Search results for: Chandan Deep Singh
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 3028

Search results for: Chandan Deep Singh

2758 A Comparison of Methods for Neural Network Aggregation

Authors: John Pomerat, Aviv Segev

Abstract:

Recently, deep learning has had many theoretical breakthroughs. For deep learning to be successful in the industry, however, there need to be practical algorithms capable of handling many real-world hiccups preventing the immediate application of a learning algorithm. Although AI promises to revolutionize the healthcare industry, getting access to patient data in order to train learning algorithms has not been easy. One proposed solution to this is data- sharing. In this paper, we propose an alternative protocol, based on multi-party computation, to train deep learning models while maintaining both the privacy and security of training data. We examine three methods of training neural networks in this way: Transfer learning, average ensemble learning, and series network learning. We compare these methods to the equivalent model obtained through data-sharing across two different experiments. Additionally, we address the security concerns of this protocol. While the motivating example is healthcare, our findings regarding multi-party computation of neural network training are purely theoretical and have use-cases outside the domain of healthcare.

Keywords: neural network aggregation, multi-party computation, transfer learning, average ensemble learning

Procedia PDF Downloads 118
2757 A Unified Deep Framework for Joint 3d Pose Estimation and Action Recognition from a Single Color Camera

Authors: Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio Velastin

Abstract:

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from color video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important key points of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the Spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, Microsoft Research Redmond (MSR) Action3D, and Stony Brook University (SBU) Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that our method requires a low computational budget for training and inference.

Keywords: human action recognition, pose estimation, D-CNN, deep learning

Procedia PDF Downloads 105
2756 Electrospun Zinc Oxide Nanowires as Highly Sensitive Piezoelectric Transduction Elements for Nano-Scale Devices

Authors: K. Brince Paul, Nagendra Pratap Singh, Shiv Govind Singh, Siva Rama Krishna Vanjari

Abstract:

In this paper, we report optimized procedure for synthesizing highly oriented, horizontally aligned, Zinc oxide (ZnO) nanowires targeted towards developing highly sensitive piezoelectric transduction elements. The synthesis was carried out using Electrospinning technique, a facile, robust, low cost technique for producing nanowires. The as-synthesized ZnO nanowires were characterized by X-ray powder diffraction (XRD), Field Emission scanning electron microscopy (FESEM) and Energy-dispersive X-ray spectroscopy (EDX).The Piezoelectric behavior of these nanowires was characterized using Peizoelectric Force microscopy (PFM). A very high d33 coefficient of 23.1 pm/V obtained through the PFM measurements is an indicative of its potential application towards developing miniaturized piezoelectric transduction elements for nanoscale devices.

Keywords: electrospinning, piezoelectric, technique, zinc oxide

Procedia PDF Downloads 365
2755 Parallel Processing in near Absence of Attention: A Study Using Dual-Task Paradigm

Authors: Aarushi Agarwal, Tara Singh, I.L Singh, Anju Lata Singh, Trayambak Tiwari

Abstract:

Simple discrimination in near absence of attention has been widely observed. Dual-task studies with natural scenes studies have been claimed as being preattentive in nature that facilitated categorization simultaneously with the attentional demanding task. So in this study, multiple images at the periphery are presented, initiating parallel processing in near absence of attention. For the central demanding task rotated letters were presented in both conditions, while in periphery natural and animal images were presented. To understand the breakpoint of ability to perform in near absence of attention one, two and three peripheral images were presented simultaneously with central task and subjects had to respond when all belong to the same category. Individual participant performance did not show a significant difference in both conditions central and peripheral task when the single peripheral image was shown. In case of two images high-level parallel processing could take place with little attentional resources. The eye tracking results supports the evidence as no major saccade was made in a large number of trials. Three image presentations proved to be a breaking point of the capacities to perform outside attentional assistance as participants showed a confused eye gaze pattern which failed to make the natural and animal image discriminations. Thus, we can conclude attention and awareness being independent mechanisms having limited capacities.

