Search results for: Artificial Neural network

Authors: John Lachapelle

Abstract:

Introduction: Neural stimulation is increasingly targeted toward treatment of back pain, PTSD, Parkinson’s disease, and for sensory perception. Sensory recording during stimulation is important in order to examine neural response to stimulation. Most neural amplifiers (headstages) focus on noise efficiency factor (NEF). Conversely, neural headstages need to handle artifacts from several sources including power lines, movement (EMG), and neural stimulation itself. In this work a layered approach to artifact rejection is used to reduce corruption of the neural ENG signal by 60dBv, resulting in recovery of sensory signals in rats and primates that would previously not be possible. Methods: The approach combines analog techniques to reduce and handle unwanted signal amplitudes. The methods include optimized (1) sensory electrode placement, (2) amplifier configuration, and (3) artifact blanking when necessary. The techniques together are like concentric moats protecting a castle; only the wanted neural signal can penetrate. There are two conditions in which the headstage operates: unwanted artifact < 50mV, linear operation, and artifact > 50mV, fast-settle gain reduction signal limiting (covered in more detail in a separate paper). Unwanted Signals at the headstage input: Consider: (a) EMG signals are by nature < 10mV. (b) 60 Hz power line signals may be > 50mV with poor electrode cable conditions; with careful routing much of the signal is common to both reference and active electrode and rejected in the differential amplifier with <50mV remaining. (c) An unwanted (to the neural recorder) stimulation signal is attenuated from stimulation to sensory electrode. The voltage seen at the sensory electrode can be modeled Φ_m=I_o/4πσr. For a 1 mA stimulation signal, with 1 cm spacing between electrodes, the signal is <20mV at the headstage. Headstage ASIC design: The front end ASIC design is designed to produce < 1% THD at 50mV input; 50 times higher than typical headstage ASICs, with no increase in noise floor. This requires careful balance of amplifier stages in the headstage ASIC, as well as consideration of the electrodes effect on noise. The ASIC is designed to allow extremely small signal extraction on low impedance (< 10kohm) electrodes with configuration of the headstage ASIC noise floor to < 700nV/rt-Hz. Smaller high impedance electrodes (> 100kohm) are typically located closer to neural sources and transduce higher amplitude signals (> 10uV); the ASIC low-power mode conserves power with 2uV/rt-Hz noise. Findings: The enhanced neural processing ASIC has been compared with a commercial neural recording amplifier IC. Chronically implanted primates at MGH demonstrated the presence of commercial neural amplifier saturation as a result of large environmental artifacts. The enhanced artifact suppression headstage ASIC, in the same setup, was able to recover and process the wanted neural signal separately from the suppressed unwanted artifacts. Separately, the enhanced artifact suppression headstage ASIC was able to separate sensory neural signals from unwanted artifacts in mouse-implanted peripheral intrafascicular electrodes. Conclusion: Optimizing headstage ASICs allow observation of neural signals in the presence of large artifacts that will be present in real-life implanted applications, and are targeted toward human implantation in the DARPA HAPTIX program.

Keywords: ASIC, biosensors, biomedical signal processing, biomedical sensors

Procedia PDF Downloads 326

Authors: Justin Durham, Chanda Rooney, Robert Mather, Mickie Vanhoy

Abstract:

The psychological construct of empathy is to understand a person’s cognitive perspective and experience the other person’s emotional state. Deciphering emotional states is conducive for interpreting vicarious pain. Observing others' physical pain activates neural networks related to the actual experience of pain itself. The study addresses empathy as a nonlinear dynamic process of simulation for individuals to understand the mental states of others and experience vicarious pain, exhibiting self-organized criticality. Such criticality follows from a combination of neural networks with an excitatory feedback loop generating bistability to resonate permutated empathy. Cortical networks exhibit diverse patterns of activity, including oscillations, synchrony and waves, however, the temporal dynamics of neurophysiological activities underlying empathic processes remain poorly understood. Mu rhythms are EEG oscillations with dominant frequencies of 8-13 Hz becoming synchronized when the body is relaxed with eyes open and when the sensorimotor system is in idle, thus, mu rhythm synchrony is expected to be highest in baseline conditions. When the sensorimotor system is activated either by performing or simulating action, mu rhythms become suppressed or desynchronize, thus, should be suppressed while observing video clips of painful injuries if previous research on mirror system activation holds. Twelve undergraduates contributed EEG data and survey responses to empathy and psychopathy scales in addition to watching consecutive video clips of sports injuries. Participants watched a blank, black image on a computer monitor before and after observing a video of consecutive sports injuries incidents. Each video condition lasted five-minutes long. A BIOPAC MP150 recorded EEG signals from sensorimotor and thalamocortical regions related to a complex neural network called the ‘pain matrix’. Physical and social pain are activated in this network to resonate vicarious pain responses to processing empathy. Five EEG single electrode locations were applied to regions measuring sensorimotor electrical activity in microvolts (μV) to monitor mu rhythms. EEG signals were sampled at a rate of 200 Hz. Mu rhythm desynchronization was measured via 8-13 Hz at electrode sites (F3 & F4). Data for each participant’s mu rhythms were analyzed via Fast Fourier Transformation (FFT) and multifractal time series analysis.

