Search results for: neural interface

Authors: Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev

Abstract:

The neural network quantization is highly desired procedure to perform before running neural networks on mobile devices. Quantization without fine-tuning leads to accuracy drop of the model, whereas commonly used training with quantization is done on the full set of the labeled data and therefore is both time- and resource-consuming. Real life applications require simplification and acceleration of quantization procedure that will maintain accuracy of full-precision neural network, especially for modern mobile neural network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with quantization procedure by introducing the trained scale factors for discretization thresholds that are separate for each filter. Using the proposed technique, we quantize the modern mobile architectures of neural networks with the set of train data of only ∼ 10% of the total ImageNet 2012 sample. Such reduction of train dataset size and small number of trainable parameters allow to fine-tune the network for several hours while maintaining the high accuracy of quantized model (accuracy drop was less than 0.5%). Ready-for-use models and code are available in the GitHub repository.

Keywords: distillation, machine learning, neural networks, quantization

Procedia PDF Downloads 291

Authors: Sorin Valcan, Mihail Gaianu

Abstract:

Labeling is a very costly and time consuming process which aims to generate datasets for training neural networks in several functionalities and projects. For driver monitoring system projects, the need for labeled images has a significant impact on the budget and distribution of effort. This paper presents the modifications done to an algorithm used for the generation of ground truth data for 2D eyes location on infrared images with drivers in order to improve the quality of the data and performance of the trained neural networks. The algorithm restrictions become tougher, which makes it more accurate but also less constant. The resulting dataset becomes smaller and shall not be altered by any kind of manual label adjustment before being used in the neural networks training process. These changes resulted in a much better performance of the trained neural networks.

Keywords: labeling automation, infrared camera, driver monitoring, eye detection, convolutional neural networks

Procedia PDF Downloads 80

Authors: Chai Mingming, Li Lei, Lu Xiaoxia

Abstract:

In this paper, the mechanism of stratified liquids’ mixing in a cylinder is investigated. It is focused on the effects of Rayleigh-Taylor Instability (RTI) and rotation of the cylinder on liquid interface mixing. For miscible liquids, Planar Laser Induced Fluorescence (PLIF) technique is applied to record the concentration field for one liquid. Intensity of Segregation (IOS) is used to describe the mixing status. For immiscible liquids, High Speed Camera is adopted to record the development of the interface. The experiment of RTI indicates that it plays a great role in the mixing process, and meanwhile the large-scale mixing is triggered, and subsequently the span of the stripes decreases, showing that the mesoscale mixing is coming into being. The rotation experiments show that the spin-down process has a great role in liquid mixing, during which the upper liquid falls down rapidly along the wall and crashes into the lower liquid. During this process, a lot of interface instabilities are excited. Liquids mix rapidly in the spin-down process. It can be concluded that no matter what ways have been adopted to speed up liquid mixing, the fundamental reason is the interface instabilities which increase the area of the interface between liquids and increase the relative velocity of the two liquids.

Keywords: interface instability, liquid mixing, Rayleigh-Taylor Instability, spin-down process, spin-up process

Procedia PDF Downloads 267

Authors: Joon Ho Kim, Tae Kwon Ha

Abstract:

Effect of aging treatment on microstructural aspects of interfacial layers of the Cu/Al clad sheet produced by Differential Speed Rolling (DSR) process were studied by Electron Back Scattered Diffraction (EBSD). Clad sheet of Al/Cu has been fabricated by using DSR, which caused severe shear deformation between Al and Cu plate to easily bond to each other. Rolling was carried out at 100°C with speed ratio of 2, in which the total thickness reduction was 45%. Interface layers of clad sheet were analyzed by EBSD after subsequent annealing at 400°C for 30 to 120 min. With increasing annealing time, thickness of interface layer and fraction of high angle grain boundary were increased and average grain size was decreased.

