Electrical and Electronic Engineering, Computer Engineering
25
Scopus Publications
280
Scholar Citations
9
Scholar h-index
7
Scholar i10-index
Scopus Publications
Exploring principal component analysis and convolutional neural network (PCA-CNN) based architecture for enhanced emotion classification in EEG signal extraction Sheetal Patil, Rudragoud Patil, Sangeeta Sangani, Pankaja Patil, Uttam Deshpande Discover Applied Sciences, 2026 The current work on emotion recognition considering EEG signals has attracted significant attention due to its advantages in fields like mental health, neural computing, and human-computer interaction. Nonetheless, accurately classifying emotions using EEG signals poses a challenge, mainly due to issues such as noise, artefacts, and high dimensionality found within EEG data. Moreover, the current problem lies in extracting meaningful emotional features while efficiently addressing the above-described challenges to improve classification accuracy. Hence, this work proposed an approach for solving the challenges in emotion classification by presenting a model that integrates Principal Component Analysis (PCA) and Convolutional Neural Network (CNN). The PCA was used for removing noise and for dimensionality reduction. In contrast, the CNN was used for extracting emotion-related features and classifying emotions, mainly the two classes, arousal and valence. The proposed PCA-CNN model was evaluated considering the DEAP dataset, where the PCA-CNN model achieved 93.58% accuracy for arousal and 92.75% for valence for subject-dependent and 81.40% accuracy for arousal and 79.84% for valence for subject-independent. The findings also show that the PCA-CNN model provided better results in handling noise and reducing data complexity, ensuring high classification performance. The novelty of the PCA-CNN model is that PCA was used for preprocessing the EEG data, and CNN was used for feature optimization, which created a more efficient emotion classifier.
ICAG-Net: An Interactive CNN–Transformer Architecture With Attention-Guided Gated Fusion for Crop Disease Detection Kapil Arvind Chavan, Uttam U. Deshpande, Sudhindra B. Deshpande, Sowmyashree H. Srinivasaiah, Mukesh Kumar, Sukhdev B. Waghmode Engineering Reports, 2026 Smart agriculture based on the use of Artificial Intelligence for crop disease detection to ensure food security. Fungal disease is one of the major causes that affects the quality of the vegetables. Convolutional neural networks (CNNs) and vision transformers (ViTs) enable the detection of crop diseases at an early stage, allowing farmers to take preventive measures and minimize further losses. The proposed method introduces an ensemble of Custom CNN to understand multilevel local features and Pretrained ViT to capture global dependencies as well as contextual information from the dataset. An interactive cross attention module (ICAM) facilitates bidirectional information exchange between CNN and transformer token representations, while an attention guided gated fusion (AGGF) mechanism adaptively combines complementary features. The Indian Crop Visual Disease Dataset (ICVDD‐5) has been developed in a real field for the proposed work with the help of domain experts. The dataset contains 880 diverse images depicting both healthy and diseased specimens of five vegetable crops. The crops selected for this research initiative include Brinjal, Cabbage, Chili, Okra, and Tomato. These five crops are examined for about 21 distinct disease classes. Comprehensive ablation studies are conducted to prove the contributions of each architectural component, including CNN‐only, ICAM‐disabled, and AGGF‐disabled configurations. Experimental results demonstrate that the proposed ICAG‐Net achieves a test accuracy of approximately 70%–73% with improved macro‐F1 score compared to baseline CNN models under identical training settings. The novelty of this work lies in an extensible solution for real world crop disease diagnosis systems and offers insights into hybrid CNN–transformer architectures for small scale agricultural datasets.
