April 30, 2020
Dr. A. Shahina – Professor & Head of the Department
IT
Shahina’s mission is to create artificial intelligence based systems that better the lives of people and society. Towards this, she works on applying machine learning, deep learning and reinforcement learning algorithms in the fields of healthcare, security and surveillance.
Education and Experience
Shahina obtained her PhD in 2008 from the department of Computer Science and Engineering of IIT-Madras, India. She also has an M.Tech from IIT-Madras. She has 25 years of teaching and research experience, which began with 5 exclusive research years working as a project officer for a DRDO-sponsored project on speech processing at IIT-Madras.
Recent Research Interests
Shahina’s research group focuses on harnessing the potential of artificial intelligence to amplify human intelligence. The teams work on projects such as speech and speaker recognition in noisy ambience, new biometrics for person authentication systems and medical diagnostic tools, harnessing the power of machine learning and deep learning techniques. Lombard speech (increased vocal effort in noisy ambiance) causes degradation in performance of speech systems that are developed in laboratories and deployed in a noisy environment. We focus on building robust speech systems by estimating normal speech from Lombard speech through mapping, and using this to build robust systems. Popular person authentication systems could be affected due to spoofing attacks. We are building a scam-proof biometric system that is robust to spoof attacks using otoacoustic emissions. We have built automatic speech recognition systems for Tamil and other under-resourced languages, and are working on improvising them. We have also been working with medical images and signals, where we address multiple issues in the field of medical diagnosis, especially those associated with the brain.
Research Publications
Journals
Varugeese A, Shahina A, Nawaz K, Nayeemulla Khan A, “EarNet: Biometric Embeddings for End to End Person Authentication System Using Transient Evoked Otoacoustic Emission Signals”, Neural Processing Letters (2021), https://doi.org/10.1007/s11063-021-10546-2
Uma Maheswari, A.Shahina, A. Nayeemulla Khan, “Understanding Lombard Speech: A Review of compensation techniques towards improving Speech Based Recognition Systems”, Artificial Intelligence Review, 54, pages 2495–2523 (2021)
Sriya Ravi, Shreenidhi S, Shahina A, Ilakiselvan N, Nayeemulla Khan A, “Seizure Detection using Deep Learning on Recurrence Plots of EEG Signals”, Multimedia Tools and Applications, Jan 2022. https://doi.org/10.1007/s11042-021-11608-2
Mohamed Hashim C, Shahina A, Badri Narayanan M, and Nayeemulla Khan A, “End to end speech recognition of Tamil language”, Intelligent Automation and Soft Computing , Vol.32, No.2, pp. 1309-1323, 2022, (published Nov, 2021). DOI:10.32604/iasc.2022.022021
Ilakiyaselvan, A. Nayeemulla Khan, A.Shahina, ” Reconstructed phase space portraits for detecting brain diseases using deep learning “, Biomedical Signal Processing and Control,Vol.71 (2022)
Uma Maheswari, Rishickesh Ramesh, A.Shahina, A. Nayeemulla Khan, “A Study on the Impact of Lombard Effect on Recognition of Hindi Syllabic Units Using CNN Based Multimodal ASR Systems”, Archives of Acoustics, Vol. 45, No. 3, pp. 419–431 (April 2020)
John Wesley, A. Nayeemulla Khan, and A. Shahina, “Phoneme classification in reconstructed phase space with convolutional neural networks”, Pattern Recognition Letters, Volume 135, pp. 299-306, July 2020
V. Thomas Abraham, A. Nayeemulla Khan and, A. Shahina, ” A deep learning approach for robust speaker identification using chroma energy normalized statistics and mel frequency cepstral coefficients”, International Journal of Speech Technology, Aug. 2021. https://doi.org/10.1007/s10772-021-09888-y
Radha, A. Shahina,, P. Prabha, B.T. Preethi Sri, A. Nayeemulla Khan, “An Analysis of The Effect of Combining Standard and Alternate Sensor Signals on Recognition of Syllabic Units for Multimodal Speech Recognition”, Pattern Recognition Letters, Volume 115 (2018)
Khadar Nawas K, Shahina A, Harshini V, Dhanwin T, Nayeemulla Khan A, ” Biometric Identification Using Transient Evoked Otoacoustic Emission SIgnals Based on Recurrent Plots and Convolutional Neural Networks”, Journal of Huazhong University of Science and Technology, Vol. 50 (08), Aug. 2021, pp. 1-11. (Scopus – citescore = 0.6)
Koushika P, Mahima S, Shahina A, Nayeemulla Khan A, ” On the Impact of Climatic, Fiscal, and Environmental Factors on Covid-19: A Regression and Correlation based study”, Artificial and Computational Intelligence, Vol. 2(2), Jul. 2021
Ilakiyaselvan, A. Nayeemulla khan , A. Shahina, “Deep learning approach to detect seizure using reconstructed phase space images”, Journal of Biomedical Research(Scopus indexed), 2020 34(3): 238–248.