Keywords: aluminium/copper clad sheet, differential speed rolling, interface layer, microstructure, annealing, electron back scattered diffraction

Procedia PDF Downloads 342

Authors: Minh Tu Le, Quang Huy Nguyen, Mai Lan Nguyen

Abstract:

Bonding characteristics between pavement layers have an important influence on responses of pavement structures. This paper deals with analytical solution for the stresses, strains, and deflections of double-layered asphalt pavement structure. This solution is based on the homogeneous half-space of layered theory developed by Burmister (1943). The partial interaction between the layers is taken into account by considering an interface bonding behavior which is obtained by push-out shear test. Numerical applications considering three cases of bonding (unbonded, partially bonded, and fully bonded overlays) are carried out to the influence of the interface bonding on the structural behavior of asphalt pavement under static loading. Further, it was observed that numerical results indicate that the horizontal shear reaction modulus at the interface (Ks) will significantly affect pavement structure behavior.

Keywords: analytical solution, interface bonding, shear test keyword, double-layered asphalt, shear reaction modulus

Procedia PDF Downloads 196

Authors: John Kabuba

Abstract:

The study investigated the implementation of the Neural Network (NN) techniques for prediction of the loading of Cu ions onto clinoptilolite. The experimental design using analysis of variance (ANOVA) was chosen for testing the adequacy of the Neural Network and for optimizing of the effective input parameters (pH, temperature and initial concentration). Feed forward, multi-layer perceptron (MLP) NN successfully tracked the non-linear behavior of the adsorption process versus the input parameters with mean squared error (MSE), correlation coefficient (R) and minimum squared error (MSRE) of 0.102, 0.998 and 0.004 respectively. The results showed that NN modeling techniques could effectively predict and simulate the highly complex system and non-linear process such as ion-exchange.

Keywords: clinoptilolite, loading, modeling, neural network

Procedia PDF Downloads 389

Authors: Valentin P. Velikov

Abstract:

Automatic program generation saves time, human resources, and allows receiving syntactically clear and logically correct modules. The 4-th generation programming languages are related to drawing the data and the processes of the subject area, as well as, to obtain a frame of the respective information system. The application can be separated in interface and business logic. That means, for an interactive generation of the needed system to be used an already existing toolkit or to be created a new one.

Keywords: computer science, graphical user interface, user dialog interface, dialog frames, data modeling, subject area modeling

Procedia PDF Downloads 282

Authors: Zongyan Li, Matt Best

Abstract:

This paper presents an optimization method for reducing the number of input channels and the complexity of the feed-forward NARX neural network (NN) without compromising the accuracy of the NN model. By utilizing the correlation analysis method, the most significant regressors are selected to form the input layer of the NN structure. An application of vehicle dynamic model identification is also presented in this paper to demonstrate the optimization technique and the optimal input layer structure and the optimal number of neurons for the neural network is investigated.

Keywords: correlation analysis, F-ratio, levenberg-marquardt, MSE, NARX, neural network, optimisation

Procedia PDF Downloads 340

Authors: Adel. M. Sharaf, Foad H. Gandoman

Abstract:

Nowadays, Photovoltaic-PV Farms/ Parks and large PV-Smart Grid Interface Schemes are emerging and commonly utilized in Renewable Energy distributed generation. However, PV-hybrid-Dc-Ac Schemes using interface power electronic converters usually has negative impact on power quality and stabilization of modern electrical network under load excursions and network fault conditions in smart grid. Consequently, robust FACTS based interface schemes are required to ensure efficient energy utilization and stabilization of bus voltages as well as limiting switching/fault onrush current condition. FACTS devices are also used in smart grid-Battery Interface and Storage Schemes with PV-Battery Storage hybrid systems as an elegant alternative to renewable energy utilization with backup battery storage for electric utility energy and demand side management to provide needed energy and power capacity under heavy load conditions. The paper presents a robust interface PV-Li-Ion Battery Storage Interface Scheme for Distribution/Utilization Low Voltage Interface using FACTS stabilization enhancement and dynamic maximum PV power tracking controllers. Digital simulation and validation of the proposed scheme is done using MATLAB/Simulink software environment for Low Voltage- Distribution/Utilization system feeding a hybrid Linear-Motorized inrush and nonlinear type loads from a DC-AC Interface VSC-6-pulse Inverter Fed from the PV Park/Farm with a back-up Li-Ion Storage Battery.

