Deep Learning-Based Visual Identification of Signs of Bat Presence in Bridge Infrastructure Images: A Transfer Learning Approach

2021 ◽  
pp. 036119812110319
Author(s):  
Tianshu Li ◽  
Mohamad Alipour ◽  
Bridget M. Donaldson ◽  
Devin K. Harris
Keyword(s):  
Deep Learning ◽  
Web Application ◽  
Large Scale ◽  
Visual Recognition ◽  
Automated Detection ◽  
Department Of Transportation ◽  
Feature Representations ◽  
Visual Identification ◽  
Structural Deterioration ◽  
Virginia Department

Bat inventory surveys on bridges, structures, and dwellings are an important step in protecting threatened and endangered bat species that use the infrastructure as roosting locations. Observing guano droppings and staining is a common indicator of bat presence, but it can be difficult to verify whether certain stains originated from bats or other sources such as water seeps, rust staining, asphalt leaching, or other structural deterioration mechanisms. While humans find it hard to distinguish bat indicators without training, from a computer vision perspective they show different features that, coupled with expert opinion, can be used for automated detection of bat presence. To facilitate bat presence detection and streamline bat surveys, this paper leverages recent advances in visual recognition using deep learning to develop an image classification system that identifies bat indicators. An array of state-of-the-art convolutional neural networks were investigated. To overcome the shortage of data, parameters previously trained on large-scale datasets were used to transfer the learned feature representations. Using a pool of digital photographs collected by Virginia Department of Transportation (VDOT), a visual recognition model was developed and achieved 92.0% accuracy during testing. To facilitate the application of the developed model, a prototype web application was created to allow users to interactively upload images of stains on structures and receive classification results from the model. The web application is being deployed by VDOT in a pilot study and the success of the proposed approach is expected to help facilitate bat inventory surveys and the resulting conservation efforts.

scholarly journals Classification of Very-High-Spatial-Resolution Aerial Images Based on Multiscale Features with Limited Semantic Information

2021 ◽  
Vol 13 (3) ◽  
pp. 364
Author(s):  
Han Gao ◽  
Jinhui Guo ◽  
Peng Guo ◽  
Xiuwan Chen
Keyword(s):  
Deep Learning ◽  
Land Cover ◽  
Spatial Resolution ◽  
Large Scale ◽  
High Spatial Resolution ◽  
Training Data ◽  
Aerial Images ◽  
Rural Landscapes ◽  
Feature Representations ◽  
Object Based

Recently, deep learning has become the most innovative trend for a variety of high-spatial-resolution remote sensing imaging applications. However, large-scale land cover classification via traditional convolutional neural networks (CNNs) with sliding windows is computationally expensive and produces coarse results. Additionally, although such supervised learning approaches have performed well, collecting and annotating datasets for every task are extremely laborious, especially for those fully supervised cases where the pixel-level ground-truth labels are dense. In this work, we propose a new object-oriented deep learning framework that leverages residual networks with different depths to learn adjacent feature representations by embedding a multibranch architecture in the deep learning pipeline. The idea is to exploit limited training data at different neighboring scales to make a tradeoff between weak semantics and strong feature representations for operational land cover mapping tasks. We draw from established geographic object-based image analysis (GEOBIA) as an auxiliary module to reduce the computational burden of spatial reasoning and optimize the classification boundaries. We evaluated the proposed approach on two subdecimeter-resolution datasets involving both urban and rural landscapes. It presented better classification accuracy (88.9%) compared to traditional object-based deep learning methods and achieves an excellent inference time (11.3 s/ha).

scholarly journals Image Classification Using Transfer Learning and Deep Learning

2021 ◽  
Vol 10 (9) ◽  
pp. 25394-25398
Author(s):  
Chitra Desai
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Image Classification ◽  
Transfer Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Large Scale ◽  
Deep Neural Network ◽  
Visual Recognition ◽  
Classification Of Images

Deep learning models have demonstrated improved efficacy in image classification since the ImageNet Large Scale Visual Recognition Challenge started since 2010. Classification of images has further augmented in the field of computer vision with the dawn of transfer learning. To train a model on huge dataset demands huge computational resources and add a lot of cost to learning. Transfer learning allows to reduce on cost of learning and also help avoid reinventing the wheel. There are several pretrained models like VGG16, VGG19, ResNet50, Inceptionv3, EfficientNet etc which are widely used.   This paper demonstrates image classification using pretrained deep neural network model VGG16 which is trained on images from ImageNet dataset. After obtaining the convolutional base model, a new deep neural network model is built on top of it for image classification based on fully connected network. This classifier will use features extracted from the convolutional base model.

scholarly journals Experimental Analysis for Semantic based Large Scale Service Composition using Deep Learning

2019 ◽  
Vol 8 (10) ◽  
pp. 4280-4283
Keyword(s):  
Deep Learning ◽  
Web Services ◽  
Web Service ◽  
Service Composition ◽  
Web Application ◽  
Large Scale ◽  
Learning Algorithm ◽  
Computational Cost ◽  
Web Service Composition ◽  
User Requirement

