Rajarathnam Chandramouli
Rajarathnam Chandramouli has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Koduvayur Subbalakshmi
Stevens Inst of Technology
3 shared publications - Bingyang Wen
Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken, NJ United States
2 shared publications - Ning Wang
Jiangnan University
2 shared publications - Ellen E. Lee
Department of Psychiatry, University of California San Diego, La Jolla, CA, USA
1 shared publication - Fan Luo
School of Management, Wuhan University of Technology, Wuhan 430070, China
1 shared publication - Hafiz Malik
University of Michigan, Dearborn, MI, USA
1 shared publication
Latest Publications
- Open Access
- 2 May 2023
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 7 (1) , e36590
Revealing the Roles of Part-of-Speech Taggers in Alzheimer Disease Detection: Scientific Discovery Using One-Intervention Causal Explanation
Background: Recently, rich computational methods that use deep learning or machine learning have been developed using linguistic biomarkers for the diagnosis of early-stage Alzheimer disease (AD). Moreover, some qualitative and quantitative studies have indicated that certain part-of-speech (PoS) features or tags could be good indicators of AD. However, there has not been a systematic attempt to discover the underlying relationships between PoS features and AD. Moreover, there has not been any attempt to quantify the relative importance of PoS features in detecting AD. Objective: Our goal was to disclose the underlying relationship between PoS features and AD, understand whether PoS features are useful in AD diagnosis, and explore which PoS features play a vital role in the diagnosis. Methods: The DementiaBank, containing 1049 transcripts from 208 patients with AD and 243 transcripts from 104 older control individuals, was used. A total of 27 PoS features were extracted from each record. Then, the relationship between AD and each of the PoS features was explored. A transformer-based deep learning model for AD prediction using PoS features was trained. Then, a global explainable artificial intelligence method was proposed and used to discover which PoS features were the most important in AD diagnosis using the transformer-based predictor. A global (model-level) feature importance measure was derived as a summary from the local (example-level) feature importance metric, which was obtained using the proposed causally aware counterfactual explanation method. The unique feature of this method is that it considers causal relations among PoS features and can, hence, preclude counterfactuals that are improbable and result in more reliable explanations. Results: The deep learning–based AD predictor achieved an accuracy of 92.2% and an F1-score of 0.955 when distinguishing patients with AD from healthy controls. The proposed explanation method identified 12 PoS features as being important for distinguishing patients with AD from healthy controls. Of these 12 features, 3 (25%) have been identified by other researchers in previous works in psychology and natural language processing. The remaining 75% (9/12) of PoS features have not been previously identified. We believe that this is an interesting finding that can be used in creating tests that might aid in the diagnosis of AD. Note that although our method is focused on PoS features, it should be possible to extend it to more types of features, perhaps even those derived from other biomarkers, such as syntactic features. Conclusions: The high classification accuracy of the proposed deep learner indicates that PoS features are strong clues in AD diagnosis. There are 12 PoS features that are strongly tied to AD, and because language is a noninvasive and potentially cheap method for detecting AD, this work shows some promising directions in this field.
- 2 May 2023
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 7 (1) , e36590
Open AccessRevealing the Roles of Part-of-Speech Taggers in Alzheimer Disease Detection: Scientific Discovery Using One-Intervention Causal Explanation
Background: Recently, rich computational methods that use deep learning or machine learning have been developed using linguistic biomarkers for the diagnosis of early-stage Alzheimer disease (AD). Moreover, some qualitative and quantitative studies have indicated that certain part-of-speech (PoS) features or tags could be good indicators of AD. However, there has not been a systematic attempt to discover the underlying relationships between PoS features and AD. Moreover, there has not been any attempt to quantify the relative importance of PoS features in detecting AD. Objective: Our goal was to disclose the underlying relationship between PoS features and AD, understand whether PoS features are useful in AD diagnosis, and explore which PoS features play a vital role in the diagnosis. Methods: The DementiaBank, containing 1049 transcripts from 208 patients with AD and 243 transcripts from 104 older control individuals, was used. A total of 27 PoS features were extracted from each record. Then, the relationship between AD and each of the PoS features was explored. A transformer-based deep learning model for AD prediction using PoS features was trained. Then, a global explainable artificial intelligence method was proposed and used to discover which PoS features were the most important in AD diagnosis using the transformer-based predictor. A global (model-level) feature importance measure was derived as a summary from the local (example-level) feature importance metric, which was obtained using the proposed causally aware counterfactual explanation method. The unique feature of this method is that it considers causal relations among PoS features and can, hence, preclude counterfactuals that are improbable and result in more reliable explanations. Results: The deep learning–based AD predictor achieved an accuracy of 92.2% and an F1-score of 0.955 when distinguishing patients with AD from healthy controls. The proposed explanation method identified 12 PoS features as being important for distinguishing patients with AD from healthy controls. Of these 12 features, 3 (25%) have been identified by other researchers in previous works in psychology and natural language processing. The remaining 75% (9/12) of PoS features have not been previously identified. We believe that this is an interesting finding that can be used in creating tests that might aid in the diagnosis of AD. Note that although our method is focused on PoS features, it should be possible to extend it to more types of features, perhaps even those derived from other biomarkers, such as syntactic features. Conclusions: The high classification accuracy of the proposed deep learner indicates that PoS features are strong clues in AD diagnosis. There are 12 PoS features that are strongly tied to AD, and because language is a noninvasive and potentially cheap method for detecting AD, this work shows some promising directions in this field.
