scholarly journals Multi-Dimensional Enhanced Seizure Prediction Framework Based on Graph Convolutional Network

2021 ◽  
Vol 15 ◽  
Author(s):  
Xin Chen ◽  
Yuanjie Zheng ◽  
Changxu Dong ◽  
Sutao Song
Keyword(s):  
Frequency Band ◽  
Scientific Research ◽  
Spatial Relationship ◽  
Space Time ◽  
Multiple Channels ◽  
Research Subject ◽  
Seizure Prediction ◽  
Graph State ◽  
Convolutional Network ◽  
Proposed Model

In terms of seizure prediction, how to fully mine relational data information among multiple channels of epileptic EEG? This is a scientific research subject worthy of further exploration. Recently, we propose a multi-dimensional enhanced seizure prediction framework, which mainly includes information reconstruction space, graph state encoder, and space-time predictor. It takes multi-channel spatial relationship as breakthrough point. At the same time, it reconstructs data unit from frequency band level, updates graph coding representation, and explores space-time relationship. Through experiments on CHB-MIT dataset, sensitivity of the model reaches 98.61%, which proves effectiveness of the proposed model.

Discreteness of Space and Its Consequences

2021 ◽  
pp. 132-141
Author(s):  
Аnatoly М. Shutyi ◽  
Keyword(s):  
Spatial Configuration ◽  
Relativistic Effects ◽  
Space Time ◽  
Maximum Speed ◽  
Speed Of Light ◽  
Quantum Uncertainty ◽  
Proposed Model ◽  
Spatial Configurations ◽  
New Interpretation ◽  
Component Particle

Based on the general principle of the unity of the nature of interacting entities and the principle of the relativity of motion, as well as following the requirement of an indissoluble and conditioning connection of space and time, the model of a discrete space-time consisting of identical interacting particles is proposed as the most acceptable one. We consider the consequences of the discreteness of space, such as: the occurrence of time quanta, the limiting speed of signal propa­gation, and the constancy of this speed, regardless of the motion of the reference frame. Regularly performed acts of particles of space-time (PST) interaction en­sure the connectivity of space, set the quantum of time and the maximum speed – the speed of light. In the process of PST communication, their mixing occurs, which ensures the relativity of inertial motion, and can also underlie quantum uncertainty. In this case, elementary particles are spatial configurations of an excited “lattice” of PST, and particles with mass must contain loop struc­tures in their configuration. A new interpretation of quantum mechanics is pro­posed, according to which the wave function determines the probability of de­struction of a spatial configuration (representing a quantum object) in its corresponding region, which leads to the contraction of the entire structure to a given, detectable component. Particle entanglement is explained by the appear­ance of additional links between the PST – the appearance of a local coordinate along which the distance between entangled objects does not increase. It is shown that the movement of a body should lead to an asymmetry of the tension of the bonds between the PST – to the asymmetry of its effective gravity, the es­tablishment of which is one of the possibilities for experimental verification of the proposed model. It is shown that the constancy of the speed of light in a vac­uum and the appearance of relativistic effects are based on ensuring the connec­tivity of space-time, i.e. striving to prevent its rupture.

K-Nearest Neighbors Algorithm (KNN)

2021 ◽  
pp. 161-178
Author(s):  
Abdelaziz Elbaghdadi ◽  
Soufiane Mezroui ◽  
Ahmed El Oualkadi
Keyword(s):  
Business Process ◽  
Scientific Research ◽  
Nearest Neighbors ◽  
Local Information ◽  
K Nearest Neighbors ◽  
Blockchain Technology ◽  
Use Of Data ◽  
Proposed Model

The cryptocurrency is the first implementation of blockchain technology. This technology provides a set of tracks and innovation in scientific research, such as use of data either to detect anomalies either to predict price in the Bitcoin and the Ethereum. Furthermore, the blockchain technology provide a set of technique to automate the business process. This chapter presents a review of some research works related to cryptocurrency. A model with a KNN algorithm is proposed to detect illicit transaction. The proposed model uses both the elliptic dataset and KNN algorithm to detect illicit transaction. Furthermore, the elliptic dataset contains 203,769 nodes and 234,355 edges; it allows to classify the data into three classes: illicit, licit, or unknown. Each node has associated 166 features. The first 94 features represent local information about the transaction. The remaining 72 features are called aggregated features. The accuracy exceeded 90% with k=2 and k=4, the recall reaches 56% with k=3, and the precision reaches 78% with k=4.