In Service Oriented Architecture (SOA) web services plays important role. Web services are web application components that can be published, found, and used on the Web. Also machine-to-machine communication over a network can be achieved through web services. Cloud computing and distributed computing brings lot of web services into WWW. Web service composition is the process of combing two or more web services to together to satisfy the user requirements. Tremendous increase in the number of services and the complexity in user requirement specification make web service composition as challenging task. The automated service composition is a technique in which Web Service Composition can be done automatically with minimal or no human intervention. In this paper we propose a approach of web service composition methods for large scale environment by considering the QoS Parameters. We have used stacked autoencoders to learn features of web services. Recurrent Neural Network (RNN) leverages uses the learned features to predict the new composition. Experiment results show the efficiency and scalability. Use of deep learning algorithm in web service composition, leads to high success rate and less computational cost.

scholarly journals Multi-stage malaria parasite recognition by deep learning

GigaScience ◽  
2021 ◽  
Vol 10 (6) ◽  
Author(s):  
Sen Li ◽  
Zeyu Du ◽  
Xiangjie Meng ◽  
Yang Zhang
Keyword(s):  
Deep Learning ◽  
Malaria Parasite ◽  
Large Scale ◽  
Blood Smear ◽  
Growth Stages ◽  
Malaria Parasites ◽  
Convolutional Network ◽  
Feature Representations ◽  
Multi Stage ◽  
Wide Range

Abstract Motivation Malaria, a mosquito-borne infectious disease affecting humans and other animals, is widespread in tropical and subtropical regions. Microscopy is the most common method for diagnosing the malaria parasite from stained blood smear samples. However, this technique is time consuming and must be performed by a well-trained professional, yet it remains prone to errors. Distinguishing the multiple growth stages of parasites remains an especially challenging task. Results In this article, we develop a novel deep learning approach for the recognition of malaria parasites of various stages in blood smear images using a deep transfer graph convolutional network (DTGCN). To our knowledge, this is the first application of graph convolutional network (GCN) on multi-stage malaria parasite recognition in such images. The proposed DTGCN model is based on unsupervised learning by transferring knowledge learnt from source images that contain the discriminative morphology characteristics of multi-stage malaria parasites. This transferred information guarantees the effectiveness of the target parasite recognition. This approach first learns the identical representations from the source to establish topological correlations between source class groups and the unlabelled target samples. At this stage, the GCN is implemented to extract graph feature representations for multi-stage malaria parasite recognition. The proposed method showed higher accuracy and effectiveness in publicly available microscopic images of multi-stage malaria parasites compared to a wide range of state-of-the-art approaches. Furthermore, this method is also evaluated on a large-scale dataset of unseen malaria parasites and the Babesia dataset. Availability Code and dataset are available at https://github.com/senli2018/DTGCN_2021 under a MIT license.

scholarly journals An ecologically motivated image dataset for deep learning yields better models of human vision

2021 ◽  
Vol 118 (8) ◽  
pp. e2011417118
Author(s):  
Johannes Mehrer ◽  
Courtney J. Spoerer ◽  
Emer C. Jones ◽  
Nikolaus Kriegeskorte ◽  
Tim C. Kietzmann
Keyword(s):  
Deep Learning ◽  
Visual Information ◽  
Large Scale ◽  
Visual Recognition ◽  
Network Models ◽  
Progressive Increase ◽  
Human Vision ◽  
Visual Object ◽  
Visual Object Recognition ◽  
Visual Neuroscience

Deep neural networks provide the current best models of visual information processing in the primate brain. Drawing on work from computer vision, the most commonly used networks are pretrained on data from the ImageNet Large Scale Visual Recognition Challenge. This dataset comprises images from 1,000 categories, selected to provide a challenging testbed for automated visual object recognition systems. Moving beyond this common practice, we here introduce ecoset, a collection of >1.5 million images from 565 basic-level categories selected to better capture the distribution of objects relevant to humans. Ecoset categories were chosen to be both frequent in linguistic usage and concrete, thereby mirroring important physical objects in the world. We test the effects of training on this ecologically more valid dataset using multiple instances of two neural network architectures: AlexNet and vNet, a novel architecture designed to mimic the progressive increase in receptive field sizes along the human ventral stream. We show that training on ecoset leads to significant improvements in predicting representations in human higher-level visual cortex and perceptual judgments, surpassing the previous state of the art. Significant and highly consistent benefits are demonstrated for both architectures on two separate functional magnetic resonance imaging (fMRI) datasets and behavioral data, jointly covering responses to 1,292 visual stimuli from a wide variety of object categories. These results suggest that computational visual neuroscience may take better advantage of the deep learning framework by using image sets that reflect the human perceptual and cognitive experience. Ecoset and trained network models are openly available to the research community.

scholarly journals Deep Learning based NLP Techniques In Text to Speech Synthesis for Communication Recognition