Hybrid GRA–Machine Learning Framework for Surface and Performance Optimization of Ti49.3Ni50.7 SMA in Biomedical Applications Adik M. Takale, Uday A. Dabade, Mukesh Kumar, B. Vinod, Manjunath G. Avalappa, Uttam U. Deshpande, Kishor K. Powar Engineering Reports, 2026 Shape memory alloys (SMAs), such as Ti49.3Ni50.7, are well known for their remarkable mechanical and biocompatibility with human bone tissues. Thus, creating research opportunities in innovative machining processes using these alloys to design high‐quality biomedical implants using these alloys. However, this alloy's complex thermo‐mechanical reaction makes the standard machining process more challenging. To overcome this problem, we propose an enhanced Wire Electrical Discharge Machining (WEDM) process specifically designed to produce Ti49.3Ni50.7 orthopedic components. The effects of five important machining elements were investigated using a systematic experimental framework based on a Taguchi L18 orthogonal design. Gray relational analysis (GRA) was used to optimize both surface roughness and material removal rate, while Random Forest Regression combined with Bayesian optimisation was used to improve to optimal condition predictions. An experimental validation confirmed the surface roughness of 1.298 μm and a material removal rate of 2.537 mm 3 /min. To evaluate the post‐machining surface integrity, SEM, XRD, microhardness profiling, and residual stress analysis were used. The results revealed reduced tensile stress concentrations, enhanced hardness gradients, and minimal recast layer formation. Bending recovery tests confirmed that the alloy's shape memory behavior was restored by post‐machining annealing. This comprehensive strategy creates a reliable and scalable framework for the high‐precision TiNi‐based orthopedic implant production.
Integrating Facial Emotion Recognition, Speech to Text Transcription, and Natural Language Processing for Customer Satisfaction Analysis from Video Reviews Sudhindra B. Deshpande, Goh Kah Ong Michael, Uttam U. Deshpande, K. S. Mathad, N. V. Karekar, Kiran K. Tangod Engineering Technology and Applied Science Research, 2026 Customer satisfaction is a decisive factor in the success of products and services provided, yet conventional text-based reviews often fail to capture the full spectrum of user emotions needed to assess satisfaction. On the other hand, video product or service reviews offer a more informative medium for evaluating customer satisfaction. To leverage this, the present study proposes a multimodal machine learning framework for video-based customer feedback analysis, integrating facial emotion recognition, speech-to-text transcription, and Natural Language Processing (NLP). A dataset of 1,000 video reviews was processed through a multistage pipeline that involved frame extraction, face detection, emotion classification, audio transcription, sentiment analysis, and late fusion of modalities. Experimental results highlight the limitations of unimodal models: visual-only sentiment prediction achieved 62.3% accuracy (precision = 0.61, recall = 0.63, F1-score = 0.62, Area Under Curve (AUC) = 0.65), while audio-only sentiment prediction reached 59.5% accuracy (precision = 0.58, recall = 0.59, F1-score = 0.59, AUC = 0.61). The text-based model provided a stronger baseline at 72.1% accuracy (precision = 0.70, recall = 0.72, F1-score = 0.71, AUC = 0.75). In contrast, the multimodal fusion framework substantially outperformed unimodal approaches, achieving 79.9% accuracy, precision = 0.80, recall = 0.81, F1-score = 0.80, and the highest AUC of 0.86. Additionally, aspect-level analysis revealed that camera quality (+0.16) was the most positively perceived feature, while app performance (-0.33) and delivery (-0.09) emerged as primary concerns. Temporal analysis showed satisfaction scores fluctuating between 52.1 and 63.4 (0-100 scale) over 20 weeks, underscoring the value of continuous monitoring. These findings demonstrate that multimodal video feedback analysis yields more comprehensive, reliable, and fair performance than single-channel methods.
Overview of Emerging Technologies in Education Ramchandra Alias Ameet Chate, Ganesh R. Chate, Gourav V. Kulkarni, Uttam U. Deshpande, Vaibhav R. Chate, Raviraj M. Kulkarni Designing Inclusive Classrooms Integrating Emerging Technologies for Equity and Social Justice, 2026 In this chapter, an effort is made to highlight the application of new technologies in the education sector. Emerging technologies in education are transforming conventional educational systems to the next level, thereby enhancing the understanding capabilities of educational systems. The new technologies such as augmented reality, virtual reality, and artificial intelligence help in personalized learning and immersive experiences. IoT helps in smart classrooms for better understanding during and after class hours. The benefits of using these new technologies in the education sector and also challenges in adapting them are discussed in this chapter. These technologies also help in getting better feedback which is the most essential aspect of continuous improvement and focused learning with more interaction. Educators also learn these new technologies to improve the teaching and learning process. These emerging technologies not only improve understanding capability but also will cultivate an innovative mindset.