Radha, A. Shahina, A. Nayeemulla Khan, “Visual Speech Recognition using fusion of Motion and Geometric Features” Procedia Computer Science Journal, Vol. 171, pp. 923-933, Jun. 2020. (Scopus indexed).
Rishickesh, A. Shahina, A. Nayeemulla Khan, “Prediction of West Nile Virus using Ensemble Classifiers”, International Journal of Engineering and Advanced Technology (IJEAT) (Scopus indexed), Volume-9 Issue-1, October 2019, pp.3744-3749.
Rishickesh, P. Ram Kumar, A. Shahina, A. Nayeemulla Khan, “Identification of Duplication in Questions Posed on Knowledge Sharing Platform Quora using Machine Learning Techniques”, International Journal of Innovative Technology and Exploring Engineering (IJITEE) (Scopus indexed), Volume-8 Issue-12, October 2019, pp. 2444-2451.
Ilakiyaselvan, Hardik Bhatt, Utkarsh Shukla, A. Nayeemulla khan, A. Shahina, “Epileptic Seizure Prediction Through Machine Learning and Spatio-Temporal Features Based Time Series Analysis of Intracranial Electroencephalogram Data”, International Journal of Engineering and Advanced Technology (IJEAT)(Scopus indexed), Volume-9 Issue-1, October 2019, pp. 4763-4770.
Rishickesh, A. Shahina, A. Nayeemulla Khan, “Predicting Forest Fires using Supervised and Ensemble Machine Learning Algorithms”, International Journal of Recent Technology and Engineering (IJRTE), ISSN: 2277-3878, Volume-8 Issue-2, July 2019, pp. 3697-3705.
Tejasvi, A.Nayeemulla Khan, A.Shahina, “Perfecting Counterfeit Banknote Detection-A Classification Strategy”, International Journal of Innovative Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-8 Issue-6, April 2019 (Scopus indexed)
J.V. Thomas Abraham, A. Shahina, A. Nayeemulla Khan, “Enhancing Noisy Speech using WEMD”, International Journal of Recent Technology and Engineering, April 2019 (Scopus indexed)
Shanmuga Skandh Vinayak, A.Shahina, A. Nayeemulla Khan, “Detection of Alzheimer’s Disease on Brain MRI using Inception V3 Network”, Intl. Jl. Engg. Research and Tech. Vol. 9(10), Oct. 2020.
Shanmuga Skandh Vinayak, A.Shahina, A. Nayeemulla Khan, “Dementia Prediction on OASIS Dataset using Supervised and Ensemble Learning Techniques”, Intl. Jl. Engg.and Adv. Tech. Vol. 10(1), Oct. 2020.
Shanmuga Skandh Vinayak, A.Shahina, A. Nayeemulla Khan, “Advertisement Recommendation Engine – Improving YouTube Advertisement Services”, Intl. Jl. Recent Tech and Engg. Vol. 9(4), Nov. 2020.
Shanmuga Skandh Vinayak, A.Shahina, A. Nayeemulla Khan, “Epilepsy Prediction Using a Combined LSTM – XGBoost System on EEG Signals”, Intl. Jl. Innovative Tech and Exploring Engg. Vol. 10(1), Nov. 2020
Radha, A. Shahina, and A. Nayeemulla Khan,”An Improved Visual Speech Recognition of Isolated Words using Combined Pixel and Geometric Features”, Indian Journal of Science and Technology, Vol 9(44), DOI: 10.17485/ijst/2016/v9i44/102234, November 2016.
Uma Maheswari, J. Divya, A. Shahina, A. Nayeemulla Khan, “Spectral Transformation of Lombard Speech to Normal Speech for Speaker Recognition Systems”, Australian Journal of Basic and Applied Sciences, 9(16), pp. 146-154, 2015.
Arun Marx, G. Vinoth, A. Shahina, and A. Nayeemulla Khan, “Throat Microphone Speech Corpus for Speech and Speaker Recognition”, MES Journal of Technology and Management (ISSN 0976 3724), vol. 2, issue 1, May 2011.
Shahina and B. Yegnanarayana, “Mapping Speech Spectra from Throat Microphone to Close-Speaking Microphone: A Neural Network Approach,” EURASIP Journal on Advances in Signal Processing, vol. 2007, Article ID 87219, 10 pages, 2007, doi:10.1155/2007/87219.
