Search results for: neural electrodes

Authors: Radhamanohar Aepuru, R. V. Mangalaraja

Abstract:

Flexible electronic devices have drawn potential interest and provide significant new insights to develop energy conversion and storage devices such as photodetectors and nanogenerators. Recently, self-powered electronic systems have captivated huge attention for next generation MEMS/NEMS devices that can operate independently by generating built-in field without any need of external bias voltage and have wide variety of applications in telecommunication, imaging, environmental and defence sectors. The basic physical process involved in these devices are charge generation, separation, and charge flow across the electrodes. Many inorganic nanostructures have been exploring to fabricate various optoelectronic and electromechanical devices. However, the interaction of nanostructures and their excited charge carrier dynamics, photoinduced charge separation, and fast carrier mobility are yet to be studied. The proposed research is to address one such area and to realize the self-powered electronic devices. In the present work, nanocomposites of inorganic nanostructures based on ZnO, metal halide perovskites; and polyvinylidene fluoride (PVDF) based nanocomposites are realized for photodetectors and nanogenerators. The characterization of the inorganic nanostructures is carried out through steady state optical absorption and luminescence spectroscopies as well as X-ray diffraction and high-resolution transmission electron microscopy (TEM) studies. The detailed carrier dynamics is investigated using various spectroscopic techniques. The developed composite nanostructures exhibit significant optical and electrical properties, which have wide potential applications in various MEMS/NEMS devices such as photodetectors and nanogenerators.

Keywords: dielectrics, nanocomposites, nanogenerators, photodetectors

Procedia PDF Downloads 130

Authors: Beata Zima, Octavio A. Márquez Reyes, Masoud Mohammadgholiha, Jochen Moll, Luca de Marchi

Abstract:

This document presents the approach of using compressed sensing in signal encoding and information transferring within a guided wave sensor network, comprised of specially designed frequency steerable acoustic transducers (FSATs). Wave propagation in a damaged plate was simulated using commercial FEM-based software COMSOL. Guided waves were excited by means of FSATs, characterized by the special shape of its electrodes, and modeled using PIC255 piezoelectric material. The special shape of the FSAT, allows for focusing wave energy in a certain direction, accordingly to the frequency components of its actuation signal, which makes available a larger monitored area. The process begins when a FSAT detects and records reflection from damage in the structure, this signal is then encoded and prepared for transmission, using a combined approach, based on Compressed Sensing Matching Pursuit and Quadrature Amplitude Modulation (QAM). After codification of the signal is in binary chars the information is transmitted between the nodes in the network. The message reaches the last node, where it is finally decoded and processed, to be used for damage detection and localization purposes. The main aim of the investigation is to determine the location of detected damage using reconstructed signals. The study demonstrates that the special steerable capabilities of FSATs, not only facilitate the detection of damage but also permit transmitting the damage information to a chosen area in a specific direction of the investigated structure.

Keywords: data compression, ultrasonic communication, guided waves, FEM analysis

Procedia PDF Downloads 125

Authors: Guezouli Larbi, Belkacem Soundes

Abstract:

The automation of the text detection process can help the human in his driving task. Its application can be very useful to help drivers to have more information about their environment by facilitating the reading of road signs such as directional signs, events, stores, etc. In this paper, a system consisting of two stages has been proposed. In the first one, we used pseudo-Zernike moments to pinpoint areas of the image that may contain text. The architecture of this part is based on three main steps, region of interest (ROI) detection, text localization, and non-text region filtering. Then, in the second step, we present a convolutional neural network architecture (On-Road Text Detection Network - ORTDN) which is considered a classification phase. The results show that the proposed framework achieved ≈ 35 fps and an mAP of ≈ 90%, thus a low computational time with competitive accuracy.

Keywords: text detection, CNN, PZM, deep learning

Procedia PDF Downloads 84

Authors: Vedant Vardhan Rathour, Anant Agrawal

Abstract:

The project aims to provide a touchless, intuitive interface for human-computer interaction, enabling users to control their computer using hand gestures and voice commands. The system leverages advanced computer vision techniques using the MediaPipe framework and OpenCV to detect and interpret real time hand gestures, transforming them into mouse actions such as clicking, dragging, and scrolling. Additionally, the integration of a voice assistant powered by the Speech Recognition library allows for seamless execution of tasks like web searches, location navigation and gesture control on the system through voice commands.

Keywords: gesture recognition, hand tracking, machine learning, convolutional neural networks

Procedia PDF Downloads 18

Authors: Boris M. Fedorov, Liudmila P. Goncharenko, Sergey A. Sybachin, Natalia A. Mamedova, Ekaterina V. Makarenkova, Saule Rakhimova

Abstract:

In modern economic conditions, the question of the possibility of correct recognition of a signature on digital documents in order to verify the expression of will or confirm a certain operation is relevant. The additional complexity of processing lies in the dynamic variability of the signature for each individual, as well as in the way information is processed because the signature refers to biometric data. The article discusses the issues of using artificial intelligence models in order to improve the quality of signature confirmation in document recognition. The analysis of several possible options for using the model is carried out. The results of the study are given, in which it is possible to correctly determine the authenticity of the signature on small samples.