- Open Access
- 27 January 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Revealing the Roles of Part-of-Speech Taggers in Alzheimer Disease Detection: Scientific Discovery Using One-Intervention Causal Explanation (Preprint)
BACKGROUND Recently, rich computational methods that use deep learning or machine learning have been developed using linguistic biomarkers for the diagnosis of early-stage Alzheimer disease (AD). Moreover, some qualitative and quantitative studies have indicated that certain part-of-speech (PoS) features or tags could be good indicators of AD. However, there has not been a systematic attempt to discover the underlying relationships between PoS features and AD. Moreover, there has not been any attempt to quantify the relative importance of PoS features in detecting AD. OBJECTIVE Our goal was to disclose the underlying relationship between PoS features and AD, understand whether PoS features are useful in AD diagnosis, and explore which PoS features play a vital role in the diagnosis. METHODS The DementiaBank, containing 1049 transcripts from 208 patients with AD and 243 transcripts from 104 older control individuals, was used. A total of 27 PoS features were extracted from each record. Then, the relationship between AD and each of the PoS features was explored. A transformer-based deep learning model for AD prediction using PoS features was trained. Then, a global explainable artificial intelligence method was proposed and used to discover which PoS features were the most important in AD diagnosis using the transformer-based predictor. A global (model-level) feature importance measure was derived as a summary from the local (example-level) feature importance metric, which was obtained using the proposed causally aware counterfactual explanation method. The unique feature of this method is that it considers causal relations among PoS features and can, hence, preclude counterfactuals that are improbable and result in more reliable explanations. RESULTS The deep learning–based AD predictor achieved an accuracy of 92.2% and an F1-score of 0.955 when distinguishing patients with AD from healthy controls. The proposed explanation method identified 12 PoS features as being important for distinguishing patients with AD from healthy controls. Of these 12 features, 3 (25%) have been identified by other researchers in previous works in psychology and natural language processing. The remaining 75% (9/12) of PoS features have not been previously identified. We believe that this is an interesting finding that can be used in creating tests that might aid in the diagnosis of AD. Note that although our method is focused on PoS features, it should be possible to extend it to more types of features, perhaps even those derived from other biomarkers, such as syntactic features. CONCLUSIONS The high classification accuracy of the proposed deep learner indicates that PoS features are strong clues in AD diagnosis. There are 12 PoS features that are strongly tied to AD, and because language is a noninvasive and potentially cheap method for detecting AD, this work shows some promising directions in this field.
- 27 January 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessRevealing the Roles of Part-of-Speech Taggers in Alzheimer Disease Detection: Scientific Discovery Using One-Intervention Causal Explanation (Preprint)
BACKGROUND Recently, rich computational methods that use deep learning or machine learning have been developed using linguistic biomarkers for the diagnosis of early-stage Alzheimer disease (AD). Moreover, some qualitative and quantitative studies have indicated that certain part-of-speech (PoS) features or tags could be good indicators of AD. However, there has not been a systematic attempt to discover the underlying relationships between PoS features and AD. Moreover, there has not been any attempt to quantify the relative importance of PoS features in detecting AD. OBJECTIVE Our goal was to disclose the underlying relationship between PoS features and AD, understand whether PoS features are useful in AD diagnosis, and explore which PoS features play a vital role in the diagnosis. METHODS The DementiaBank, containing 1049 transcripts from 208 patients with AD and 243 transcripts from 104 older control individuals, was used. A total of 27 PoS features were extracted from each record. Then, the relationship between AD and each of the PoS features was explored. A transformer-based deep learning model for AD prediction using PoS features was trained. Then, a global explainable artificial intelligence method was proposed and used to discover which PoS features were the most important in AD diagnosis using the transformer-based predictor. A global (model-level) feature importance measure was derived as a summary from the local (example-level) feature importance metric, which was obtained using the proposed causally aware counterfactual explanation method. The unique feature of this method is that it considers causal relations among PoS features and can, hence, preclude counterfactuals that are improbable and result in more reliable explanations. RESULTS The deep learning–based AD predictor achieved an accuracy of 92.2% and an F1-score of 0.955 when distinguishing patients with AD from healthy controls. The proposed explanation method identified 12 PoS features as being important for distinguishing patients with AD from healthy controls. Of these 12 features, 3 (25%) have been identified by other researchers in previous works in psychology and natural language processing. The remaining 75% (9/12) of PoS features have not been previously identified. We believe that this is an interesting finding that can be used in creating tests that might aid in the diagnosis of AD. Note that although our method is focused on PoS features, it should be possible to extend it to more types of features, perhaps even those derived from other biomarkers, such as syntactic features. CONCLUSIONS The high classification accuracy of the proposed deep learner indicates that PoS features are strong clues in AD diagnosis. There are 12 PoS features that are strongly tied to AD, and because language is a noninvasive and potentially cheap method for detecting AD, this work shows some promising directions in this field.