Shahina and A. Nayeemulla Khan, “Enhancement of Throat Microphone Speech Using Self-Organizing Maps”, in Special Issue On Recent Advances in Pattern Recognition Using Signal Processing, International Journal of Tomography and Statistics, pp. 10-19, vol. 5, No. AI207, 2007
Conferences
Debadyuti Bhattacharya, Sri Hari Karthick N, Shahina A, ” Early Detection of Suicidal tendencies from text data using LSTM “, Proc. 3rd Intl. Conf. Innovations in Power and Advanced Computing Technologies (i-PACT), Kualalumpur, Malaysia, November 27-29, 2021.
Sriram Na,Vishaq J, Harshini V, Dhanwin T, Shahina A, and Nayeemulla Khan A, “Covid-19 detection using chest X-rays: CNN as a classifier vs CNN as a feature extractor” Proc. 2nd Intl.Conf. Machine Intelligence and Smart Systems 2021 (MISS 2021), Gwalior, India, September 24-25, 2021
Keshav Balachandar, Anam Saatvik Reddy, A. Shahina, Nayeemulla Khan, “Summarization of Commercial Contracts“, Proc. 2nd International Conference on Machine Learning, IOT and Blockchain (MLIOB 2021), August 21-22, 2021, Chennai, India.
P Koushika, M Mahima, A. Shahina, A Nayeemulla Khan, “EDA on The Relationship between Covid-19 Cases And Climatic Zones, GDP and HDI”, Proc. 2nd International Conference on Covid-19 Studies, April 17-19, 2021, Istanbul, Turkey.
N Radha, A Shahina, A Nayeemulla Khan, “A Survey on Visual Speech Recognition Approaches”, Proc. Intl. Conf. Artificial Intelligence and Smart Systems, Coimbatore, India, pp. 934-939, Mar. 25-27, 2021
N Radha, A Shahina, A Nayeemulla Khan, “Visual Speech Recognition using Fusion of Motion and Geometric Features”, Proc. 3rd International Conference on Computing and Network Communications (CoCoNet’19), Trivandrum, Kerala
Abhishek P, Manav M and Shahina A,“G-EyeNet: A Convolutional Autoencoding Classifier Framework for the Detection of Glaucoma from Retinal Fundus Images”accepted for publication in IEEE Intl. Conf. onImage processing(ICIP), Athens, Greece, Oct.2018.
Radha, A. Shahina, A. Nayeemulla Khan,”A Study On Alternate Speech Sensor”, in Proc.IEEE Intl. Conf. Computer, Communication, and Signal Processing (ICCCSP2018), Chennai, India, Jan. 2018.
Radha, A. Shahina, A. Nayeemulla Khan,”Improving Recognition of Speech System using Multimodal Approach”, in Proc. Intl. Conf. Innovative Computing and Communication (ICICC2018), Delhi, India, May 2018.
Ilakiyaselvan,A., A. Nayeemulla Khan, A. Shahina, “Prediction Of Interictal And Preictal States From EEG Signals Using K-Means Clustering, Intl. Conf. on Mathematical Computer Engineering, 3-4 Nov., 2017, VIT Chennai, India.
Radha, A. Shahina, A. Nayeemulla Khan,” A Person Identification System Combining Recognition of Face and Lip-read Passwords”, in Proc.IEEE Intl. Conf. Computing and Network Communication, Kerala, India, pp. 882-885, Dec. 2015, DOI: 10.1109/CoCoNet.2015.7411294
Uma Maheswari, A. Shahina, A. Nayeemulla Khan, J. Divya, “Spectral Transformation of Lombard Speech to Normal Speech for Speaker Recognition Systems”, Proc. Intl. Conf. Soft Computing Systems, Thukulay, India, Apr. 2015. This paper got the best paper award in the conference.
Meenatchi.D. Aishwarya.R, A. Shahina,” A Voice Recognizing Elevator System”, Proc. Intl. Conf. Soft Computing Systems, Thukulay, India, Apr. 2015.
A. Kanagaraj, D. Kamalakannan, M. Devosh, A. Shahina, S. Uma Maheswari, A. N. Khan, “Automated Health Monitoring through Emotion Identification”, Proc.Intl. Conf. Soft Computing Systems, Thukulay, India, Apr. 2015.
Radha, A. Shahina, G. Vinoth, A. Nayeemulla Khan,” Improving recognition of syllabic units of Hindi language using combined features of throat microphone and normal microphone speech “, in Proc.Int.Conf. Control Instrumentation Communication and Computational Technologies (ICCICCT), (Thuckalay, India), pp.1498-1503, July 2014.