Keywords: AC FACTS, smart grid, stabilization, PV-battery storage, Switched Filter-Compensation (SFC)

Procedia PDF Downloads 388

Authors: Debneil Saha Roy

Abstract:

Weather forecasting is a complex topic and is well suited for analysis by deep learning approaches. With the wide availability of weather observation data nowadays, these approaches can be utilized to identify immediate comparisons between historical weather forecasts and current observations. This work explores the application of deep learning techniques to weather forecasting in order to accurately predict the weather over a given forecast hori­zon. Three deep neural networks are used in this study, namely, Multi-Layer Perceptron (MLP), Long Short Tunn Memory Network (LSTM) and a combination of Convolutional Neural Network (CNN) and LSTM. The predictive performance of these models is compared using two evaluation metrics. The results show that forecasting accuracy increases with an increase in the complexity of deep neural networks.

Keywords: convolutional neural network, deep learning, long short term memory, multi-layer perceptron

Procedia PDF Downloads 137

Authors: Sheng-Bo Zhang, Huan-Hao Zhang, Zhi-Hua Chen, Chun Zheng

Abstract:

In this paper, the Richtmyer-Meshkov instability has been studied numerically by using the high-resolution Roe scheme based on the two-dimensional unsteady Euler equation, which was caused by the interaction between shock wave and the helium circular light gas cylinder with different component distributions. The numerical results further discuss the deformation process of the gas cylinder, the wave structure of the flow field and quantitatively analyze the characteristic dimensions (length, height, and central axial width) of the gas cylinder, the volume compression ratio of the cylinder over time. In addition, the flow mechanism of shock-driven interface gas mixing is analyzed from multiple perspectives by combining it with the flow field pressure, velocity, circulation, and gas mixing rate. Then the effects of different initial component distribution conditions on interface instability are investigated. The results show when the diffusion interface transit to the sharp interface, the reflection coefficient gradually increases on both sides of the interface. When the incident shock wave interacts with the cylinder, the transmission of the shock wave will transit from conventional transmission to unconventional transmission. At the same time, the reflected shock wave is gradually strengthened, and the transmitted shock wave is gradually weakened, which leads to an increase in the Richtmyer-Meshkov instability. Moreover, the Atwood number on both sides of the interface also increases as the diffusion interface transit to the sharp interface, which leads to an increase in the Rayleigh-Taylor instability and the Kelvin-Helmholtz instability. Therefore, the increase in instability will lead to an increase the circulation, resulting in an increase in the growth rate of gas mixing rate.

Keywords: shock wave, He light cylinder, Richtmyer-Meshkov instability, Gaussian distribution

Procedia PDF Downloads 49

Authors: Rodrigo S. Moreira, Nelson F. F. Ebecken

Abstract:

This paper proposes a maritime vessel tracker composed of an ensemble of WiSARD weightless neural network classifiers. A failure detector analyzes vessel movement with a Kalman filter and corrects the tracking, if necessary, using FFT matching. The use of the WiSARD neural network to track objects is uncommon. The additional contributions of the present study include a performance comparison with four state-of-art trackers, an experimental study of the features that improve maritime vessel tracking, the first use of an ensemble of classifiers to track maritime vessels and a new quantization algorithm that compares the values of pixel pairs.

Keywords: ram memory, WiSARD weightless neural network, object tracking, quantization

Procedia PDF Downloads 281

Authors: Chico Horacio Jose Sambo

Abstract:

Recently neural network has gained popularity when come to solve complex nonlinear problems. Permeability is one of fundamental reservoir characteristics system that are anisotropic distributed and non-linear manner. For this reason, permeability prediction from well log data is well suited by using neural networks and other computer-based techniques. The main goal of this paper is to predict reservoir permeability from well logs data by using neural network approach. A multi-layered perceptron trained by back propagation algorithm was used to build the predictive model. The performance of the model on net results was measured by correlation coefficient. The correlation coefficient from testing, training, validation and all data sets was evaluated. The results show that neural network was capable of reproducing permeability with accuracy in all cases, so that the calculated correlation coefficients for training, testing and validation permeability were 0.96273, 0.89991 and 0.87858, respectively. The generalization of the results to other field can be made after examining new data, and a regional study might be possible to study reservoir properties with cheap and very fast constructed models.

