S.M.I.L.E

Sensing, Modeling, Inferring, Learning, evolving

Research Excellence

In the IFFS-ML Lab, students gain excellence in research and excel in ethical and responsible research. The research theme—with the believe that there always exists a much smarter solution for any given artificial intelligence, data science, or big data problem in the infinite family of feature (IFF) space—is to search for hidden patterns (i.e., useful information) in the IFF space by leveraging efficient computational techniques along with smart machine learning, machine active learning, actively regularized tensor learning approaches, and big data technologies. The goal is to define and analyze the intrinsic “necessary and sufficient” conditions of the IFF space and machine learning models and algorithms to solve modern any-data (big or trivial data) problems for peace-of-mind adaptation. The research goal includes the study of the asymptotic behavior of the IFF space to derive models that are smart and secure, while handling data complexity, heterogeneity and scalability problems, and the adaptation of the concept of infinite family of feature space for discovering transformative knowledge from any data and developing secure and smart machine learning methods—machine learning as a master-key—for interdisciplinary research.

We have accomplished many interdisciplinary research projects, in collaboration with national and international experts, that include cyber-threat detection (e.g., malicious activities), privacy-preserving models, anomaly detection, retinal disease classification, facial emotion detection, brain tumor detection, traffic crash hot-spot detection, pedestrian detection, urban expansion modeling, students mental models analytics, natural language prediction, and mixed fruits and vegetables classification, optimization of big data techniques, and technologies.

Frequency-Driven Machine Learning

Facial Emotion Characterization and Detection using Fourier Transform and Machine Learning

Machine’s Conceptual Development using FNet

Using Machine Learning to Detect Circular Frequencies for Emotion Detection

Detecting Sobol Frequencies using Machine Learning to Predict Human Emotions

Machine Learning for Emotion Detection in Audio-Video Data

Computational and Predictive Modeling of Sleep Patterns from RGB Images

Current Graduate Students

  • Adarsh Gadari - Computational ophthalmology research - PhD Student - Started Fall 2022

  • Aditi Darandale - Detecting Sobol frequencies using machine learning to predict human emotions - Spring 2022 - Fall 2022

  • Amitabha Dey - Dialogue representation using task transfer and few-shot learning in open-domain dialogue - Spring 2022 - Fall 2022

  • Raveena Arasikere Rakesh - Using machine learning to detect circular frequencies for emotion detection - Spring 2022 - Fall 2022

  • Sai Manideep Chittiprolu - Computational and predictive modeling of sleep patterns from RGB images - Fall 2022

  • Atreya Avadhanula - Machine learning for emotion detection in audio-video data - Fall 2022

IFFS-ML LAB IS IN ACTION

















Recently GraduateD Students

  • Aishwarya Gouru - Facial emotion characterization and detection using Fourier transformation and frequency bands - Graduated Fall 2021

  • Deepa Jayanna - Machine’s conceptual development using FNet (Natural language next sentence prediction) - Graduated Spring 2022

  • Chandan Chunduru - Unsupervised manifold learning of severity regions of traffic accidents for improved traffic safety - Graduated Spring 2022

  • Chandra Malgari - Uncertainty based active learning on prediction probability using DBSCAN - Graduated Spring 2022

  • Divya Sanga - Feature learning from periapical dental X-ray images using machine learning - Graduated Spring 2022

  • Pragna Tarali Talluri - Empirical optimization of model parameters to detect facial emotions - Graduated Spring 2022

advisees Honors and Awards

Consistent success in advising students for the last 15 years! Pandemic didn't stop my students' productivity either!

  • Congratulations to Aishwarya Gouru! Our paper "Facial Emotion Characterization and Detection using Fourier Transform and Machine Learning" received the best paper award and published in the 37th International Conference on Computers and Applications (CATA 2022).

  • Congratulations to Ritu Pandey Joshi! Our paper "Pixel-Level Feature Space Modeling and Brain Tumor Detection Using Machine Learning" has been published in 19th IEEE International Conference on Machine Learning and Applications, pp. 821-826, 2020.

  • Congratulation to Naseeb Thapaliya and Lavanya Goluguri! Our paper "Asymptotically Stable Privacy Protection Technique for fMRI Shared Data over Distributed Computer Networks" has been published in the ACM-BCB 2020: Proceedings of the 11th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics.

  • Congratulations to Firoozeh Karimi! Our paper “An Enhanced Support Vector Machine Model for Urban Expansion Prediction” has been published in the Elsevier journal of Computers, Environment, and Urban Systems (2019).