Keywords: desynchronization, dynamical systems theory, electroencephalography (EEG), empathy, multifractal time series analysis, mu waveform, neurophysiology, pain simulation, social cognition

Procedia PDF Downloads 280

Authors: Saulius Minkevicius, Edvinas Greicius

Abstract:

The paper is devoted to the analysis of queueing systems in the context of the network and communications theory. We investigate the inequality in an open queueing network and its applications to the theorems in heavy traffic conditions (fluid approximation, functional limit theorem, and law of the iterated logarithm) for a queue of customers in an open queueing network.

Keywords: fluid approximation, heavy traffic, models of information systems, open queueing network, queue length of customers, queueing theory

Procedia PDF Downloads 282

Authors: Manpreet Kaur, Amita Rani, Sanjay Kumar

Abstract:

The Internet of Things (IoT), a cyber-physical paradigm, allows a large number of devices to connect and send the sensory data in the network simultaneously. This tremendous amount of data generated leads to very high network load consequently resulting in network congestion. It further amounts to frequent loss of useful information and depletion of significant amount of nodes’ energy. Therefore, there is a need to control congestion in IoT so as to prolong network lifetime and improve the quality of service (QoS). Hence, we propose a two-level clustering based routing algorithm considering congestion score and packet priority metrics that focus on minimizing the network congestion. In the proposed Priority based Congestion Control (PBCC) protocol the sensor nodes in IoT network form clusters that reduces the amount of traffic and the nodes are prioritized to emphasize important data. Simultaneously, a congestion score determines the occurrence of congestion at a particular node. The proposed protocol outperforms the existing Packet Discard Network Clustering (PDNC) protocol in terms of buffer size, packet transmission range, network region and number of nodes, under various simulation scenarios.

Keywords: internet of things, cyber-physical systems, congestion control, priority, transmission rate

Procedia PDF Downloads 303

Authors: Che Z. Zulkifli, Nursyahida M. Noor, Siti N. Semunab, Shafawati A. Malek

Abstract:

Wireless sensors, also known as wireless sensor nodes, have been making a significant impact on human daily life. The Radio Frequency Identification (RFID) and Wireless Sensor Network (WSN) are two complementary technologies; hence, an integrated implementation of these technologies expands the overall functionality in obtaining long-range and real-time information on the location and properties of objects and people. An approach for integrating ZigBee and RFID networks is proposed in this paper, to create an energy-efficient network improved by the benefits of combining ZigBee and RFID architecture. Furthermore, the compatibility and requirements of the ZigBee device and communication links in the typical RFID system which is presented with the real world experiment on the capabilities of the proposed RFID system.

Keywords: mesh network, RFID, wireless sensor network, zigbee

Procedia PDF Downloads 453

Authors: Contimi Kenfack Mouafo, Sebastian Klick

Abstract:

In the rural and remote areas of Cameroon, access to electricity is very limited since most of the population is not connected to the main utility grid. Throughout the country, efforts are underway to not only expand the utility grid to these regions but also to provide reliable off-grid access to electricity. The Cameroonian company Solahydrowatt is currently working on the design and planning of one of the first hybrid solar-hydropower plants of Cameroon in Fotetsa, in the western region of the country, to provide the population with reliable access to electricity. This paper models and proposes a design for the low-voltage network with a hybrid solar-hydropower plant in Fotetsa. The modelling takes into consideration the voltage compliance of the distribution network, the maximum load of operating equipment, and most importantly, the ability for the network to operate as an off-grid system. The resulting modelled distribution network does not only comply with the Cameroonian voltage deviation standard, but it is also capable of being operated as a stand-alone network independent of the main utility grid.