- Open Access
Learning Models for Suicide Prediction from Social Media Posts
We propose a deep learning architecture and test three other machine learning models to automatically detect individuals that will attempt suicide within (1) 30 days and (2) six months, using their social media post data provided in the CLPsych 2021 shared task. Additionally, we create and extract three sets of handcrafted features for suicide risk detection based on the three-stage theory of suicide and prior work on emotions and the use of pronouns among persons exhibiting suicidal ideations. Extensive experimentations show that some of the traditional machine learning methods outperform the baseline with an F1 score of 0.741 and F2 score of 0.833 on subtask 1 (prediction of a suicide attempt 30 days prior). However, the proposed deep learning method outperforms the baseline with F1 score of 0.737 and F2 score of 0.843 on subtask 2 (prediction of suicide 6 months prior).
Open AccessLearning Models for Suicide Prediction from Social Media Posts
We propose a deep learning architecture and test three other machine learning models to automatically detect individuals that will attempt suicide within (1) 30 days and (2) six months, using their social media post data provided in the CLPsych 2021 shared task. Additionally, we create and extract three sets of handcrafted features for suicide risk detection based on the three-stage theory of suicide and prior work on emotions and the use of pronouns among persons exhibiting suicidal ideations. Extensive experimentations show that some of the traditional machine learning methods outperform the baseline with an F1 score of 0.741 and F2 score of 0.833 on subtask 1 (prediction of a suicide attempt 30 days prior). However, the proposed deep learning method outperforms the baseline with F1 score of 0.737 and F2 score of 0.843 on subtask 2 (prediction of suicide 6 months prior).
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Spectrum Management over Dynamic Spectrum Access based HetNets
This paper presents spectrum management in dynamic spectrum access (DSA) based 5G heterogeneous wireless networks (HetNets). Current literature studies architectures and signaling mechanisms for network selection, but rarely discuss proper bandwidth management for users over multiple HetNets. This paper considers users connected to multiple service providers in HetNets. A non-cooperative game is presented to determine the optimal bandwidth required at each service provider. The existence of a unique Nash equilibrium is shown. Results indicate that optimal allocation of spectrum is achieved when fairness is achieved. in other words, bandwidth available at any service provider is allocated equally to all users. This agrees with some empirical experimental studies available in the literature. Results also show that the proposed approach reduces user churning rate 1 , compared to traditional spectrum management approaches. The improvement is about 22–50% for delay intolerant traffic and 15-65% for delay tolerant traffic. 1 Defined as the percentage of users that do not meet the quality-of-service.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Spectrum Management over Dynamic Spectrum Access based HetNets
This paper presents spectrum management in dynamic spectrum access (DSA) based 5G heterogeneous wireless networks (HetNets). Current literature studies architectures and signaling mechanisms for network selection, but rarely discuss proper bandwidth management for users over multiple HetNets. This paper considers users connected to multiple service providers in HetNets. A non-cooperative game is presented to determine the optimal bandwidth required at each service provider. The existence of a unique Nash equilibrium is shown. Results indicate that optimal allocation of spectrum is achieved when fairness is achieved. in other words, bandwidth available at any service provider is allocated equally to all users. This agrees with some empirical experimental studies available in the literature. Results also show that the proposed approach reduces user churning rate 1 , compared to traditional spectrum management approaches. The improvement is about 22–50% for delay intolerant traffic and 15-65% for delay tolerant traffic. 1 Defined as the percentage of users that do not meet the quality-of-service.
- 18 January 2011
- Published by IGI Global Scientific Publishing
Steganalysis
Steganalysis: Trends and Challenges: 10.4018/978-1-59904-869-7.ch012: In this chapter we provide a detailed overview of the state of the art in steganalysis. Performance of some steganalysis techniques are compared based on
- 18 January 2011
- Published by IGI Global Scientific Publishing
Steganalysis
Steganalysis: Trends and Challenges: 10.4018/978-1-59904-869-7.ch012: In this chapter we provide a detailed overview of the state of the art in steganalysis. Performance of some steganalysis techniques are compared based on