  • Congratulations to Michael Ellis and Naseeb Thapaliya! Our poster for Stanford Compression Workshop 2019 titled “Illuminating privacy weaknesses in predictive models of fMRI data using compressed sensing and compressed learning” has been accepted (2019).

  • Congratulations to Vishali Vadakattu! Our paper “Feature Extraction using Apparent Power and Real Power for Smart Home Data Classification” has been published in the ICMLA 2018 conference proceedings (2018).

  • Congratulations to Shravya Yalamanchili! She received an award (course fellowship) to attend the short course on big data images processing and analysis (BigDIPA) offered by the Center for Complex Biological Systems, University of California Irvine (2017).

  • Congratulations to Tyler Wendell! He successfully defended his master’s thesis entitled “Feature Extraction and Feature Reduction for Spoken Letter Recognition,” directed by me. It has been published at https://libres.uncg.edu/ir/uncg/listing.aspx?styp=ti&id=19822 (2016).

  • Congratulations to Aswini Sen! She won an Outstanding Student Presentation Award in the graduate student category at the 12th Annual UNCG Regional Mathematics and Statistics Conference, on November 12, 2016. She presented our joint work on “Study of the Sensitivity of Supervised Classification Models Towards the Increased Complexity of Data” (2016).

  • Congratulations to Mokhaled Al-Hamadani! He presented our joint research work on the “Evaluation of The Performance of Deep Learning Techniques,” at the 2015 Graduate Research and Creativity Expo, on April 9, (2015).

  • Congratulations to Jeff Whitworth! He presented our joint work on “Security problems and challenges in a machine learning-based hybrid big data processing network systems at the ACM SIGMETRICS and it has been published in the ACM SIGMETRICS Performance Evaluation Review (2014).

  • Congratulations to Kiranmayi Kotipalli! She presented our joint research work on “Modeling of class imbalance using an empirical approach with spambase dataset and random forest classification”, now published in the proceedings of the ACM SIGITE/RIIT conference (2014).

  • Congratulations to Harry Rybacki! for presenting his research and senior project work entitled “An IPython Notebook Based Collaborative Platform for Ellipsoid Modeling Sensor Data,” (directed by me) at the 2014 State of North Carolina Undergraduate Research and Creativity Symposium in Raleigh (2014).

  • Congratulations to Laxmi Sunkara and Sweta Keshapagu! Our joint research work on “Lame Curve-based signature discovery learning technique for network traffic classification has been published in the proceedings of the Workshop on Signature Discovery for Intelligence and Security. IEEE International Conference on Intelligence and Security Informatics (2013).

  • Congratulations to Archana Polisetti! She won the Best Paper Presentation Awards in the graduate student category at the International Conference on Advances in Interdisciplinary Statistics and Combinatorics. She presented our joint research work on “Simultaneous Classification and Feature Selection for Intrusion Detection Systems” (2012).

  • Congratulations to Karthik Vinnakota! Our joint research work on “An approach for automatic selection of relevance features in intrusion detection systems” has been published in the proceedings of the International Conference on Security and Management (2011).

  • Congratulations to Mohammed Alzahrani! Our research work on “Labelled data collection for anomaly detection in wireless sensor networks has been published in the proceedings of the 6th International Conference on Intelligent Sensors, Sensor Networks and Information Processing (2010).

  • Congratulations to Abhinav Chawade! Our research work on “Energy ecient DNA-based scheduling scheme for wireless sensor networks has been published in proceedings of the International Conference on Wireless Algorithms, Systems and Applications (Lecture Notes in Computer Science) (2009).

  • Congratulations to Surender Kumar! Our research work on “Measuring available bandwidth: pathChirps chirp train structure remodeled” has been published in the proceedings of the Australian Telecommunications Networks and Application Conference (2008).

Advisees and Phd dissertation

  1. Firoozeh Karimi, Serving as a dissertation committee member, Department of Geography, Environment, and Sustainability, 2018-current, UNCG.

  2. Three students, Served as a doctoral dissertation committee member, Department of Mathematics and Statistics, 2014-2016, UNCG.

  3. David Lai , Advised him as an associate supervisor on the topic "Security issues of distributed computer network systems," along with his supervisor Dr. Zhongwei Zhang, 2005-2010, University of Southern Queensland, Australia.

  4. Ivan Lee, Advised him as an associate supervisor on the topic "Digital video coding, compression and transmission," along with his supervisor Dr. Ling Guan, 1998-200, University of Sydney, Australia.