Keywords: Cameroon, rural electrification, hybrid solar-hydro, off-grid electricity supply, network simulation

Procedia PDF Downloads 117

Authors: Pranav Gunhal., Krish Jhurani

Abstract:

This study tackles the significant computational challenge of predicting excited state dynamics in organic photovoltaic (OPV) materials—a pivotal factor in the performance of solar energy solutions. Time-dependent density functional theory (TDDFT), though effective, is computationally prohibitive for larger and more complex molecules. As a solution, the research explores the application of transformer neural networks, a type of artificial intelligence (AI) model known for its superior performance in natural language processing, to predict excited state dynamics in OPV materials. The methodology involves a two-fold process. First, the transformer model is trained on an extensive dataset comprising over 10,000 TDDFT calculations of excited state dynamics from a diverse set of OPV materials. Each training example includes a molecular structure and the corresponding TDDFT-calculated excited state lifetimes and key electronic transitions. Second, the trained model is tested on a separate set of molecules, and its predictions are rigorously compared to independent TDDFT calculations. The results indicate a remarkable degree of predictive accuracy. Specifically, for a test set of 1,000 OPV materials, the transformer model predicted excited state lifetimes with a mean absolute error of 0.15 picoseconds, a negligible deviation from TDDFT-calculated values. The model also correctly identified key electronic transitions contributing to the excited state dynamics in 92% of the test cases, signifying a substantial concordance with the results obtained via conventional quantum chemistry calculations. The practical integration of the transformer model with existing quantum chemistry software was also realized, demonstrating its potential as a powerful tool in the arsenal of materials scientists and chemists. The implementation of this AI model is estimated to reduce the computational cost of predicting excited state dynamics by two orders of magnitude compared to conventional TDDFT calculations. The successful utilization of transformer neural networks to accurately predict excited state dynamics provides an efficient computational pathway for the accelerated discovery and design of new OPV materials, potentially catalyzing advancements in the realm of sustainable energy solutions.

Keywords: transformer neural networks, organic photovoltaic materials, excited state dynamics, time-dependent density functional theory, predictive modeling

Procedia PDF Downloads 110

Authors: Noman Shabbir, Roheel Nawaz, Muhammad N. Iqbal, Junaid Zafar

Abstract:

This paper focuses on the performance evaluation of routing protocols in WLAN based Wireless Sensor Networks (WSNs). A comparative analysis of routing protocols such as Ad-hoc On-demand Distance Vector Routing System (AODV), Dynamic Source Routing (DSR) and Optimized Link State Routing (OLSR) is been made against different network parameters like network load, end to end delay and throughput in small, medium and large-scale sensor network scenarios to identify the best performing protocol. Simulation results indicate that OLSR gives minimum network load in all three scenarios while AODV gives the best throughput in small scale network but in medium and large scale networks, DSR is better. In terms of delay, OLSR is more efficient in small and medium scale network while AODV is slightly better in large networks.

Keywords: WLAN, WSN, AODV, DSR, OLSR

Procedia PDF Downloads 443

Authors: Skiker Kaoutar, Mounir Maouene

Abstract:

Neuroimaging studies indicate that a large fronto-parieto-temporal network support nouns and their features, with some areas store semantic knowledge (visual, auditory, olfactory, gustatory,…), other areas store lexical representation and other areas are implicated in general semantic processing. However, it is not well understood how this fronto-parieto-temporal network can be modulated by different semantic tasks and different semantic relations between nouns. In this study, we combine a behavioral semantic network, functional MRI studies involving object’s related nouns and brain network studies to explain how different semantic tasks and different semantic relations between nouns can modulate the activity within the brain network of nouns and their features. We first describe how nouns and their features form a large scale brain network. For this end, we examine the connectivities between areas recruited during the processing of nouns to know which configurations of interaction areas are possible. We can thus identify if, for example, brain areas that store semantic knowledge communicate via functional/structural links with areas that store lexical representations. Second, we examine how this network is modulated by different semantic tasks involving nouns and finally, we examine how category specific activation may result from the semantic relations among nouns. The results indicate that brain network of nouns and their features is highly modulated and flexible by different semantic tasks and semantic relations. At the end, this study can be used as a guide to help neurosientifics to interpret the pattern of fMRI activations detected in the semantic processing of nouns. Specifically; this study can help to interpret the category specific activations observed extensively in a large number of neuroimaging studies and clinical studies.

Keywords: nouns, features, network, category specificity

Procedia PDF Downloads 514

Authors: Dereje Ferede, Solomon Negash

Abstract:

Artificial Intelligence (AI) is a key enabler and driver to transform and revolutionize the healthcare industries. However, utilizing AI and achieving these benefits is challenging for different sectors in wide-ranging, more difficult for developing economy healthcare. Due to this, real-world clinical execution and implementation of AI have not yet aged. We believe that examining the determinants is key to addressing these challenges. Furthermore, the literature does not yet particularize determinants of AI capabilities and ways of empowering the healthcare ecosystem to develop AI capabilities in a developing economy. Thus, this study aims to position AI as a digital transformation weapon for the healthcare ecosystem by examining AI capability determinants and providing insights on better empowering the healthcare industry to develop AI capabilities. To do so, we base on the technology-organization-environment (TOE) model and will apply a mixed research approach. We will conclude with recommendations based on findings for future practitioners and researchers.

