Search results for: neural activation

Authors: M. R. Homaeinezhad, E. Tavakkoli, M. Habibi, S. A. Atyabi, A. Ghaffari

Abstract:

This paper describes a new supervised fusion (hybrid) electrocardiogram (ECG) classification solution consisting of a new QRS complex geometrical feature extraction as well as a new version of the learning vector quantization (LVQ) classification algorithm aimed for overcoming the stability-plasticity dilemma. Toward this objective, after detection and delineation of the major events of ECG signal via an appropriate algorithm, each QRS region and also its corresponding discrete wavelet transform (DWT) are supposed as virtual images and each of them is divided into eight polar sectors. Then, the curve length of each excerpted segment is calculated and is used as the element of the feature space. To increase the robustness of the proposed classification algorithm versus noise, artifacts and arrhythmic outliers, a fusion structure consisting of five different classifiers namely as Support Vector Machine (SVM), Modified Learning Vector Quantization (MLVQ) and three Multi Layer Perceptron-Back Propagation (MLP–BP) neural networks with different topologies were designed and implemented. The new proposed algorithm was applied to all 48 MIT–BIH Arrhythmia Database records (within–record analysis) and the discrimination power of the classifier in isolation of different beat types of each record was assessed and as the result, the average accuracy value Acc=98.51% was obtained. Also, the proposed method was applied to 6 number of arrhythmias (Normal, LBBB, RBBB, PVC, APB, PB) belonging to 20 different records of the aforementioned database (between– record analysis) and the average value of Acc=95.6% was achieved. To evaluate performance quality of the new proposed hybrid learning machine, the obtained results were compared with similar peer– reviewed studies in this area.

Keywords: Feature Extraction, Curve Length Method, SupportVector Machine, Learning Vector Quantization, Multi Layer Perceptron, Fusion (Hybrid) Classification, Arrhythmia Classification, Supervised Learning Machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2229

Authors: Yehjune Heo

Abstract:

As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.

Keywords: Anti-spoofing, CNN, fingerprint recognition, loss function, optimizer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 422

Authors: Kaushik Sathupadi, Sandesh Achar

Abstract:

Pervasive computing is a growing research field that aims to acknowledge human physical life routines (HPLR) based on body-worn sensors such as MEMS (Micro-Electro-Mechanical Systems) sensors-based technologies. The use of these technologies for human activity recognition is progressively increasing. On the other hand, personalizing human life routines using numerous machine-learning techniques has always been an intriguing topic. In contrast, various methods have demonstrated the ability to recognize basic movement patterns. However, it still needs to be improved to anticipate the dynamics of human living patterns. This study presents state-of-the-art techniques for recognizing static and dynamic patterns and forecasting those challenging activities from multi-fused sensors. Furthermore, numerous MEMS signals are extracted from one self-annotated IM-WSHA dataset and two benchmarked datasets. First, raw data were processed with z-normalization and denoiser methods. Then, we adopted statistical, local binary pattern, auto-regressive model, and intrinsic time scale decomposition major features for feature extraction from different domains. Next, the acquired features are optimized using maximum relevance and minimum redundancy (mRMR). Finally, the artificial neural network is applied to analyze the whole system's performance. As a result, we attained a 90.27% recognition rate for the self-annotated dataset, while the HARTH and KU-HAR achieved 83% on nine living activities and 90.94% on 18 static and dynamic routines. Thus, the proposed HPLR system outperformed other state-of-the-art systems when evaluated with other methods in the literature.