Advisees and MS thesis

  1. Tyler Wendell, Feature Extraction and Feature Reduction for Spoken Letter Recognition, 2016, UNCG.

  2. Mokhaled Al-Hamadani, Evaluation of the performance of deep learning techniques over tampered data for a distributed machine learning environment, 2015, UNCG.

  3. Jeff Whitworth, Security problems and challenges in a machine learning-based hybrid Big Data processing network system, 2013, UNCG.

  4. Jiyoung Oh, Stabilizing RED queue oscillation using the logistic map in AutoRED mechanism, 2009, UNCG.

  5. Surender Kumar, e-Chirp: measuring available bandwidth for the Internet using multiple Chirp packet trains, 2008, UNCG.

  6. Robert Misior , Wi-Fi 802.11 based mobile robotics positioning system, 2007, UNCG.

  7. S. Rednour, An analysis of a sparse linearization attack on the advanced encryption standard, 2006, UNCG.

  8. C. Chatchaiyan, Congestion control for TCP/IP networks, 2004, UNCG.


Advisees and MS projects

  1. Shireeshma Parepalli, Machine learning for retinal disease signature classification using OCT volumetric data, 2021, UNCG.

  2. Aparna Muppalla, Brain tumor detection using machine learning trained on multi-modality pixel level feature space, 2020, UNCG.

  3. Nisha Saini, Detection of retinal diseases using image filtering, image aggregation, and machine learning, 2020, UNCG

  4. Ryan Soorya, Machine learning using Benford’s law and gradient image filters to detect retinal disease signatures, 2020, UNCG.

  5. Ritu Joshi, Pixel-Level Feature Space Modeling and Brain Tumor Detection Using Image Filtering and Machine Learning, 2020, UNCG.

  6. Lavanya Goluguri , High dimensionality reduction in fMRI brain data using Random Forest feature learning algorithm, 2019, UNCG.

  7. Naseeb Thapaliya, Compressed sensing and compressed learning with asymptotic Markov chain on fMRI brain data, 2019, UNCG.

  8. Michael Ellis, fMRI data analytics using compressed sensing and learning with transition properties, 2019, UNCG.

  9. Peng Chen, Evaluation and characterization of machine learning models for fruits and vegetable classification using digital images, 2018, UNCG.

  10. Bhavana Yennam, Evaluation and validation of chandelier decision tree learning using imbalanced data sets, 2018, UNCG.

  11. Yashwanth Sunkara, Evaluation the newly proposed software engineering framework SETh using real-world examples, 2018, UNCG.

  12. Shraddha Dafare, Survey of Cluster Analysis using R and Python, 2018, UNCG.

  13. Pavand Kethinedi, Number recognition IOS App, 2018, UNCG.

  14. Mukund Nuthi, Characterization of Resource Utilization in Big Data Systems with Machine Learning Applications, 2018, UNCG.

  15. Shravya Sree Yalamanchili, Quantification of Diabetic Retinopathy using Random Forest Learning, 2018, UNCG.

  16. Komal Kotresh Kubsad, Study of the NSL-KDD dataset using Big Data concepts and algorithms, 2018, UNCG.

  17. Balaram Remala, Identification of Brain Tumor from MRI Scans Using Machine Learning, 2017, UNCG.

  18. Vishali Vadakattu, Effect of Real Power and Apparent Power on Household Device Classification Accuracy, 2017, UNCG.

  19. Pawan Gandham, Automated airport exit system, 2017, UNCG.

  20. Manasa Konda, Data Preprocessing and Class Dependence on Feature Importance using Random Forest, 2017, UNCG.

  21. Jayakrishna Araveti, Classification of Human Activities By Random Forest Algorithm, 2016, UNCG.

  22. Nitin Gaikwad, Simple solutions for missing data problem in Big data domain, 2016.

  23. Anirudh Karra, A Study of Diabetic Conditions in the U.S. Population Using Random Forest Classification, 2016, UNCG.

  24. Aswini Sen, Study of the sensitivity of supervised classification models towards the increased complexity of data, 2016, UNCG.

  25. Anubhav Shukla, Pedestrian Detection using Machine learning, 2016, UNCG.

  26. Valluri Aditya, Split Merge Split Application, 2016, UNCG.

  27. Divya Tottempudi, Medical record system software, 2016, UNCG.

  28. Sushma Singireddy, Evaluation of chandelier decision tree and random chandelier, 2016, UNCG.

  29. Shruti Majety, Analysis of machine learning techniques: decision tree, random forest and chandelier decision tree, 2016, UNCG.

