scholarly journals EmbeddedPigDet—Fast and Accurate Pig Detection for Embedded Board Implementations

2020 ◽  
Vol 10 (8) ◽  
pp. 2878 ◽  
Author(s):  
Jihyun Seo ◽  
Hanse Ahn ◽  
Daewon Kim ◽  
Sungju Lee ◽  
Yongwha Chung ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Low Cost ◽  
Input Image ◽  
Monitoring Cost ◽  
Fast Detection ◽  
Execution Speed ◽  
Pig Farm ◽  
Integrated Performance ◽  
Speed And Accuracy

Automated pig monitoring is an important issue in the surveillance environment of a pig farm. For a large-scale pig farm in particular, practical issues such as monitoring cost should be considered but such consideration based on low-cost embedded boards has not yet been reported. Since low-cost embedded boards have more limited computing power than typical PCs and have tradeoffs between execution speed and accuracy, achieving fast and accurate detection of individual pigs for “on-device” pig monitoring applications is very challenging. Therefore, in this paper, we propose a method for the fast detection of individual pigs by reducing the computational workload of 3 × 3 convolution in widely-used, deep learning-based object detectors. Then, in order to recover the accuracy of the “light-weight” deep learning-based object detector, we generate a three-channel composite image as its input image, through “simple” image preprocessing techniques. Our experimental results on an NVIDIA Jetson Nano embedded board show that the proposed method can improve the integrated performance of both execution speed and accuracy of widely-used, deep learning-based object detectors, by a factor of up to 8.7.

scholarly journals A Weakly Supervised and Deep Learning Method for an Additive Topic Analysis of Large Corpora

2019 ◽  
Author(s):  
Yair Fogel-Dror ◽  
Shaul R. Shenhav ◽  
Tamir Sheafer
Keyword(s):  
Content Analysis ◽  
Deep Learning ◽  
Text Classification ◽  
Large Scale ◽  
Low Cost ◽  
Initial Number ◽  
Analysis Method ◽  
Training Set ◽  
Topic Analysis ◽  
Weakly Supervised

The collaborative effort of theory-driven content analysis can benefit significantly from the use of topic analysis methods, which allow researchers to add more categories while developing or testing a theory. This additive approach enables the reuse of previous efforts of analysis or even the merging of separate research projects, thereby making these methods more accessible and increasing the discipline’s ability to create and share content analysis capabilities. This paper proposes a weakly supervised topic analysis method that uses both a low-cost unsupervised method to compile a training set and supervised deep learning as an additive and accurate text classification method. We test the validity of the method, specifically its additivity, by comparing the results of the method after adding 200 categories to an initial number of 450. We show that the suggested method provides a foundation for a low-cost solution for large-scale topic analysis.

scholarly journals A Weakly Supervised and Deep Learning Method for an Additive Topic Analysis of Large Corpora

2021 ◽  
Vol 3 (1) ◽  
pp. 29-59
Author(s):  
Yair Fogel-Dror ◽  
Shaul R. Shenhav ◽  
Tamir Sheafer
Keyword(s):  
Content Analysis ◽  
Deep Learning ◽  
Text Classification ◽  
Large Scale ◽  
Low Cost ◽  
Initial Number ◽  
Analysis Method ◽  
Training Set ◽  
Topic Analysis ◽  
Weakly Supervised

Abstract The collaborative effort of theory-driven content analysis can benefit significantly from the use of topic analysis methods, which allow researchers to add more categories while developing or testing a theory. This additive approach enables the reuse of previous efforts of analysis or even the merging of separate research projects, thereby making these methods more accessible and increasing the discipline’s ability to create and share content analysis capabilities. This paper proposes a weakly supervised topic analysis method that uses both a low-cost unsupervised method to compile a training set and supervised deep learning as an additive and accurate text classification method. We test the validity of the method, specifically its additivity, by comparing the results of the method after adding 200 categories to an initial number of 450. We show that the suggested method provides a foundation for a low-cost solution for large-scale topic analysis.

scholarly journals DEEP LEARNING FOR VESSEL DETECTION AND IDENTIFICATION FROM SPACEBORNE OPTICAL IMAGERY

2021 ◽  
Vol V-3-2021 ◽  
pp. 303-310
Author(s):  
G. Matasci ◽  
J. Plante ◽  
K. Kasa ◽  
P. Mousavi ◽  
A. Stewart ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Input Image ◽  
Automatic Identification ◽  
Identification System ◽  
Optical Remote Sensing ◽  
Detection Model ◽  
Model Based ◽  
Optical Images ◽  
Vessel Detection