Keywords: Artificial intelligence, machine learning, gait analysis, local binary pattern, statistical features, micro-electro-mechanical systems, maximum relevance and minimum redundancy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18

Authors: Jorge Rodriguez-Guerra, Carlos Calleja, Aron Pujana, Iker Elorza, Ana Maria Macarulla

Abstract:

Society demands more reliable manufacturing processes capable of producing high quality products in shorter production cycles. New control algorithms have been studied to satisfy this paradigm, in which Fault-Tolerant Control (FTC) plays a significant role. It is suitable to detect, isolate and adapt a system when a harmful or faulty situation appears. In this paper, a general overview about FTC characteristics are exposed; highlighting the properties a system must ensure to be considered faultless. In addition, a research to identify which are the main FTC techniques and a classification based on their characteristics is presented in two main groups: Active Fault-Tolerant Controllers (AFTCs) and Passive Fault-Tolerant Controllers (PFTCs). AFTC encompasses the techniques capable of re-configuring the process control algorithm after the fault has been detected, while PFTC comprehends the algorithms robust enough to bypass the fault without further modifications. The mentioned re-configuration requires two stages, one focused on detection, isolation and identification of the fault source and the other one in charge of re-designing the control algorithm by two approaches: fault accommodation and control re-design. From the algorithms studied, one has been selected and applied to a case study based on an industrial hydraulic-press. The developed model has been embedded under a real-time validation platform, which allows testing the FTC algorithms and analyse how the system will respond when a fault arises in similar conditions as a machine will have on factory. One AFTC approach has been picked up as the methodology the system will follow in the fault recovery process. In a first instance, the fault will be detected, isolated and identified by means of a neural network. In a second instance, the control algorithm will be re-configured to overcome the fault and continue working without human interaction.

Keywords: Fault-tolerant control, electro-hydraulic actuator, fault detection and isolation, control re-design, real-time.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 841

Authors: Zhenzhen Xu, Chunfu Shao, Shengyou Wang, Chunjiao Dong

Abstract:

To improve the satisfaction of residents' travel, this paper analyzes the characteristics and influencing factors of urban residents' travel behavior. First, a Multinominal Logit Model (MNL) model is built to analyze the characteristics of residents' travel behavior, reveal the influence of individual attributes, family attributes and travel characteristics on the choice of travel mode, and identify the significant factors. Then put forward suggestions for policy improvement. Finally, Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) models are introduced to evaluate the policy effect. This paper selects Futian Street in Futian District, Shenzhen City for investigation and research. The results show that gender, age, education, income, number of cars owned, travel purpose, departure time, journey time, travel distance and times all have a significant influence on residents' choice of travel mode. Based on the above results, two policy improvement suggestions are put forward from reducing public transportation and non-motor vehicle travel time, and the policy effect is evaluated. Before the evaluation, the prediction effect of MNL, SVM and MLP models was evaluated. After parameter optimization, it was found that the prediction accuracy of the three models was 72.80%, 71.42%, and 76.42%, respectively. The MLP model with the highest prediction accuracy was selected to evaluate the effect of policy improvement. The results showed that after the implementation of the policy, the proportion of public transportation in plan 1 and plan 2 increased by 14.04% and 9.86%, respectively, while the proportion of private cars decreased by 3.47% and 2.54%, respectively. The proportion of car trips decreased obviously, while the proportion of public transport trips increased. It can be considered that the measures have a positive effect on promoting green trips and improving the satisfaction of urban residents, and can provide a reference for relevant departments to formulate transportation policies.

Keywords: Travel characteristics analysis, transportation choice, travel sharing rate, neural network model, traffic resource allocation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 622

Authors: Samaneh Nazeri, Bagher Mojazi Amiri, Hamid Farahmand

Abstract:

Production of high quality fish eggs with reasonable hatching rate makes a success in aquaculture industries. It is influenced by the environmental stimulators and inhibitors. Diazinon is a widely-used pesticide in Golestan province (Southern Caspian Sea, North of Iran) which is washed to the aquatic environment (3 mg/L in the river). It is little known about the effect of this pesticide on the embryogenesis of sturgeon fish, the valuable species of the Caspian Sea. Hormonal content of the egg is an important factor to guaranty the successful passes of embryonic stages. In this study, the fate of Persian sturgeon embryo to 24, 48, 72, and 96-hours exposure of diazinon (LC₅₀ dose) was tested. Also, the effect of thyroid hormones (T3 and T4) on these embryos was tested concurrently or separately with diazinon LC ₅₀ dose. Fertilized eggs are exposed to T3 (low dose: 1 ng/ml, high dose: 10 ng/ml), T4 (low dose: 1 ng/ml, high dose: 10 ng/ml). Six eggs were randomly selected from each treatment (with three replicates) in five developmental stages (two cell- division, neural, heart present, heart beaten, and hatched larvae). The possibility of changing T3, T4, and cortisol contents of the embryos were determined in all treated groups and in every mentioned embryonic stage. The hatching rate in treated groups was assayed at the end of the embryogenesis to clarify the effect of thyroid hormones and diazinon. The results indicated significant differences in thyroid hormone contents, but no significant differences were recognized in cortisol levels at various early life stages of embryos. There was also significant difference in thyroid hormones in (T3, T4) + diazinon treated embryos (P˂0.05), while no significant difference between control and treatments in cortisol levels was observed. The highest hatching rate was recorded in HT3 treatment, while the lowest hatching rate was recorded for diazinon LC₅₀ treatment. The result confirmed that Persian sturgeon embryo is less sensitive to diazinon compared to teleost embryos, and thyroid hormones may increase hatching rate even in the presence of diazinon.

Keywords: Persian sturgeon, diazinon, thyroid hormones, cortisol, embryo.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1293

Authors: Brennan Lodge

Abstract:

Amidst a complex regulatory landscape, Retrieval Augmented Generation (RAG) emerges as a transformative tool for Governance Risk and Compliance (GRC) officers. This paper details the application of RAG in synthesizing Large Language Models (LLMs) with external knowledge bases, offering GRC professionals an advanced means to adapt to rapid changes in compliance requirements. While the development for standalone LLMs is exciting, such models do have their downsides. LLMs cannot easily expand or revise their memory, and they cannot straightforwardly provide insight into their predictions, and may produce “hallucinations.” Leveraging a pre-trained seq2seq transformer and a dense vector index of domain-specific data, this approach integrates real-time data retrieval into the generative process, enabling gap analysis and the dynamic generation of compliance and risk management content. We delve into the mechanics of RAG, focusing on its dual structure that pairs parametric knowledge contained within the transformer model with non-parametric data extracted from an updatable corpus. This hybrid model enhances decision-making through context-rich insights, drawing from the most current and relevant information, thereby enabling GRC officers to maintain a proactive compliance stance. Our methodology aligns with the latest advances in neural network fine-tuning, providing a granular, token-level application of retrieved information to inform and generate compliance narratives. By employing RAG, we exhibit a scalable solution that can adapt to novel regulatory challenges and cybersecurity threats, offering GRC officers a robust, predictive tool that augments their expertise. The granular application of RAG’s dual structure not only improves compliance and risk management protocols but also informs the development of compliance narratives with pinpoint accuracy. It underscores AI’s emerging role in strategic risk mitigation and proactive policy formation, positioning GRC officers to anticipate and navigate the complexities of regulatory evolution confidently.

Keywords: Retrieval Augmented Generation, Governance Risk and Compliance, Cybersecurity, AI-driven Compliance, Risk Management, Generative AI.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 133

Authors: Bahar Hazal Yalçınkaya, Bayram Yılmaz, Mustafa Özilgen

Abstract:

Brain information transmission in the neuronal network occurs in the form of electrical signals. Neural work transmits information between the neurons or neurons and target cells by moving charged particles in a voltage field; a fraction of the energy utilized in this process is dissipated via entropy generation. Exergy loss and entropy generation models demonstrate the inefficiencies of the communication along the dendritic trees. In this study, neurons of 4 different animals were analyzed with one dimensional cable model with N=6 identical dendritic trees and M=3 order of symmetrical branching. Each branch symmetrically bifurcates in accordance with the 3/2 power law in an infinitely long cylinder with the usual core conductor assumptions, where membrane potential is conserved in the core conductor at all branching points. In the model, exergy loss and entropy generation rates are calculated for each branch of equivalent cylinders of electrotonic length (L) ranging from 0.1 to 1.5 for four different dendritic branches, input branch (BI), and sister branch (BS) and two cousin branches (BC-1 & BC-2). Thermodynamic analysis with the data coming from two different cat motoneuron studies show that in both experiments nearly the same amount of exergy is lost while generating nearly the same amount of entropy. Guinea pig vagal motoneuron loses twofold more exergy compared to the cat models and the squid exergy loss and entropy generation were nearly tenfold compared to the guinea pig vagal motoneuron model. Thermodynamic analysis show that the dissipated energy in the dendritic tress is directly proportional with the electrotonic length, exergy loss and entropy generation. Entropy generation and exergy loss show variability not only between the vertebrate and invertebrates but also within the same class. Concurrently, single action potential Na⁺ ion load, metabolic energy utilization and its thermodynamic aspect contributed for squid giant axon and mammalian motoneuron model. Energy demand is supplied to the neurons in the form of Adenosine triphosphate (ATP). Exergy destruction and entropy generation upon ATP hydrolysis are calculated. ATP utilization, exergy destruction and entropy generation showed differences in each model depending on the variations in the ion transport along the channels.