Keywords: signature recognition, biometric data, artificial intelligence, neural networks

Procedia PDF Downloads 149

Authors: Hamed Rajabzadeh Gatabi, Soroush Dastgheibifard, Mahsa Asnafi

Abstract:

There is no doubt that reinforced concrete is known as one of the most significant materials which is used in construction industry for many years. Although, some natural elements in dealing with environment can contribute to its corrosion or failure. One of which is bar or so-called reinforcement failure. So as to combat this problem, one of the oxidization prevention methods investigated was the barrier protection method implemented over the application of an organic coating, specifically fusion-bonded epoxy. In this study comparative method is prepared on two different kinds of covered bars (zinc-riches epoxy and polyamide epoxy coated bars) and also uncoated bar. With the aim of evaluate these reinforced concretes, the stickiness, toughness, thickness and corrosion performance of coatings were compared by some tools like Cu/CuSo4 electrodes, EIS and etc. Different types of concretes were exposed to the salty environment (NaCl 3.5%) and their durability was measured. As stated by the experiments in research and investigations, thick coatings (named epoxies) have acceptable stickiness and strength. Polyamide epoxy coatings stickiness to the bars was a bit better than that of zinc-rich epoxy coatings; nonetheless it was stiffer than the zinc rich epoxy coatings. Conversely, coated bars with zinc-rich epoxy showed more negative oxidization potentials, which take revenge protection of bars by zinc particles. On the whole, zinc-rich epoxy coverings is more corrosion-proof than polyamide epoxy coatings due to consuming zinc elements and some other parameters, additionally if the epoxy coatings without surface defects are applied on the rebar surface carefully, it can be said that the life of steel structures is subjected to increase dramatically.

Keywords: surface coating, epoxy polyamide, reinforce concrete bars, salty environment

Procedia PDF Downloads 290

Authors: Tolulope Aremu

Abstract:

This paper is based on the idea of using deep learning methodology for optimizing production yield by tuning a few key process parameters in a manufacturing environment. The study was explicitly on how to maximize production yield and minimize operational costs by utilizing advanced neural network models, specifically Long Short-Term Memory and Convolutional Neural Networks. These models were implemented using Python-based frameworks—TensorFlow and Keras. The targets of the research are the precision molding processes in which temperature ranges between 150°C and 220°C, the pressure ranges between 5 and 15 bar, and the material flow rate ranges between 10 and 50 kg/h, which are critical parameters that have a great effect on yield. A dataset of 1 million production cycles has been considered for five continuous years, where detailed logs are present showing the exact setting of parameters and yield output. The LSTM model would model time-dependent trends in production data, while CNN analyzed the spatial correlations between parameters. Models are designed in a supervised learning manner. For the model's loss, an MSE loss function is used, optimized through the Adam optimizer. After running a total of 100 training epochs, 95% accuracy was achieved by the models recommending optimal parameter configurations. Results indicated that with the use of RSM and DOE traditional methods, there was an increase in production yield of 12%. Besides, the error margin was reduced by 8%, hence consistent quality products from the deep learning models. The monetary value was annually around $2.5 million, the cost saved from material waste, energy consumption, and equipment wear resulting from the implementation of optimized process parameters. This system was deployed in an industrial production environment with the help of a hybrid cloud system: Microsoft Azure, for data storage, and the training and deployment of their models were performed on Google Cloud AI. The functionality of real-time monitoring of the process and automatic tuning of parameters depends on cloud infrastructure. To put it into perspective, deep learning models, especially those employing LSTM and CNN, optimize the production yield by fine-tuning process parameters. Future research will consider reinforcement learning with a view to achieving further enhancement of system autonomy and scalability across various manufacturing sectors.

Keywords: production yield optimization, deep learning, tuning of process parameters, LSTM, CNN, precision manufacturing, TensorFlow, Keras, cloud infrastructure, cost saving

Procedia PDF Downloads 34

Authors: Ole-Christian Galbo Engstrøm, Erik Schou Dreier, Birthe Møller Jespersen, Kim Steenstrup Pedersen

Abstract:

Grain quality analysis is a multi-parameterized problem that includes a variety of qualitative and quantitative parameters such as grain type classification, damage type classification, and nutrient regression. Currently, these parameters require human inspection, a multitude of instruments employing a variety of sensor technologies, and predictive model types or destructive and slow chemical analysis. This paper investigates the feasibility of applying near-infrared hyperspectral imaging (NIR-HSI) to grain quality analysis. For this study two datasets of NIR hyperspectral images in the wavelength range of 900 nm - 1700 nm have been used. Both datasets contain images of sparsely and densely packed grain kernels. The first dataset contains ~87,000 image crops of bulk wheat samples from 63 harvests where protein value has been determined by the FOSS Infratec NOVA which is the golden industry standard for protein content estimation in bulk samples of cereal grain. The second dataset consists of ~28,000 image crops of bulk grain kernels from seven different wheat varieties and a single rye variety. In the first dataset, protein regression analysis is the problem to solve while variety classification analysis is the problem to solve in the second dataset. Deep convolutional neural networks (CNNs) have the potential to utilize spatio-spectral correlations within a hyperspectral image to simultaneously estimate the qualitative and quantitative parameters. CNNs can autonomously derive meaningful representations of the input data reducing the need for advanced preprocessing techniques required for classical chemometric model types such as artificial neural networks (ANNs) and partial least-squares regression (PLS-R). A comparison between different CNN architectures utilizing 2D and 3D convolution is conducted. These results are compared to the performance of ANNs and PLS-R. Additionally, a variety of preprocessing techniques from image analysis and chemometrics are tested. These include centering, scaling, standard normal variate (SNV), Savitzky-Golay (SG) filtering, and detrending. The results indicate that the combination of NIR-HSI and CNNs has the potential to be the foundation for an automatic system unifying qualitative and quantitative grain quality analysis within a single sensor technology and predictive model type.

Keywords: deep learning, grain analysis, hyperspectral imaging, preprocessing techniques

Procedia PDF Downloads 100

Authors: Le Zhao, Alain Nogaret

Abstract:

We have built universal Central Pattern Generator (CPG) hardware by interconnecting Hodgkin-Huxley neurons with reciprocally inhibitory synapses. We investigate the dynamics of neuron oscillations as a function of the time delay between current steps applied to individual neurons. We demonstrate stimulus dependent switching between spiking polyrhythms and map the phase portraits of the neuron oscillations to reveal the basins of attraction of the system. We experimentally study the dependence of the attraction basins on the network parameters: the neuron response time and the strength of inhibitory connections.

