behavior Rating Inventory of Executive Function (BRIEF), The Vineland Adaptive Behavior Scales (VINELAND, Social Support Scale (MOS-SSS) and others neuropsychological measures. This study was approved by the ethics committee of Universidad del Norte in Colombia. Informed parental written consent was obtained for all participants. Results: children were able to identify three goals and use the global strategy ‘goal-plan-do-check’ during each session. Verbal self-instruction was used by all children. CO-OP showed a clinically significant improvement in goals regarding with independence level and behavior according to parents and teachers. Conclusion: The results indicated that CO-OP and the use of a global strategy such as ‘goal-plan-do-check’ can be used in children with ABI in order to improve their specific goals. This is a preliminary version of a big study carrying in Colombia as part of the experimental design.

Keywords: cognitive rehabilitation, acquired brain injury, pediatric population, cognitive orientation to daily occupational performance

Procedia PDF Downloads 106

Authors: Joseph Gear, Yue Xu, Ernest Foo, Praveen Gauravaran, Zahra Jadidi, Leonie Simpson

Abstract:

Deep learning methods have been seeing an increasing application to the long-standing security research goal of automatic vulnerability detection for source code. Attention, however, must still be paid to the task of producing vector representations for source code (code embeddings) as input for these deep learning models. Graphical representations of code, most predominantly Abstract Syntax Trees and Code Property Graphs, have received some use in this task of late; however, for very large graphs representing very large code snip- pets, learning becomes prohibitively computationally expensive. This expense may be reduced by intelligently pruning this input to only vulnerability-relevant information; however, little research in this area has been performed. Additionally, most existing work comprehends code based solely on the structure of the graph at the expense of the information contained by the node in the graph. This paper proposes Semantic-enhanced Code Embedding for Vulnerability Discovery (SCEVD), a deep learning model which uses semantic-based feature selection for its vulnerability classification model. It uses information from the nodes as well as the structure of the code graph in order to select features which are most indicative of the presence or absence of vulnerabilities. This model is implemented and experimentally tested using the SARD Juliet vulnerability test suite to determine its efficacy. It is able to improve on existing code graph feature selection methods, as demonstrated by its improved ability to discover vulnerabilities.

Keywords: code representation, deep learning, source code semantics, vulnerability discovery

Procedia PDF Downloads 159

Authors: Wei Zhang

Abstract:

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Keywords: deep learning, field programmable gate array, FPGA, hardware accelerator, convolutional neural networks, CNN

Procedia PDF Downloads 128

Authors: Akhtar Aman, Abida Raza, Shumaila Bashir, Mehboob Alam

Abstract:

The development of efficient delivery systems remains a major concern in cancer chemotherapy as many efficacious anticancer drugs are hydrophobic and difficult to formulate. Nanomedicines based on drug-loaded amphiphilic glycol chitosan micelles offer potential advantages for the formulation of drugs such as etoposide that may improve the pharmacokinetics and reduce the formulation-related adverse effects observed with current formulations. Amphiphilic derivatives of glycol chitosan were synthesized by chemical grafting of palmitic acid N-hydroxysuccinimide and quaternization to glycol chitosan backbone. To this end, a 7.9 kDa glycol chitosan was modified by palmitoylation and quaternization, yielding a 13 kDa amphiphilic polymer. Micelles prepared from this amphiphilic polymer had a size of 162nm and were able to encapsulate up to 3 mg/ml etoposide. Pharmacokinetic results indicated that the GCPQ micelles transformed the biodistribution pattern and increased etoposide concentration in the brain significantly compared to free drugs after intravenous administration. AUC 0.5-24h showed statistically significant difference in ETP-GCPQ vs. Commercial preparation in liver (25 vs.70, p<0.001), spleen (27 vs.36, p<0.05), lungs (42 vs.136,p<0.001),kidneys(25 vs.70,p< 0.05),and brain(19 vs.9,p<0.001). ETP-GCPQ crossed the blood-brain barrier, and 4, 3.5, 2.6, 1.8, 1.7, 1.5, and 2.5 fold higher levels of etoposide were observed at 0.5, 1, 2, 4, 6, 12, and 24hrs; respectively suggesting these systems could deliver hydrophobic anticancer drugs such as etoposide to tumors but also increased their transport through the biological barriers, thus making it a good delivery system