Keywords: artificial intelligence, capability, digital transformation, developing economies, healthcare

Procedia PDF Downloads 223

Authors: M. Yoneda

Abstract:

In this paper, a lateral walking design force per person is proposed and compared with Imperial College test results. Numerical simulations considering the proposed walking design force which is incorporated into the neural-oscillator model are carried out placing much emphasis on the synchronization (the lock-in phenomenon) for a pedestrian bridge model with the span length of 50 m. Numerical analyses are also conducted for an existing pedestrian suspension bridge. As compared with full scale measurements for this suspension bridge, it is confirmed that the analytical method based on the neural-oscillator model might be one of the useful ways to explain the synchronization (the lock-in phenomenon) of pedestrians being on the bridge.

Keywords: pedestrian bridge, human-induced lateral vibration, neural-oscillator, full scale measurement, dynamic response analysis

Procedia PDF Downloads 197

Authors: Natalie Riley, Anita Quigley, Robert M. I. Kapsa, George W. Greene

Abstract:

As the fields of medicine and bionics grow rapidly in technological advancement, the future and success of it depends on the ability to effectively interface between the artificial and the biological worlds. The biggest obstacle when it comes to implantable, electronic medical devices, is maintaining a ‘clean’, low noise electrical connection that allows for efficient sharing of electrical information between the artificial and biological systems. Implant fouling occurs with the adhesion and accumulation of proteins and various cell types as a result of the immune response to protect itself from the foreign object, essentially forming an electrical insulation barrier that often leads to implant failure over time. Lubricin (LUB) functions as a major boundary lubricant in articular joints, a unique glycoprotein with impressive anti-adhesive properties that self-assembles to virtually any substrate to form a highly ordered, ‘telechelic’ polymer brush. LUB does not passivate electroactive surfaces which makes it ideal, along with its innate biocompatibility, as a coating for implantable bionic electrodes. It is the aim of the study to investigate LUB’s anti-fouling properties and its potential as a safe, bioinspired material for coating applications to enhance the performance and longevity of implantable medical devices as well as reducing the frequency of implant replacement surgeries. Native, bovine-derived LUB (N-LUB) and recombinant LUB (R-LUB) were applied to gold-coated mylar surfaces. Fibroblast, chondrocyte and neural cell types were cultured and grown on the coatings under both passive and electrically stimulated conditions to test the stability and anti-adhesive property of the LUB coating in the presence of an electric field. Lactate dehydrogenase (LDH) assays were conducted as a directly proportional cell population count on each surface along with immunofluorescent microscopy to visualize cells. One-way analysis of variance (ANOVA) with post-hoc Tukey’s test was used to test for statistical significance. Under both passive and electrically stimulated conditions, LUB significantly reduced cell attachment compared to bare gold. Comparing the two coating types, R-LUB reduced cell attachment significantly compared to its native counterpart. Immunofluorescent micrographs visually confirmed LUB’s antiadhesive property, R-LUB consistently demonstrating significantly less attached cells for both fibroblasts and chondrocytes. Preliminary results investigating neural cells have so far demonstrated that R-LUB has little effect on reducing neural cell attachment; the study is ongoing. Recombinant LUB coatings demonstrated impressive anti-adhesive properties, reducing cell attachment in fibroblasts and chondrocytes. These findings and the availability of recombinant LUB brings into question the results of previous experiments conducted using native-derived LUB, its potential not adequately represented nor realized due to unknown factors and impurities that warrant further study. R-LUB is stable and maintains its anti-fouling property under electrical stimulation, making it suitable for electroactive surfaces.

Keywords: anti-fouling, bioinspired, cell attachment, lubricin

Procedia PDF Downloads 118

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo Ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring. SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, polarimetric SAR image, convolutional neural network, deep learnig, deep neural network

Procedia PDF Downloads 65

Authors: Sevde Altuntas, Fatih Buyukserin

Abstract:

Alzheimer’s disease is responsible for irreversible neural damage of brain parts. One of the disease markers is Amyloid-β 1-42 protein that accumulates in the brain in the form plaques. The basic problem for detection of the protein is the low amount of protein that cannot be detected properly in body liquids such as blood, saliva or urine. To solve this problem, tests like ELISA or PCR are proposed which are expensive, require specialized personnel and can contain complex protocols. Therefore, Surface-enhanced Raman Spectroscopy (SERS) a good candidate for detection of Amyloid-β 1-42 protein. Because the spectroscopic technique can potentially allow even single molecule detection from liquid and solid surfaces. Besides SERS signal can be improved by using nanopattern surface and also is specific to molecules. In this context, our study proposes to fabricate diagnostic test models that utilize Au-coated nanopatterned polycarbonate (PC) surfaces modified with Thioflavin - T to detect low concentrations of Amyloid-β 1-42 protein in water and artificial saliva medium by the enhancement of protein SERS signal. The nanopatterned PC surface that was used to enhance SERS signal was fabricated by using Anodic Alumina Membranes (AAM) as a template. It is possible to produce AAMs with different column structures and varying thicknesses depending on voltage and anodization time. After fabrication process, the pore diameter of AAMs can be arranged with dilute acid solution treatment. In this study, two different columns structures were prepared. After a surface modification to decrease their surface energy, AAMs were treated with PC solution. Following the solvent evaporation, nanopatterned PC films with tunable pillared structures were peeled off from the membrane surface. The PC film was then modified with Au and Thioflavin-T for the detection of Amyloid-β 1-42 protein. The protein detection studies were conducted first in water via this biosensor platform. Same measurements were conducted in artificial saliva to detect the presence of Amyloid Amyloid-β 1-42 protein. SEM, SERS and contact angle measurements were carried out for the characterization of different surfaces and further demonstration of the protein attachment. SERS enhancement factor calculations were also completed via experimental results. As a result, our research group fabricated diagnostic test models that utilize Au-coated nanopatterned polycarbonate (PC) surfaces modified with Thioflavin-T to detect low concentrations of Alzheimer’s Amiloid – β protein in water and artificial saliva medium. This work was supported by The Scientific and Technological Research Council of Turkey (TUBITAK) Grant No: 214Z167.

Keywords: alzheimer, anodic aluminum oxide, nanotopography, surface enhanced Raman spectroscopy

Procedia PDF Downloads 285

Authors: A. Degale Desta, Cheng Jian

Abstract:

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

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

Procedia PDF Downloads 153

Authors: Ashish Jaiswal, Ashwin Ramesh Babu, Mohammad Zaki Zadeh, Fillia Makedon, Glenn Wylie

Abstract:

Functional magnetic resonance imaging (fMRI) is a neuroimaging technique that records neural activations in the brain by capturing the blood oxygen level in different regions based on the task performed by a subject. Given fMRI data, the problem of predicting the state of cognitive fatigue in a person has not been investigated to its full extent. This paper proposes tackling this issue as a multi-class classification problem by dividing the state of cognitive fatigue into six different levels, ranging from no-fatigue to extreme fatigue conditions. We built a spatio-temporal model that uses convolutional neural networks (CNN) for spatial feature extraction and a long short-term memory (LSTM) network for temporal modeling of 4D fMRI scans. We also applied a self-supervised method called MoCo (Momentum Contrast) to pre-train our model on a public dataset BOLD5000 and fine-tuned it on our labeled dataset to predict cognitive fatigue. Our novel dataset contains fMRI scans from Traumatic Brain Injury (TBI) patients and healthy controls (HCs) while performing a series of N-back cognitive tasks. This method establishes a state-of-the-art technique to analyze cognitive fatigue from fMRI data and beats previous approaches to solve this problem.

Keywords: fMRI, brain imaging, deep learning, self-supervised learning, contrastive learning, cognitive fatigue

Procedia PDF Downloads 181

Authors: Chaudhary Muhammad Aqdus Ilyas, Matthias Rehm, Kamal Nasrollahi, Thomas B. Moeslund

Abstract:

This paper presents the investigation of data collection procedures, associated with robots when placed with traumatic brain injured (TBI) patients for rehabilitation purposes through facial expression and mood analysis. Rehabilitation after TBI is very crucial due to nature of injury and variation in recovery time. It is advantageous to analyze these emotional signals in a contactless manner, due to the non-supportive behavior of patients, limited muscle movements and increase in negative emotional expressions. This work aims at the development of framework where robots can recognize TBI emotions through facial expressions to perform rehabilitation tasks by physical, cognitive or interactive activities. The result of these studies shows that with customized data collection strategies, proposed framework identify facial and emotional expressions more accurately that can be utilized in enhancing recovery treatment and social interaction in robotic context.

Keywords: computer vision, convolution neural network- long short term memory network (CNN-LSTM), facial expression and mood recognition, multimodal (RGB-thermal) analysis, rehabilitation, robots, traumatic brain injured patients

Procedia PDF Downloads 146

Authors: Katharina M. Rischer, Angelika Dierolf, Ana M. Gonzalez-Roldan, Pedro Montoya, Fernand Anton, Marian van der Meulen

Abstract:

Even though age has been associated with increased and prolonged episodes of pain, little is known about potential age-related changes in the ˈtop-downˈ modulation of pain, such as cognitive distraction from pain. The analgesic effects of distraction result from competition for attentional resources in the prefrontal cortex (PFC), a region that is also involved in executive functions. Given that the PFC shows pronounced age-related atrophy, distraction may be less effective in reducing pain in older compared to younger adults. The aim of this study was to investigate the influence of aging on task-related analgesia and the underpinning neural mechanisms, with a focus on the role of executive functions in distraction from pain. In a first session, 64 participants (32 young adults: 26.69 ± 4.14 years; 32 older adults: 68.28 ± 7.00 years) completed a battery of neuropsychological tests. In a second session, participants underwent a pain distraction paradigm, while fMRI images were acquired. In this paradigm, participants completed a low (0-back) and a high (2-back) load condition of a working memory task while receiving either warm or painful thermal stimuli to their lower arm. To control for age-related differences in sensitivity to pain and perceived task difficulty, stimulus intensity, and task speed were individually calibrated. Results indicate that both age groups showed significantly reduced activity in a network of regions involved in pain processing when completing the high load distraction task; however, young adults showed a larger neural distraction effect in different parts of the insula and the thalamus. Moreover, better executive functions, in particular inhibitory control abilities, were associated with a larger behavioral and neural distraction effect. These findings clearly demonstrate that top-down control of pain is affected in older age, and could explain the higher vulnerability for older adults to develop chronic pain. Moreover, our findings suggest that the assessment of executive functions may be a useful tool for predicting the efficacy of cognitive pain modulation strategies in older adults.

Keywords: executive functions, cognitive pain modulation, fMRI, PFC

Procedia PDF Downloads 139

Authors: Subhash Reddy

Abstract:

Mobile communication in today’s world means a lot to the human kind, through this many deals are made and others are broken, within seconds. That is because of our sophisticated methods of transporting the data at very high speeds and to very long distances, within no time. That is also because we kept on changing the method of serving the connections as the no of connections kept on increasing, that has led to many methods like TDMA, CDMA, and FDMA, etc. in wireless communications. And also the areas, where the connections are provided are also divided into CELLS, which are the basic blocks for cellular communications. Along with the wireless network, providing a wired network in mobile phones would serve as a very good alternative and would divert the extra traffic of a cell, so that a CELL which is providing wireless network can operate more efficiently.

Keywords: CDMA, FDMA, TDMA, CELL

Procedia PDF Downloads 483

Authors: Yinghui Shang, Ziqing Zhou, Rong Han, Hang Wang, Xiaodi Liu, Yong Yang

Abstract:

The design of advanced amorphous solids, such as metallic glasses, with targeted properties through artificial intelligence signifies a paradigmatic shift in physical metallurgy and materials technology. Here, we developed a machine-learning architecture that facilitates the generation of metallic glasses with targeted multifunctional properties. Our architecture integrates the state-of-the-art unsupervised generative adversarial network model with supervised models, allowing the incorporation of general prior knowledge derived from thousands of data points across a vast range of alloy compositions, into the creation of data points for a specific type of composition, which overcame the common issue of data scarcity typically encountered in the design of a given type of metallic glasses. Using our generative model, we have successfully designed copper-based metallic glasses, which display exceptionally high hardness or a remarkably low modulus. Notably, our architecture can not only explore uncharted regions in the targeted compositional space but also permits self-improvement after experimentally validated data points are added to the initial dataset for subsequent cycles of data generation, hence paving the way for the customized design of amorphous solids without human intervention.

Keywords: metallic glass, artificial intelligence, mechanical property, automated generation

Procedia PDF Downloads 48

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring . SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, deep learning, convolutional neural network, deep neural network, SAR polarimetry

Procedia PDF Downloads 84

Authors: Tammam A. Benmusa, Mohamed A. Shlibek, Rawad M. Swesi

Abstract:

The investigation of Buildings Penetration Loss (BPL) of radio signal is getting more and more important. It plays an important role in calculating the indoor coverage for wireless communication networks. In this paper, the theory behind BPL and its mechanisms have been reviewed. The operating frequency, coverage area type, climate condition, time of measurement, and other factors affecting the values of BPL have been discussed. The practical part of this work was conducting 4000 measurements of BPL in different areas in the Libyan capital, Tripoli, to get empirical model for this loss. The measurements were taken for 2 different types of wireless communication networks; mobile telephone network (for Almadar company), which operates at 900 MHz and WiMAX network (LTT company) which operates at 2500 MHz. The results for each network were summarized and presented in several graphs. The graphs are showing how the BPL affected by: time of measurement, morphology (type of area), and climatic environment.