Keywords: central pattern generator, winnerless competition principle, artificial neural networks, synapses

Procedia PDF Downloads 477

Authors: Debananda Mohapatra, Subramanya Badrayyana, Smrutiranjan Parida

Abstract:

Recognizing the upcoming era of carbon nanostructures and their revolutionary applications, we investigated the formation and supercapacitor application of highly pure and hydrophilic carbon nano-onions (CNOs) by economical one-step flame-synthesis procedure. The facile and scalable method uses easily available organic carbon source such as clarified butter, restricting the use of any catalyst, sophisticated instrumentation, high vacuum and post processing purification procedure. The active material was conformally coated onto a locally available cotton wipe by “sonicating and drying” process to obtain novel, lightweight, inexpensive, flexible, binder-free electrodes with strong adhesion between nanoparticles and porous wipe. This interesting electrode with CNO as the active material delivers a specific capacitance of 102.16 F/g, the energy density of 14.18 Wh/kg and power density of 2448 W/kg which are the highest values reported so far in symmetrical two electrode cell configuration with 1M Na2SO4 as an electrolyte. Incorporation of CuO nanoparticles to these functionalized CNOs by one-step hydrothermal method add up to a significant specific capacitance of 420 F/g with deliverable energy and power density at 58.33 Wh/kg and 4228 W/kg, respectively. The free standing CNOs, as well as CNO-CuO composite electrode, showed an excellent cyclic performance and stability retaining 95 and 90% initial capacitance even after 5000 charge-discharge cycles at a current density of 5 A/g. This work presents a new platform for high performance supercapacitors for next generation wearable electronic devices.

Keywords: binder-free, flame synthesis, flexible, carbon nano-onion

Procedia PDF Downloads 198

Authors: Samira Baghbanbari, A. B. P. Lever, Payam S. Shabestari, Donald Weaver

Abstract:

Existing signal transmission models, although undoubtedly useful, have proven insufficient to explain the full complexity of information transfer within the central nervous system. The development of transformative models will necessitate a more comprehensive understanding of neuronal lipid membrane electrophysiology. Pursuant to this goal, the role of highly organized interfacial phospholipid-water layers emerges as a promising case study. A series of phospholipids in neural-glial gap junction interfaces as well as cholesterol molecules have been computationally modelled using high-performance density functional theory (DFT) calculations. Subsequent 'charge decomposition analysis' calculations have revealed a net transfer of charge from phospholipid orbitals through the organized interfacial water layer before ultimately finding its way to cholesterol acceptor molecules. The specific pathway of charge transfer from phospholipid via water layers towards cholesterol has been mapped in detail. Cholesterol is an essential membrane component that is overrepresented in neuronal membranes as compared to other mammalian cells; given this relative abundance, its apparent role as an electronic acceptor may prove to be a relevant factor in further signal transmission studies of the central nervous system. The timescales over which this electronic charge transfer occurs have also been evaluated by utilizing a system design that systematically increases the number of water molecules separating lipids and cholesterol. Memory loss through hydrogen-bonded networks in water can occur at femtosecond timescales, whereas existing action potential-based models are limited to micro or nanosecond scales. As such, the development of future models that attempt to explain faster timescale signal transmission in the central nervous system may benefit from our work, which provides additional information regarding fast timescale energy transfer mechanisms occurring through interfacial water. The study possesses a dataset that includes six distinct phospholipids and a collection of cholesterol. Ten optimized geometric characteristics (features) were employed to conduct binary classification through an artificial neural network (ANN), differentiating cholesterol from the various phospholipids. This stems from our understanding that all lipids within the first group function as electronic charge donors, while cholesterol serves as an electronic charge acceptor.

Keywords: charge transfer, signal transmission, phospholipids, water layers, ANN

Procedia PDF Downloads 75

Authors: Aishrith Rao

Abstract:

COVID 19 is a pandemic which has resulted in thousands of deaths around the world and a huge impact on the global economy. Testing is a huge issue as the test kits have limited availability and are expensive to manufacture. Using deep learning methods on radiology images in the detection of the coronavirus as these images contain information about the spread of the virus in the lungs is extremely economical and time-saving as it can be used in areas with a lack of testing facilities. This paper focuses on binary classification and multi-class classification of COVID 19 and other diseases such as pneumonia, tuberculosis, etc. Different deep learning methods such as VGG-19, COVID-Net, ResNET+ SVM, Deep CNN, DarkCovidnet, etc., have been used, and their accuracy has been compared using the Chest X-Ray dataset.

Keywords: deep learning, computer vision, radiology, COVID-19, ResNet, VGG-19, deep neural networks

Procedia PDF Downloads 161

Authors: Amina Farooq, Nauman Zafar Butt

Abstract:

This paper is about methods and tools for counting particles of interest, such as cells. A microfluidic system with interconnected electronics on a flexible substrate, inlet-outlet ports and interface schemes, sensitive and selective detection of cells specificity, and processing of cell counting at polymer interfaces in a microscale biosensor for use in the detection of target biological and non-biological cells. The development of fluidic channels, planar fluidic contact ports, integrated metal electrodes on a flexible substrate for impedance measurements, and a surface modification plasma treatment as an intermediate bonding layer are all part of the fabrication process. Magnetron DC sputtering is used to deposit a double metal layer (Ti/Pt) over the polypropylene film. Using a photoresist layer, specified and etched zones are established. Small fluid volumes, a reduced detection region, and electrical impedance measurements over a range of frequencies for cell counts improve detection sensitivity and specificity. The procedure involves continuous flow of fluid samples that contain particles of interest through the microfluidic channels, counting all types of particles in a portion of the sample using the electrical differential counter to generate a bipolar pulse for each passing cell—calculating the total number of particles of interest originally in the fluid sample by using MATLAB program and signal processing. It's indeed potential to develop a robust and economical kit for cell counting in whole-blood samples using these methods and similar devices.