Abstract. We present a deep learning-based vessel detection and (re-)identification approach from spaceborne optical images. We introduce these two components as part of a maritime surveillance from space pipeline and present experimental results on challenging real-world maritime datasets derived from WorldView imagery. First, we developed a vessel detection model based on RetinaNet achieving a performance of 0.795 F1-score on a challenging multi-scale dataset. We then collected a large-scale dataset for vessel identification by applying the detection model on 200+ optical images, detecting the vessels therein and assigning them an identity via an Automatic Identification System association framework. A vessel re-identification model based on Twin neural networks has then been trained on this dataset featuring 2500+ unique vessels with multiple repeated occurrences across different acquisitions. The model allows to naturally establish similarities between vessel images. It returns a relevant ranking of candidate vessels from a database when provided an input image for a specific vessel the user might be interested in, with top-1 and top-10 accuracies of 38.7% and 76.5%, respectively. This study demonstrates the potential offered by the latest advances in deep learning and computer vision when applied to optical remote sensing imagery in a maritime context, opening new opportunities for automated vessel monitoring and tracking capabilities from space.

scholarly journals Deep Learning with Open Data for Desert Road Mapping

2020 ◽  
Vol 12 (14) ◽  
pp. 2274
Author(s):  
Christopher Stewart ◽  
Michele Lazzarini ◽  
Adrian Luna ◽  
Sergio Albani
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Data Augmentation ◽  
Low Cost ◽  
Open Data ◽  
Cost Effective ◽  
Training Data ◽  
Desert Sand ◽  
Model Training ◽  
Shifting Sand

The availability of free and open data from Earth observation programmes such as Copernicus, and from collaborative projects such as Open Street Map (OSM), enables low cost artificial intelligence (AI) based monitoring applications. This creates opportunities, particularly in developing countries with scarce economic resources, for large–scale monitoring in remote regions. A significant portion of Earth’s surface comprises desert dune fields, where shifting sand affects infrastructure and hinders movement. A robust, cost–effective and scalable methodology is proposed for road detection and monitoring in regions covered by desert sand. The technique uses Copernicus Sentinel–1 synthetic aperture radar (SAR) satellite data as an input to a deep learning model based on the U–Net architecture for image segmentation. OSM data is used for model training. The method comprises two steps: The first involves processing time series of Sentinel–1 SAR interferometric wide swath (IW) acquisitions in the same geometry to produce multitemporal backscatter and coherence averages. These are divided into patches and matched with masks of OSM roads to form the training data, the quantity of which is increased through data augmentation. The second step includes the U–Net deep learning workflow. The methodology has been applied to three different dune fields in Africa and Asia. A performance evaluation through the calculation of the Jaccard similarity coefficient was carried out for each area, and ranges from 84% to 89% for the best available input. The rank distance, calculated from the completeness and correctness percentages, was also calculated and ranged from 75% to 80%. Over all areas there are more missed detections than false positives. In some cases, this was due to mixed infrastructure in the same resolution cell of the input SAR data. Drift sand and dune migration covering infrastructure is a concern in many desert regions, and broken segments in the resulting road detections are sometimes due to sand burial. The results also show that, in most cases, the Sentinel–1 vertical transmit–vertical receive (VV) backscatter averages alone constitute the best input to the U–Net model. The detection and monitoring of roads in desert areas are key concerns, particularly given a growing population increasingly on the move.

An Assessment of a Low-Cost Wastewater Disposal System after Twenty-Five Years of Operation

1987 ◽  
Vol 19 (5-6) ◽  
pp. 701-710 ◽  
Author(s):  
B. L. Reidy ◽  
G. W. Samson
Keyword(s):  
Large Scale ◽  
Low Cost ◽  
Wastewater Disposal ◽  
Industrial Base ◽  
Industrial Wastewaters ◽  
The Past ◽  
Gasification Process ◽  
Appropriate Treatment ◽  
Environmentally Safe ◽  
Coal Resource

A low-cost wastewater disposal system was commissioned in 1959 to treat domestic and industrial wastewaters generated in the Latrobe River valley in the province of Gippsland, within the State of Victoria, Australia (Figure 1). The Latrobe Valley is the centre for large-scale generation of electricity and for the production of pulp and paper. In addition other industries have utilized the brown coal resource of the region e.g. gasification process and char production. Consequently, industrial wastewaters have been dominant in the disposal system for the past twenty-five years. The mixed industrial-domestic wastewaters were to be transported some eighty kilometres to be treated and disposed of by irrigation to land. Several important lessons have been learnt during twenty-five years of operating this system. Firstly the composition of the mixed waste stream has varied significantly with the passage of time and the development of the industrial base in the Valley, so that what was appropriate treatment in 1959 is not necessarily acceptable in 1985. Secondly the magnitude of adverse environmental impacts engendered by this low-cost disposal procedure was not imagined when the proposal was implemented. As a consequence, clean-up procedures which could remedy the adverse effects of twenty-five years of impact are likely to be costly. The question then may be asked - when the total costs including rehabilitation are considered, is there really a low-cost solution for environmentally safe disposal of complex wastewater streams?

