scholarly journals AgriPest: A Large-Scale Domain-Specific Benchmark Dataset for Practical Agricultural Pest Detection in the Wild

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1601
Author(s):  
Rujing Wang ◽  
Liu Liu ◽  
Chengjun Xie ◽  
Po Yang ◽  
Rui Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Benchmark Dataset ◽  
Domain Specific ◽  
Pest Monitoring ◽  
Field Environment ◽  
Learning Techniques ◽  
Monitoring Applications ◽  
In The Wild ◽  
Bounding Boxes

The recent explosion of large volume of standard dataset of annotated images has offered promising opportunities for deep learning techniques in effective and efficient object detection applications. However, due to a huge difference of quality between these standardized dataset and practical raw data, it is still a critical problem on how to maximize utilization of deep learning techniques in practical agriculture applications. Here, we introduce a domain-specific benchmark dataset, called AgriPest, in tiny wild pest recognition and detection, providing the researchers and communities with a standard large-scale dataset of practically wild pest images and annotations, as well as evaluation procedures. During the past seven years, AgriPest captures 49.7K images of four crops containing 14 species of pests by our designed image collection equipment in the field environment. All of the images are manually annotated by agricultural experts with up to 264.7K bounding boxes of locating pests. This paper also offers a detailed analysis of AgriPest where the validation set is split into four types of scenes that are common in practical pest monitoring applications. We explore and evaluate the performance of state-of-the-art deep learning techniques over AgriPest. We believe that the scale, accuracy, and diversity of AgriPest can offer great opportunities to researchers in computer vision as well as pest monitoring applications.

scholarly journals BO-LSTM: Classifying relations via long short-term memory networks along biomedical ontologies

2018 ◽  
Author(s):  
Andre Lamurias ◽  
Luka A. Clarke ◽  
Francisco M. Couto
Keyword(s):  
Deep Learning ◽  
Text Mining ◽  
Drug Interactions ◽  
Short Term Memory ◽  
Biomedical Ontologies ◽  
Short Term ◽  
Term Memory ◽  
Domain Specific ◽  
Learning Techniques ◽  
Long Short Term Memory

AbstractRecent studies have proposed deep learning techniques, namely recurrent neural networks, to improve biomedical text mining tasks. However, these techniques rarely take advantage of existing domain-specific resources, such as ontologies. In Life and Health Sciences there is a vast and valuable set of such resources publicly available, which are continuously being updated. Biomedical ontologies are nowadays a mainstream approach to formalize existing knowledge about entities, such as genes, chemicals, phenotypes, and disorders. These resources contain supplementary information that may not be yet encoded in training data, particularly in domains with limited labeled data.We propose a new model, BO-LSTM, that takes advantage of domain-specific ontologies, by representing each entity as the sequence of its ancestors in the ontology. We implemented BO-LSTM as a recurrent neural network with long short-term memory units and using an open biomedical ontology, which in our case-study was Chemical Entities of Biological Interest (ChEBI). We assessed the performance of BO-LSTM on detecting and classifying drug-drug interactions in a publicly available corpus from an international challenge, composed of 792 drug descriptions and 233 scientific abstracts. By using the domain-specific ontology in addition to word embeddings and WordNet, BO-LSTM improved both the F1-score of the detection and classification of drug-drug interactions, particularly in a document set with a limited number of annotations. Our findings demonstrate that besides the high performance of current deep learning techniques, domain-specific ontologies can still be useful to mitigate the lack of labeled data.Author summaryA high quantity of biomedical information is only available in documents such as scientific articles and patents. Due to the rate at which new documents are produced, we need automatic methods to extract useful information from them. Text mining is a subfield of information retrieval which aims at extracting relevant information from text. Scientific literature is a challenge to text mining because of the complexity and specificity of the topics approached. In recent years, deep learning has obtained promising results in various text mining tasks by exploring large datasets. On the other hand, ontologies provide a detailed and sound representation of a domain and have been developed to diverse biomedical domains. We propose a model that combines deep learning algorithms with biomedical ontologies to identify relations between concepts in text. We demonstrate the potential of this model to extract drug-drug interactions from abstracts and drug descriptions. This model can be applied to other biomedical domains using an annotated corpus of documents and an ontology related to that domain to train a new classifier.

scholarly journals Mol-BERT: An Effective Molecular Representation with BERT for Molecular Property Prediction

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Juncai Li ◽  
Xiaofei Jiang
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Large Scale ◽  
Molecular Data ◽  
Molecular Property ◽  
Property Prediction ◽  
Learning Framework ◽  
Learning Techniques ◽  
Potential Benefits ◽  
Current Sequence