Keywords: impedance, biochip, cell counting, microfluidics

Procedia PDF Downloads 162

Authors: Alexandre H. Okano, Pedro M. D. Agrícola, Daniel G. Da S. Machado, Luiz I. Do N. Neto, Luiz F. Farias Junior, Paulo H. D. Nascimento, Rickson C. Mesquita, John F. Araujo, Eduardo B. Fontes, Hassan M. Elsangedy, Shinsuke Shimojo, Li M. Li

Abstract:

The prefrontal cortex is involved in the reward system and the insular cortex integrates the afferent inputs arriving from the body’ systems and turns into feelings. Therefore, modulating neuronal activity in these regions may change individuals’ perception in a given situation such as exercise. We tested whether transcranial direct current stimulation (tDCS) change cerebral oxygenation and pleasure during exercise. Fourteen volunteer healthy adult men were assessed into five different sessions. First, subjects underwent to a maximum incremental test on a cycle ergometer. Then, subjects were randomly assigned to a transcranial direct current stimulation (2mA for 15 min) intervention in a cross over design in four different conditions: anode and cathode electrodes on T3 and Fp2 targeting the insular cortex, and Fpz and F4 targeting prefrontal cortex, respectively; and their respective sham. These sessions were followed by 30 min of moderate intensity exercise. Brain oxygenation was measured in prefrontal cortex with a near infrared spectroscopy. Perceived exertion and pleasure were also measured during exercise. The asymmetry in prefrontal cortex oxygenation before the stimulation decreased only when it was applied over this region which did not occur after insular cortex or sham stimulation. Furthermore, pleasure was maintained during exercise only after prefrontal cortex stimulation (P > 0.7), while there was a decrease throughout exercise (P < 0.03) during the other conditions. We conclude that tDCS over the prefrontal cortex changes brain oxygenation in ventromedial prefrontal cortex and maintains perceived pleasure during exercise. Therefore, this technique might be used to enhance effective responses related to exercise.

Keywords: affect, brain stimulation, dopamine neuromodulation, pleasure, reward, transcranial direct current stimulation

Procedia PDF Downloads 327

Authors: Angelo Gabriel Buenaventura, Allan Christopher Yago

Abstract:

A carbon paste electrode (CPE) composed of Multiwalled Carbon Nanotube (MWCNT) conducting particle and Polydimethylsiloxane (PDMS) binder was used for simultaneous detection of Dopamine (DA) and Uric Acid (UA) in the presence of Ascorbic Acid (AA) at physiological level. The MWCNT-PDMS CPE was initially activated via potentiodynamic cycling in a basic (NaOH) solution, which resulted in enhanced electrochemical properties. Electrochemical Impedance Spectroscopy measurements revealed a significantly lower charge transfer resistance (Rct) for the OH--activated MWCNT-PDMS CPE (Rct = 5.08kΩ) as compared to buffer (pH 7)-activated MWCNT-PDMS CPE (Rct = 25.9kΩ). Reversibility analysis of Fe(CN)63-/4- redox couple of both Buffer-Activated CPE and OH--Activated CPE showed that the OH—Activated CPE have peak current ratio (Ia/Ic) of 1.11 at 100mV/s while 2.12 for the Buffer-Activated CPE; this showed an electrochemically reversible behavior for Fe(CN)63-/4- redox couple even at relatively fast scan rate using the OH--activated CPE. Enhanced voltammetric signal for DA and significant peak separation between DA and UA was obtained using the OH--activated MWCNT-PDMS CPE in the presence of 50 μM AA via Differential Pulse Voltammetry technique. The anodic peak currents which appeared at 0.263V and 0.414 V were linearly increasing with increasing concentrations of DA and UA, respectively. The linear ranges were obtained at 25 μM – 100 μM for both DA and UA. The detection limit was determined to be 3.86 μM for DA and 5.61 μM for UA. These results indicate a practical approach in the simultaneous detection of important bio-organic molecules using a simple CPE composed of MWCNT and PDMS with base anodization as activation technique.

Keywords: anodization, ascorbic acid, carbon paste electrodes, dopamine, uric acid

Procedia PDF Downloads 287

Authors: Theo H. G. Moundzounga

Abstract:

Arsenic and 2-chlorophenol are priority pollutants that pose serious health threats to humans and ecology. An electrochemical sensor, based on graphitic carbon nitride (g-C₃N₄) and carbon dots (CDs), was fabricated and used for the determination of arsenic and 2-chlorophenol. The g-C₃N₄/CDs nanocomposite was prepared via microwave irradiation heating method and was dropped-dried on the surface of the glassy carbon electrode (GCE). Transmission electron microscopy (TEM), X-ray diffraction (XRD), photoluminescence (PL), Fourier transform infrared spectroscopy (FTIR), UV-Vis diffuse reflectance spectroscopy (UV-Vis DRS) were used for the characterization of structure and morphology of the nanocomposite. Electrochemical characterization was done by electrochemical impedance spectroscopy (EIS) and cyclic voltammetry (CV). The electrochemical behaviors of arsenic and 2-chlorophenol on different electrodes (GCE, CDs/GCE, and g-C₃N₄/CDs/GCE) was investigated by differential pulse voltammetry (DPV). The results demonstrated that the g-C₃N₄/CDs/GCE significantly enhanced the oxidation peak current of both analytes. The analytes detection sensitivity was greatly improved, suggesting that this new modified electrode has great potential in the determination of trace level of arsenic and 2-chlorophenol. Experimental conditions which affect the electrochemical response of arsenic and 2-chlorophenol were studied, the oxidation peak currents displayed a good linear relationship to concentration for 2-chlorophenol (R²=0.948, n=5) and arsenic (R²=0.9524, n=5), with a linear range from 0.5 to 2.5μM for 2-CP and arsenic and a detection limit of 2.15μM and 0.39μM respectively. The modified electrode was used to determine arsenic and 2-chlorophenol in spiked tap and effluent water samples by the standard addition method, and the results were satisfying. According to the measurement, the new modified electrode is a good alternative as chemical sensor for determination of other phenols.