  30. Swarna Bonam, Implementation and evaluation of support vector machine with Python on significant data sets, 2015, UNCG.

  31. Naga Padmaja Tirumala Reddy, Ellipsoid modeling for anomaly detection in multi-hop wireless sensor networks using machine learning, 2015, UNCG.

  32. Chitra Reddy Musku, Classification of Twitter data set with Ebola information using random forest approach, 2015, UNCG.

  33. Varnika Mittal, Ellipsoid modeling for anomaly detection in single-hop wireless sensor networks using machine learning, 2015, UNCG.

  34. Tejo Chennupati, Analysis of user knowledge modeling data set using random forest on virtual machine and Hadoop machine, 2015, UNCG.

  35. Sumanth Reddy Yanala, Performance analysis of random forest with and without Hadoop, 2014, UNCG.

  36. Kiranmayi Kotipalli, Empirical study on classification of imbalanced classes using Random Forest and SMOTE, 2014, UNCG.

  37. Piyush Agarwal, Comparison of random forest classifier over different platforms, 2014, UNCG.

  38. Laxmi Sunkara, Signature discovery algorithms for network traffic classification, 2013, UNCG.

  39. Swathi Kota, Simulation of human intruder behavior in public spaces using wireless sensor networks, 2013, UNCG.

  40. Sweta Keshapagu, Classification of network traffic protocols http and https using machine learning approaches, 2013, UNCG.

  41. Anudeep Katangoori, Analyzing large datasets with HADOOP multinode clusters, 2013, UNCG.

  42. Archana Polisetti, Simultaneous classification and feature selection algorithm for intrusion detection system, 2012, UNCG.

  43. Naga Vaddanapu, UNCG Cloud Computing: Installation and setup of cloud computing network with virtual machines, 2012, UNCG.

  44. Shiva Gullapelli, UNCG Network Simulator: A teaching tool to teach the concepts of computer networking, 2012, UNCG.

  45. Snigdha Bandari, Intruder detection in public space using suspicious behavior phenomena and wireless sensor networks, 2012, UNCG.

  46. Tejaswi Panchagnula, Evaluation of intrusion detection datasets for accuracy with respect to relevance feature selection, 2011, UNCG.

  47. Karthik Vinnakota, An approach for automatic selection of relevance features in KDD’99 intrusion detection dataset, 2011, UNCG.

  48. Vinnay Podduturi, Automatic threshold selection for fingerprint segmentation and analysis, 2011, UNCG.

  49. Mohammed Alzahrani, Labeled data collection for anomaly detection in wireless sensor networks, 2010, UNCG.

  50. Hamzeh Qabaja, Performance comparison of AutoRED under different TCP variations, 2009, UNCG.

  51. Abhijit Chattopadhyay, Generalize TCP-DCR protocol with better choice of congestion response delay τ, 2009, UNCG.

  52. Yaser Banoun, Visualizing encryption tools for advanced encryption standard (AES), 2007, UNCG.

  53. Ramu Pulipati, Analysis of TCP/IP traffic: real-time versus synthetic traffic scenarios, 2006, UNCG.

  54. Keith Berlin, OPNET simulation of a university network backbone analysis and visualization, 2006, UNCG.

  55. Kevin Nguyen, Visualization teaching tool for teaching the theory of Data Encryption Standard (DES), 2006, UNCG.

  56. Arundhati Anavekar, Grid computing infrastructure: installation, security and problems, 2005, UNCG.

  57. Dani Luca, Crypto Chat System v 1.0 – A system of modules to enhance security in mobile user communication, 2005, UNCG.

  58. Eric McCandles, NS2GUI: A graphical source code generator for NS2 Network Simulator, 2005, UNCG.

  59. Jonathan Thyer, TCP round trip time analysis in a university network environment, 2004, UNCG.

  60. Sheetal Sahasrabhdhe, Performance evaluation of congestion control techniques in TCP/IP networks, 2003, UNCG.

  61. Jyothsna Reddy, Visualization teaching tool for simulation of OSI seven layer architecture, 2003, UNCG.

  62. Swapna Koppula, New algorithms and Graphical User Interface tools for cryptography and its applications, 2003, UNCG.

  63. Saritha Suvva, An interface for teaching and research tools in cryptographic algorithms, 2003.

  64. Rob McCartney, A video codec for low power, bandwidth-poor devices, 2002, UNCG.