scholarly journals Graph-Driven Generative Models for Heterogeneous Multi-Task Learning

2020 ◽  
Vol 34 (01) ◽  
pp. 979-988
Author(s):  
Wenlin Wang ◽  
Hongteng Xu ◽  
Zhe Gan ◽  
Bai Li ◽  
Guoyin Wang ◽  
...  
Keyword(s):  
Generative Models ◽  
Healthcare Applications ◽  
Convolutional Network ◽  
Learning Tasks ◽  
Proposed Model ◽  
Heterogeneous Learning ◽  
Clinical Topic ◽  
Generative Processes ◽  
Admission Type ◽  
Uniform Manner

We propose a novel graph-driven generative model, that unifies multiple heterogeneous learning tasks into the same framework. The proposed model is based on the fact that heterogeneous learning tasks, which correspond to different generative processes, often rely on data with a shared graph structure. Accordingly, our model combines a graph convolutional network (GCN) with multiple variational autoencoders, thus embedding the nodes of the graph (i.e., samples for the tasks) in a uniform manner, while specializing their organization and usage to different tasks. With a focus on healthcare applications (tasks), including clinical topic modeling, procedure recommendation and admission-type prediction, we demonstrate that our method successfully leverages information across different tasks, boosting performance in all tasks and outperforming existing state-of-the-art approaches.

scholarly journals Research on Discriminative Skeleton-Based Action Recognition in Spatiotemporal Fusion and Human-Robot Interaction

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Qiubo Zhong ◽  
Caiming Zheng ◽  
Haoxiang Zhang
Keyword(s):  
Action Recognition ◽  
Human Body ◽  
Sequence Data ◽  
Spatial Relationship ◽  
Human Robot Interaction ◽  
Robot Interaction ◽  
Convolutional Network ◽  
Action Sequence ◽  
Interaction System ◽  
High Discrimination

A novel posture motion-based spatiotemporal fused graph convolutional network (PM-STGCN) is presented for skeleton-based action recognition. Existing methods on skeleton-based action recognition focus on independently calculating the joint information in single frame and motion information of joints between adjacent frames from the human body skeleton structure and then combine the classification results. However, that does not take into consideration of the complicated temporal and spatial relationship of the human body action sequence, so they are not very efficient in distinguishing similar actions. In this work, we enhance the ability of distinguishing similar actions by focusing on spatiotemporal fusion and adaptive feature extraction for high discrimination information. Firstly, the local posture motion-based attention (LPM-TAM) module is proposed for the purpose of suppressing the skeleton sequence data with a low amount of motion in the temporal domain, and the representation of motion posture features is concentrated. Besides, the local posture motion-based channel attention module (LPM-CAM) is introduced to make use of the strongly discriminative representation between different action classes of similarity. Finally, the posture motion-based spatiotemporal fusion (PM-STF) module is constructed which fuses the spatiotemporal skeleton data by filtering out the low-information sequence and enhances the posture motion features adaptively with high discrimination. Extensive experiments have been conducted, and the results demonstrate that the proposed model is superior to the commonly used action recognition methods. The designed human-robot interaction system based on action recognition has competitive performance compared with the speech interaction system.

scholarly journals Revisiting Graph Based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach

2020 ◽  
Vol 34 (01) ◽  
pp. 27-34 ◽  
Author(s):  
Lei Chen ◽  
Le Wu ◽  
Richang Hong ◽  
Kun Zhang ◽  
Meng Wang
Keyword(s):  
Collaborative Filtering ◽  
Representation Learning ◽  
Superior Performance ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Proposed Model ◽  
Non Linear ◽  
Efficiency And Effectiveness ◽  
Residual Graph ◽  
Interaction Modeling