Keywords: glycol chitosan, micelles, pharmacokinetics, tissue distribution

Procedia PDF Downloads 104

Authors: Ammar Aljabri, Alhussain Halawani, Alaa Ashqar, Omar Alageely

Abstract:

Objective: mild Traumatic Brain Injury (mTBI) or concussion is a common yet undermanaged and underreported condition. This systematic review and meta-analysis aim to determine the efficacy of VRT as a treatment option for mTBI. Method: This review and meta-analysis was performed following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines and included RCTs and pre-VRT/post-VRT retrospective chart reviews. Records meeting the inclusion criteria were extracted from the following databases: Medline, Embase, and Cochrane Register of Controlled Trials (CENTRAL). Results: Eight articles met the inclusion criteria, and six RCTs were included in the meta-analysis. VRT demonstrated significant improvement in decreasing perceived dizziness at the end of the intervention program, as shown by DHI scores (SMD= -0.33, 95% CI -0.62 to -0.03, p=0.03, I2= 0%). However, no significant reduction in DHI was evident after two months of follow-up (SMD= 0.15, 95% CI -0.23 to 0.52, p=0.44, I2=0%). Quantitative analysis also depicts significant reduction in both VOMS (SMD=-0.40, 95% CI -0.60 to -0.20, p<0.0001, I2=0%) and PCSS (SMD= -0.39, 95% CI -0.71 to -0.07, p=0.02, I2=0%) following the intervention. Lastly, there was no significant difference between intervention groups on BESS scores (SMD= -31, 95% CI -0.71 to 0.10, p=0.14, I2=0%) and return to sport/function (95% CI 0.32 to 30.80, p=0.32, I2=82%). Conclusions: Current evidence on the efficacy of VRT for mTBI is limited. This review and analysis provide evidence that supports the role of VRT in improving perceived symptoms following concussion. There is still a need for high-quality trials evaluating the benefit of VRT using a standardized approach.

Keywords: concussion, traumatic brain injury, vestibular rehabilitation, neurorehabilitation

Procedia PDF Downloads 143

Authors: Derejaw Lake Melie, Alemu Kumlachew Tegegne

Abstract:

The increasing prevalence of social media in Ethiopia has exacerbated societal challenges by fostering the proliferation of negative emotional posts and comments. Illicit use of social media has further exacerbated divisions among the population. Addressing these issues through manual identification and aggregation of emotions from millions of users for swift decision-making poses significant challenges, particularly given the rapid growth of Amharic language usage on social platforms. Consequently, there is a critical need to develop an intelligent system capable of automatically detecting and categorizing negative emotional content into social, religious, and political categories while also filtering out toxic online content. This paper aims to leverage sentiment analysis techniques to achieve automatic detection and filtering of negative emotional content from Amharic social media texts, employing a comparative study of deep learning algorithms. The study utilized a dataset comprising 29,962 comments collected from social media platforms using comment exporter software. Data pre-processing techniques were applied to enhance data quality, followed by the implementation of deep learning methods for training, testing, and evaluation. The results showed that CNN, GRU, LSTM, and Bi-LSTM classification models achieved accuracies of 83%, 50%, 84%, and 86%, respectively. Among these models, Bi-LSTM demonstrated the highest accuracy of 86% in the experiment.

Keywords: negative emotion, emotion detection, social media filtering sentiment analysis, deep learning.

Procedia PDF Downloads 24

Authors: Zhong Ma, Zhuping Wang, Congxin Liu, Xiangzeng Liu

Abstract:

Satellite imagery classification is a challenging problem with many practical applications. In this paper, we designed a deep convolution neural network (DCNN) to classify the satellite imagery. The contributions of this paper are twofold — First, to cope with the large-scale variance in the satellite image, we introduced the inception module, which has multiple filters with different size at the same level, as the building block to build our DCNN model. Second, we proposed a genetic algorithm based method to efficiently search the best hyper-parameters of the DCNN in a large search space. The proposed method is evaluated on the benchmark database. The results of the proposed hyper-parameters search method show it will guide the search towards better regions of the parameter space. Based on the found hyper-parameters, we built our DCNN models, and evaluated its performance on satellite imagery classification, the results show the classification accuracy of proposed models outperform the state of the art method.