Keywords: ATP utilization, entropy generation, exergy loss, neuronal information transmittance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1015

Authors: Maxence Queyrel, Edi Prifti, Alexandre Templier, Jean-Daniel Zucker

Abstract:

Analysis of the human microbiome using metagenomic sequencing data has demonstrated high ability in discriminating various human diseases. Raw metagenomic sequencing data require multiple complex and computationally heavy bioinformatics steps prior to data analysis. Such data contain millions of short sequences read from the fragmented DNA sequences and stored as fastq files. Conventional processing pipelines consist in multiple steps including quality control, filtering, alignment of sequences against genomic catalogs (genes, species, taxonomic levels, functional pathways, etc.). These pipelines are complex to use, time consuming and rely on a large number of parameters that often provide variability and impact the estimation of the microbiome elements. Training Deep Neural Networks directly from raw sequencing data is a promising approach to bypass some of the challenges associated with mainstream bioinformatics pipelines. Most of these methods use the concept of word and sentence embeddings that create a meaningful and numerical representation of DNA sequences, while extracting features and reducing the dimensionality of the data. In this paper we present an end-to-end approach that classifies patients into disease groups directly from raw metagenomic reads: metagenome2vec. This approach is composed of four steps (i) generating a vocabulary of k-mers and learning their numerical embeddings; (ii) learning DNA sequence (read) embeddings; (iii) identifying the genome from which the sequence is most likely to come and (iv) training a multiple instance learning classifier which predicts the phenotype based on the vector representation of the raw data. An attention mechanism is applied in the network so that the model can be interpreted, assigning a weight to the influence of the prediction for each genome. Using two public real-life data-sets as well a simulated one, we demonstrated that this original approach reaches high performance, comparable with the state-of-the-art methods applied directly on processed data though mainstream bioinformatics workflows. These results are encouraging for this proof of concept work. We believe that with further dedication, the DNN models have the potential to surpass mainstream bioinformatics workflows in disease classification tasks.

Keywords: Metagenomics, phenotype prediction, deep learning, embeddings, multiple instance learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 914

Authors: Xiangtuo Chen, Paul-Henry Cournéde

Abstract:

Crop yield prediction is a paramount issue in agriculture. The main idea of this paper is to find out efficient way to predict the yield of corn based meteorological records. The prediction models used in this paper can be classified into model-driven approaches and data-driven approaches, according to the different modeling methodologies. The model-driven approaches are based on crop mechanistic modeling. They describe crop growth in interaction with their environment as dynamical systems. But the calibration process of the dynamic system comes up with much difficulty, because it turns out to be a multidimensional non-convex optimization problem. An original contribution of this paper is to propose a statistical methodology, Multi-Scenarios Parameters Estimation (MSPE), for the parametrization of potentially complex mechanistic models from a new type of datasets (climatic data, final yield in many situations). It is tested with CORNFLO, a crop model for maize growth. On the other hand, the data-driven approach for yield prediction is free of the complex biophysical process. But it has some strict requirements about the dataset. A second contribution of the paper is the comparison of these model-driven methods with classical data-driven methods. For this purpose, we consider two classes of regression methods, methods derived from linear regression (Ridge and Lasso Regression, Principal Components Regression or Partial Least Squares Regression) and machine learning methods (Random Forest, k-Nearest Neighbor, Artificial Neural Network and SVM regression). The dataset consists of 720 records of corn yield at county scale provided by the United States Department of Agriculture (USDA) and the associated climatic data. A 5-folds cross-validation process and two accuracy metrics: root mean square error of prediction(RMSEP), mean absolute error of prediction(MAEP) were used to evaluate the crop prediction capacity. The results show that among the data-driven approaches, Random Forest is the most robust and generally achieves the best prediction error (MAEP 4.27%). It also outperforms our model-driven approach (MAEP 6.11%). However, the method to calibrate the mechanistic model from dataset easy to access offers several side-perspectives. The mechanistic model can potentially help to underline the stresses suffered by the crop or to identify the biological parameters of interest for breeding purposes. For this reason, an interesting perspective is to combine these two types of approaches.