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.

scholarly journals Rapid, large-scale species discovery in hyperdiverse taxa using 1D MinION sequencing

BMC Biology ◽  
2019 ◽  
Vol 17 (1) ◽  
Author(s):  
Amrita Srivathsan ◽  
Emily Hartop ◽  
Jayanthi Puniamoorthy ◽  
Wan Ting Lee ◽  
Sujatha Narayanan Kutty ◽  
...  
Keyword(s):  
Dna Sequences ◽  
Large Scale ◽  
Low Cost ◽  
Small Body ◽  
Small Subset ◽  
Similar Species ◽  
Large Species ◽  
Morphological Examination ◽  
Species Discovery ◽  
Short Period

Abstract Background More than 80% of all animal species remain unknown to science. Most of these species live in the tropics and belong to animal taxa that combine small body size with high specimen abundance and large species richness. For such clades, using morphology for species discovery is slow because large numbers of specimens must be sorted based on detailed microscopic investigations. Fortunately, species discovery could be greatly accelerated if DNA sequences could be used for sorting specimens to species. Morphological verification of such “molecular operational taxonomic units” (mOTUs) could then be based on dissection of a small subset of specimens. However, this approach requires cost-effective and low-tech DNA barcoding techniques because well-equipped, well-funded molecular laboratories are not readily available in many biodiverse countries. Results We here document how MinION sequencing can be used for large-scale species discovery in a specimen- and species-rich taxon like the hyperdiverse fly family Phoridae (Diptera). We sequenced 7059 specimens collected in a single Malaise trap in Kibale National Park, Uganda, over the short period of 8 weeks. We discovered > 650 species which exceeds the number of phorid species currently described for the entire Afrotropical region. The barcodes were obtained using an improved low-cost MinION pipeline that increased the barcoding capacity sevenfold from 500 to 3500 barcodes per flowcell. This was achieved by adopting 1D sequencing, resequencing weak amplicons on a used flowcell, and improving demultiplexing. Comparison with Illumina data revealed that the MinION barcodes were very accurate (99.99% accuracy, 0.46% Ns) and thus yielded very similar species units (match ratio 0.991). Morphological examination of 100 mOTUs also confirmed good congruence with morphology (93% of mOTUs; > 99% of specimens) and revealed that 90% of the putative species belong to the neglected, megadiverse genus Megaselia. We demonstrate for one Megaselia species how the molecular data can guide the description of a new species (Megaselia sepsioides sp. nov.). Conclusions We document that one field site in Africa can be home to an estimated 1000 species of phorids and speculate that the Afrotropical diversity could exceed 200,000 species. We furthermore conclude that low-cost MinION sequencers are very suitable for reliable, rapid, and large-scale species discovery in hyperdiverse taxa. MinION sequencing could quickly reveal the extent of the unknown diversity and is especially suitable for biodiverse countries with limited access to capital-intensive sequencing facilities.

scholarly journals Application of Deep Learning in Integrated Pest Management: A Real-Time System for Detection and Diagnosis of Oilseed Rape Pests

2019 ◽  
Vol 2019 ◽  
pp. 1-14 ◽  
Author(s):  
Yong He ◽  
Hong Zeng ◽  
Yangyang Fan ◽  
Shuaisheng Ji ◽  
Jianjian Wu
Keyword(s):  
Deep Learning ◽  
Integrated Pest Management ◽  
Pest Management ◽  
Real Time ◽  
Oilseed Rape ◽  
Data Augmentation ◽  
Low Cost ◽  
Response Speed ◽  
Original Model ◽  
Real Time System

In this paper, we proposed an approach to detect oilseed rape pests based on deep learning, which improves the mean average precision (mAP) to 77.14%; the result increased by 9.7% with the original model. We adopt this model to mobile platform to let every farmer able to use this program, which will diagnose pests in real time and provide suggestions on pest controlling. We designed an oilseed rape pest imaging database with 12 typical oilseed rape pests and compared the performance of five models, SSD w/Inception is chosen as the optimal model. Moreover, for the purpose of the high mAP, we have used data augmentation (DA) and added a dropout layer. The experiments are performed on the Android application we developed, and the result shows that our approach surpasses the original model obviously and is helpful for integrated pest management. This application has improved environmental adaptability, response speed, and accuracy by contrast with the past works and has the advantage of low cost and simple operation, which are suitable for the pest monitoring mission of drones and Internet of Things (IoT).

scholarly journals Deep Learning-Based Large-Scale Automatic Satellite Crosswalk Classification

2017 ◽  
Vol 14 (9) ◽  
pp. 1513-1517 ◽  
Author(s):  
Rodrigo F. Berriel ◽  
Andre Teixeira Lopes ◽  
Alberto F. de Souza ◽  
Thiago Oliveira-Santos
Keyword(s):  
Deep Learning ◽  
Large Scale
Sign in / Sign up

Export Citation Format

Share Document