scholarly journals Regularized Evolution for Image Classifier Architecture Search

2019 ◽  
Vol 33 ◽  
pp. 4780-4789 ◽  
Author(s):  
Esteban Real ◽  
Alok Aggarwal ◽  
Yanping Huang ◽  
Quoc V. Le
Keyword(s):  
Neural Network ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Simple Method ◽  
Current State ◽  
Network Topologies ◽  
Comparable Accuracy ◽  
Tournament Selection ◽  
Complex Architecture ◽  
First Time

The effort devoted to hand-crafting neural network image classifiers has motivated the use of architecture search to discover them automatically. Although evolutionary algorithms have been repeatedly applied to neural network topologies, the image classifiers thus discovered have remained inferior to human-crafted ones. Here, we evolve an image classifier— AmoebaNet-A—that surpasses hand-designs for the first time. To do this, we modify the tournament selection evolutionary algorithm by introducing an age property to favor the younger genotypes. Matching size, AmoebaNet-A has comparable accuracy to current state-of-the-art ImageNet models discovered with more complex architecture-search methods. Scaled to larger size, AmoebaNet-A sets a new state-of-theart 83.9% top-1 / 96.6% top-5 ImageNet accuracy. In a controlled comparison against a well known reinforcement learning algorithm, we give evidence that evolution can obtain results faster with the same hardware, especially at the earlier stages of the search. This is relevant when fewer compute resources are available. Evolution is, thus, a simple method to effectively discover high-quality architectures.

scholarly journals Electro-Quasistatic Animal Body Communication for Untethered Rodent Biopotential Recording

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shreeya Sriram ◽  
Shitij Avlani ◽  
Matthew P. Ward ◽  
Shreyas Sen
Keyword(s):  
Lower Energy ◽  
Sensor Node ◽  
State Of The Art ◽  
The Body ◽  
Animal Body ◽  
Current State ◽  
Communication Modalities ◽  
First Time ◽  
Biopotential Recording

AbstractContinuous multi-channel monitoring of biopotential signals is vital in understanding the body as a whole, facilitating accurate models and predictions in neural research. The current state of the art in wireless technologies for untethered biopotential recordings rely on radiative electromagnetic (EM) fields. In such transmissions, only a small fraction of this energy is received since the EM fields are widely radiated resulting in lossy inefficient systems. Using the body as a communication medium (similar to a ’wire’) allows for the containment of the energy within the body, yielding order(s) of magnitude lower energy than radiative EM communication. In this work, we introduce Animal Body Communication (ABC), which utilizes the concept of using the body as a medium into the domain of untethered animal biopotential recording. This work, for the first time, develops the theory and models for animal body communication circuitry and channel loss. Using this theoretical model, a sub-inch$$^3$$ 3 [1″ × 1″ × 0.4″], custom-designed sensor node is built using off the shelf components which is capable of sensing and transmitting biopotential signals, through the body of the rat at significantly lower powers compared to traditional wireless transmissions. In-vivo experimental analysis proves that ABC successfully transmits acquired electrocardiogram (EKG) signals through the body with correlation $$>99\%$$ > 99 % when compared to traditional wireless communication modalities, with a 50$$\times$$ × reduction in power consumption.

scholarly journals A Step by Step Methodology for Building Sustainable Cementitious Matrices

2020 ◽  
Vol 10 (8) ◽  
pp. 2955 ◽  
Author(s):  
Styliani Papatzani ◽  
Kevin Paine
Keyword(s):  
Fly Ash ◽  
Portland Cement ◽  
Silica Fume ◽  
Carbon Footprint ◽  
State Of The Art ◽  
Cost Effective ◽  
Strength Development ◽  
Low Carbon ◽  
Current State ◽  
First Time

