Deep neural learning techniques with long short-term memory for gesture recognition

2020 ◽  
Vol 32 (20) ◽  
pp. 16073-16089
Author(s):  
Deepak Kumar Jain ◽  
Aniket Mahanti ◽  
Pourya Shamsolmoali ◽  
Ramachandran Manikandan
Keyword(s):  
Gesture Recognition ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Neural Learning ◽  
Learning Techniques ◽  
Long Short Term Memory

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 Two-Step Biometrics Using Electromyogram Signal Based on Convolutional Neural Network-Long Short-Term Memory Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6824
Author(s):  
Jin-Su Kim ◽  
Min-Gu Kim ◽  
Sung-Bum Pan
Keyword(s):  
Neural Network ◽  
Data Fusion ◽  
Convolutional Neural Network ◽  
Gesture Recognition ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Emg Signal ◽  
Long Short Term Memory ◽  
Lstm Network

Electromyogram (EMG) signals cannot be forged and have the advantage of being able to change the registered data as they are characterized by the waveform, which varies depending on the gesture. In this paper, a two-step biometrics method was proposed using EMG signals based on a convolutional neural network–long short-term memory (CNN-LSTM) network. After preprocessing of the EMG signals, the time domain features and LSTM network were used to examine whether the gesture matched, and single biometrics was performed if the gesture matched. In single biometrics, EMG signals were converted into a two-dimensional spectrogram, and training and classification were performed through the CNN-LSTM network. Data fusion of the gesture recognition and single biometrics was performed in the form of an AND. The experiment used Ninapro EMG signal data as the proposed two-step biometrics method, and the results showed 83.91% gesture recognition performance and 99.17% single biometrics performance. In addition, the false acceptance rate (FAR) was observed to have been reduced by 64.7% through data fusion.

scholarly journals COMPARATIVE ANALYSIS AND EVALUATION OF THE APPLICATION OF DEEP LEARNING TECHNIQUES TO CYBERSECURITY DATASETS

10.6036/10007 ◽  
2021 ◽  
Vol 96 (5) ◽  
pp. 528-533
Author(s):  
XAVIER LARRIVA NOVO ◽  
MARIO VEGA BARBAS ◽  
VICTOR VILLAGRA ◽  
JULIO BERROCAL
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
High Performance ◽  
New Technologies ◽  
Short Term Memory ◽  
Machine Learning Techniques ◽  
Short Term ◽  
Term Memory ◽  
Learning Techniques ◽  
Long Short Term Memory

Cybersecurity has stood out in recent years with the aim of protecting information systems. Different methods, techniques and tools have been used to make the most of the existing vulnerabilities in these systems. Therefore, it is essential to develop and improve new technologies, as well as intrusion detection systems that allow detecting possible threats. However, the use of these technologies requires highly qualified cybersecurity personnel to analyze the results and reduce the large number of false positives that these technologies presents in their results. Therefore, this generates the need to research and develop new high-performance cybersecurity systems that allow efficient analysis and resolution of these results. This research presents the application of machine learning techniques to classify real traffic, in order to identify possible attacks. The study has been carried out using machine learning tools applying deep learning algorithms such as multi-layer perceptron and long-short-term-memory. Additionally, this document presents a comparison between the results obtained by applying the aforementioned algorithms and algorithms that are not deep learning, such as: random forest and decision tree. Finally, the results obtained are presented, showing that the long-short-term-memory algorithm is the one that provides the best results in relation to precision and logarithmic loss.

scholarly journals Comparative Analysis of Deep Learning Techniques for the Classification of Hate Speech

2021 ◽  
Vol 4 (1) ◽  
pp. 121-128
Author(s):  
A Iorliam ◽  
S Agber ◽  
MP Dzungwe ◽  
DK Kwaghtyo ◽  
S Bum
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Deep Learning ◽  
Hate Speech ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Learning Techniques ◽  
Or Groups ◽  
Long Short Term Memory

Social media provides opportunities for individuals to anonymously communicate and express hateful feelings and opinions at the comfort of their rooms. This anonymity has become a shield for many individuals or groups who use social media to express deep hatred for other individuals or groups, tribes or race, religion, gender, as well as belief systems. In this study, a comparative analysis is performed using Long Short-Term Memory and Convolutional Neural Network deep learning techniques for Hate Speech classification. This analysis demonstrates that the Long Short-Term Memory classifier achieved an accuracy of 92.47%, while the Convolutional Neural Network classifier achieved an accuracy of 92.74%. These results showed that deep learning techniques can effectively classify hate speech from normal speech.

HUMAN ROBOT INTERACTIVE INTENTION PREDICTION USING DEEP LEARNING TECHNIQUES

2021 ◽  
pp. 1-12
Author(s):  
Thang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
The Neural Network ◽  
Learning Techniques ◽  
Long Short Term Memory ◽  
Deep Learning Neural Network

In this research, we propose a method of human robot interactive intention prediction. The proposed algorithm makes use of a OpenPose library and a Long-short term memory deep learning neural network. The neural network observes the human posture in a time series, then predicts the human interactive intention. We train the deep neural network using dataset generated by us. The experimental results show that, our proposed method is able to predict the human robot interactive intention, providing 92% the accuracy on the testing set.

scholarly journals Echo State Networks and Long Short-Term Memory for Continuous Gesture Recognition: a Comparative Study

2020 ◽  
Author(s):  
Doreen Jirak ◽  
Stephan Tietz ◽  
Hassan Ali ◽  
Stefan Wermter
Keyword(s):  
Comparative Study ◽  
Real Time ◽  
Gesture Recognition ◽  
Network Architecture ◽  
Short Term Memory ◽  
Medical Rehabilitation ◽  
Measurement Unit ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Abstract Recent developments of sensors that allow tracking of human movements and gestures enable rapid progress of applications in domains like medical rehabilitation or robotic control. Especially the inertial measurement unit (IMU) is an excellent device for real-time scenarios as it rapidly delivers data input. Therefore, a computational model must be able to learn gesture sequences in a fast yet robust way. We recently introduced an echo state network (ESN) framework for continuous gesture recognition (Tietz et al., 2019) including novel approaches for gesture spotting, i.e., the automatic detection of the start and end phase of a gesture. Although our results showed good classification performance, we identified significant factors which also negatively impact the performance like subgestures and gesture variability. To address these issues, we include experiments with Long Short-Term Memory (LSTM) networks, which is a state-of-the-art model for sequence processing, to compare the obtained results with our framework and to evaluate their robustness regarding pitfalls in the recognition process. In this study, we analyze the two conceptually different approaches processing continuous, variable-length gesture sequences, which shows interesting results comparing the distinct gesture accomplishments. In addition, our results demonstrate that our ESN framework achieves comparably good performance as the LSTM network but has significantly lower training times. We conclude from the present work that ESNs are viable models for continuous gesture recognition delivering reasonable performance for applications requiring real-time performance as in robotic or rehabilitation tasks. From our discussion of this comparative study, we suggest prospective improvements on both the experimental and network architecture level.

Sign in / Sign up

Export Citation Format

Share Document