POSTER: Bridging the Gap Between Deep Learning and Sparse Matrix Format Selection

2017 ◽  
Author(s):  
Yue Zhao ◽  
Jiajia Li ◽  
Chunhua Liao ◽  
Xipeng Shen
Keyword(s):  
Deep Learning ◽  
Sparse Matrix

scholarly journals Video Object Detection through Traditional and Deep Learning Methods

2020 ◽  
Vol 9 (4) ◽  
pp. 1822-1826
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Sparse Matrix ◽  
Image Understanding ◽  
Low Rank ◽  
Detection Methods ◽  
Video Object ◽  
Learning Methods ◽  
Primary Focus ◽  
High Level

Object detection in videos is gaining more attention recently as it is related to video analytics and facilitates image understanding and applicable to . The video object detection methods can be divided into traditional and deep learning based methods. Trajectory classification, low rank sparse matrix, background subtraction and object tracking are considered as traditional object detection methods as they primary focus is informative feature collection, region selection and classification. The deep learning methods are more popular now days as they facilitate high-level features and problem solving in object detection algorithms. We have discussed various object detection methods and challenges in this paper.

Soft detection of 5-day BOD with sparse matrix in city harbor water using deep learning techniques

2020 ◽  
Vol 170 ◽  
pp. 115350 ◽  
Author(s):  
Jun Ma ◽  
Yuexiong Ding ◽  
Jack C.P. Cheng ◽  
Feifeng Jiang ◽  
Zherui Xu
Keyword(s):  
Deep Learning ◽  
Sparse Matrix ◽  
Soft Detection ◽  
Learning Techniques

scholarly journals Automatic Recommendation Algorithm for Video Background Music Based on Deep Learning

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Hong Kai
Keyword(s):  
Deep Learning ◽  
Collaborative Filtering ◽  
Performance Test ◽  
Sparse Matrix ◽  
Auxiliary Information ◽  
Background Music ◽  
Model Design ◽  
Fusion Model ◽  
Recommendation Algorithm ◽  
Tightly Coupled

As one of the traditional entertainment items, video background music has gradually changed from traditional consumption to network consumption, which naturally also has the problem of information overload. From the perspective of model design and auxiliary information, this paper proposes a tightly coupled fusion model based on deep learning and collaborative filtering to alleviate the problem of poor prediction accuracy due to sparse matrix in the scoring prediction problem. In the use of auxiliary information, this paper uses crawler technology to obtain auxiliary information on the user side and the video background music side and compensates for the model’s sensitivity to the sparsity of the score matrix from a data perspective. In terms of model design, this paper conducts auxiliary information mining based on the diversity and structural differences of auxiliary information, uses an improved stack autoencoder to learn user’s interests, and uses convolutional neural networks to mine hidden features of video background music. Based on the idea of probabilistic matrix decomposition, the tightly coupled fusion of multiple deep learning models and collaborative filtering is realized. By comprehensively considering user’s interest and video background music characteristics, the collaborative filtering process is supervised, and the optimized prediction result is finally obtained. The performance test and function test of the system were carried out, respectively, to verify the effectiveness of the hybrid recommendation algorithm and the effect of the system for recommendation. Through experimental analysis, it is proved that the algorithm designed in this paper can improve the recommendation quality and achieve the expected goal.

scholarly journals Gene Mutation Classification through Text Evidence Facilitating Cancer Tumour Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Meenu Gupta ◽  
Hao Wu ◽  
Simrann Arora ◽  
Akash Gupta ◽  
Gopal Chaudhary ◽  
...  
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Clinical Evidence ◽  
Sparse Matrix ◽  
Confusion Matrix ◽  
Genetic Mutation ◽  
Cancer Center ◽  
Genetic Mutations ◽  
Accuracy Score ◽  
Machine Learning Classification