Keywords: neural network, permeability, multilayer perceptron, well log

Procedia PDF Downloads 365

Authors: Ying Su, Morgan C. Wang

Abstract:

Long-term time series forecasting is an important research area for automated machine learning (AutoML). Currently, forecasting based on either machine learning or statistical learning is usually built by experts, and it requires significant manual effort, from model construction, feature engineering, and hyper-parameter tuning to the construction of the time series model. Automation is not possible since there are too many human interventions. To overcome these limitations, this article proposed to use recurrent neural networks (RNN) through the memory state of RNN to perform long-term time series prediction. We have shown that this proposed approach is better than the traditional Autoregressive Integrated Moving Average (ARIMA). In addition, we also found it is better than other network systems, including Fully Connected Neural Networks (FNN), Convolutional Neural Networks (CNN), and Nonpooling Convolutional Neural Networks (NPCNN).

Keywords: automated machines learning, autoregressive integrated moving average, neural networks, time series analysis

Procedia PDF Downloads 46

Authors: O. P. Oladipo, O. A. Falode

Abstract:

The determination of Recovery Factor is of great importance to the reservoir engineer since it relates reserves to the initial oil in place. Reserves are the producible portion of reservoirs and give an indication of the profitability of a field Development. The core objective of this project is to develop an artificial neural network model using selected reservoir data to predict Recovery Factors (RF) of hydrocarbon reservoirs and compare the model with a couple of the existing correlations. The type of Artificial Neural Network model developed was the Single Layer Feed Forward Network. MATLAB was used as the network simulator and the network was trained using the supervised learning method, Afterwards, the network was tested with input data never seen by the network. The results of the predicted values of the recovery factors of the Artificial Neural Network Model, API Correlation for water drive reservoirs (Sands and Sandstones) and Guthrie and Greenberger Correlation Equation were obtained and compared. It was noted that the coefficient of correlation of the Artificial Neural Network Model was higher than the coefficient of correlations of the other two correlation equations, thus making it a more accurate prediction tool. The Artificial Neural Network, because of its accurate prediction ability is helpful in the correct prediction of hydrocarbon reservoir factors. Artificial Neural Network could be applied in the prediction of other Petroleum Engineering parameters because it is able to recognise complex patterns of data set and establish a relationship between them.

Keywords: recovery factor, reservoir, reserves, artificial neural network, hydrocarbon, MATLAB, API, Guthrie, Greenberger

Procedia PDF Downloads 408

Authors: Sajjad Baghernezhad

Abstract:

Meta-heuristic and hybrid algorithms have high adeer in modeling medical problems. In this study, a neural network was used to predict covid-19 among high-risk and low-risk patients. This study was conducted to collect the applied method and its target population consisting of 550 high-risk and low-risk patients from the Kerman University of medical sciences medical center to predict the coronavirus. In this study, the memetic algorithm, which is a combination of a genetic algorithm and a local search algorithm, has been used to update the weights of the neural network and develop the accuracy of the neural network. The initial study showed that the accuracy of the neural network was 88%. After updating the weights, the memetic algorithm increased by 93%. For the proposed model, sensitivity, specificity, positive predictivity value, value/accuracy to 97.4, 92.3, 95.8, 96.2, and 0.918, respectively; for the genetic algorithm model, 87.05, 9.20 7, 89.45, 97.30 and 0.967 and for logistic regression model were 87.40, 95.20, 93.79, 0.87 and 0.916. Based on the findings of this study, neural network models have a lower error rate in the diagnosis of patients based on individual variables and vital signs compared to the regression model. The findings of this study can help planners and health care providers in signing programs and early diagnosis of COVID-19 or Corona.

Keywords: COVID-19, decision support technique, neural network, genetic algorithm, memetic algorithm

Procedia PDF Downloads 48

Authors: Dhaladhuli Pranavi, Amirtham Rajagopal

Abstract:

There are various failure modes in ceramic matrix composites; notable ones are fiber breakage, matrix cracking and fiber matrix debonding. Crack nucleation and propagation in microstructure of such composites requires an understanding of interaction of crack with the multiple inclusion heterogeneous system and interfaces. In order to assess structural integrity, the material parameters especially of the interface that governs the crack growth should be determined. In the present work, a nonlocal phase field approach is proposed to model the crack interface interaction in such composites. Nonlocal approaches help in understanding the complex mechanisms of delamination growth and mitigation and operates at a material length scale. The performance of the proposed formulation is illustrated through representative numerical examples. The model proposed is implemented in the framework of the finite element method. Several parametric studies on interface crack interaction are conducted. The proposed model is easy and simple to implement and works very well in modeling fracture in composite systems.