Keywords: Crop yield prediction, crop model, sensitivity analysis, paramater estimation, particle swarm optimization, random forest.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1178

Authors: Mohammad H. Taheri, David J. Brown, Nasser Sherkat

Abstract:

Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.

Keywords: Affective computing in education, affect detection, continuous performance test, engagement, flow, HCI, interaction, learning disabilities, machine learning, multimodal, multisensor, physiological sensors, Signal Detection Theory, student engagement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1266

Authors: Anna Słupik, Anna Mosiołek, Sebastian Wójtowicz, Dariusz Białoszewski

Abstract:

Introduction: Whole-Body Vibration (WBV) uses high frequency mechanical stimuli generated by a vibration plate and transmitted through bone, muscle and connective tissues to the whole body. Research has shown that long-term vibration-plate training improves neuromuscular facilitation, especially in afferent neural pathways, responsible for the conduction of vibration and proprioceptive stimuli, muscle function, balance and proprioception. Some researchers suggest that the vibration stimulus briefly inhibits the conduction of afferent signals from proprioceptors and can interfere with the maintenance of body balance. The aim of this study was to evaluate the influence of a single set of exercises associated with whole-body vibration on the joint position sense and body balance. Material and methods: The study enrolled 55 people aged 19-24 years. These individuals were randomly divided into a test group (30 persons) and a control group (25 persons). Both groups performed the same set of exercises on a vibration plate. The following vibration parameters: frequency of 20Hz and amplitude of 3mm, were used in the test group. The control group performed exercises on the vibration plate while it was off. All participants were instructed to perform six dynamic exercises lasting 30 seconds each with a 60-second period of rest between them. The exercises involved large muscle groups of the trunk, pelvis and lower limbs. Measurements were carried out before and immediately after exercise. Joint position sense (JPS) was measured in the knee joint for the starting position at 45° in an open kinematic chain. JPS error was measured using a digital inclinometer. Balance was assessed in a standing position with both feet on the ground with the eyes open and closed (each test lasting 30 sec). Balance was assessed using Matscan with FootMat 7.0 SAM software. The surface of the ellipse of confidence and front-back as well as right-left swing were measured to assess balance. Statistical analysis was performed using Statistica 10.0 PL software. Results: There were no significant differences between the groups, both before and after the exercise (p> 0.05). JPS did not change in both the test (10.7° vs. 8.4°) and control groups (9.0° vs. 8.4°). No significant differences were shown in any of the test parameters during balance tests with the eyes open or closed in both the test and control groups (p> 0.05). Conclusions: 1. Deterioration in proprioception or balance was not observed immediately after the vibration stimulus. This suggests that vibrationinduced blockage of proprioceptive stimuli conduction can have only a short-lasting effect that occurs only as long as a vibration stimulus is present. 2. Short-term use of vibration in treatment does not impair proprioception and seems to be safe for patients with proprioceptive impairment. 3. These results need to be supplemented with an assessment of proprioception during the application of vibration stimuli. Additionally, the impact of vibration parameters used in the exercises should be evaluated.

Keywords: Balance, joint position sense, proprioception, whole body vibration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1609