A cancer tumour consists of thousands of genetic mutations. Even after advancement in technology, the task of distinguishing genetic mutations, which act as driver for the growth of tumour with passengers (Neutral Genetic Mutations), is still being done manually. This is a time-consuming process where pathologists interpret every genetic mutation from the clinical evidence manually. These clinical shreds of evidence belong to a total of nine classes, but the criterion of classification is still unknown. The main aim of this research is to propose a multiclass classifier to classify the genetic mutations based on clinical evidence (i.e., the text description of these genetic mutations) using Natural Language Processing (NLP) techniques. The dataset for this research is taken from Kaggle and is provided by the Memorial Sloan Kettering Cancer Center (MSKCC). The world-class researchers and oncologists contribute the dataset. Three text transformation models, namely, CountVectorizer, TfidfVectorizer, and Word2Vec, are utilized for the conversion of text to a matrix of token counts. Three machine learning classification models, namely, Logistic Regression (LR), Random Forest (RF), and XGBoost (XGB), along with the Recurrent Neural Network (RNN) model of deep learning, are applied to the sparse matrix (keywords count representation) of text descriptions. The accuracy score of all the proposed classifiers is evaluated by using the confusion matrix. Finally, the empirical results show that the RNN model of deep learning has performed better than other proposed classifiers with the highest accuracy of 70%.

scholarly journals Artificial intelligence enhanced two-dimensional nanoscale nuclear magnetic resonance spectroscopy

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Xi Kong ◽  
Leixin Zhou ◽  
Zhijie Li ◽  
Zhiping Yang ◽  
Bensheng Qiu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Nuclear Magnetic Resonance ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Single Molecule ◽  
Sparse Matrix ◽  
Nitrogen Vacancy ◽  
Resonance Spectroscopy ◽  
Two Dimensional ◽  
Nuclear Magnetic

Abstract Two-dimensional nuclear magnetic resonance (NMR) is indispensable to molecule structure determination. Nitrogen-vacancy center in diamond has been proposed and developed as an outstanding quantum sensor to realize NMR in nanoscale or even single molecule. However, like conventional multi-dimensional NMR, a more efficient data accumulation and processing method is necessary to realize applicable two-dimensional (2D) nanoscale NMR with a high spatial resolution nitrogen-vacancy sensor. Deep learning is an artificial algorithm, which mimics the network of neurons of human brain, has been demonstrated superb capability in pattern identifying and noise canceling. Here we report a method, combining deep learning and sparse matrix completion, to speed up 2D nanoscale NMR spectroscopy. The signal-to-noise ratio is enhanced by 5.7 ± 1.3 dB in 10% sampling coverage by an artificial intelligence protocol on 2D nanoscale NMR of a single nuclear spin cluster. The artificial intelligence algorithm enhanced 2D nanoscale NMR protocol intrinsically suppresses the observation noise and thus improves sensitivity.

scholarly journals Implementation of Deep Dictionary Learning and Coding Network for Plant Disease Detection in Agricultural Field

2021 ◽  
pp. 547-553
Author(s):  
Snehal A. Lale ◽  
Dr. V. K. Shandilya
Keyword(s):  
Deep Learning ◽  
Dictionary Learning ◽  
Plant Disease ◽  
Sparse Matrix ◽  
Agricultural Field ◽  
Plant Leaves ◽  
End User ◽  
Data Set ◽  
Online Application ◽  
Web Based

A web based online application is built to detect the diseases present on plant leaves. This will help farmer/end user to find out which diseases are present on that leaves. In older times, this task requires much time & resources to do the detection. A approach has of DDLCN has been taken in this project which will help to find out the best match features. In this approach. I have taken up to 3 layers of DDLCN which will filter the most match features of the diseases present on plant leaves. The proposed DDLCN combines the two things that is deep learning & dictionary learning. Deep learning which the branch of AI. It has a structures inspired by the human brain. It has the artificial neural networks which helps to train the data. Now taking about the dictionary learning which has a literal meaning having large number of data set. Dictionary learning is also called as sparse representation which will help to arrange the data in proper manner and without wasting the storage. Because it will only count the non zeros numbers present in the sparse matrix.

Sign in / Sign up

Export Citation Format

Share Document