In an effort to produce cost-effective and environmentally friendly cementitious binders. mainly ternary (Portland cement + limestone + pozzolanas) formulations have been investigated so far. Various proportions of constituents have been suggested, all, however, employing typical Portland cement (PC) substitution rates, as prescribed by the current codes. With the current paper a step by step methodology on developing low carbon footprint binary, ternary and quaternary cementitious binders is presented (PC replacement up to 57%). Best performing binary (60% PC and 40% LS (limestone)) and ternary formulations (60% PC, 20% LS, 20% FA (fly ash) or 43% PC, 20% LS 37% FA) were selected on the grounds of sustainability and strength development and were further optimized with the addition of silica fume. For the first time a protocol for successfully selecting and testing binders was discussed and the combined effect of highly pozzolanic constituents in low PC content formulations was assessed and a number of successful matrices were recommended. The present paper enriched the current state of the art in composite low carbon footprint cementitious binders and can serve as a basis for further enhancements by other researchers in the field.

scholarly journals A RESTful middleware for AI controlled sensors, actuators and smart devices

2019 ◽  
Vol 11 (7) ◽  
pp. 2963-2986 ◽  
Author(s):  
Nikos Dipsis ◽  
Kostas Stathis
Keyword(s):  
Smart Home ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Smart Devices ◽  
Machine Learning Algorithm ◽  
Concrete Case ◽  
Domain Specific ◽  
Sensor Actuator ◽  
Current State

Abstract The numerous applications of internet of things (IoT) and sensor networks combined with specialized devices used in each has led to a proliferation of domain specific middleware, which in turn creates interoperability issues between the corresponding architectures and the technologies used. But what if we wanted to use a machine learning algorithm to an IoT application so that it adapts intelligently to changes of the environment, or enable a software agent to enrich with artificial intelligence (AI) a smart home consisting of multiple and possibly incompatible technologies? In this work we answer these questions by studying a framework that explores how to simplify the incorporation of AI capabilities to existing sensor-actuator networks or IoT infrastructures making the services offered in such settings smarter. Towards this goal we present eVATAR+, a middleware that implements the interactions within the context of such integrations systematically and transparently from the developers’ perspective. It also provides a simple and easy to use interface for developers to use. eVATAR+ uses JAVA server technologies enhanced by mediator functionality providing interoperability, maintainability and heterogeneity support. We exemplify eVATAR+ with a concrete case study and we evaluate the relative merits of our approach by comparing our work with the current state of the art.

Ablation Free Dicing of 4H-SiC Wafers with Feed Rates up to 200 mm/s by Using Thermal Laser Separation

2012 ◽  
Vol 1433 ◽  
Author(s):  
Dirk Lewke ◽  
Matthias Koitzsch ◽  
Martin Schellenberger ◽  
Lothar Pfitzner ◽  
Heiner Ryssel ◽  
...  
Keyword(s):  
Silicon Carbide ◽  
State Of The Art ◽  
Separation Process ◽  
Back Side ◽  
Current State ◽  
Edge Quality ◽  
First Time ◽  
Metal Layers ◽  
Laser Separation ◽  
Street Width

ABSTRACTThis paper presents Thermal Laser Separation (TLS) as a novel dicing technology for silicon carbide (SiC) wafers. Results of this work will play an important role in improving the SiC dicing process regarding throughput and edge quality. TLS process parameters were developed for separating 4H-SiC wafers. Separated SiC dies were analyzed and compared with results produced with current state of the art blade dicing technology. For the first time, fully processed 100 mm 4H-SiC wafers with a thickness of 450 μm, including epi-layer and back side metal layers, could be separated with feed rates up to 200 mm/s. Besides the vastly improved dicing speed, the TLS separation process results in two important features of the separated SiC devices: First, edges are free of chipping and therefore of higher quality than the edges produced by blade dicing. Second, the TLS process is kerf free, which allows for reducing the necessary dicing street width and hence increasing the number of devices per wafer.

scholarly journals Electrode-free visual prosthesis/exoskeleton control using augmented reality glasses in a first proof-of-technical-concept study