Divya, A. Shahina, S. Uma Maheswari, “Building Speaker Recognition System using Lombard Speech”, in Proc.9th International Conference on Electrical, Electronics, Robotics and Mechanical Engineering (ICEERME), May, 2014.
Mehala, A. Shahina, S. Uma Maheswari, “Mapping Lombard Speech to Normal Speech”, in Proc. 9th International Conference on Electrical, Electronics, Robotics and Mechanical Engineering (ICEERME), May, 2014.
Ananda Kanagaraj. S, Shahina. A, Devosh. M, Kamalakannan. N, “EmoMeter: Measuring Mixed Emotions Using Weighted Combinational Model,” Proc. Fourth International Conference on Recent Trends in Information Technology, Chennai, India, April. 10-12, 2014.
Ananda K. S.; Arjun G.; Shahina, “Cheeka: A Mobile Application for Safety”, in Proc. 9th IEEE Intl. Conf. Collaborative Networking Applications and Worksharing, Austin, Texas, USA, pp. 289-294, 20-23 Oct. 2013.
R. Bharath Ram, R. Jayakumaur, R. Narayan, A. Shahinaand A. Nayeemulla Khan, “An Efficient Voice Enabled Web Content Retrieval System for Limited Vocabulary”, in Proc. Intl. Conf. Wireless Networks and Computational Intelligence (ICIP 2012), Bangalore, India, Aug. 2012.
Mubeen, N.; Shahina, A.; Khan, A.N.; Vinoth, G, “Combining spectral features of standard and Throat Microphones for speaker identification”, in IEEE Proc. Intl. Conf. Recent Trends In Information Technology (ICRTIT), (MIT, Chennai) pp. 119-122, 2012.
Mubeen, N.; Shahina, A.; Khan, A.N, “Pitch Synchronous Source And System Characteristics Of Throat Sensor Speech For Speaker Recognition”, in Proc. Intl. Conf. Recent Trends in Computer Science and Engineering (ICRTCSE), (Chennai), 2012.
Abirami, S; Madhuri V.B.; Shahina, A.; Khan, A.N, “Speech Enabled Desktop Search Engine”, in Proc. Intl. Conf. Recent Trends in Computer Science and Engineering (ICRTCSE), (Chennai), 2012
Arun Marx, G. Vinoth, A. Shahina, and A. Nayeemulla Khan, “Throat Microphone Speech Corpus for Speaker Recognition”, in Int. Conf. Information Systems and Technology, (Kerala, India), May 2011.
A.Shahina, C. Saranya, and A. Nayeemulla Khan, “Subjective and Objective Evaluation of Speech Coders”, accepted in Int. Conf. Language Processing (ICON), (IIT-Kharagpur, India), Dec. 2010.
Shahina, B. Yegnanarayana, A. Nayeemulla Khan, and M. R. Kesheorey, “Throat Microphone Signals for Syllable Recognition using Linear Prediction Cepstrum”, in Proc. Int. Conf. Language Processing (ICON), (C-DAC Pune, India), pp. 111-117, Dec. 2008.
Shahina, R. Karthikeyan, R. Rakhi, G. Maya, and A. Nayeemulla Khan, “Discrimination of Chronic Alcoholics from Visually Evoked Potentials Using Autoassociative Neural Networks”, in Proc. IEEE Int. Conf. Computing, Comm. Networking, (ICCCN), (India), Dec. 2008.
Shahinaand B. Yegnanarayana, “Mapping Neural Networks for Bandwidth Extension of Narrowband Speech,” in Proc. Int. Conf. Spoken Language Processing (Interspeech), (Pittsburg, Pennsylvania, USA), pp. 1435-1438, Sep. 2006.
Shahina and B. Yegnanarayana, “Recognition of consonant-vowel units in throat microphone speech,” in Proc. Int. Conf. Natural Language Processing (ICON), (IIT Kanpur, India), pp. 85-92, Dec. 2005.
Shahina, and B. Yegnanarayana, “Language identification in noisy environments using throat microphone signals,” in Proc. Int. Conf. Intelligent Sensing and Information Processing (ICISIP), (Chennai, India), pp. 400-403, Jan. 2005.
Shahina, B. Yegnanarayana, and M. R. Kesheorey, “Throat microphone signal for speaker recognition,” in Proc. Int. Conf. Spoken Language Processing (Interspeech), (Jeju Island, South Korea), pp. 2341-2344, Oct. 2004.
Teaching Interests
Shahina teaches artificial intelligence, machine learning, deep learning and computational intelligence courses for undergraduate and graduate students.
Research Citations
ORCID :0000-0003-4862-6611 | |
Publons ResearcherID :ABD-5905-2021 | |
Scopus ID :15027546700 | |
Google Scholar
|
|
DBLP
|