Graph Convolutional Networks~(GCNs) are state-of-the-art graph based representation learning models by iteratively stacking multiple layers of convolution aggregation operations and non-linear activation operations. Recently, in Collaborative Filtering~(CF) based Recommender Systems~(RS), by treating the user-item interaction behavior as a bipartite graph, some researchers model higher-layer collaborative signals with GCNs. These GCN based recommender models show superior performance compared to traditional works. However, these models suffer from training difficulty with non-linear activations for large user-item graphs. Besides, most GCN based models could not model deeper layers due to the over smoothing effect with the graph convolution operation. In this paper, we revisit GCN based CF models from two aspects. First, we empirically show that removing non-linearities would enhance recommendation performance, which is consistent with the theories in simple graph convolutional networks. Second, we propose a residual network structure that is specifically designed for CF with user-item interaction modeling, which alleviates the over smoothing problem in graph convolution aggregation operation with sparse user-item interaction data. The proposed model is a linear model and it is easy to train, scale to large datasets, and yield better efficiency and effectiveness on two real datasets. We publish the source code at https://github.com/newlei/LR-GCCF.

scholarly journals Performance Analysis of Grouped Multilevel Space-Time Trellis Coding Technique Using Cognitive Radio in Different Deployment Models

2019 ◽  
Vol 2019 ◽  
pp. 1-20 ◽  
Author(s):  
Shakti Raj Chopra ◽  
Akhil Gupta ◽  
Rakesh Kumar Jha
Keyword(s):  
Cognitive Radio ◽  
Error Rate ◽  
Cooperative Diversity ◽  
Symbol Error Rate ◽  
Space Time ◽  
Link Quality ◽  
Trellis Coding ◽  
Space Time Coding ◽  
Proposed Model

In this era, the number of users in a network is increasing tremendously at a faster rate; as a consequence, quality of service (QoS) is drastically deteriorating. To compensate such kinds of problems, we attempted to enhance the QoS of the network, which leads to an improvement in throughput, link quality, spectral efficiency, and many more. To meet the requirements mentioned above, many researchers intervene to advance and propose different techniques with an appropriate design methodology. In this work, we try to emphasize symbol error rate (SER) and frame error rate (FER) by implementing some of the existing space-time coding techniques like Space-Time Trellis Coding (STTC), multilevel space-time trellis coding (MLSTTC), and grouped multilevel space-time trellis coding (GMLSTTC). Though all these techniques are proved to be efficient enough, we explicitly included a powerful method of cooperative diversity-based spectrum sensing in cognitive radio scenario. From this analysis, we landed on to the conclusion that this technique is far better to deal with all these parameters, which can improve the QoS of the network. This paper has also analyzed the effect of the proposed model of GMLSTTC with cognitive radio on various deployment setups such as urban, suburban, and rural macrodeployment setup of the ITU-R M.2135 standard.

scholarly journals L'innovation, son contenu et ses vecteurs dans le domaine de la gestion environnementale forestière | Content and Vectors of Innovation in Environmental Forest Management

2000 ◽  
Vol 151 (12) ◽  
pp. 527-530
Author(s):  
Alexandre Buttler
Keyword(s):  
Forest Management ◽  
Time Scale ◽  
Scientific Research ◽  
Space Time ◽  
Innovative Approach ◽  
Sectoral Approach ◽  
Forest Law

The significance of an innovative approach in the solutionfinding of forest engineers is analysed on the basis of actual situations, and the role of scientific research is emphasised. The new Swiss Forest Law is clearly developing towards creativity and increasingly calls for innovative actions. These actions vary significantly and can be related to products and processes, new functions for these products and processes, interactions between organisations or even the new orientation of organisations. Innovative actions always imply risks. Innovation in scientific research is closely correlated to the innovation in forest management. It is important to take into consideration the space-time scale of innovation in order to fully understand the decisions which are taken in practice as well as the interventions carried out in the field. Within a process leading from a rather sectoral approach of ecosystem-sustainability towards a broader understanding with regard to development, new opportunities of innovation are given today which contribute to a closer co-operation between scientific research and forest management. Thus, the integration of interests and partners may be seen as an innovation itself.

scholarly journals Sentence Compression Using BERT and Graph Convolutional Networks

2021 ◽  
Vol 11 (21) ◽  
pp. 9910
Author(s):  
Yo-Han Park ◽  
Gyong-Ho Lee ◽  
Yong-Seok Choi ◽  
Kong-Joo Lee
Keyword(s):  
Language Processing ◽  
Large Scale ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Compression Model ◽  
Sentence Compression ◽  
Dependency Tree ◽  
Proposed Model ◽  
Syntactic Information ◽  
Input Sentence