Molecular property prediction is an essential task in drug discovery. Most computational approaches with deep learning techniques either focus on designing novel molecular representation or combining with some advanced models together. However, researchers pay fewer attention to the potential benefits in massive unlabeled molecular data (e.g., ZINC). This task becomes increasingly challenging owing to the limitation of the scale of labeled data. Motivated by the recent advancements of pretrained models in natural language processing, the drug molecule can be naturally viewed as language to some extent. In this paper, we investigate how to develop the pretrained model BERT to extract useful molecular substructure information for molecular property prediction. We present a novel end-to-end deep learning framework, named Mol-BERT, that combines an effective molecular representation with pretrained BERT model tailored for molecular property prediction. Specifically, a large-scale prediction BERT model is pretrained to generate the embedding of molecular substructures, by using four million unlabeled drug SMILES (i.e., ZINC 15 and ChEMBL 27). Then, the pretrained BERT model can be fine-tuned on various molecular property prediction tasks. To examine the performance of our proposed Mol-BERT, we conduct several experiments on 4 widely used molecular datasets. In comparison to the traditional and state-of-the-art baselines, the results illustrate that our proposed Mol-BERT can outperform the current sequence-based methods and achieve at least 2% improvement on ROC-AUC score on Tox21, SIDER, and ClinTox dataset.

scholarly journals A Systematic Analysis of Big Image Data Methodologies in Various Applications

2020 ◽  
Vol 9 (5) ◽  
pp. 483-487
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Large Scale ◽  
Image Data ◽  
Computational Time ◽  
Process Data ◽  
Systematic Analysis ◽  
Large Scale Data ◽  
Learning Techniques ◽  
Effective Performance

Big data is large-scale data collected for knowledge discovery, it has been widely used in various applications. Big data often has image data from the various applications and requires effective technique to process data. In this paper, survey has been done in the big image data researches to analysis the effective performance of the methods. Deep learning techniques provides the effective performance compared to other methods included wavelet based methods. The deep learning techniques has the problem of requiring more computational time, and this can be overcome by lightweight methods.

Efficient Large-Scale Stance Detection in Tweets

2020 ◽  
pp. 667-683
Author(s):  
Yilin Yan ◽  
Jonathan Chen ◽  
Mei-Ling Shyu
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Large Scale ◽  
Research Direction ◽  
Detection Methods ◽  
Use Case ◽  
Learning Techniques ◽  
Test Use ◽  
Presidential Election Campaign ◽  
Important Research Direction

Stance detection is an important research direction which attempts to automatically determine the attitude (positive, negative, or neutral) of the author of text (such as tweets), towards a target. Nowadays, a number of frameworks have been proposed using deep learning techniques that show promising results in application domains such as automatic speech recognition and computer vision, as well as natural language processing (NLP). This article shows a novel deep learning-based fast stance detection framework in bipolar affinities on Twitter. It is noted that millions of tweets regarding Clinton and Trump were produced per day on Twitter during the 2016 United States presidential election campaign, and thus it is used as a test use case because of its significant and unique counter-factual properties. In addition, stance detection can be utilized to imply the political tendency of the general public. Experimental results show that the proposed framework achieves high accuracy results when compared to several existing stance detection methods.

scholarly journals Species Distribution Modelling Using Deep Learning

2019 ◽  
Vol 3 ◽  
Author(s):  
Rutger Vos ◽  
Mark Rademaker ◽  
Laurens Hogeweg
Keyword(s):  
Deep Learning ◽  
Species Distribution ◽  
Large Scale ◽  
Species Distribution Modelling ◽  
Climate Change Scenarios ◽  
Niche Modelling ◽  
Distribution Modelling ◽  
Biodiversity Science ◽  
Learning Techniques ◽  
Correlative Models

Species distribution modelling, or ecological niche modelling, is a collection of techniques for the construction of correlative models based on the combination of species occurrences and GIS data. Using such models, a variety of research questions in biodiversity science can be investigated, among which are the assessment of habitat suitability around the globe (e.g. in the case of invasive species), the response of species to alternative climatic regimes (e.g. by forecasting climate change scenarios, or by hindcasting into palaeoclimates), and the overlap of species in niche space. The algorithms used for the construction of such models include maximum entropy, neural networks, and random forests. Recent advances both in computing power and in algorithm development raise the possibility that deep learning techniques will provide valuable additions to these existing approaches. Here, we present our recent findings in the development of workflows to apply deep learning to species distribution modelling, and discuss the prospects for the large-scale application of deep learning in web service infrastructures to analyze the growing corpus of species occurrence data in biodiversity information facilities.