Keywords: attention, dual task pardigm, parallel processing, break point, saccade

Procedia PDF Downloads 182
2754 Deep Learning for Renewable Power Forecasting: An Approach Using LSTM Neural Networks

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 220
2753 Automated Weight Painting: Using Deep Neural Networks to Adjust 3D Mesh Skeletal Weights

Authors: John Gibbs, Benjamin Flanders, Dylan Pozorski, Weixuan Liu

Abstract:

Weight Painting–adjusting the influence a skeletal joint has on a given vertex in a character mesh–is an arduous and time con- suming part of the 3D animation pipeline. This process generally requires a trained technical animator and many hours of work to complete. Our skiNNer plug-in, which works within Autodesk’s Maya 3D animation software, uses Machine Learning and data pro- cessing techniques to create a deep neural network model that can accomplish the weight painting task in seconds rather than hours for bipedal quasi-humanoid character meshes. In order to create a properly trained network, a number of challenges were overcome, including curating an appropriately large data library, managing an arbitrary 3D mesh size, handling arbitrary skeletal architectures, accounting for extreme numeric values (most data points are near 0 or 1 for weight maps), and constructing an appropriate neural network model that can properly capture the high frequency alter- ation between high weight values (near 1.0) and low weight values (near 0.0). The arrived at neural network model is a cross between a traditional CNN, deep residual network, and fully dense network. The resultant network captures the unusually hard-edged features of a weight map matrix, and produces excellent results on many bipedal models.

Keywords: 3d animation, animation, character, rigging, skinning, weight painting, machine learning, artificial intelligence, neural network, deep neural network

Procedia PDF Downloads 229
2752 Assessing Performance of Data Augmentation Techniques for a Convolutional Network Trained for Recognizing Humans in Drone Images

Authors: Masood Varshosaz, Kamyar Hasanpour

Abstract:

In recent years, we have seen growing interest in recognizing humans in drone images for post-disaster search and rescue operations. Deep learning algorithms have shown great promise in this area, but they often require large amounts of labeled data to train the models. To keep the data acquisition cost low, augmentation techniques can be used to create additional data from existing images. There are many techniques of such that can help generate variations of an original image to improve the performance of deep learning algorithms. While data augmentation is potentially assumed to improve the accuracy and robustness of the models, it is important to ensure that the performance gains are not outweighed by the additional computational cost or complexity of implementing the techniques. To this end, it is important to evaluate the impact of data augmentation on the performance of the deep learning models. In this paper, we evaluated the most currently available 2D data augmentation techniques on a standard convolutional network which was trained for recognizing humans in drone images. The techniques include rotation, scaling, random cropping, flipping, shifting, and their combination. The results showed that the augmented models perform 1-3% better compared to a base network. However, as the augmented images only contain the human parts already visible in the original images, a new data augmentation approach is needed to include the invisible parts of the human body. Thus, we suggest a new method that employs simulated 3D human models to generate new data for training the network.

Keywords: human recognition, deep learning, drones, disaster mitigation

Procedia PDF Downloads 52
2751 A Follow up Study on Indoor 222Rn, 220Rn and Their Decay Product Concentrations in a Mineralized Zone of Himachal Pradesh, India

Authors: B. S. Bajwa, Parminder Singh, Prabhjot Singh, Surinder Singh, B. K. Sahoo, B. K. Sapra

Abstract:

A follow up study was taken up in a mineralized zone situated in Hamirpur district, Himachal Pradesh, India to investigate high values of radon concentration reported in past studies as well to update the old radon data based on bare SSNTD technique. In the present investigation, indoor radon, thoron and their decay products concentrations have been measured using the newly developed Radon-Thoron discriminating diffusion chamber with single entry face, direct radon and thoron progeny sensors (DRPS/DTPS) respectively. The measurements have been carried out in seventy five dwellings of fourteen different villages. Houses were selected taking into consideration of the past data as well as the type of houses such as mud, concrete, brick etc. It was observed that high values of earlier reported radon concentrations were mainly because of thoron interference in the Solid State Nuclear Track Detector (LR-115 type II) exposed in bare mode. Now, the average concentration values and the estimated annual inhalation dose in these villages have been found to be within the reference level as recommended by the ICRP. The annual average indoor radon and thoron concentrations observed in these dwellings have been found to vary from 44±12-157±73 Bq m-3 and 44±11-240±125 Bq m-3 respectively. The equilibrium equivalent concentrations of radon and thoron decay products have been observed to be in the range of 10-63 Bq m-3 and 1-5 Bq m-3 respectively.