Modelling of ARM’s PrimeCell DMA Controller (PL080) using SystemC Uttam U. Deshpande, Ramesh Koti, Supriya Shanbhag, Akshay Bhosale, Rudragoud Patil, Sudhindra Deshpande, Ramchandra Alias Ameet Chate Journal of the Institution of Engineers India Series B, 2026
Multimodal sentiment analysis using image and text fusion for emotion detection Uttam U. Deshpande, Supriya Shanbhag, Amit Sukhasare, Mahendra M. Dixit, Rudragoud Patil, Sangeeta Sangani, Sowmyashree H. Srinivasaiah, Swetha Goudar, Manjunath Managuli Discover Computing, 2025 Social media has become an essential platform for expressing personal experiences and emotions. Today’s youth frequently share images that reflect their emotional states, including happiness, excitement, sadness, anxiety, and distress. Accurately analyzing these images using new frameworks can offer beneficial insights into the emotional well-being of individuals. Beyond mental health applications, image sentiment analysis has significant potential in marketing and advertising. Brands and Marketers can get a more comprehensive understanding of consumer sentiments and preferences by examining the emotional reactions elicited by visual content. For instance, companies can analyze images shared by customers to gauge sentiment towards their products and services. Positive or negative feedback expressed through images can offer practical insights for improving products and customer experience. Additionally, Sentiment analysis is one tool that marketers can use to gauge the effectiveness of their advertising campaigns. By analyzing the sentiments of images associated with a campaign, they can determine which aspects resonate most with the audience and adjust their strategies accordingly. Our research focuses on creating an advanced multimodal sentiment analysis system that combines BERT and Vision Transformers (ViT) to analyze textual and image data. High-precision sentiment classification is achieved by our technique using a preprocessed AllenTAN dataset from Hugging Face. It conducts sentiment analysis using BERT, creates captions for unlabeled photos, and uses OCR to retrieve embedded image text. The suggested ViT + BERT technique performs well with a variety of social network content. The proposed system achieves an accuracy of 96.91%, demonstrating its robust performance across diverse social media content and benchmark models. This technology has several uses, particularly in social media monitoring to promote mental health content, as teens frequently use visuals to describe their feelings.
Automatic two-wheeler rider identification and triple-riding detection in surveillance systems using deep-learning models Uttam U. Deshpande, Supriya Shanbhag, Rudragoud Patil, Ramchandra Alias Ameet Chate, Sufola Das Chagas Silva Araujo, Kevin Pinto, J. Arjun, Mayankraj Patil, Balagouda Nirwani Discover Artificial Intelligence, 2025 Uncontrolled road traffic conditions are commonly seen in South Asian countries, which result in the majority of motorcycle accidents due to triple riding, and helmetless driving traffic violation incidents. Triple riding is a dangerous act that can result in serious legal consequences. Each rider should be aware of the stringent traffic safety regulations of helmet wear and triple-riding violations. Public safety can be improved by reducing the number of road accidents. To do this, these riders must be identified and prosecuted. With little assistance from humans, the automated traffic monitoring system can enforce rigorous adherence to traffic laws. The current methods are effective when applied to widely used datasets, like Kaggle and COCO, which offer a helpful research platform. However, it is difficult to obtain satisfactory detection accuracies because this dataset contains minimal triple-riding images and lacks the sensation of realistic traffic CCTV images obtained from specific heights and angles. We provide a real-time solution that employs surveillance cameras placed at various angles and heights to detect two-wheelers, identify the number of riders, and recognize the vehicle involved in this traffic violation. To address challenging environments like occlusions and precise vehicle detection from a long distance we use the ResNet18-based DetectNet_v2 model. To reliably predict triple riding from several riders sitting on a two-wheeler and extract license plate information, we employ a cutting-edge YOLOv8 object-detection algorithm that operates on the Darknet framework. After experiment analysis, we found that our proposed model demonstrated a promising triple-rider, two-wheeler, and numberplate detection accuracy of 91.42%, 98%, and 81% respectively under challenging situations.