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Simon Hazubski ◽  
Harald Hoppe ◽  
Andreas Otte
Keyword(s):  
Augmented Reality ◽  
State Of The Art ◽  
Visual Prosthesis ◽  
Control Mechanisms ◽  
Proof Of Concept ◽  
End Effector ◽  
Concept Study ◽  
Current State ◽  
First Time ◽  
Robust Systems

Abstract In the field of neuroprosthetics, the current state-of-the-art method involves controlling the prosthesis with electromyography (EMG) or electrooculography/electroencephalography (EOG/EEG). However, these systems are both expensive and time consuming to calibrate, susceptible to interference, and require a lengthy learning phase by the patient. Therefore, it is an open challenge to design more robust systems that are suitable for everyday use and meet the needs of patients. In this paper, we present a new concept of complete visual control for a prosthesis, an exoskeleton or another end effector using augmented reality (AR) glasses presented for the first time in a proof-of-concept study. By using AR glasses equipped with a monocular camera, a marker attached to the prosthesis is tracked. Minimal relative movements of the head with respect to the prosthesis are registered by tracking and used for control. Two possible control mechanisms including visual feedback are presented and implemented for both a motorized hand orthosis and a motorized hand prosthesis. Since the grasping process is mainly controlled by vision, the proposed approach appears to be natural and intuitive.

scholarly journals Improving Lives of Indebted Farmers Using Deep Learning: Predicting Agricultural Produce Prices Using Convolutional Neural Networks

2020 ◽  
Vol 34 (08) ◽  
pp. 13294-13299
Author(s):  
Hangzhi Guo ◽  
Alexander Woodruff ◽  
Amulya Yadav
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Architecture ◽  
Prediction Models ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Machine Learning Algorithms ◽  
Volume Data ◽  
Farmer Suicides ◽  
Spatio Temporal

Farmer suicides have become an urgent social problem which governments around the world are trying hard to solve. Most farmers are driven to suicide due to an inability to sell their produce at desired profit levels, which is caused by the widespread uncertainty/fluctuation in produce prices resulting from varying market conditions. To prevent farmer suicides, this paper takes the first step towards resolving the issue of produce price uncertainty by presenting PECAD, a deep learning algorithm for accurate prediction of future produce prices based on past pricing and volume patterns. While previous work presents machine learning algorithms for prediction of produce prices, they suffer from two limitations: (i) they do not explicitly consider the spatio-temporal dependence of future prices on past data; and as a result, (ii) they rely on classical ML prediction models which often perform poorly when applied to spatio-temporal datasets. PECAD addresses these limitations via three major contributions: (i) we gather real-world daily price and (produced) volume data of different crops over a period of 11 years from an official Indian government administered website; (ii) we pre-process this raw dataset via state-of-the-art imputation techniques to account for missing data entries; and (iii) PECAD proposes a novel wide and deep neural network architecture which consists of two separate convolutional neural network models (trained for pricing and volume data respectively). Our simulation results show that PECAD outperforms existing state-of-the-art baseline methods by achieving significantly lesser root mean squared error (RMSE) - PECAD achieves ∼25% lesser coefficient of variance than state-of-the-art baselines. Our work is done in collaboration with a non-profit agency that works on preventing farmer suicides in the Indian state of Jharkhand, and PECAD is currently being reviewed by them for potential deployment.

scholarly journals Deep Convolutional Neural Network for Pedestrian Detection with Multi-Levels Features Fusion

2018 ◽  
Vol 232 ◽  
pp. 01061
Author(s):  
Danhua Li ◽  
Xiaofeng Di ◽  
Xuan Qu ◽  
Yunfei Zhao ◽  
Honggang Kong
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Pedestrian Detection ◽  
Deep Convolutional Neural Network ◽  
High Quality ◽  
Low Level ◽  
Features Fusion ◽  
Current State ◽  
High Level

Pedestrian detection aims to localize and recognize every pedestrian instance in an image with a bounding box. The current state-of-the-art method is Faster RCNN, which is such a network that uses a region proposal network (RPN) to generate high quality region proposals, while Fast RCNN is used to classifiers extract features into corresponding categories. The contribution of this paper is integrated low-level features and high-level features into a Faster RCNN-based pedestrian detection framework, which efficiently increase the capacity of the feature. Through our experiments, we comprehensively evaluate our framework, on the Caltech pedestrian detection benchmark and our methods achieve state-of-the-art accuracy and present a competitive result on Caltech dataset.