Keywords: radon, thoron, progeny concentration, dosimeter

Procedia PDF Downloads 415
2750 Depiction of a Circulated Double Psi-Shaped Microstrip Antenna for Ku-Band Satellite Applications

Authors: M. Naimur Rahman, Mohammad Tariqul Islam, Mandeep Singh Jit Singh, Norbahiah Misran

Abstract:

This paper presents the architecture and exploration of a compact, circulated double Psi-shaped microstrip patch antenna for Ku-band satellite applications. The antenna is composed of the double Psi-shaped patch in opposite focus which is circulated with a ring. The antenna size is 24 mm × 18 mm and the prototype is imprinted on Rogers RT/duroid 5880 materials with the depth of 1.57 mm. The substrate has a relative permittivity of 2.2 and the dielectric constant of 0.0009. The excitation is supplied through a 50Ω microstrip line. The performance of the presented antenna has been simulated and verified with the High-Frequency Structural Simulator (HFSS). The results depict that the antenna covers the frequency spectrum 14.6 - 17.4 GHz (Ku-band) with 10 dB return loss. The antenna has a 4.40 dBi maximum gain with stable radiation patterns throughout the operating band which makes the proposed antenna compatible for the satellite application in Ku-band.

Keywords: Ku-band antenna, microstrip antenna, psi-shaped antenna, satellite applications

Procedia PDF Downloads 261
2749 Comparative Performance and Emission Analysis of Diesel Engine Fueled with Diesel and Bitter Apricot Kernal Oil Biodiesel Blends

Authors: Virender Singh Gurau, Akash Deep, Sarbjot S. Sandhu

Abstract:

Vegetable oils are produced from numerous oil seed crops. While all vegetable oils have high energy content, most require some processing to assure safe use in internal combustion engines. Some of these oils already have been evaluated as substitutes for diesel fuels. In the present research work Bitter Apricot kernel oil was employed as a feedstock for the production of biodiesel. The physicochemical properties of the Bitter Apricot kernel oil methyl ester were investigated as per ASTM D6751. From the series of engine testing, it is concluded that the brake thermal efficiency (BTE) with biodiesel blend was little lower than that of diesel. BSEC is slightly higher for Bitter apricot kernel oil methyl ester blends than neat diesel. For biodiesel blends, CO emission was lower than diesel fuel as B 20 reduced CO emissions by 18.75%. Approximately 11% increase in NOx emission was observed with 20% biodiesel blend. It is observed that HC emissions tend to decrease for biodiesel based fuels and Smoke opacity was found lower for biodiesel blends in comparison to diesel fuel.

Keywords: biodiesel, transesterification, bitter apricot kernel oil, performance and emission testing

Procedia PDF Downloads 286
2748 Hyperspectral Band Selection for Oil Spill Detection Using Deep Neural Network

Authors: Asmau Mukhtar Ahmed, Olga Duran

Abstract:

Hydrocarbon (HC) spills constitute a significant problem that causes great concern to the environment. With the latest technology (hyperspectral images) and state of the earth techniques (image processing tools), hydrocarbon spills can easily be detected at an early stage to mitigate the effects caused by such menace. In this study; a controlled laboratory experiment was used, and clay soil was mixed and homogenized with different hydrocarbon types (diesel, bio-diesel, and petrol). The different mixtures were scanned with HYSPEX hyperspectral camera under constant illumination to generate the hypersectral datasets used for this experiment. So far, the Short Wave Infrared Region (SWIR) has been exploited in detecting HC spills with excellent accuracy. However, the Near-Infrared Region (NIR) is somewhat unexplored with regards to HC contamination and how it affects the spectrum of soils. In this study, Deep Neural Network (DNN) was applied to the controlled datasets to detect and quantify the amount of HC spills in soils in the Near-Infrared Region. The initial results are extremely encouraging because it indicates that the DNN was able to identify features of HC in the Near-Infrared Region with a good level of accuracy.