A review of machine learning techniques for ergonomic risk assessment based on human pose estimation Uttam U. Deshpande, Sufola Das Chagas Silva Araujo, Sudhindra Deshpande, Veena Kangralkar, Rudragoud Patil, Ramchandra Alias Ameet Chate, Prabal Birajdar, Siddhu Singadi, Prathamesh Raikar, Shreyas Arjunwadkar Discover Artificial Intelligence, 2025 Human pose estimation (HPE) has emerged as a vital tool for automating ergonomic risk assessment (ERA), enabling more effective evaluation of employees’ occupational health and safety. Observation-based ERA techniques are becoming more effective at identifying and reducing musculoskeletal injuries associated with the workplace by utilizing computer vision and machine learning technologies. The study thoroughly investigates recent developments in data collection methods, including depth cameras, marker-based motion capture, and deep learning-based pose estimation techniques. Along with methods for connected body poses, 2D and 3D HPE, and ergonomic risk categorisation, it examines developments in depth cameras, marker-based motion capture, and deep learning-based pose estimation. The efficiency of many ERA methods in determining posture-related risks is assessed. For this review study, we selected relevant studies using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Of the 210 research articles collected from the IEEE Xplore, Web of Science, and Scopus databases, 32 satisfied the review requirements for in-depth examination. From these articles, we observed that the deep learning-based HPE systems produced promising accuracies, but they struggled during real-time processing and occluded images. We investigate the potential of techniques that can strike a balance between performance and speed. The effects of HPE on ergonomics are examined, with an emphasis on how it might enable automated risk assessment systems, increase worker safety, and enhance productivity. The survey concludes by exploring future research possibilities, including the integration of multi-modal sensing, domain adaptation for various industries, and the creation of real-time, artificial intelligence-driven ergonomic monitoring systems.
ICAG-Net: An Interactive CNN–Transformer Architecture With Attention-Guided Gated Fusion for Crop Disease Detection SBW Kapil Arvind Chavan, Uttam U. Deshpande, Sudhindra B. Deshpande ... Engineering Reports 8 (5) , 2026 2026
Hybrid GRA–Machine Learning Framework for Surface and Performance Optimization of Ti49.3Ni50.7 SMA in Biomedical Applications KKP Adik M. Takale, Uday A. Dabade, Mukesh Kumar, B. Vinod, Manjunath G ... Engineering Reports , 2026 2026
Integrating Facial Emotion Recognition, Speech to Text Transcription, and Natural Language Processing for Customer Satisfaction Analysis from Video Reviews SB Deshpande, GKO Michael, UU Deshpande, KS Mathad, NV Karekar, ... Engineering, Technology & Applied Science Research 16 (2), 34615-34622 , 2026 2026
Exploring principal component analysis and convolutional neural network (PCA-CNN) based architecture for enhanced emotion classification in EEG signal extraction S Patil, R Patil, S Sangani, P Patil, UU Deshpande Discover Applied Sciences , 2026 2026
Modelling of ARM’s PrimeCell DMA Controller (PL080) using SystemC UU Deshpande, R Koti, S Shanbhag, A Bhosale, R Patil, S Deshpande, ... Journal of The Institution of Engineers (India): Series B, 1-18 , 2026 2026