Image De-Noising Using Deep Learning

2014 ◽  
Vol 641-642 ◽  
pp. 1287-1290
Author(s):  
Lan Zhang ◽  
Yu Feng Nie ◽  
Zhen Hai Wang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Input Data ◽  
Deep Neural Network ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Large Data ◽  
Image Database ◽  
Learning Problems ◽  
Deep Learning Algorithm

Deep neural network as a part of deep learning algorithm is a state-of-the-art approach to find higher level representations of input data which has been introduced to many practical and challenging learning problems successfully. The primary goal of deep learning is to use large data to help solving a given task on machine learning. We propose an methodology for image de-noising project defined by this model and conduct training a large image database to get the experimental output. The result shows the robustness and efficient our our algorithm.

scholarly journals Analyzing Depthwise Convolution Based Neural Network: Study Case in Ship Detection and Land Cover Classification

2019 ◽  
Vol 12 (2) ◽  
pp. 103
Author(s):  
Kuntoro Adi Nugroho ◽  
Yudi Eko Windarto
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
State Of The Art ◽  
Learning Algorithms ◽  
Satellite Image ◽  
Feature Learning ◽  
Feature Extraction Method ◽  
Current State ◽  
Study Case ◽  
Unsupervised Feature Extraction

Various methods are available to perform feature extraction on satellite images. Among the available alternatives, deep convolutional neural network (ConvNet) is the state of the art method. Although previous studies have reported successful attempts on developing and implementing ConvNet on remote sensing application, several issues are not well explored, such as the use of depthwise convolution, final pooling layer size, and comparison between grayscale and RGB settings. The objective of this study is to perform analysis to address these issues. Two feature learning algorithms were proposed, namely ConvNet as the current state of the art for satellite image classification and Gray Level Co-occurence Matrix (GLCM) which represents a classic unsupervised feature extraction method. The experiment demonstrated consistent result with previous studies that ConvNet is superior in most cases compared to GLCM, especially with 3x3xn final pooling. The performance of the learning algorithms are much higher on features from RGB channels, except for ConvNet with relatively small number of features.

scholarly journals Automated Fruit Classification Using Deep Convolutional Neural Network

2020 ◽  
Vol 3 (2) ◽  
pp. 177-178
Author(s):  
John Jowil D. Orquia ◽  
El Jireh Bibangco
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
New Technologies ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Complex Model ◽  
Deep Convolutional Neural Network ◽  
Machine Learning Algorithm ◽  
Learning Models

Manual Fruit classification is the traditional way of classifying fruits. It is manual contact-labor that is time-consuming and often results in lesser productivity, inconsistency, and sometimes damaging the fruits (Prabha & Kumar, 2012). Thus, new technologies such as deep learning paved the way for a faster and more efficient method of fruit classification (Faridi & Aboonajmi, 2017). A deep convolutional neural network, or deep learning, is a machine learning algorithm that contains several layers of neural networks stacked together to create a more complex model capable of solving complex problems. The utilization of state-of-the-art pre-trained deep learning models such as AlexNet, GoogLeNet, and ResNet-50 was widely used. However, such models were not explicitly trained for fruit classification (Dyrmann, Karstoft, & Midtiby, 2016). The study aimed to create a new deep convolutional neural network and compared its performance to fine-tuned models based on accuracy, precision, sensitivity, and specificity.

Sign in / Sign up

Export Citation Format

Share Document