Keywords: satellite imagery classification, deep convolution network, genetic algorithm, hyper-parameter optimization

Procedia PDF Downloads 301

Authors: Chaomeng Liu, Li Li, Xiao Wang, Li Ren, Qinge Zhang

Abstract:

Late-life depression (LLD) is a prevalent mental disorder among the elderly, frequently accompanied by significant cognitive decline, and has emerged as a worldwide public health concern. Microglia, astrocytes, and peripheral immune cells play pivotal roles in regulating inflammatory responses within the central nervous system (CNS) across diverse cerebral disorders. This review commences with the clinical research findings and accentuates the recent advancements pertaining to microglia and astrocytes in the neuroinflammation process of LLD. The reciprocal communication network between the CNS and immune system is of paramount importance in the pathogenesis of depression and cognitive decline. Stress-induced downregulation of tight and gap junction proteins in the brain results in increased blood-brain barrier permeability and impaired astrocyte function. Concurrently, activated microglia release inflammatory mediators, initiating the kynurenine metabolic pathway and exacerbating the quinolinic acid/kynurenic acid imbalance. Moreover, the balance between Th17 and Treg cells is implicated in the preservation of immune homeostasis within the cerebral milieu of individuals suffering from LLD. The ultimate objective of this review is to present future strategies for the management and treatment of LLD, informed by the most recent advancements in research, with the aim of averting or postponing the onset of AD.

Keywords: neuroinflammation, late-life depression, microglia, astrocytes, central nervous system, blood-brain barrier, Kynurenine pathway

Procedia PDF Downloads 46

Authors: Tokihiko Akita, Seiichi Mita

Abstract:

A millimeter-wave radar is the most robust against adverse environments, making it an essential environment recognition sensor for automated driving. However, the reflection signal is sparse and unstable, so it is difficult to obtain the high recognition accuracy. Deep learning provides high accuracy even for them in recognition, but requires large scale datasets with ground truth. Specially, it takes a lot of cost to annotate for a millimeter-wave radar. For the solution, utilizing a simulator that can generate an annotated huge dataset is effective. Simulation of the radar is more difficult to match with real world data than camera image, and recognition by deep learning with higher-order features using the simulator causes further deviation. We have challenged to improve the accuracy of traffic participant classification by fusing simulator and real-world data with domain adaptation technique. Experimental results with the domain adaptation network created by us show that classification accuracy can be improved even with a few real-world data.

Keywords: millimeter-wave radar, object classification, deep learning, simulation, domain adaptation

Procedia PDF Downloads 93

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 94

Authors: Aoxue Yang, Weili Tian, Yonghe Wu, Haikun Liu

Abstract:

Brain tumor stem cells (BTSCs) are resistant to therapy and give rise to recurrent tumors. These rare and elusive cells are likely to disseminate during cancer progression, and some may enter dormancy, remaining viable but not increasing. The identification of dormant BTSCs is thus necessary to design effective therapies for glioblastoma (GBM) patients. Little progress has been made in therapeutic treatment of glioblastoma in the last decade despite rapid progress in molecular understanding of brain tumors1. Here we show that the stress hormone glucocorticoid is essential for the maintenance of brain tumor stem cells (BTSCs), which are resistant to conventional therapy. The glucocorticoid receptor (GR) regulates metabolic plasticity and chemoresistance of the dormant BTSC via controlling expression of GPD1 (glycerol-3-phosphate dehydrogenase 1), which is an essential regulator of lipid metabolism in BTSCs. Genomic, lipidomic and cellular analysis confirm that GR/GPD1 regulation is essential for BTSCs metabolic plasticity and survival. We further demonstrate that the GR agonist dexamethasone (DEXA), which is commonly used to control edema in glioblastoma, abolishes the effect of chemotherapy drug temozolomide (TMZ) by upregulating GPD1 and thus promoting tumor cell dormancy in vivo, this provides a mechanistic explanation and thus settle the long-standing debate of usage of steroid in brain tumor patient edema control. Pharmacological inhibition of GR/GPD1 pathway disrupts metabolic plasticity of BTSCs and prolong animal survival, which is superior to standard chemotherapy. Patient case study shows that GR antagonist mifepristone blocks tumor progression and leads to symptomatic improvement. This study identifies an important mechanism regulating cancer stem cell dormancy and provides a new opportunity for glioblastoma treatment.