Overview of Emerging Technologies in Education RAA Chate, GR Chate, GV Kulkarni, UU Deshpande, VR Chate, ... Designing Inclusive Classrooms: Integrating Emerging Technologies for Equity … , 2026 2026 Citations: 1
Design and Implementation of Intelligent and Advanced Drier Assistance System M Managuli, SC Managuli, U Deshpande, RB Koti, N Inamdar, SI Goudar International Conference on Computing and Communication Systems for … , 2026 2026
ResNet-18 based multi-task visual inference and adaptive control for an edge-deployed autonomous robot SDC Silva Araujo, GK Ong Michael, UU Deshpande, S Deshpande, ... Frontiers in Robotics and AI 12, 1680285 , 2025 2025 Citations: 1
CROP DISEASE DETECTION WITH DEEP LEARNING: A SURVEY OF MODERN APPROACHES UUD Kapil A. Chavan, Sudhindra Deshpande International Journal of Applied Mathematics 38 (1s), 1482-1508 , 2025 2025
A review of machine learning techniques for ergonomic risk assessment based on human pose estimation UU Deshpande, SDCS Araujo, S Deshpande, V Kangralkar, R Patil, ... Discover Artificial Intelligence 5 (1), 287 , 2025 2025 Citations: 7
Multimodal sentiment analysis using image and text fusion for emotion detection UU Deshpande, S Shanbhag, A Sukhasare, MM Dixit, R Patil, S Sangani, ... Discover Computing 28 (1), 1-24 , 2025 2025 Citations: 4
Effect of Cavitation Inducers on Slurry Erosion Resistance of HVOF-Sprayed Stainless-Steel Coatings MG Avalappa, UU Deshpande Frontiers in Materials 12, 1671031 , 2025 2025 Citations: 2
Optimising Content Recommendations in Context‐Aware Mobile Learning Platform Through Machine Learning SB Deshpande, GKO Michael, RJ Kadkol, NV Karekar, U Deshpande, ... Applied Computational Intelligence and Soft Computing 2025 (1), 6982455 , 2025 2025 Citations: 1
Post-COVID-19 Heart Attack Mortality Rate Prediction and Classification in Vaccinated Adults Using Random Forest Algorithm UU Deshpande, MM Dixit, RAA Chate, SH Srinivasaiah, A Jamakandi, ... Cureus Journals 2 (1) , 2025 2025
An Integrated Experimental and Machine Learning Approach for Machinability Assessment and Tool Life Prediction in Drilling of 14NiCr10 Alloy Using AlTiN‐Coated Carbide Tools AM Takale, UA Dabade, MG Avalappa, UU Deshpande, M Kumar Engineering Reports 7 (9), e70397 , 2025 2025 Citations: 2
Correction to: Enhanced Technique for Exemplar Based Image Inpainting Method S Patil, VS Malemath, S Muddapur, UU Deshpande First International Conference on Advances in Computer Vision and Artificial … , 2025 2025 Citations: 1
Real-time fire and smoke detection system for diverse indoor and outdoor industrial environmental conditions using a vision-based transfer learning approach UU Deshpande, GKO Michael, SH Srinivasaiah, H Malawade, Y Kulkarni, ... Frontiers in Computer Science 7, 1636758 , 2025 2025
A Machine Learning-Based Approach to Personification and Safety Measures in Social Media Applications P Sahane, S Rangdale, SH Srinivasaiah, D Patil, S Patil, UU Deshpande 2025
Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8 Uttam U. Deshpande, Goh Kah Ong Michael, Sufola Das Chagas Silva Araujo et. al. Frontiers in Artificial Intelligence 8, 1582257 , 2025 2025 Citations: 4
A Hybrid Machine Learning Framework for Financial Fraud Detection in Corporate Management Systems PKS Anand Kumar Dohare, Uttam U. Deshpande, Aman Dahiya, Kanchan Dabre ... EKSPLORIUM-BULETIN PUSAT TEKNOLOGI BAHAN GALIAN NUKLIR 46 (02), 139–154-139–154 , 2025 2025 Citations: 24
MOST CITED SCHOLAR PUBLICATIONS
Iot based real time ecg monitoring system using cypress wiced UU Deshpande, MA Kulkarni International Journal of advanced research in electrical, electronics and … , 2017 2017 Citations: 51
