Riad Hossain | Machine Learning | Innovative Research Award

Published on by Global CSE Awards

Innovative Research Award: Riad Hossain

Riad Hossain — East Delta University, Bangladesh

Riad Hossain
Name Riad Hossain
Affiliation East Delta University
Country Bangladesh
Scopus ID 59521054900
Documents 21
Citations 14
h-index 2
Subject Area Machine Learning
Event Global CSE Awards

Riad Hossain is a machine learning researcher affiliated with East Delta University, Bangladesh. The supplied Scopus record lists 21 documents, 14 citations, and an h-index of 2. His publication record includes research on explainable machine learning for Parkinson’s disease detection, Bengali speech analysis, and WiFi-based occupancy detection using CSI today.

Abstract

Riad Hossain is identified in the supplied profile as a Machine Learning researcher associated with East Delta University, Bangladesh. His listed Scopus record contains 21 documents, 14 citations, and an h-index of 2. His research outputs include explainable machine learning for Parkinson’s disease detection from Bengali conversational speech, machine learning analysis of Bengali voice recordings, and CSI-based people counting in WiFi networks. These studies apply feature extraction, feature selection, classification, deep learning, and explainability across healthcare and wireless sensing applications. The publication record provides documented evidence of interdisciplinary research activity relevant to contemporary computer science and machine learning research domains. [1] [2] [3]

Keywords

  • Machine Learning
  • Explainable Artificial Intelligence
  • Parkinson’s Disease Detection
  • Bengali Speech Analysis
  • Voice-Based Machine Learning
  • WiFi Sensing
  • Channel State Information
  • Deep Learning

Introduction

Hossain’s documented research is situated within machine learning and its application to practical computational problems. The available publications address Bengali speech-based health analysis and WiFi sensing, demonstrating applications of computational methods to biomedical and networking contexts. These studies illustrate how machine learning techniques can process complex speech and wireless signal data. [1] [2] [3]

Research Profile

Hossain’s research profile centers on machine learning applications involving speech, healthcare analytics, and wireless sensing. His listed subject area is Machine Learning, while his publications demonstrate interdisciplinary work connecting artificial intelligence with biomedical signal analysis and computer networking. The record combines methodological development, feature engineering, classification, and data-driven evaluation domains. [1] [2] [3]

Research Contributions

The reported contributions include development of BenSParX, an explainable machine learning framework using Bengali conversational speech for Parkinson’s disease detection, and machine learning approaches for Bengali voice recordings. His work also addresses WiFi channel-state-information sensing for people counting, applying CNN and LSTM architectures to sequential wireless data environments. [1] [2] [3]

Publications

The supplied publication set comprises three research works. BenSParX presents a Bengali conversational speech framework for Parkinson’s disease detection; the ICCIT paper studies Parkinson’s detection from Bengali voice recordings; and the COMPAS paper investigates CSI-based people counting. Together, these publications represent applications of machine learning across healthcare and wireless sensing. [1] [2] [3]

Research Impact

The publications indicate research activity across two application domains: machine-learning-assisted health assessment and privacy-oriented wireless occupancy sensing. The reported studies use feature selection, acoustic measurements, classification algorithms, explainability, and deep learning methods. Their documented results provide research outputs that can support further investigation into Bengali speech analytics and WiFi sensing. [1] [2] [3]

Award Suitability

For the Global CSE Awards context, the supplied profile documents a machine-learning-focused research record, identifiable Scopus metrics, and publications with DOI-linked scholarly records. The evidence includes work in explainable artificial intelligence, speech-based disease detection, and wireless sensing. Award assessment should additionally follow the event’s published eligibility, nomination, and evaluation criteria. [1] [2] [3]

Conclusion

Riad Hossain’s supplied academic profile presents research activity in machine learning with publications spanning Bengali speech analysis, Parkinson’s disease detection, explainable models, and WiFi-based occupancy detection. The documented Scopus metrics and cited scholarly outputs provide identifiable evidence of research activity. The record can be reviewed alongside the award’s official criteria. [1] [2] [3]

 

References

    1. Hossain, R., Kabir, M. A., Mowla, A. I. G., Roy, A. C., & Ghosh, R. K. (2026). BenSParX: A robust explainable machine learning framework for Parkinson’s disease detection from Bengali conversational speech. Artificial Intelligence in Medicine, 182, 103538.DOI:
      https://www.sciencedirect.com/science/article/pii/S0933365726001909
    2. Mowla, A. I. G., Hossain, R., & Asaduzzaman. (2024). CSI-based people counting in WiFi networks: Leveraging occupancy detection. In 2024 IEEE International Conference on Computing, Applications and Systems (COMPAS).DOI:
      https://ieeexplore.ieee.org/abstract/document/10796139
    3. Hossain, R., Roy, A. C., & Mowla, A. I. G. (2024). Parkinson’s disease detection from Bengali voice recordings using machine learning approach. In 2024 27th International Conference on Computer and Information Technology (ICCIT).DOI:
      https://ieeexplore.ieee.org/abstract/document/11021761