Keywords: electrochemistry, electrode, limit of detection, sensor

Procedia PDF Downloads 145

Authors: C. Jameke

Abstract:

During the cognitivist era in cognitive psychology, a theory of internal rules and symbolic representations was posited as an account of human cognition. This type of cognitive architecture had its heyday during the 1970s and 80s, but it has now been largely abandoned in favour of subsymbolic architectures (e.g. connectionism), non-representational frameworks (e.g. dynamical systems theory), and statistical approaches such as Bayesian theory. In this presentation I describe this changing landscape of research, and comment on the increasing influence of neuroscience on cognitive psychology. I then briefly review a few recent developments in connectionism, and neurocomputation relevant to cognitive psychology, and critically discuss the assumption made by some researchers in these frameworks that higher-level aspects of human cognition are simply emergent properties of massively large distributed neural networks

Keywords: connectionism, emergentism, postocgnitivist, representations, subsymbolic archiitecture

Procedia PDF Downloads 579

Authors: Fernando Ojedo, Alejandro Alvarez, Pedro Macizo

Abstract:

In the present study, we explored electrophysiological correlates of Arabic digits naming to determine semantic processing of numbers. Participants named Arabic digits grouped by category or intermixed with exemplars of other semantic categories while the N400 event-related potential was examined. Around 350-450 ms after the presentation of Arabic digits, brain waves were more positive in anterior regions and more negative in posterior regions when stimuli were grouped by category relative to the mixed condition. Contrary to what was found in other studies, electrophysiological results suggested that the production of numerals involved semantic mediation.

Keywords: Arabic digit naming, event-related potentials, semantic processing, number production

Procedia PDF Downloads 583

Authors: Eiman Kattan, Hong Wei

Abstract:

In using Convolutional Neural Network (CNN) for classification, there is a set of hyperparameters available for the configuration purpose. This study aims to evaluate the impact of a range of parameters in CNN architecture i.e. AlexNet on land cover classification based on four remotely sensed datasets. The evaluation tests the influence of a set of hyperparameters on the classification performance. The parameters concerned are epoch values, batch size, and convolutional filter size against input image size. Thus, a set of experiments were conducted to specify the effectiveness of the selected parameters using two implementing approaches, named pertained and fine-tuned. We first explore the number of epochs under several selected batch size values (32, 64, 128 and 200). The impact of kernel size of convolutional filters (1, 3, 5, 7, 10, 15, 20, 25 and 30) was evaluated against the image size under testing (64, 96, 128, 180 and 224), which gave us insight of the relationship between the size of convolutional filters and image size. To generalise the validation, four remote sensing datasets, AID, RSD, UCMerced and RSCCN, which have different land covers and are publicly available, were used in the experiments. These datasets have a wide diversity of input data, such as number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in both training and testing. The results have shown that increasing the number of epochs leads to a higher accuracy rate, as expected. However, the convergence state is highly related to datasets. For the batch size evaluation, it has shown that a larger batch size slightly decreases the classification accuracy compared to a small batch size. For example, selecting the value 32 as the batch size on the RSCCN dataset achieves the accuracy rate of 90.34 % at the 11th epoch while decreasing the epoch value to one makes the accuracy rate drop to 74%. On the other extreme, setting an increased value of batch size to 200 decreases the accuracy rate at the 11th epoch is 86.5%, and 63% when using one epoch only. On the other hand, selecting the kernel size is loosely related to data set. From a practical point of view, the filter size 20 produces 70.4286%. The last performed image size experiment shows a dependency in the accuracy improvement. However, an expensive performance gain had been noticed. The represented conclusion opens the opportunities toward a better classification performance in various applications such as planetary remote sensing.

Keywords: CNNs, hyperparamters, remote sensing, land cover, land use

Procedia PDF Downloads 170

Authors: Ann D. Christy, Beenish Saba

Abstract:

The Microbial fuel Cell (MFC) is a successful integrated technology for power production and wastewater treatment. MFCs are recognized for their dual function, but research in this field is still ongoing to increase efficiency and power output. One such effort is successful integration of phototrophic and autotrophic microorganisms to create bacterio-algal MFCs for sustainable electricity production along with wastewater treatment and algal biomass production. An MFC is typically configured with an anaerobic anodic chamber containing exoelectrogenic microorganisms separated by a cation exchange membrane from an adjacent aerobic cathodic chamber. The two electrodes are connected by an external circuit. This conventional MFC can be converted into a phototrophic MFC by introducing photosynthetic microorganisms into the cathode chamber. This study examines adding a third desalination chamber to a two-chamber bacterio-algal MFC. Successful results have been observed from these three-chamber MFCs demonstrating wastewater treatment in the anodic chamber, phototrophic algal growth in the cathodic chamber, and desalination in the middle chamber. The present article will summarize successful results of the bacterio-algal fuel cells and offer insights about the mechanisms involved. Tables summarizing the input substrate along with optimized operational conditions and output performance in terms of power production and efficiencies of water and wastewater treatment will be presented. The negative impacts and challenges will be discussed, along with possible future research directions. Results suggest that the three chamber bacterio-algal desalination cell has potential as a feasible technology for power production, wastewater treatment and desalination, but it needs further investigation under optimized conditions.