Sentence compression is a natural language-processing task that produces a short paraphrase of an input sentence by deleting words from the input sentence while ensuring grammatical correctness and preserving meaningful core information. This study introduces a graph convolutional network (GCN) into a sentence compression task to encode syntactic information, such as dependency trees. As we upgrade the GCN to activate a directed edge, the compression model with the GCN layers can distinguish between parent and child nodes in a dependency tree when aggregating adjacent nodes. Furthermore, by increasing the number of GCN layers, the model can gradually collect high-order information of a dependency tree when propagating node information through the layers. We implement a sentence compression model for Korean and English, respectively. This model consists of three components: pre-trained BERT model, GCN layers, and a scoring layer. The scoring layer can determine whether a word should remain in a compressed sentence by relying on the word vector containing contextual and syntactic information encoded by BERT and GCN layers. To train and evaluate the proposed model, we used the Google sentence compression dataset for English and a Korean sentence compression corpus containing about 140,000 sentence pairs for Korean. The experimental results demonstrate that the proposed model achieves state-of-the-art performance for English. To the best of our knowledge, this sentence compression model based on the deep learning model trained with a large-scale corpus is the first attempt for Korean.

scholarly journals Identifying Human Daily Activity Types with Time-Aware Interactions

2020 ◽  
Vol 10 (24) ◽  
pp. 8922
Author(s):  
Renyao Chen ◽  
Hong Yao ◽  
Runjia Li ◽  
Xiaojun Kang ◽  
Shengwen Li ◽  
...  
Keyword(s):  
Social Media ◽  
Human Activity ◽  
Model Performance ◽  
Heterogeneous Data ◽  
Accurate Identification ◽  
Convolutional Network ◽  
Proposed Model ◽  
Crowdsourced Data ◽  
Activity Types ◽  
Media Data

Human activities embedded in crowdsourced data, such as social media trajectory, represent individual daily styles and patterns, which are valuable in many applications. However, the accurate identification of human activity types (HATs) from social media is challenging, possibly because interactions between posts and users at different time are overlooked. To fill this gap, we propose a novel model that introduces the interactions hidden in social media and synthesizes Graph Convolutional Network (GCN) for identifying HAT. The model first characterizes interactions among words, posts, dates, and users, and then derives a Time Gated Human Activity Graph Convolutional Network (TG-HAGCN) to predict the HATs of social media trajectory. To examine the proposed model performance, we built a new dataset including interactions between post content, post time, and users from the open Yelp dataset. Experimental results show that exploiting interactions hidden in social media to recognize HATs achieves state-of-the-art performance with high accuracy. The study indicates that interactions among social media promotes ability of machine learning on social media data mining and intelligent applications, and offers a reference solution for how to fuse multi-type heterogeneous data in social media.

scholarly journals HGMAN: Multi-Hop and Multi-Answer Question Answering Based on Heterogeneous Knowledge Graph (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13953-13954
Author(s):  
Xu Wang ◽  
Shuai Zhao ◽  
Bo Cheng ◽  
Jiale Han ◽  
Yingting Li ◽  
...  
Keyword(s):  
Question Answering ◽  
Binary Classification ◽  
Experimental Results ◽  
Ranking Method ◽  
Knowledge Graph ◽  
Convolutional Network ◽  
Proposed Model ◽  
The Right ◽  
Novel Model ◽  
Heterogeneous Knowledge

Multi-hop question answering models based on knowledge graph have been extensively studied. Most existing models predict a single answer with the highest probability by ranking candidate answers. However, they are stuck in predicting all the right answers caused by the ranking method. In this paper, we propose a novel model that converts the ranking of candidate answers into individual predictions for each candidate, named heterogeneous knowledge graph based multi-hop and multi-answer model (HGMAN). HGMAN is capable of capturing more informative representations for relations assisted by our heterogeneous graph, which consists of multiple entity nodes and relation nodes. We rely on graph convolutional network for multi-hop reasoning and then binary classification for each node to get multiple answers. Experimental results on MetaQA dataset show the performance of our proposed model over all baselines.

Sign in / Sign up

Export Citation Format

Share Document