Keywords: cancer stem cell, dormancy, glioblastoma, glycerol-3-phosphate dehydrogenase 1, glucocorticoid receptor, dexamethasone, RNA-sequencing, phosphoglycerides.

Procedia PDF Downloads 84

Authors: Avalloy McCarthy-Curvin

Abstract:

For over fifty years there has been widespread dissatisfaction with the teaching of Mathematics in Jamaica. Studies, done in the Jamaican context highlight that teachers at the end of training do not have a deep understanding of the mathematics content they teach. Little research has been done in the Jamaican context that targets the advancement of contextual knowledge on the problem to ultimately provide a solution. The aim of the study is to identify what influences this outcome of teacher education in Jamaica so as to remedy the problem. This study formatively evaluated the curriculum documents, assessments and the delivery of the curriculum that are being used in teacher training institutions in Jamaica to determine their rigor -the extent to which written document, instruction, and the assessments focused on enabling pre-service teachers to develop deep understanding of mathematics and relevance- the extent to which the curriculum document, instruction, and the assessments are focus on developing the requisite knowledge for teaching mathematics. The findings show that neither the curriculum document, instruction nor assessments ensure rigor and enable pre-service teachers to develop the knowledge and skills they need to teach mathematics effectively.

Keywords: relevance, rigor, deep understanding, formative evaluation

Procedia PDF Downloads 237

Authors: Öznur Özge Özcan, Canan Sercan, Hamza Kulaksız, Mesut Karahan, Korkut Ulucan

Abstract:

Genetic structure is very important to understand the brain dopamine system which is related to athletic performance. Hopefully, there will be enough studies about athletics performance in the terms of addiction-related genetic markers in the future. In the present study, we intended to investigate the Receptor-2 Gene (DRD2) rs1800497, which is related to brain dopaminergic system. 10 sprinter and 10 endurance athletes were enrolled in the study. Real-Time Polymerase Chain Reaction method was used for genotyping. According to results, A1A1, A1A2 and A2A2 genotypes in athletes were 0 (%0), 3 (%15) and 17 (%85). A1A1 genotype was not found and A2 allele was counted as the dominating allele in our cohort. These findings show that dopaminergic mechanism effects on sport genetic may be explained by the polygenic and multifactorial view.

Keywords: addiction, athletic performance, genotype, sport genetics

Procedia PDF Downloads 214

Authors: Shariful Islam, Sharun Akter Khushbu, S. M. Shaqib, Shahriar Sultan Ramit

Abstract:

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwear. The suggested method precisely locates these safety items by using the YOLO v7 (You Only Look Once) object detection algorithm. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a [email protected] score of 87.7%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research contributes to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry.

Keywords: deep learning, safety equipment detection, YOLOv7, computer vision, workplace safety

Procedia PDF Downloads 68

Authors: Anoop T. R., Otman Basir, Robert F. Hess, Eileen E. Birch, Brooke A. Koritala, Reed M. Jost, Becky Luu, David Stager, Ben Thompson

Abstract:

Strabismus refers to a misalignment of the eyes. Early detection and treatment of strabismus in childhood can prevent the development of permanent vision loss due to abnormal development of visual brain areas. We developed a two-stage method for strabismus detection and classification based on photographs of the face. The first stage detects the presence or absence of strabismus, and the second stage classifies the type of strabismus. The first stage comprises face detection using Haar cascade, facial landmark estimation, face alignment, aligned face landmark detection, segmentation of the eye region, and detection of strabismus using VGG 16 convolution neural networks. Face alignment transforms the face to a canonical pose to ensure consistency in subsequent analysis. Using facial landmarks, the eye region is segmented from the aligned face and fed into a VGG 16 CNN model, which has been trained to classify strabismus. The CNN determines whether strabismus is present and classifies the type of strabismus (exotropia, esotropia, and vertical deviation). If stage 1 detects strabismus, the eye region image is fed into stage 2, which starts with the estimation of pupil center coordinates using mask R-CNN deep neural networks. Then, the distance between the pupil coordinates and eye landmarks is calculated along with the angle that the pupil coordinates make with the horizontal and vertical axis. The distance and angle information is used to characterize the degree and direction of the strabismic eye misalignment. This model was tested on 100 clinically labeled images of children with (n = 50) and without (n = 50) strabismus. The True Positive Rate (TPR) and False Positive Rate (FPR) of the first stage were 94% and 6% respectively. The classification stage has produced a TPR of 94.73%, 94.44%, and 100% for esotropia, exotropia, and vertical deviations, respectively. This method also had an FPR of 5.26%, 5.55%, and 0% for esotropia, exotropia, and vertical deviation, respectively. The addition of one more feature related to the location of corneal light reflections may reduce the FPR, which was primarily due to children with pseudo-strabismus (the appearance of strabismus due to a wide nasal bridge or skin folds on the nasal side of the eyes).

Keywords: strabismus, deep neural networks, face detection, facial landmarks, face alignment, segmentation, VGG 16, mask R-CNN, pupil coordinates, angle deviation, horizontal and vertical deviation

Procedia PDF Downloads 93

Authors: Qian Mao, Xiaozan Wang, Jiarong Zhong, Xiaolin Zou

Abstract:

Introduction: As a result of the decline of students' physical health level and the increase of study pressure, students’ academic performance is not so good. Objective: This study aims to verify whether the Brain-Break intervention in the fourth-grade classroom of primary school can improve students' physical health and academic performance. Methods: According to the principle of no difference in pre-test data, students from two classes of grade four in Fuhai Road Primary School, Fushan district, Yantai city, Shandong province, were selected as experimental subjects, including 50 students in the experimental class (25 males and 25 females) and 50 students in the control class (24 males and 26 females). The content of the experiment was that the students were asked to perform a 4-minute Brain-Berak program designed by the researcher in the second class in the morning and the afternoon, and the intervention lasted for 12 weeks. In addition, the lung capacity, 50-meter run, sitting body forward bend, one-minute jumping rope and one-minute sit-ups stipulated in the national standards for physical fitness of students (revised in 2014) were selected as the indicators of physical health. The scores of Chinese, Mathematics, and English in the unified academic test of the municipal education bureau were selected as the indicators of academic performance. The independent-sample t-test was used to compare and analyze the data of each index between the two classes. The paired-sample t-test was used to compare and analyze the data of each index in the two classes. This paper presents only results with significant differences. Results: in terms of physical health, lung capacity (P=0.002, T= -2.254), one-minute rope skipping (P=0.000, T=3.043), and one-minute sit-ups (P=0.045, T=6.153) were significantly different between the experimental class and the control class. In terms of academic performance, there is a significant difference between the Chinese performance of the experimental class and the control class (P=0.009, T=4.833). Conclusion: Adding Brain-Berak intervention in the classroom can effectively improve the cardiorespiratory endurance (lung capacity), coordination (jumping rope), and abdominal strength (sit-ups) of fourth-grade students. At the same time, it can also effectively improve their Chinese performance. Therefore, it is suggested to promote micro-sports in the classroom of primary schools throughout the country so as to help students improve their physical health and academic performance.

Keywords: academic performance, brain break, fourth grade, physical health

Procedia PDF Downloads 101

Authors: Rachid El Khoury

Abstract:

Chronic pain is perhaps the most burdensome health issue facing the planet. Our understanding of the pathophysiology of chronic pain has increased substantially over the past 25 years, including but not limited to changes in the brain. However, we still do not know why chronic pain develops in some people and not in others. Most of the recent developments in pain science, that have direct relevance to clinical management, relate to our understanding of the role of the brain, the role of the immune system, or the role of cognitive and behavioral factors. Although the Biopsychosocial model of pain management was presented decades ago, the Bio-reductionist model remains, unfortunately, at the heart of many practices across professional and geographic boundaries. A large body of evidence shows that nociception is neither sufficient nor necessary for pain. Pain is a conscious experience that can certainly be, and often is, associated with nociception, however, always modulated by countless neurobiological, environmental, and cognitive factors. This study will clarify the current misconceptions of chronic pain concepts, and their misperceptions by clinicians. It will also attempt to bridge the considerable gap between what we already know on pain but somehow disregarded, the development in pain science, and clinical practice.