Keywords: composite, interface, nonlocal, phase field

Procedia PDF Downloads 114

Authors: Kyung-Jin You, Kiwon Rhee, Marc H. Schieber, Nitish V. Thakor, Hyun-Chool Shin

Abstract:

It remains unknown whether M1 neurons encode multi-finger movements independently or as a certain neural network of single finger movements although multi-finger movements are physically a combination of single finger movements. We present an evidence of correlation between single and multi-finger movements and also attempt a challenging task of semi-blind decoding of neural data with minimum training of the neural decoder. Data were collected from 115 task-related neurons in M1 of a trained rhesus monkey performing flexion and extension of each finger and the wrist (12 single and 6 two-finger-movements). By exploiting correlation of temporal firing pattern between movements, we found that correlation coefficient for physically related movements pairs is greater than others; neurons tuned to single finger movements increased their firing rate when multi-finger commands were instructed. According to this knowledge, neural semi-blind decoding is done by choosing the greatest and the second greatest likelihood for canonical candidates. We achieved a decoding accuracy about 60% for multiple finger movement without corresponding training data set. this results suggest that only with the neural activities on single finger movements can be exploited to control dexterous multi-fingered neuroprosthetics.

Keywords: finger movement, neural activity, blind decoding, M1

Procedia PDF Downloads 287

Authors: Oladapo Tolulope Ibitoye

Abstract:

Neural networks have become prominent and widely engaged in algorithmic-based machine learning networks. They are perfect in solving day-to-day issues to a certain extent. Neural networks are computing systems with several interconnected nodes. One of the numerous areas of application of neural networks is object detection. This is a prominent area due to the coronavirus disease pandemic and the post-pandemic phases. Wearing a face mask in public slows the spread of the virus, according to experts’ submission. This calls for the development of a reliable and effective model for detecting face masks on people's faces during compliance checks. The existing neural network models for facemask detection are characterized by their black-box nature and large dataset requirement. The highlighted challenges have compromised the performance of the existing models. The proposed model utilized Faster R-CNN Model on Inception V3 backbone to reduce system complexity and dataset requirement. The model was trained and validated with very few datasets and evaluation results shows an overall accuracy of 96% regardless of skin tone.

Keywords: convolutional neural network, face detection, face mask, masked faces

Procedia PDF Downloads 44

Authors: Kathleen Moyer, Nora Ait Boucherbil, Murtaza Zohair, Janna Eaves-Rathert, Cary Pint

Abstract:

This study demonstrates the significance of interface engineering in the field of structural energy by being the first case where the performance of the system with the structural battery is greater than the performance of the same system with a battery separate from the system. The benefits of improving the interface in the structural battery were tested by creating carbon fiber composite batteries (and independent graphite electrodes and lithium iron phosphate electrodes) with and without an improved interface. Mechanical data on the structural batteries were collected using tensile tests and electrochemical data was collected using scanning electron microscopy equipment. The full-cell lithium-ion structural batteries had capacity retention of over 80% exceeding 100 cycles with an average energy density of 52 W h kg−1 and a maximum energy density of 58 W h kg−1. Most scientific developments in the field of structural energy have been done with supercapacitors. Most scientific developments with structural batteries have been done where batteries are simply incorporated into the structural element. That method has limited advantages and can create mechanical disadvantages. This study aims to show that a large improvement in structure energy research can be made by improving the interface between the structural device and the battery.

Keywords: composite materials, electrochemical performance, mechanical properties, polymer interface, structural batteries

Procedia PDF Downloads 76

Authors: S. Neelima, P. S. Subramanyam

Abstract:

The major tool for distribution planning is load forecasting, which is the anticipation of the load in advance. Artificial neural networks have found wide applications in load forecasting to obtain an efficient strategy for planning and management. In this paper, the application of neural networks to study the design of short term load forecasting (STLF) Systems was explored. Our work presents a pragmatic methodology for short term load forecasting (STLF) using proposed two-stage model of wavelet transform (WT) and artificial neural network (ANN). It is a two-stage prediction system which involves wavelet decomposition of input data at the first stage and the decomposed data with another input is trained using a separate neural network to forecast the load. The forecasted load is obtained by reconstruction of the decomposed data. The hybrid model has been trained and validated using load data from Telangana State Electricity Board.