Keywords: hydrocarbon, Deep Neural Network, short wave infrared region, near-infrared region, hyperspectral image

Procedia PDF Downloads 77
2747 Vertical Structure and Frequencies of Deep Convection during Active Periods of the West African Monsoon Season

Authors: Balogun R. Ayodeji, Adefisan E. Adesanya, Adeyewa Z. Debo, E. C. Okogbue

Abstract:

Deep convective systems during active periods of the West African monsoon season have not been properly investigated over better temporal and spatial resolution in West Africa. Deep convective systems are investigated over seven climatic zones of the West African sub-region, which are; west-coast rainforest, dry rainforest, Nigeria-Cameroon rainforest, Nigeria savannah, Central African and South Sudan (CASS) Savannah, Sudano-Sahel, and Sahel, using data from Tropical Rainfall Measurement Mission (TRMM) Precipitation Feature (PF) database. The vertical structure of the convective systems indicated by the presence of at least one 40 dBZ and reaching (attaining) at least 1km in the atmosphere showed strong core (highest frequency (%)) of reflectivity values around 2 km which is below the freezing level (4-5km) for all the zones. Echoes are detected above the 15km altitude much more frequently in the rainforest and Savannah zones than the Sudano and Sahel zones during active periods in March-May (MAM), whereas during active periods in June-September (JJAS) the savannahs, Sudano and Sahel zones convections tend to reach higher altitude more frequently than the rainforest zones. The percentage frequencies of deep convection indicated that the occurrences of the systems are within the range of 2.3-2.8% during both March-May (MAM) and June-September (JJAS) active periods in the rainforest and savannah zones. On the contrary, the percentage frequencies were found to be less than 2% in the Sudano and Sahel zones, except during the active-JJAS period in the Sudano zone.

Keywords: active periods, convective system, frequency, reflectivity

Procedia PDF Downloads 111
2746 Dissipation of Tebuconazole in Cropland Soils as Affected by Soil Factors

Authors: Bipul Behari Saha, Sunil Kumar Singh, P. Padmaja, Kamlesh Vishwakarma

Abstract:

Dissipation study of tebuconazole in alluvial, black and deep-black clayey soils collected from paddy, mango and peanut cropland of tropical agro-climatic zone of India at three concentration levels were carried out for monitoring the water contamination through persisted residual toxicity. The soil-slurry samples were analyzed by capillary GC-NPD methods followed by ultrasound-assisted extraction (UAE) technique and cleanup process. An excellent linear relationship between peak area and concentration obtained in the range 1 to 50 μgkg-1. The detection (S/N, 3 ± 0.5) and quantification (S/N, 7.5 ± 2.5) limits were 3 and 10 μgkg-1 respectively. Well spiked recoveries were achieved from 96.28 to 99.33 % at levels 5 and 20 μgkg-1 and method precision (% RSD) was ≤ 5%. The soils dissipation of tebuconazole was fitted in first order kinetic-model with half-life between 34.48 to 48.13 days. The soil organic-carbon (SOC) content correlated well with the dissipation rate constants (DRC) of the fungicide Tebuconazole. An increase in the SOC content resulted in faster dissipation. The results indicate that the soil organic carbon and tebuconazole concentrations plays dominant role in dissipation processes. The initial concentration illustrated that the degradation rate of tebuconazole in soils was concentration dependent.

Keywords: cropland soil, dissipation, laboratory incubation, tebuconazole

Procedia PDF Downloads 216
2745 Deepnic, A Method to Transform Each Variable into Image for Deep Learning

Authors: Nguyen J. M., Lucas G., Brunner M., Ruan S., Antonioli D.

Abstract:

Deep learning based on convolutional neural networks (CNN) is a very powerful technique for classifying information from an image. We propose a new method, DeepNic, to transform each variable of a tabular dataset into an image where each pixel represents a set of conditions that allow the variable to make an error-free prediction. The contrast of each pixel is proportional to its prediction performance and the color of each pixel corresponds to a sub-family of NICs. NICs are probabilities that depend on the number of inputs to each neuron and the range of coefficients of the inputs. Each variable can therefore be expressed as a function of a matrix of 2 vectors corresponding to an image whose pixels express predictive capabilities. Our objective is to transform each variable of tabular data into images into an image that can be analysed by CNNs, unlike other methods which use all the variables to construct an image. We analyse the NIC information of each variable and express it as a function of the number of neurons and the range of coefficients used. The predictive value and the category of the NIC are expressed by the contrast and the color of the pixel. We have developed a pipeline to implement this technology and have successfully applied it to genomic expressions on an Affymetrix chip.