Keywords: chronic pain, nociception, biopsychosocial, neuroplasticity

Procedia PDF Downloads 63

Authors: Rubina Shakya, Srijana Dangol, Dil Islam Mansur

Abstract:

The exposure of constant stress stimuli in our daily lives is causing deterioration of neural connectivity in the brain. Interestingly, the improvement in larger-scale neural communication has been argued to rely on brain rhythms, which might be sensitive to binaural beats of particular frequency bands. The theoretical idea behind neural entrainment is that the rhythmic oscillatory activity within and between different brain regions can enhance cognitive function and mood state. So, we aimed to investigate whether the binaural beats of 40 Hz could enhance the cognition and the mood stability of the medical students at Kathmandu University of age 18-25 years old, which possibly, in the long run, might help to enhance their work productivity. The participants were asked to focus on the auditory stimuli of binaural beats with 200 Hz on the right side and 240 Hz on the left side of the headset for 15 minutes, every alternative day of three consecutive weeks. The Stroop’s test and the Brunel Mood Scale (BRUMS) were applied to assess the cognitive function and the mood state, respectively. The binaural beats significantly decreased the reaction time for the incoherent component of Stroop’s test in both male and female participants. For the mood state, scores of all positive emotions except ‘Calmness’ were significantly increased in the case of males. Whereas, scores of all positive emotions except ‘Vigor’ were significantly increased in the case of females. The results suggested that the meditation aided by binaural beats of 40 Hz helps in improving cognition and mood states to some extent.

Keywords: binaural beats, cognitive function, gamma neural oscillation, mood states

Procedia PDF Downloads 141

Authors: Fidel Lòpez Saca, Carlos Avilés-Cruz, Miguel Magos-Rivera, José Antonio Lara-Chávez

Abstract:

Automated object recognition and identification systems are widely used throughout the world, particularly in assembly lines, where they perform quality control and automatic part selection tasks. This article presents the design and implementation of an object recognition system in an assembly line. The proposed shapes-color recognition system is based on deep learning theory in a specially designed convolutional network architecture. The used methodology involve stages such as: image capturing, color filtering, location of object mass centers, horizontal and vertical object boundaries, and object clipping. Once the objects are cut out, they are sent to a convolutional neural network, which automatically identifies the type of figure. The identification system works in real-time. The implementation was done on a Raspberry Pi 3 system and on a Jetson-Nano device. The proposal is used in an assembly course of bachelor’s degree in industrial engineering. The results presented include studying the efficiency of the recognition and processing time.

Keywords: deep-learning, image classification, image identification, industrial engineering.

Procedia PDF Downloads 161

Authors: Yahya Al-Gabri

Abstract:

This study aimed to identify the availability degree of transformational leadership dimensions among heads of scientific departments in the Education Faculty at King Saud University. It also aimed to identify the degree of opinions divergence of the study sample on the availability degree of transformational leadership dimensions among the department heads according to the variable of scientific rank. The researcher used the descriptive approach. The study sample consisted of (34) members of education faculty which chosen randomly. To collect the data, the researcher developed a questionnaire consisting of (47) items distributed on four areas after ensuring validity and reliability. Results showed that the degree of practicing the dimensions of transformational leadership by the heads of scientific departments was medium and the mean was (3.21). The dimension of Individualized consideration came first and had a high degree of availability with a mean of (3.31) and the dimension of idealized influence came secondly and had a medium degree (near of high) of availability with a mean of (3.25), also and the dimension of inspirational motivation came thirdly and had a medium degree of availability with a mean of (3.16), whereas the dimension of intellectual stimulation came finally and had a medium degree of availability with a mean of (3.13). The study also showed that there are no statistically significant differences at the level of significance (0.05) in the availability degree of transformational leadership dimensions among the heads of scientific departments at the Faculty of Education according to the scientific rank variable. Finally, the researcher made a number of recommendations and suggestions.

