Intrusion Prediction and Detection with Deep Sequence Modeling

2020 ◽  
pp. 11-25
Author(s):  
Gaurav Sarraf ◽  
M. S. Swetha
Keyword(s):  
Sequence Modeling

scholarly journals What You Say or How You Say It? Depression Detection Through Joint Modeling of Linguistic and Acoustic Aspects of Speech

2021 ◽  
Author(s):  
Nujud Aloshban ◽  
Anna Esposito ◽  
Alessandro Vinciarelli
Keyword(s):  
Short Term Memory ◽  
Joint Modeling ◽  
Joint Analysis ◽  
Health Issues ◽  
Multimodal Analysis ◽  
Sequence Modeling ◽  
Depression Detection ◽  
Long Short Term Memory ◽  
Joint Representation ◽  
Better Than

AbstractDepression is one of the most common mental health issues. (It affects more than 4% of the world’s population, according to recent estimates.) This article shows that the joint analysis of linguistic and acoustic aspects of speech allows one to discriminate between depressed and nondepressed speakers with an accuracy above 80%. The approach used in the work is based on networks designed for sequence modeling (bidirectional Long-Short Term Memory networks) and multimodal analysis methodologies (late fusion, joint representation and gated multimodal units). The experiments were performed over a corpus of 59 interviews (roughly 4 hours of material) involving 29 individuals diagnosed with depression and 30 control participants. In addition to an accuracy of 80%, the results show that multimodal approaches perform better than unimodal ones owing to people’s tendency to manifest their condition through one modality only, a source of diversity across unimodal approaches. In addition, the experiments show that it is possible to measure the “confidence” of the approach and automatically identify a subset of the test data in which the performance is above a predefined threshold. It is possible to effectively detect depression by using unobtrusive and inexpensive technologies based on the automatic analysis of speech and language.

3D Simulation of a Peripheral Adapter J-Groove Attachment Weld in a Vessel Head

2014 ◽  
Author(s):  
Philippe Mourgue ◽  
Vincent Robin ◽  
Philippe Gilles ◽  
Florence Gommez ◽  
Alexandre Brosse ◽  
...  
Keyword(s):  
Complex Geometry ◽  
3D Simulation ◽  
Welding Parameters ◽  
Manufacturing Processes ◽  
Pressurized Water ◽  
Control Rod ◽  
Sequence Modeling ◽  
Component Design ◽  
Water Reactors ◽  
Welding Processes

In Pressurized Water Reactors, most of heavy components and pipes have a large thickness and their manufacturing processes often require multi-pass welding. Despite the stiffness of these components, the distortion issue may be important for operational requirements (e.g. misalignment) or controllability reasons (Non Destructive Examinations have to be achievable, therefore ovalization should be limited). These requirements may be difficult to achieve by simply adjusting welding processes. Indeed because of the complexity of mechanisms involved during a welding operation and the high number of influencing parameters, this process is still essentially based on the experience of the welder. Furthermore the experimental estimation of the stress and distortion level in the component remains a difficult task that is subject to errors even if techniques are currently improved to become more accurate. These are the reasons why AREVA has put a large effort to improve welding numerical simulations, in order to have a better understanding of the involved physical phenomena and also to predict the residual state through the structure. Computational welding mechanics is used to qualify the manufacturing processes in the very early phase of the welded component design. Within the framework of a R&D program whose main objective was to improve tools for the numerical simulation of welding regarding industrial needs, AREVA has decided to validate new methodologies based on 3D computation by comparison with measurements. For this validation task the chosen industrial demonstrator was a Control Rod Drive Mechanism (CRDM) Nozzle with a J-groove attachment weld to the vessel head. For such an application, operations of post-joining straightening have to be limited, if not prohibited, because of their cost or the impossibility to use them in front of a steel giant. The control of distortion during welding operations is a key issue for which simulation can be of great help. Regarding distortion issues, both accurate metal deposit sequence modeling and respect of the real welding parameters are mandatory, especially for multi-pass operation on such a complex geometry. The aim of this paper is to present the simulation of the distortion of a peripheral adapter J-groove attachment weld mock-up. This new full 3D simulation improves the result of the previous one based on lumped pass deposits. It is the result of a fruitful collaboration between AREVA and ESI-Group.

scholarly journals End-to-end recognition of streaming Japanese speech using CTC and local attention

2020 ◽  
Vol 9 ◽  
Author(s):  
Jiahao Chen ◽  
Ryota Nishimura ◽  
Norihide Kitaoka
Keyword(s):  
Speech Recognition ◽  
Recognition Performance ◽  
Time Lag ◽  
Recognition Algorithm ◽  
Streaming Data ◽  
Continuous Speech Recognition ◽  
Voice Input ◽  
Sequence Modeling ◽  
End To End ◽  
Bidirectional Networks

Many end-to-end, large vocabulary, continuous speech recognition systems are now able to achieve better speech recognition performance than conventional systems. Most of these approaches are based on bidirectional networks and sequence-to-sequence modeling however, so automatic speech recognition (ASR) systems using such techniques need to wait for an entire segment of voice input to be entered before they can begin processing the data, resulting in a lengthy time-lag, which can be a serious drawback in some applications. An obvious solution to this problem is to develop a speech recognition algorithm capable of processing streaming data. Therefore, in this paper we explore the possibility of a streaming, online, ASR system for Japanese using a model based on unidirectional LSTMs trained using connectionist temporal classification (CTC) criteria, with local attention. Such an approach has not been well investigated for use with Japanese, as most Japanese-language ASR systems employ bidirectional networks. The best result for our proposed system during experimental evaluation was a character error rate of 9.87%.

I Know What You Need: Investigating Document Retrieval Effectiveness with Partial Session Contexts

2022 ◽  
Vol 40 (3) ◽  
pp. 1-30
Author(s):  
Procheta Sen ◽  
Debasis Ganguly ◽  
Gareth J. F. Jones
Keyword(s):  
Relevant Information ◽  
Document Retrieval ◽  
Context Information ◽  
Information Need ◽  
Search System ◽  
Query Log ◽  
Sequence Modeling ◽  
Joint Embedding ◽  
One Step ◽  
A Current

Reducing user effort in finding relevant information is one of the key objectives of search systems. Existing approaches have been shown to effectively exploit the context from the current search session of users for automatically suggesting queries to reduce their search efforts. However, these approaches do not accomplish the end goal of a search system—that of retrieving a set of potentially relevant documents for the evolving information need during a search session. This article takes the problem of query prediction one step further by investigating the problem of contextual recommendation within a search session. More specifically, given the partial context information of a session in the form of a small number of queries, we investigate how a search system can effectively predict the documents that a user would have been presented with had he continued the search session by submitting subsequent queries. To address the problem, we propose a model of contextual recommendation that seeks to capture the underlying semantics of information need transitions of a current user’s search context. This model leverages information from a number of past interactions of other users with similar interactions from an existing search log. To identify similar interactions, as a novel contribution, we propose an embedding approach that jointly learns representations of both individual query terms and also those of queries (in their entirety) from a search log data by leveraging session-level containment relationships. Our experiments conducted on a large query log, namely the AOL, demonstrate that using a joint embedding of queries and their terms within our proposed framework of document retrieval outperforms a number of text-only and sequence modeling based baselines.

Sign in / Sign up

Export Citation Format

Share Document