Keywords: building penetration loss, wireless network, mobile network, link budget, indoor network performance

Procedia PDF Downloads 374

Authors: Sawsan Eissa, Momen Gharib, Omnia Kabbany

Abstract:

A flushing numerical study has been performed for intended artificial islands on the Persian Gulf coast in Abu Dhabi, UAE. The island masterplan was tested for flushing using the DELFT 3D hydrodynamic model, and it was found that its residence time exceeds the acceptable PIANC flushing Criteria. Therefore, a number of mitigation measures were applied and tested one by one using the flushing model. Namely, changing the location of the entrance opening, dredging, removing part of the mangrove existing in the near vicinity to create a channel, removing the mangrove altogether, using culverts of different numbers and locations, and pumping at selected points. The pumping option gave the best solution, but it was disregarded due to high capital and running costs. Therefore, it opted for a combination of other solutions, including removing mangroves, introducing culverts, and adjusting island boundaries and types of protection.

Keywords: hydrodynamics, flushing, delft 3d, Persian Gulf, artificial islands.

Procedia PDF Downloads 49

Authors: Joseph Uzuazomaro Oju

Abstract:

The ease at which manipulated media can be created, and the increasing difficulty in identifying fake media makes it a great threat. Most of the applications used for the creation of these high-quality fake videos and images are built with deep learning. Hence, the use of deep learning in creating a detection mechanism cannot be overemphasized. Any successful fake media that is being detected before it reached the populace will save people from the self-doubt of either a content is genuine or fake and will ensure the credibility of videos and images. The methodology introduced in this paper approaches the manipulated media detection challenge using a combo of VGG-19 and a deep capsule network. In the case of videos, they are converted into frames, which, in turn, are resized and cropped to the face region. These preprocessed images/videos are fed to the VGG-19 network to extract the latent features. The extracted latent features are inputted into a deep capsule network enhanced with a 3D -convolution dynamic routing agreement. The 3D –convolution dynamic routing agreement algorithm helps to reduce the linkages between capsules networks. Thereby limiting the poor learning shortcoming of multiple capsule network layers. The resultant output from the deep capsule network will indicate a media to be either genuine or fake.

Keywords: deep capsule network, dynamic routing, fake media detection, manipulated media

Procedia PDF Downloads 126

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 335

Authors: Amartya Hatua, Trung Nguyen, Andrew Sung

Abstract:

In this paper, we study the information diffusion process on Twitter as a multivariate time series problem. Our model concerns three measures (volume, network influence, and sentiment of tweets) based on 10 features, and we collected 27 million tweets to build our information diffusion time series dataset for analysis. Then, different time series clustering techniques with Dynamic Time Warping (DTW) distance were used to identify different patterns of information diffusion. Finally, we built the information diffusion prediction models for new hashtags which comprise two phrases: The first phrase is recognizing the pattern using k-NN with DTW distance; the second phrase is building the forecasting model using the traditional Autoregressive Integrated Moving Average (ARIMA) model and the non-linear recurrent neural network of Long Short-Term Memory (LSTM). Preliminary results of performance evaluation between different forecasting models show that LSTM with clustering information notably outperforms other models. Therefore, our approach can be applied in real-world applications to analyze and predict the information diffusion characteristics of selected topics or memes (hashtags) in Twitter.

Keywords: ARIMA, DTW, information diffusion, LSTM, RNN, time series clustering, time series forecasting, Twitter

Procedia PDF Downloads 388

Authors: Dweepabiswa Bagchi, D. V. Senthilkumar

Abstract:

Numerous studies have typically demonstrated the devastation of invasions on an isolated ecosystem or, at most, a network of dispersively coupled similar ecosystem patches. Using such a simplistic 2-D network model, one can only consider dispersal coupling and inter-species trophic interactions. However, in a realistic ecosystem, numerous species co-exist and interact trophically and non-trophically in groups of 2 or more. Even different types of dispersal can introduce complexity in an ecological network. Therefore, a more accurate representation of actual ecosystems (or ecological networks) is a complex network consisting of motifs formed by two or more interacting species. Here, the apropos structure of the network should be multiplex or multi-layered. Motifs between different patches or species should be identical within the same layer and vary from one layer to another. This study investigates three distinct ecological multiplex networks facing invasion from one or more external species. This work determines and quantifies the criteria for the increased extinction risk of these networks. The dynamical states of the network with high extinction risk, i.e., the danger states, and those with low extinction risk, i.e., the resistive network states, are both subsequently identified. The analysis done in this study further quantifies the persistence of the entire network corresponding to simultaneous changes in the strength of invasive dispersal and higher-order trophic and non-trophic interactions. This study also demonstrates that the ecosystems enjoy an inherent advantage against invasions due to their multiplex network structure.