Keywords: transformational leadership, heads of scientific departments, individualized consideration, idealized influence, inspirational motivation, intellectual stimulation

Procedia PDF Downloads 155

Authors: Nikita Pasricha, Karen Smith, Simone Marshall, Vincent DePaul, Jessica Trier

Abstract:

Understanding that physical activity in rehabilitation programs shapes outcomes in acquired brain injury (ABI) populations is not a new concept. However, there is a void in understanding the physical activity patterns of inpatients in ABI rehabilitation, the trajectory of physical activity recovery, and factors that contribute to the recovery of physical activity over the initial months post-ABI. The purpose of this study was to determine if physical activity patterns vary in people with recent ABI in inpatient rehabilitation. The study also investigated differences in physical activity patterns in ABI patients compared to age-related healthy participants. Results revealed that ABI patients spent approximately 6.7 times longer per day in sedentary postures than in active positions. In comparison, the control group spent only 2.8 times longer in sedentary postures compared to active positions. Patients with ABI took significantly fewer steps than age-matched health control participants. Within the ABI population, patients took 0.78 times fewer steps on weekends compared to weekdays. Participants with greater mobility limitations had a greater difference in WD to WE steps taken. Potential reasons could be from no structured weekend rehabilitation programs, lower availability of staff, or varying schedules. Given that the rehabilitation program is only structured on weekdays, further research to investigate the benefits of structured physical activities like group walking programs on weekends for ABI patients in inpatient rehabilitation programs is warranted.

Keywords: brain, ABI, TBI, rehabilitation

Procedia PDF Downloads 54

Authors: Joseph George, Anne Kotteswara Roa

Abstract:

Skin disease is one of the most common and popular kinds of health issues faced by people nowadays. Skin cancer (SC) is one among them, and its detection relies on the skin biopsy outputs and the expertise of the doctors, but it consumes more time and some inaccurate results. At the early stage, skin cancer detection is a challenging task, and it easily spreads to the whole body and leads to an increase in the mortality rate. Skin cancer is curable when it is detected at an early stage. In order to classify correct and accurate skin cancer, the critical task is skin cancer identification and classification, and it is more based on the cancer disease features such as shape, size, color, symmetry and etc. More similar characteristics are present in many skin diseases; hence it makes it a challenging issue to select important features from a skin cancer dataset images. Hence, the skin cancer diagnostic accuracy is improved by requiring an automated skin cancer detection and classification framework; thereby, the human expert’s scarcity is handled. Recently, the deep learning techniques like Convolutional neural network (CNN), Deep belief neural network (DBN), Artificial neural network (ANN), Recurrent neural network (RNN), and Long and short term memory (LSTM) have been widely used for the identification and classification of skin cancers. This survey reviews different DL techniques for skin cancer identification and classification. The performance metrics such as precision, recall, accuracy, sensitivity, specificity, and F-measures are used to evaluate the effectiveness of SC identification using DL techniques. By using these DL techniques, the classification accuracy increases along with the mitigation of computational complexities and time consumption.

Keywords: skin cancer, deep learning, performance measures, accuracy, datasets

Procedia PDF Downloads 129

Authors: Amin Akbari, Dongcai Wang, Huiru Li, Xiaoping Du, Jie Chen

Abstract:

The effect of vibrational force (VF) on accelerating orthodontic tooth movement depends on the level of delivered stimulation to the tooth in terms of peak load (PL), which requires contacts between the tooth and the VF device. A personalized device ensures the contacts, but the resulting PL distribution on the teeth is unknown. Furthermore, it is unclear whether the PL on particular teeth can be adjusted to the prescribed values. The objective of this study was to investigate the efficacy of apersonalized VF device in controlling the level of stimulation on two teeth, the mandibular canines and 2nd molars. A 3-D finite element (FE) model of human dentition, including teeth, PDL, and alveolar bone, was created from the cone beam computed tomography images of an anonymous subject. The VF was applied to the teeth through a VFdevice consisting of a mouthpiece with engraved tooth profile of the subject and a VF source that applied 0.3 N force with the frequency of 30 Hz. The dentition and mouthpiece were meshed using 10-node tetrahedral elements. Interface elements were created at the interfaces between the teeth and the mouthpiece. The upper and lower teeth bite on the mouthpiece to receive the vibration. The depth of engraved individual tooth profile could be adjusted, which was accomplished by adding a layer of material as an interference or removing a layer of material as a clearance to change the PL on the tooth. The interference increases the PL while the clearance decreases it. Fivemouthpiece design cases were simulated, which included a mouthpiece without interference/clearance; the mouthpieces with bilateral interferences on both mandibular canines and 2nd molars with magnitudes of 0.1, 0.15, and 0.2-mm, respectively; and mouthpiece with bilateral 0.3-mm clearances on the four teeth. Then, the force distributions on the entire dentition were compared corresponding to these adjustments. The PL distribution on the teeth is uneven when there is no interference or clearance. Among all teeth, the anterior segment receives the highest level of PL. Adding 0.1, 0.15, and 0.2-mm interferences to the canines and 2nd molars bilaterally leads to increase of the PL on the canines by 10, 62, and 73 percent and on the 2nd molar by 14, 55, and 87 percent, respectively. Adding clearances to the canines and 2nd molars by removing the contactsbetween these teeth and the mouthpiece results in zero PL on them. Moreover, introducing interference to mandibular canines and 2nd molarsredistributes the PL on the entireteeth. The share of the PL on the anterior teeth are reduced. The use of the personalized mouthpiece ensures contactsof the teeth to the mouthpiece so that all teeth can be stimulated. However, the PL distribution is uneven. Adding interference between a tooth and the mouthpiece increases the PL while introducing clearance decreases the PL. As a result, the PL is redistributed. This study confirms that the level of VF stimulation on the individual tooth can be adjusted to a prescribed value.

Keywords: finite element method, orthodontic treatment, stress analysis, tooth movement, vibrational force

Procedia PDF Downloads 224

Authors: Yusser Olguín, Diego Benavente, Fernando Dorta, Nicole Orellana, Cristian Acevedo

Abstract:

One of the greatest challenges of tissue engineering is the generation of materials in which the highest possible number of conditions can be incorporated to stimulate the proliferation and differentiation of cells, which will be transformed together with the material into new functional tissue. In this sense, considering the properties of microfluidics and its relationship with cellular micro-environments, the possibility of controlling flow patterns and the ability to design diverse patterns in the chips, a microfluidic cell culture system can be established as a means for the evaluation of the effect of different parameters in a controlled and precise manner. Specifically in relation to the study and development of alternatives in peripheral nervous tissue engineering, it is necessary to consider different physical and chemical neurotrophic stimuli that promote cell growth and differentiation. Chemical stimuli include certain vitamins, glucocorticoids, gangliosides, and growth factors, while physical stimuli include topological stimuli, mechanical forces of the cellular environment and electrical stimulation. In this context, the present investigation shows the results of cell stimulation in a microbioreactor using electrical and chemical stimuli, where the differentiation of PC12 cells as a neuronal model is evidenced by neurite expression, dependent on the stimuli and their combination. The results were analysed with a multi-factor statistical approach, showing several relationships and dependencies between different parameters. Chip design, operating parameters and concentrations of neurotrophic chemical factors were found to be preponderant, based on the characteristics of the electrical stimuli.

Keywords: microfluidics, nerve tissue engineering, microbioreactor, electrical stimuli

Procedia PDF Downloads 85

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 278

Authors: Liang Wang, Beste F. Yuksel, David Guy Brizan

Abstract:

A computational model of affect that can distinguish between spontaneous and posed smiles with no errors on a large, popular data set using deep learning techniques is presented in this paper. A Long Short-Term Memory (LSTM) classifier, a type of Recurrent Neural Network, is utilized and compared to human classification. Results showed that while human classification (mean of 0.7133) was above chance, the LSTM model was more accurate than human classification and other comparable state-of-the-art systems. Additionally, a high accuracy rate was maintained with small amounts of training videos (70 instances). The derivation of important features to further understand the success of our computational model were analyzed, and it was inferred that thousands of pairs of points within the eyes and mouth are important throughout all time segments in a smile. This suggests that distinguishing between a posed and spontaneous smile is a complex task, one which may account for the difficulty and lower accuracy of human classification compared to machine learning models.

Keywords: affective computing, affect detection, computer vision, deep learning, human-computer interaction, machine learning, posed smile detection, spontaneous smile detection

Procedia PDF Downloads 125