2020 ◽  
Vol 2 (4) ◽  
pp. 209-215
Author(s):  
Eriss Eisa Babikir Adam
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Speech Synthesis ◽  
Large Scale ◽  
Feature Representations ◽  
Large Scale Data ◽  
Learning Techniques ◽  
Text To Speech Synthesis

The computer system is developing the model for speech synthesis of various aspects for natural language processing. The speech synthesis explores by articulatory, formant and concatenate synthesis. These techniques lead more aperiodic distortion and give exponentially increasing error rate during process of the system. Recently, advances on speech synthesis are tremendously moves towards deep learning process in order to achieve better performance. Due to leverage of large scale data gives effective feature representations to speech synthesis. The main objective of this research article is that implements deep learning techniques into speech synthesis and compares the performance in terms of aperiodic distortion with prior model of algorithms in natural language processing.

scholarly journals A Review of Deep Learning Based Speech Synthesis

2019 ◽  
Vol 9 (19) ◽  
pp. 4050 ◽  
Author(s):  
Yishuang Ning ◽  
Sheng He ◽  
Zhiyong Wu ◽  
Chunxiao Xing ◽  
Liang-Jie Zhang
Keyword(s):  
Deep Learning ◽  
Speech Synthesis ◽  
Large Scale ◽  
Synthesis Methods ◽  
Research Directions ◽  
Feature Representations ◽  
Wide Range ◽  
New Frontier ◽  
Speech Interaction ◽  
End To End

Speech synthesis, also known as text-to-speech (TTS), has attracted increasingly more attention. Recent advances on speech synthesis are overwhelmingly contributed by deep learning or even end-to-end techniques which have been utilized to enhance a wide range of application scenarios such as intelligent speech interaction, chatbot or conversational artificial intelligence (AI). For speech synthesis, deep learning based techniques can leverage a large scale of <text, speech> pairs to learn effective feature representations to bridge the gap between text and speech, thus better characterizing the properties of events. To better understand the research dynamics in the speech synthesis field, this paper firstly introduces the traditional speech synthesis methods and highlights the importance of the acoustic modeling from the composition of the statistical parametric speech synthesis (SPSS) system. It then gives an overview of the advances on deep learning based speech synthesis, including the end-to-end approaches which have achieved start-of-the-art performance in recent years. Finally, it discusses the problems of the deep learning methods for speech synthesis, and also points out some appealing research directions that can bring the speech synthesis research into a new frontier.

Integrating multi-level deep learning and concept ontology for large-scale visual recognition

2018 ◽  
Vol 78 ◽  
pp. 198-214 ◽  
Author(s):  
Zhenzhong Kuang ◽  
Jun Yu ◽  
Zongmin Li ◽  
Baopeng Zhang ◽  
Jianping Fan
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Visual Recognition ◽  
Multi Level

Multi Disease-Prediction Framework Using Hybrid Deep Learning: An Optimal Prediction Model (Preprint)

2020 ◽  
Author(s):  
Anusha Ampavathi ◽  
Vijaya Saradhi T
Keyword(s):  
Feature Extraction ◽  
Big Data ◽  
Deep Learning ◽  
Weight Function ◽  
Optimization Algorithm ◽  
Large Scale ◽  
Heuristic Algorithms ◽  
Disease Prediction ◽  
Health Care Decisions ◽  
Proposed Model

UNSTRUCTURED Big data and its approaches are generally helpful for healthcare and biomedical sectors for predicting the disease. For trivial symptoms, the difficulty is to meet the doctors at any time in the hospital. Thus, big data provides essential data regarding the diseases on the basis of the patient’s symptoms. For several medical organizations, disease prediction is important for making the best feasible health care decisions. Conversely, the conventional medical care model offers input as structured that requires more accurate and consistent prediction. This paper is planned to develop the multi-disease prediction using the improvised deep learning concept. Here, the different datasets pertain to “Diabetes, Hepatitis, lung cancer, liver tumor, heart disease, Parkinson’s disease, and Alzheimer’s disease”, from the benchmark UCI repository is gathered for conducting the experiment. The proposed model involves three phases (a) Data normalization (b) Weighted normalized feature extraction, and (c) prediction. Initially, the dataset is normalized in order to make the attribute's range at a certain level. Further, weighted feature extraction is performed, in which a weight function is multiplied with each attribute value for making large scale deviation. Here, the weight function is optimized using the combination of two meta-heuristic algorithms termed as Jaya Algorithm-based Multi-Verse Optimization algorithm (JA-MVO). The optimally extracted features are subjected to the hybrid deep learning algorithms like “Deep Belief Network (DBN) and Recurrent Neural Network (RNN)”. As a modification to hybrid deep learning architecture, the weight of both DBN and RNN is optimized using the same hybrid optimization algorithm. Further, the comparative evaluation of the proposed prediction over the existing models certifies its effectiveness through various performance measures.

Sign in / Sign up

Export Citation Format

Share Document