Keywords: increased ecosystem persistence, invasion on ecosystems, multiplex networks, non-trophic interactions

Procedia PDF Downloads 59

Authors: Susan Diamond

Abstract:

Machine Learning workloads have traditionally been run in high-performance computing (HPC) environments, where users log in to dedicated machines and utilize the attached GPUs to run training jobs on huge datasets. Training of large neural network models is very resource intensive, and even after exploiting parallelism and accelerators such as GPUs, a single training job can still take days. Consequently, the cost of hardware is a barrier to entry. Even when upfront cost is not a concern, the lead time to set up such an HPC environment takes months from acquiring hardware to set up the hardware with the right set of firmware, software installed and configured. Furthermore, scalability is hard to achieve in a rigid traditional lab environment. Therefore, it is slow to react to the dynamic change in the artificial intelligent industry. Watson Deep Learning as a service, a cloud-based deep learning platform that mitigates the long lead time and high upfront investment in hardware. It enables robust and scalable sharing of resources among the teams in an organization. It is designed for on-demand cloud environments. Providing a similar user experience in a multi-tenant cloud environment comes with its own unique challenges regarding fault tolerance, performance, and security. Watson Deep Learning as a service tackles these challenges and present a deep learning stack for the cloud environments in a secure, scalable and fault-tolerant manner. It supports a wide range of deep-learning frameworks such as Tensorflow, PyTorch, Caffe, Torch, Theano, and MXNet etc. These frameworks reduce the effort and skillset required to design, train, and use deep learning models. Deep Learning as a service is used at IBM by AI researchers in areas including machine translation, computer vision, and healthcare. 

Keywords: deep learning, machine learning, cognitive computing, model training

Procedia PDF Downloads 204

Authors: Mernoosh Abouzari, Shahrokh Sahraei

Abstract:

Electronic government is a way for governments to use new technology that provides people with the necessary facilities for proper access to government information and services, improving the quality of services and providing broad opportunities to participate in democratic processes and institutions. That leads to providing the possibility of easy use of information technology in order to distribute government services to the customer without holidays, which increases people's satisfaction and participation in political and economic activities. The expansion of e-government services and its movement towards intelligentization has the ability to re-establish the relationship between the government and citizens and the elements and components of the government. Electronic government is the result of the use of information and communication technology (ICT), which by implementing it at the government level, in terms of the efficiency and effectiveness of government systems and the way of providing services, tremendous commercial changes are created, which brings people's satisfaction at the wide level will follow. The main level of electronic government services has become objectified today with the presence of artificial intelligence systems, which recent advances in artificial intelligence represent a revolution in the use of machines to support predictive decision-making and Classification of data. With the use of deep learning tools, artificial intelligence can mean a significant improvement in the delivery of services to citizens and uplift the work of public service professionals while also inspiring a new generation of technocrats to enter government. This smart revolution may put aside some functions of the government, change its components, and concepts such as governance, policymaking or democracy will change in front of artificial intelligence technology, and the top-down position in governance may face serious changes, and If governments delay in using artificial intelligence, the balance of power will change and private companies will monopolize everything with their pioneering in this field, and the world order will also depend on rich multinational companies and in fact, Algorithmic systems will become the ruling systems of the world. It can be said that currently, the revolution in information technology and biotechnology has been started by engineers, large economic companies, and scientists who are rarely aware of the political complexities of their decisions and certainly do not represent anyone. Therefore, it seems that if liberalism, nationalism, or any other religion wants to organize the world of 2050, it should not only rationalize the concept of artificial intelligence and complex data algorithm but also mix them in a new and meaningful narrative. Therefore, the changes caused by artificial intelligence in the political and economic order will lead to a major change in the way all countries deal with the phenomenon of digital globalization. In this paper, while debating the role and performance of e-government, we will discuss the efficiency and application of artificial intelligence in e-government, and we will consider the developments resulting from it in the new world and the concepts of governance.

Keywords: electronic government, artificial intelligence, information and communication technology., system

Procedia PDF Downloads 92

Authors: Hamid R. Lashgarian Azad, Seyed N. Shetab Boushehri

Abstract:

Wireless sensor networks (WSN) have become progressively popular due to their wide range of applications. Wireless Sensor Network is made of numerous tiny sensor nodes that are battery-powered. It is a very significant problem to maximize the lifetime of wireless sensor networks. In this paper, we propose a two-stage protocol based on an imperialist competitive algorithm (2S-ICA) to solve a sensor network optimization problem. The energy of the sensors can be greatly reduced and the lifetime of the network reduced by long communication distances between the sensors and the sink. We can minimize the overall communication distance considerably, thereby extending the lifetime of the network lifetime through connecting sensors into a series of independent clusters using 2SICA. Comparison results of the proposed protocol and LEACH protocol, which is common to solving WSN problems, show that our protocol has a better performance in terms of improving network life and increasing the number of transmitted data.

Keywords: wireless sensor network, imperialist competitive algorithm, LEACH protocol, k-means clustering

Procedia PDF Downloads 96