Keywords: tabular data, deep learning, perfect trees, NICS

Procedia PDF Downloads 44
2744 Online Yoga Asana Trainer Using Deep Learning

Authors: Venkata Narayana Chejarla, Nafisa Parvez Shaik, Gopi Vara Prasad Marabathula, Deva Kumar Bejjam

Abstract:

Yoga is an advanced, well-recognized method with roots in Indian philosophy. Yoga benefits both the body and the psyche. Yoga is a regular exercise that helps people relax and sleep better while also enhancing their balance, endurance, and concentration. Yoga can be learned in a variety of settings, including at home with the aid of books and the internet as well as in yoga studios with the guidance of an instructor. Self-learning does not teach the proper yoga poses, and doing them without the right instruction could result in significant injuries. We developed "Online Yoga Asana Trainer using Deep Learning" so that people could practice yoga without a teacher. Our project is developed using Tensorflow, Movenet, and Keras models. The system makes use of data from Kaggle that includes 25 different yoga poses. The first part of the process involves applying the movement model for extracting the 17 key points of the body from the dataset, and the next part involves preprocessing, which includes building a pose classification model using neural networks. The system scores a 98.3% accuracy rate. The system is developed to work with live videos.

Keywords: yoga, deep learning, movenet, tensorflow, keras, CNN

Procedia PDF Downloads 199
2743 Object-Scene: Deep Convolutional Representation for Scene Classification

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

Abstract:

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

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

Procedia PDF Downloads 292
2742 An Ensemble Deep Learning Architecture for Imbalanced Classification of Thoracic Surgery Patients

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

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

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

Procedia PDF Downloads 103
2741 Code Embedding for Software Vulnerability Discovery Based on Semantic Information

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

Abstract:

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

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

Procedia PDF Downloads 118
2740 A Survey of Field Programmable Gate Array-Based Convolutional Neural Network Accelerators

Authors: Wei Zhang

Abstract:

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

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

Procedia PDF Downloads 84
2739 Assessment of Procurement-Demand of Milk Plant Using Quality Control Tools: A Case Study

Authors: Jagdeep Singh, Prem Singh

Abstract:

Milk is considered as an essential and complete food. The present study was conducted at Milk Plant Mohali especially in reference to the procurement section where the cash inflow was maximum, with the objective to achieve higher productivity and reduce wastage of milk. In milk plant it was observed that during the month of Jan-2014 to March-2014 the average procurement of milk was Rs. 4, 19, 361 liter per month and cost of procurement of milk is Rs 35/- per liter. The total cost of procurement thereby equal to Rs. 1crore 46 lakh per month, but there was mismatch in procurement-production of milk, which leads to an average loss of Rs. 12, 94, 405 per month. To solve the procurement-production problem Quality Control Tools like brainstorming, Flow Chart, Cause effect diagram and Pareto analysis are applied wherever applicable. With the successful implementation of Quality Control tools an average saving of Rs. 4, 59, 445 per month is done.

Keywords: milk, procurement-demand, quality control tools,

Procedia PDF Downloads 480
2738 Satellite Imagery Classification Based on Deep Convolution Network

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

Abstract:

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

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

Procedia PDF Downloads 262
2737 Accuracy Improvement of Traffic Participant Classification Using Millimeter-Wave Radar by Leveraging Simulator Based on Domain Adaptation

Authors: Tokihiko Akita, Seiichi Mita

Abstract:

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

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

Procedia PDF Downloads 47
2736 Comprehensive Machine Learning-Based Glucose Sensing from Near-Infrared Spectra

Authors: Bitewulign Mekonnen

Abstract:

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

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

Procedia PDF Downloads 45
2735 Optimal Placement of Phasor Measurement Units Using Gravitational Search Method

Authors: Satyendra Pratap Singh, S. P. Singh

Abstract:

This paper presents a methodology using Gravitational Search Algorithm for optimal placement of Phasor Measurement Units (PMUs) in order to achieve complete observability of the power system. The objective of proposed algorithm is to minimize the total number of PMUs at the power system buses, which in turn minimize installation cost of the PMUs. In this algorithm, the searcher agents are collection of masses which interact with each other using Newton’s laws of gravity and motion. This new Gravitational Search Algorithm based method has been applied to the IEEE 14-bus, IEEE 30-bus and IEEE 118-bus test systems. Case studies reveal optimal number of PMUs with better observability by proposed method.