Chetanpal Singh | Machine Learning | Innovative Research Award

Published on by Global CSE Awards

Innovative Research Award

Chetanpal Singh
RMIT, Australia
Chetanpal Singh
Affiliation RMIT
Country Australia
Scopus ID 57197208396
Documents 8
Citations 126
h-index 4
Subject Area Machine Learning
Event Global CSE Awards
ORCID 0000-0001-6246-444X

Chetanpal Singh is affiliated with RMIT in Australia. The profile records eight documents, 126 citations, and an h-index of four, with machine learning listed as the principal subject area. The highlighted research spans medical imaging, agricultural disease detection, and data visualization, with publications addressing applied computational methods across different domains.[1][2][3]

Abstract

Chetanpal Singh is an RMIT-affiliated researcher in Australia whose supplied profile identifies machine learning as a subject area. The record lists eight documents, 126 citations, and an h-index of four. His highlighted publications cover multimodal learning for cancer analysis, hybrid deep learning for cotton disease detection, and data visualization for audit efficiency and risk management. These works illustrate computational methods across healthcare, agriculture, and auditing. The profile is supported by Scopus and ORCID identifiers, while the cited publications provide traceable evidence of research activity. The information presented here is descriptive and should be considered alongside official award criteria and bibliographic records.[1][2][3]

Keywords

Machine learning; deep learning; multimodal learning; medical imaging; cancer detection; agricultural artificial intelligence; cotton disease detection; BERT; ResNet; particle swarm optimization; data visualization; audit efficiency; risk management; computer vision; research impact.

Introduction

Chetanpal Singh’s research profile is associated with machine learning and applied data-driven methods across medical imaging, agricultural disease detection, and data visualization. His listed publications include studies combining deep learning architectures, optimization, and analytical visualization. These works span healthcare, agriculture, and auditing applications, illustrating cross-domain use of computational methods research.[1][2][3]

Research Profile

Chetanpal Singh is affiliated with RMIT in Australia and is identified by Scopus Author ID 57197208396 and ORCID 0000-0001-6246-444X. The supplied profile records eight documents, 126 citations, and an h-index of four. His stated subject area is machine learning, with publications addressing artificial intelligence, deep learning, computer vision, and analytics.[1][2][3]

Research Contributions

The documented contributions represented by the supplied publications include multimodal deep learning for medical imaging, hybrid BERT-ResNet-PSO modelling for cotton disease recognition, and visualization-based approaches to audit efficiency and risk management. Together, these studies demonstrate applications of machine learning, neural architectures, optimization, and visual analytics to domain-specific problems and decision-support contexts.[1][2][3]

Publications

The publication record supplied for this profile contains three works. Singh and colleagues reported a graph-aware and sequence-aware multimodal framework for cancer analysis in Journal of Imaging in 2026. A 2025 Applied Sciences article addressed cotton plant disease detection using BERT-ResNet-PSO. A 2023 handbook chapter examined data visualization for auditing.[1][2][3]

Research Impact

The cited publications indicate research activity across several application domains rather than a single narrowly defined problem. The medical imaging study addresses cancer detection using graph, sequence, and multimodal learning; the agricultural study addresses cotton disease classification; and the auditing chapter discusses visualization for analytical procedures and risk management practices.[1][2][3]

Award Suitability

For an academic recognition profile, the documented record provides identifiable evidence through publications, author identifiers, citation information, and research topics. The listed work demonstrates application-oriented machine learning across healthcare, agriculture, and auditing. Any award assessment should additionally consider the event’s published eligibility criteria, nomination requirements, evidence standards, and comparison process.[1][2][3]

Conclusion

Chetanpal Singh’s research record presents a cross-domain machine learning profile supported by publications, author identifiers, and bibliometric information. The highlighted studies cover medical imaging, agricultural disease detection, and audit visualization. These materials can support a academic recognition profile, while final recognition depends on criteria and process of the awarding organization.[1][2][3]

References

  1. Singh, C., Wibowo, S., Grandhi, S., & Mandala, S. (2026). Graph-Aware and Sequence-Aware Multimodal Deep Learning Framework for Cancer Detection and Risk Analysis from Medical Imaging. Journal of Imaging, 12(9), 431.
    https://doi.org/10.3390/jimaging12090431https://www.mdpi.com/2313-433X/12/9/431
  2. Singh, C., Wibowo, S., & Grandhi, S. (2025). A Hybrid Deep Learning Approach for Cotton Plant Disease Detection Using BERT-ResNet-PSO. Applied Sciences, 15(13), 7075.
    https://doi.org/10.3390/app15137075https://www.mdpi.com/2076-3417/15/13/7075
  3. Ferdous, L. T., Singh, C., & Rana, T. (2023). A Picture Is Worth a Thousand Words: Audit Efficiency and Risk Management Through Data Visualization. In Handbook of Big Data and Analytics in Accounting and Auditing (pp. 17–39). Springer.
    https://doi.org/10.1007/978-981-19-4460-4_2Scopus record