Keywords: bacterio-algal MFC, three chamber, microbial fuel cell, wastewater treatment and desalination

Procedia PDF Downloads 363

Authors: G. Singh, H.Schuster, U. Füssel

Abstract:

The stability of electric arc and durability of electrode tip used in Tungsten Inert Gas (TIG) welding demand a metallurgical study about the chemical transport mechanism of emitter oxide particles in tungsten electrode during its real welding conditions. The tungsten electrodes doped with emitter oxides of rare earth oxides such as La₂O₃, Th₂O₃, Y₂O₃, CeO₂ and ZrO₂ feature a comparatively lower work function than tungsten and thus have superior emission characteristics due to lesser surface temperature of the cathode. The local change in concentration of these emitter particles in tungsten electrode due to high temperature diffusion (chemical transport) can change its functional properties like electrode temperature, work function, electron emission, and stability of the electrode tip shape. The resulting increment in tip surface temperature results in the electrode material loss. It was also observed that the tungsten recrystallizes to large grains at high temperature. When the shape of grain boundaries are granular in shape, the intergranular diffusion of oxide emitter particles takes more time to reach the electrode surface. In the experimental work, the microstructure of the used electrode's tip surface will be studied by scanning electron microscope and reflective X-ray technique in order to gauge the extent of the diffusion and chemical reaction of emitter particles. Besides, a simulated model is proposed to explain the effect of oxide particles diffusion on the electrode’s microstructure, electron emission characteristics, and electrode tip erosion. This model suggests metallurgical modifications in tungsten electrode to enhance its erosion resistance.

Keywords: rare-earth emitter particles, temperature-dependent diffusion, TIG welding, Tungsten electrode

Procedia PDF Downloads 187

Authors: Fatma Dridi, Mouna Marrakchi, Mohammed Gargouri, Alvaro Garcia Cruz, Sergei V. Dzyadevych, Francis Vocanson, Joëlle Saulnier, Nicole Jaffrezic-Renault, Florence Lagarde

Abstract:

An original method has been successfully developed for the immobilization of thermolysin onto gold interdigitated electrodes for the detection of ochratoxin A (OTA) in olive oil samples. A mix of polyvinyl alcohol (PVA), polyethylenimine (PEI) and gold nanoparticles (AuNPs) was used. Cross-linking sensors chip was made by using a saturated glutaraldehyde (GA) vapor atmosphere in order to render the two polymers water stable. Performance of AuNPs/ (PVA/PEI) modified electrode was compared to a traditional immobilized enzymatic method using bovine serum albumin (BSA). Atomic force microscopy (AFM) experiments were employed to provide a useful insight into the structure and morphology of the immobilized thermolysin composite membranes. The enzyme immobilization method influence the topography and the texture of the deposited layer. Biosensors optimization and analytical characteristics properties were studied. Under optimal conditions AuNPs/ (PVA/PEI) modified electrode showed a higher increment in sensitivity. A 700 enhancement factor could be achieved with a detection limit of 1 nM. The newly designed OTA biosensors showed a long-term stability and good reproducibility. The relevance of the method was evaluated using commercial doped olive oil samples. No pretreatment of the sample was needed for testing and no matrix effect was observed. Recovery values were close to 100% demonstrating the suitability of the proposed method for OTA screening in olive oil.

Keywords: thermolysin, A. ochratoxin , polyvinyl alcohol, polyethylenimine, gold nanoparticles, olive oil

Procedia PDF Downloads 591

Authors: Sophia Liang Zhou

Abstract:

For investors, businesses, consumers, and governments, an accurate assessment of future housing prices is crucial to critical decisions in resource allocation, policy formation, and investment strategies. Previous studies are contradictory about macroeconomic determinants of housing price and largely focused on one or two areas using point prediction. This study aims to develop data-driven models to accurately predict future housing market trends in different markets. This work studied five different metropolitan areas representing different market trends and compared three-time lagging situations: no lag, 6-month lag, and 12-month lag. Linear regression (LR), random forest (RF), and artificial neural network (ANN) were employed to model the real estate price using datasets with S&P/Case-Shiller home price index and 12 demographic and macroeconomic features, such as gross domestic product (GDP), resident population, personal income, etc. in five metropolitan areas: Boston, Dallas, New York, Chicago, and San Francisco. The data from March 2005 to December 2018 were collected from the Federal Reserve Bank, FBI, and Freddie Mac. In the original data, some factors are monthly, some quarterly, and some yearly. Thus, two methods to compensate missing values, backfill or interpolation, were compared. The models were evaluated by accuracy, mean absolute error, and root mean square error. The LR and ANN models outperformed the RF model due to RF’s inherent limitations. Both ANN and LR methods generated predictive models with high accuracy ( > 95%). It was found that personal income, GDP, population, and measures of debt consistently appeared as the most important factors. It also showed that technique to compensate missing values in the dataset and implementation of time lag can have a significant influence on the model performance and require further investigation. The best performing models varied for each area, but the backfilled 12-month lag LR models and the interpolated no lag ANN models showed the best stable performance overall, with accuracies > 95% for each city. This study reveals the influence of input variables in different markets. It also provides evidence to support future studies to identify the optimal time lag and data imputing methods for establishing accurate predictive models.

Keywords: linear regression, random forest, artificial neural network, real estate price prediction

Procedia PDF Downloads 103

Authors: D. W. Mohammed, J. Bowen, S. N. Kukureka

Abstract:

Successful design and fabrication of flexible devices for electrode components requires a low sheet resistance, high optical transmittance, high mechanical reliability. Indium tin oxide (ITO) film is currently the predominant transparent conductive oxide (TCO) film in potential applications such as flexible organic light- emitting diodes, flat-panel displays, solar cells, and thin film transistors (TFTs). However ITO films are too brittle and their resistivity is rather high in some cases compared with ITO/Ag/ ITO, and they cannot completely meet flexible optoelectronic device requirements. Therefore, in this work the mechanical properties of ITO /Ag/ITO multilayer film that deposited on Polyethylene terephthalate (PET) compared with the single layered ITO sample were investigated using bending fatigue, twisting fatigue and thermal cycling experiments. The electrical resistance was monitored during the application of mechanical and thermal loads to see the pattern of relationship between the load and the electrical continuity as a consequent of failure. Scanning electron microscopy and atomic force microscopy were used to provide surface characterization of the mechanically-tested samples. The effective embedment of the Ag layer between upper and lower ITO films led to metallic conductivity and superior flexibility to the single ITO electrode, due to the high failure strain of the ductile Ag layer. These results indicate that flexible ITO/Ag/ITO multilayer electrodes are a promising candidate for use as transparent conductor in flexible displays. They provided significantly reduced sheet resistance compared to ITO, and improved bending and twisting properties both as a function of radius, angle and thermal cycling.