Keywords: gravitational search algorithm (GSA), law of motion, law of gravity, observability, phasor measurement unit

Procedia PDF Downloads 465
2734 Preparation and Characterization of Lanthanum Aluminate Electrolyte Material for Solid Oxide Fuel Cell

Authors: Onkar Nath Verma, Nitish Kumar Singh, Raghvendra, Pravin Kumar, Prabhakar Singh

Abstract:

The perovskite type electrolyte material LaAlO3 was prepared by solution based auto-combustion method using Al (NO3)3.6H2O, La2O3 with dilute nitrate acid (HNO3) as precursors and citric acid (C6H8O7.H2O) as a fuel. The synthesis protocol gave an easy processing of the LaAlO3 nano-particles. The XRD measurement revealed that the material has single phase with space group R-3c (rhombohedral). Thermal behavior was measured by simultaneous differential thermal analysis and thermo gravimetric analysis (DTA-TGA). The compact pellet density was determined. Also, the surface morphology was studied using scanning electron microscopy (SEM). The conductivity of LaAlO3 was measured employing LCR meter and found to increase with increasing temperature. This increase in conductivity may be attributed to increased mobility of oxide ion.

Keywords: perovskite, LaAlO3, XRD, SEM, DTA-TGA, SOFC

Procedia PDF Downloads 461
2733 Analysis of Facial Expressions with Amazon Rekognition

Authors: Kashika P. H.

Abstract:

The development of computer vision systems has been greatly aided by the efficient and precise detection of images and videos. Although the ability to recognize and comprehend images is a strength of the human brain, employing technology to tackle this issue is exceedingly challenging. In the past few years, the use of Deep Learning algorithms to treat object detection has dramatically expanded. One of the key issues in the realm of image recognition is the recognition and detection of certain notable people from randomly acquired photographs. Face recognition uses a way to identify, assess, and compare faces for a variety of purposes, including user identification, user counting, and classification. With the aid of an accessible deep learning-based API, this article intends to recognize various faces of people and their facial descriptors more accurately. The purpose of this study is to locate suitable individuals and deliver accurate information about them by using the Amazon Rekognition system to identify a specific human from a vast image dataset. We have chosen the Amazon Rekognition system, which allows for more accurate face analysis, face comparison, and face search, to tackle this difficulty.

Keywords: Amazon rekognition, API, deep learning, computer vision, face detection, text detection

Procedia PDF Downloads 71
2732 The Rigor and Relevance of the Mathematics Component of the Teacher Education Programmes in Jamaica: An Evaluative Approach

Authors: Avalloy McCarthy-Curvin

Abstract:

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

Keywords: relevance, rigor, deep understanding, formative evaluation

Procedia PDF Downloads 197
2731 A Deep Learning Approach to Detect Complete Safety Equipment for Construction Workers Based on YOLOv7

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

Abstract:

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

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

Procedia PDF Downloads 24
2730 A CPW Fed Bowtie Microstrip Slot Antenna for Wireless Applications

Authors: Amandeep Singh, Surinder Singh

Abstract:

A slotted Bow-Tie microstrip patch antenna utilizing input of coplanar waveguide for high frequency wireless applications is proposed and analyzed in this work. RT/Duroid 5880 with its dielectric constant 2.2 is opted for the experimentation to analyze the proposed microstrip slot antenna. This antenna is exclusively designed for the frequency range of 10 GHz to 11 GHz and modelling parameters are obtained from the already existing data and dimensions of antenna are adjusted by employing some corrugated slots in the Bowtie shape to obtain the required bandwidth so that it can radiate within the specified range. The characteristics of proposed antenna are measured by a FEM electromagnetic field solver and it is found that the reflection coefficient, voltage standing wave ratio, radiated gain, feed point impedance, radiation efficiency are in a good agreement. This antenna is also exhibiting an absolute bandwidth of 1000 MHz. The validated results indicate that the proposed bowtie microstrip slot antenna comes under the wideband category and utilized in the wireless application ranges between the 10 GHz – 11 GHz.

Keywords: CPW, bowtie, FEM, corrugated

Procedia PDF Downloads 467
2729 Automatic Product Identification Based on Deep-Learning Theory in an Assembly Line

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

Abstract:

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

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

Procedia PDF Downloads 122