Keywords: electrical distribution systems, wavelet transform (WT), short term load forecasting (STLF), artificial neural network (ANN)

Procedia PDF Downloads 398

Authors: Nivine Abbas, Sergio Lagomarsino, Serena Cattari

Abstract:

The resistance domain of a generally loaded rigid shallow foundation is normally represented as an interaction diagram limited by a failure surface in the three dimensional (3D) load space (N, V, M), where N is the vertical centric load component, V is the horizontal load component and M is the bending moment component. Usually, this resistance domain is constructed neglecting the foundation sliding mechanism that take place at the level of soil-foundation interface once the applied horizontal load exceeds the interface frictional resistance of the foundation. This issue is translated in the literature by the fact that the failure limit in the (2D) load space (N, V) is constructed as a parabola having an initial slope, at the center of the coordinate system, that depends, in some works, only of the soil friction angle, and in other works, has an empirical value. However, considering a given geometry of the foundation lying on a given soil type, the initial slope of the failure limit must change, for instance, when varying the roughness of the foundation surface at its interface with the soil. The present study discusses the effect of the soil-foundation interface condition on the construction of the resistance domain, and proposes a correction to be applied to the failure limit in order to overcome this effect.

Keywords: soil-foundation interface, sliding mechanism, soil shearing, resistance domain, rigid shallow foundation

Procedia PDF Downloads 417

Authors: Han Bing, Yin Zhenjie

Abstract:

In order to analyze the status of a diesel engine, as well as conduct fault prediction, a new prediction model based on a gray system is proposed in this paper, which takes advantage of the neural network and the genetic algorithm. The proposed GBPGA prediction model builds on the GM (1.5) model and uses a neural network, which is optimized by a genetic algorithm to construct the error compensator. We verify our proposed model on the diesel faulty simulation data and the experimental results show that GBPGA has the potential to employ fault prediction on diesel.

Keywords: fault prediction, neural network, GM(1, 5) genetic algorithm, GBPGA

Procedia PDF Downloads 273

Authors: Kedwadee Sombultawee, Sakun Boon-Itt

Abstract:

This research demonstrates a systematic literature review of 62 peer-reviewed articles published in academic journals from 2000-2016 focusing on the operation and marketing interface area. The findings show the three major clusters of recent research domains, which is a review of the alignment between operations and marketing, identification of variables that impact the company and analysis of the effect of interface. Moreover, the Main Path Analysis (MPA) is mapped to show the knowledge structure of the operation and marketing interface issue. Most of the empirical research focused on company performance and new product development then analyzed the data by the structural equation model or regression. Whereas, some scholars studied the conflict of these two functions and proposed the requirement or step for alignment. Finally, the gaps in the literature are provided for future research directions.

Keywords: operations management, marketing, interface, systematic literature review

Procedia PDF Downloads 250

Authors: J. Harrison Kurunathan, R. Jayaparvathy

Abstract:

"Assistive Robotics" is the field that deals with the study of robots that helps in human motion and also empowers human abilities by interfacing the robotic systems to be manipulated by human motion. The proposed model is a robotic arm that works as a haptic interface on the basis on accelerometers and DC motors that will function with respect to the movement of the human muscle. The proposed model would effectively work as a haptic interface that would reduce human effort in the field of defense and rescue. This can be used in very critical conditions like fire accidents to avoid causalities.

Keywords: accelerometers, haptic interface, servo motors, signal processing

Procedia PDF Downloads 363

Authors: Jie Zhao, Meng Su

Abstract:

Image recognition, as one of the most critical technologies in computer vision, works to help machine-like robotics understand a scene, that is, if deployed appropriately, will trigger the revolution in remote sensing and industry automation. With the developments of AI technologies, there are many prevailing and sophisticated neural networks as technologies developed for image recognition. However, computer vision platforms as hardware, supporting neural networks for image recognition, as crucial as the neural network technologies, need to be more congruently addressed as the research subjects. In contrast, different computer vision platforms are deterministic to leverage the performance of different neural networks for recognition. In this paper, three different computer vision platforms – Jetson Nano(with 4GB), a standalone laptop(with RTX 3000s, using CUDA), and Google Colab (web-based, using GPU) are explored and four prominent neural network architectures (including AlexNet, VGG(16/19), GoogleNet, and ResNet(18/34/50)), are investigated. In the context of pairwise usage between different computer vision platforms and distinctive neural networks, with the merits of recognition accuracy and time efficiency, the performances are evaluated. In the case study using public imageNets, our findings provide a nuanced perspective on optimizing image recognition tasks across Edge-AI platforms, offering guidance on selecting appropriate neural network structures to maximize performance under hardware constraints.