Keywords: ITO/Ag/ITO multilayer, failure strain, mechanical properties, PET

Procedia PDF Downloads 297

Authors: Yuji Fujino, Kazu Amimoto, Kazuhiro Fukata, Masahide Inoue, Hidetoshi Takahashi, Shigeru Makita

Abstract:

Aim: Pusher behavior (PB) is a disorder in which stroke patients shift their body weight toward the affected side of the body (the hemiparetic side) and push away from the non-hemiparetic side. These patients often use further pushing to resist any attempts to correct their position to upright. It is known that the subcortical white matter lesion (SWML) usually correlates of gait or balance function in stroke patients. However, it is unclear whether the SWML influences PB. The purpose of this study was to investigate if the damage of SWML affects the severity of PB on acute stroke patients. Methods: Fourteen PB patients without thalamic or cortical lesions (mean age 73.4 years, 17.5 days from onset) participated in this study. Evaluation of PB was performed according to the Scale for Contraversive Pushing (SCP) for sitting and/or standing. We used modified criteria wherein the SCP subscale scores in each section of the scale were >0. As a clinical measurement, patients were evaluated by the Stroke Impairment Assessment Set (SIAS). For the depiction of SWML, we used T2-weighted fluid-attenuated inversion-recovery imaging. The degree of damage on SWML was assessed using the Fazekas scale. Patients were divided into two groups in the presence of SWML (SWML+ group; Fazekas scale grade 1-3, SWML- group; Fazekas scale grade 0). The independent t-test was used to compare the SCP and SIAS. This retrospective study was approved by the Ethics Committee. Results: In SWML+ group, the SCP was 3.7±1.0 points (mean±SD), the SIAS was 28.0 points (median). In SWML- group, the SCP was 2.0±0.2 points, and the SIAS was 31.5 points. The SCP was significantly higher in SWML+ group than in SWML- group (p<0.05). The SIAS was not significant in both groups (p>0.05). Discussion: It has been considered that the posterior thalamus is the neural structures that process the afferent sensory signals mediating graviceptive information about upright body orientation in humans. Therefore, many studies reported that PB was typically associated with unilateral lesions of the posterior thalamus. However, the result indicates that these extra-thalamic brain areas also contribute to the network controlling upright body posture. Therefore, SMWL might induce dysfunction through malperfusion in distant thalamic or other structurally intact neural structures. This study had a small sample size. Therefore, future studies should be performed with a large number of PB patients. Conclusion: The present study suggests that SWML can be definitely associated with PB. The patients with SWML may be severely incapacitating.

Keywords: pushing behavior, subcortical white matter lesion, acute phase, stroke

Procedia PDF Downloads 246

Authors: Rui Wang, Luodi Yu, Dan Huang, Hsuan-Chih Chen, Yang Zhang, Suiping Wang

Abstract:

Enhanced discrimination of pure tones but diminished discrimination of speech pitch (i.e., lexical tone) were found in children with autism who speak a tonal language (Mandarin), suggesting a speech-specific impairment of pitch perception in these children. However, in tonal languages, both lexical tone and vowel are phonemic cues and integrally dependent on each other. Therefore, it is unclear whether the presence of phonemic vowel dimension contributes to the observed lexical tone deficits in Mandarin-speaking children with autism. The current study employed a multi-feature oddball paradigm to examine how vowel and tone dimensions contribute to the neural responses for syllable change detection and involuntary attentional orienting in school-age Mandarin-speaking children with autism. In the oddball sequence, syllable /da1/ served as the standard stimulus. There were three deviant stimulus conditions, representing tone-only change (TO, /da4/), vowel-only change (VO, /du1/), and change of tone and vowel simultaneously (TV, /du4/). EEG data were collected from 25 children with autism and 20 age-matched normal controls during passive listening to the stimulation. For each deviant condition, difference waveform measuring mismatch negativity (MMN) was derived from subtracting the ERP waveform to the standard sound from that to the deviant sound for each participant. Additionally, the linear summation of TO and VO difference waveforms was compared to the TV difference waveform, to examine whether neural sensitivity for TV change detection reflects simple summation or nonlinear integration of the two individual dimensions. The MMN results showed that the autism group had smaller amplitude compared with the control group in the TO and VO conditions, suggesting impaired discriminative sensitivity for both dimensions. In the control group, amplitude of the TV difference waveform approximated the linear summation of the TO and VO waveforms only in the early time window but not in the late window, suggesting a time course from dimensional summation to nonlinear integration. In the autism group, however, the nonlinear TV integration was already present in the early window. These findings suggest that speech perception atypicality in children with autism rests not only in the processing of single phonemic dimensions, but also in the dimensional integration process.

Keywords: autism, event-related potentials , mismatch negativity, speech perception

Procedia PDF Downloads 221

Authors: Ashutosh Mishra, Nikhil Goyal

Abstract:

A 3D facial emotion recognition model based on deep learning is proposed in this paper. Two convolution layers and a pooling layer are employed in the deep learning architecture. After the convolution process, the pooling is finished. The probabilities for various classes of human faces are calculated using the sigmoid activation function. To verify the efficiency of deep learning-based systems, a set of faces. The Kaggle dataset is used to verify the accuracy of a deep learning-based face recognition model. The model's accuracy is about 65 percent, which is lower than that of other facial expression recognition techniques. Despite significant gains in representation precision due to the nonlinearity of profound image representations.