scholarly journals Identify Light-curve Signals with Deep Learning Based Object Detection Algorithm. I. Transit Detection

2021 ◽  
Vol 163 (1) ◽  
pp. 23
Author(s):  
Kaiming Cui ◽  
Junjie Liu ◽  
Fabo Feng ◽  
Jifeng Liu
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Signal To Noise Ratio ◽  
Detection Algorithm ◽  
Human Visual Perception ◽  
Lower Confidence ◽  
Learning Techniques ◽  
Confidence Threshold ◽  
Bounding Boxes ◽  
Python Package

Abstract Deep learning techniques have been well explored in the transiting exoplanet field; however, previous work mainly focuses on classification and inspection. In this work, we develop a novel detection algorithm based on a well-proven object detection framework in the computer vision field. Through training the network on the light curves of the confirmed Kepler exoplanets, our model yields about 90% precision and recall for identifying transits with signal-to-noise ratio higher than 6 (set the confidence threshold to 0.6). Giving a slightly lower confidence threshold, recall can reach higher than 95%. We also transfer the trained model to the TESS data and obtain similar performance. The results of our algorithm match the intuition of the human visual perception and make it useful to find single-transiting candidates. Moreover, the parameters of the output bounding boxes can also help to find multiplanet systems. Our network and detection functions are implemented in the Deep-Transit toolkit, which is an open-source Python package hosted on Github and PyPI.

scholarly journals A Review of Facial Landmark Extraction in 2D Images and Videos Using Deep Learning

2019 ◽  
Vol 3 (1) ◽  
pp. 14 ◽  
Author(s):  
Matteo Bodini
Keyword(s):  
Deep Learning ◽  
Future Research ◽  
3D Face Reconstruction ◽  
Research Directions ◽  
Facial Expression Analysis ◽  
Facial Landmark ◽  
Learning Techniques ◽  
In The Wild ◽  
Future Research Directions ◽  
2D Images

The task of facial landmark extraction is fundamental in several applications which involve facial analysis, such as facial expression analysis, identity and face recognition, facial animation, and 3D face reconstruction. Taking into account the most recent advances resulting from deep-learning techniques, the performance of methods for facial landmark extraction have been substantially improved, even on in-the-wild datasets. Thus, this article presents an updated survey on facial landmark extraction on 2D images and video, focusing on methods that make use of deep-learning techniques. An analysis of many approaches comparing the performances is provided. In summary, an analysis of common datasets, challenges, and future research directions are provided.

Iris Segmentation in the Wild Using Encoder-Decoder-Based Deep Learning Techniques

2021 ◽  
pp. 283-311
Author(s):  
Shreshth Saini ◽  
Divij Gupta ◽  
Ranjeet Ranjan Jha ◽  
Gaurav Jaswal ◽  
Aditya Nigam
Keyword(s):  
Deep Learning ◽  
Iris Segmentation ◽  
Learning Techniques ◽  
In The Wild

scholarly journals Emotional sounds of crowds: spectrogram-based analysis using deep learning

2020 ◽  
Vol 79 (47-48) ◽  
pp. 36063-36075 ◽  
Author(s):  
Valentina Franzoni ◽  
Giulio Biondi ◽  
Alfredo Milani
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Critical Question ◽  
Domain Specific ◽  
Visual Knowledge ◽  
Learning Techniques ◽  
Proposed Model ◽  
Political Demonstrations ◽  
Fine Tune

AbstractCrowds express emotions as a collective individual, which is evident from the sounds that a crowd produces in particular events, e.g., collective booing, laughing or cheering in sports matches, movies, theaters, concerts, political demonstrations, and riots. A critical question concerning the innovative concept of crowd emotions is whether the emotional content of crowd sounds can be characterized by frequency-amplitude features, using analysis techniques similar to those applied on individual voices, where deep learning classification is applied to spectrogram images derived by sound transformations. In this work, we present a technique based on the generation of sound spectrograms from fragments of fixed length, extracted from original audio clips recorded in high-attendance events, where the crowd acts as a collective individual. Transfer learning techniques are used on a convolutional neural network, pre-trained on low-level features using the well-known ImageNet extensive dataset of visual knowledge. The original sound clips are filtered and normalized in amplitude for a correct spectrogram generation, on which we fine-tune the domain-specific features. Experiments held on the finally trained Convolutional Neural Network show promising performances of the proposed model to classify the emotions of the crowd.

Sign in / Sign up

Export Citation Format

Share Document