Keywords: alexNet, VGG, googleNet, resNet, Jetson nano, CUDA, COCO-NET, cifar10, imageNet large scale visual recognition challenge (ILSVRC), google colab

Procedia PDF Downloads 52

Authors: Abdolreza Memari

Abstract:

In this article in order to estimate the viscosity of crude oil,a numerical method has been used. We use this method to measure the crude oil's viscosity for 3 states: Saturated oil's viscosity, viscosity above the bubble point and viscosity under the saturation pressure. Then the crude oil's viscosity is estimated by using KHAN model and roller ball method. After that using these data that include efficient conditions in measuring viscosity, the estimated viscosity by the presented method, a radial based neural method, is taught. This network is a kind of two layered artificial neural network that its stimulation function of hidden layer is Gaussian function and teaching algorithms are used to teach them. After teaching radial based neural network, results of experimental method and artificial intelligence are compared all together. Teaching this network, we are able to estimate crude oil's viscosity without using KHAN model and experimental conditions and under any other condition with acceptable accuracy. Results show that radial neural network has high capability of estimating crude oil saving in time and cost is another advantage of this investigation.

Keywords: viscosity, Iranian crude oil, radial based, neural network, roller ball method, KHAN model

Procedia PDF Downloads 459

Authors: Samuel Nii Tackie, Oyebade K. Oyedotun, Ebenezer O. Olaniyi, Adnan Khashman

Abstract:

Artificial neural networks have been used in different fields of artificial intelligence, and more specifically in machine learning. Although, other machine learning options are feasible in most situations, but the ease with which neural networks lend themselves to different problems which include pattern recognition, image compression, classification, computer vision, regression etc. has earned it a remarkable place in the machine learning field. This research exploits neural networks as a data mining tool in predicting the number of times a student repeats a course, considering some attributes relating to the course itself, the teacher, and the particular student. Neural networks were used in this work to map the relationship between some attributes related to students’ course assessment and the number of times a student will possibly repeat a course before he passes. It is the hope that the possibility to predict students’ performance from such complex relationships can help facilitate the fine-tuning of academic systems and policies implemented in learning environments. To validate the power of neural networks in data mining, Turkish students’ performance database has been used; feedforward and radial basis function networks were trained for this task; and the performances obtained from these networks evaluated in consideration of achieved recognition rates and training time.

Keywords: artificial neural network, data mining, classification, students’ evaluation

Procedia PDF Downloads 568

Authors: Oluwaponmile David Alao

Abstract:

Misdiagnosis has been the major problem in health sector. Heart attack has been one of diseases that have high level of misdiagnosis recorded on the part of physicians. In this paper, an intelligent system has been developed for diagnosis of heart attack in the health sector. Dataset of heart attack obtained from UCI repository has been used. This dataset is made up of thirteen attributes which are very vital in diagnosis of heart disease. The system is developed on the multilayer perceptron trained with back propagation neural network then simulated with feed forward neural network and a recognition rate of 87% was obtained which is a good result for diagnosis of heart attack in medical field.

Keywords: heart attack, artificial neural network, diagnosis, intelligent system

Procedia PDF Downloads 621

Authors: Ghorab Sara, Meziani Lila, Rubin Harvey Stuart

Abstract:

The rapid growth of deep learning has led to intricate and resource-intensive deep neural networks widely used in computer vision tasks. However, their complexity results in high computational demands and memory usage, hindering real-time application. To address this, research focuses on model compression techniques. The paper provides an overview of recent advancements in compressing neural networks and categorizes the various methods into four main approaches: network pruning, quantization, network decomposition, and knowledge distillation. This paper aims to provide a comprehensive outline of both the advantages and limitations of each method.

Keywords: model compression, deep neural network, pruning, knowledge distillation, quantization, low-rank decomposition

Procedia PDF Downloads 6