Keywords: facial recognition, computational intelligence, convolutional neural network, depth map

Procedia PDF Downloads 231

Authors: E. Chávez-Vargas, M. de la L. Olvera-Amador, A. Jimenez-Gonzalez, A. Maldonado

Abstract:

Undoped and fluorine doped zinc oxide (ZnO) thin films were deposited on sodocalcic glass substrates by the ultrasonic chemical spray technique. As the main goal is the manufacturing of transparent electrodes, the effects of both the solution composition and the substrate temperature on both the electrical and optical properties of ZnO thin films were studied. As a matter of fact, the effect of fluorine concentration ([F]/[F+Zn] at. %), solvent composition (acetic acid, water, methanol ratios) and ageing time, regarding solution composition, were varied. In addition, the substrate temperature and the deposition time, regarding the chemical spray technique, were also varied. Structural studies confirm the deposition of polycrystalline, hexagonal, wurtzite type, ZnO. The results show that the increase of ([F]/[F+Zn] at. %) ratio in the solution, decreases the sheet resistance, RS, of the ZnO:F films, reaching a minimum, in the order of 1.6 Ωcm, at 60 at. %; further increase in the ([F]/[F+Zn]) ratio increases the RS of the films. The same trend occurs with the variation in substrate temperature, as a minimum RS of ZnO:F thin films was encountered when deposited at TS= 450 °C. ZnO:F thin films deposited with aged solution show a significant decrease in the RS in the order of 100 ΩS. The transmittance of the films was also favorable affected by the solvent ratio and, more significantly, by the ageing of the solution. The whole evaluation of optical and electrical characteristics of the ZnO:F thin films deposited under different conditions, was done under Haacke’s figure of Merit in order to have a clear and quantitative trend as transparent conductors application.

Keywords: zinc oxide, ZnO:F, TCO, Haacke’s figure of Merit

Procedia PDF Downloads 314

Authors: Chia-Ting Chang, Chia-Yu Lin

Abstract:

We report on the decisive role of iron phosphate (FePO₄), formed in-situ during the electrochemical characterization, played in the electrocatalytic activity, especially its oxygen tolerance of iron oxides towards H₂O₂ reduction. Iron oxides studied including, Nanorod arrays (NRs) of β-FeOOH, γ-Fe₂O₃, α-Fe₂O₃, α-Fe₂O₃ nanosheets (α-Fe₂O₃NS), α-Fe₂O₃ nanoparticles (α-Fe₂O₃NP), were synthesized using chemical bath deposition. The nanostructure was controlled simply by adjusting the composition of precursor solution and reaction duration for CBD process, whereas the crystal phase was controlled by adjusting the annealing temperature. It was found that iron phosphate (FePO₄) was deposited in-situ onto the surface of this nanostructured α-Fe₂O₃ during the electrochemical pretreatment in the phosphate electrolyte, and both FePO₄ and α-Fe₂O₃ showed the activity in catalysing the electrochemical reduction of H₂O₂. In addition, the interaction/compatibility between deposited FePO₄ and iron oxides has a decisive effect on the overall electrocatalytic activity of the resultant electrodes; FePO₄ only showed synergetic effect on the overall electrocatalytic activity of α-Fe₂O₃NR and α-Fe2O₃NS. Both α-Fe₂O₃NR and α-Fe₂O₃NS showed two reduction peaks in phosphate electrolyte containing H₂O₂, one being pH-dependent and related to the electrocatalytic properties of FePO₄, and the other one being pH-independent and only related to the intrinsic electrocatalytic properties of α-Fe₂O₃NR and α-Fe₂O₃NS. However, all iron oxides showed only one pH-independent reductive peak in non-phosphate electrolyte containing H₂O₂. The synergesitic catalysis exerted by FePO₄ with α-Fe₂O₃NR or α-Fe₂O₃NS providing additional oxygen-insensitive active site for H₂O₂ reduction, which allows their applications to electrochemical detection of H₂O₂ without the interference of O₂ involving in oxidase-catalyzed chemical processes.

Keywords: H₂O₂ reduction, Iron oxide, iron phosphate, O₂ tolerance

Procedia PDF Downloads 415

Authors: Alvaro Ramírez, Martín Muñoz-Morales, Ester López- Fernández, Javier Llanos, C. Ania

Abstract:

Carbon blacks are value-added materials typically produced through the incomplete combustion or thermal decomposition of hydrocarbons. Traditionally, they have been used as catalysts in many different applications, but in the last decade, their potential in green chemistry has gained significant attention. Among them, the electrochemical production of H₂O₂ has attracted interest because of their properties as high oxidant capacity or their industrial interest as a bleaching agent. Carbon blacks are commonly used in this application in a catalytic ink that is drop-casted on supporting electrodes and acts as catalysts for the electrochemical production of H₂O₂ through oxygen reduction reaction (ORR). However, the different structural and electrochemical behaviors of each type of carbon black influence their applications. In this line, the term ‘carbon black’, has to be considered as a generic name that does not guarantee any physicochemical properties if any further description is mentioned. In fact, different specific surface area (SSA), surface functional groups, porous structure, and electro catalysts effect seem very important for electrochemical applications, and considerable differences were found during the analysis of four types of carbon blacks. Thus, the aim of this work is to evaluate the influence of SSA, porous structure, oxygen functional groups, and structural defects to differentiate among these carbon blacks (e.g. Vulcan XC72, Superior Graphite Co, Printex XE2, and Prolabo) for H₂O₂ production via ORR, using carbon paper as electrode support with improved selectivity and efficiency. Results indicate that the number and size of pores, along with surface functional groups, are key parameters that significantly affect the overall process efficiency.

Keywords: carbon blacks, oxygen reduction reaction, hydrogen peroxide, porosity, surface functional groups

Procedia PDF Downloads 46