CNNAI: a convolution neural network-based latent fingerprint matching using the combination of nearest neighbor arrangement indexing UU Deshpande, VS Malemath, SM Patil, SV Chaugule Frontiers in Robotics and AI 7, 113 , 2020 2020 Citations: 42
Automatic latent fingerprint identification system using scale and rotation invariant minutiae features UU Deshpande, VS Malemath, SM Patil, SV Chaugule International Journal of Information Technology 14 (2), 1025-1039 , 2022 2022 Citations: 28
A Hybrid Machine Learning Framework for Financial Fraud Detection in Corporate Management Systems PKS Anand Kumar Dohare, Uttam U. Deshpande, Aman Dahiya, Kanchan Dabre ... EKSPLORIUM-BULETIN PUSAT TEKNOLOGI BAHAN GALIAN NUKLIR 46 (02), 139–154-139–154 , 2025 2025 Citations: 24
Recent Trends in Image Processing and Pattern Recognition: Second International Conference, RTIP2R 2018, Solapur, India, December 21–22, 2018, Revised Selected Papers, Part I KC Santosh, RS Hegadi Springer , 2019 2019 Citations: 21
A Study on Automatic Latent Fingerprint Identification System UU Deshpande, VS Malemath https://doi.org/10.30564/jcsr.v4i1.4388 , 2022 2022 Citations: 18
End-to-end automated latent fingerprint identification with improved DCNN-FFT enhancement UU Deshpande, VS Malemath, SM Patil, SV Chaugule Frontiers in Robotics and AI 7, 594412 , 2020 2020 Citations: 15
Recent Trends in Image Processing and Pattern Recognition: Third International Conference, RTIP2R 2020, Aurangabad, India, January 3–4, 2020, Revised Selected Papers, Part I KC Santosh, B Gawali Springer Nature , 2021 2021 Citations: 9
MINU-extractnet: automatic latent fingerprint feature extraction system using deep convolutional neural network UU Deshpande, VS Malemath International Conference on Recent Trends in Image Processing and Pattern … , 2020 2020 Citations: 9
Latent fingerprint identification system based on a local combination of minutiae feature points UU Deshpande, VS Malemath, SM Patil, SV Chaugule SN Computer Science 2 (3), 206 , 2021 2021 Citations: 8
A review of machine learning techniques for ergonomic risk assessment based on human pose estimation UU Deshpande, SDCS Araujo, S Deshpande, V Kangralkar, R Patil, ... Discover Artificial Intelligence 5 (1), 287 , 2025 2025 Citations: 7
Automatic two-wheeler rider identification and triple-riding detection in surveillance systems using deep-learning models UU Deshpande, S Shanbhag, R Patil, RAA Chate, ... Discover Artificial Intelligence 5 (1), 104 , 2025 2025 Citations: 7
Recoverable data hiding in encrypted images through extent reversing before inscription M Managuli, SC Managuli, S Pujar, S Goudar, S Shanbhag, ... Journal of The Institution of Engineers (India): Series B 106 (1), 351-362 , 2025 2025 Citations: 7
Computer vision and AI-based cell phone usage detection in restricted zones of manufacturing industries UU Deshpande, S Shanbhag, R Koti, A Chate, S Deshpande, R Patil, ... Frontiers in Computer Science 7, 1535775 , 2025 2025 Citations: 5
Multimodal sentiment analysis using image and text fusion for emotion detection UU Deshpande, S Shanbhag, A Sukhasare, MM Dixit, R Patil, S Sangani, ... Discover Computing 28 (1), 1-24 , 2025 2025 Citations: 4
Computer-vision based automatic rider helmet violation detection and vehicle identification in Indian smart city scenarios using NVIDIA TAO toolkit and YOLOv8 Uttam U. Deshpande, Goh Kah Ong Michael, Sufola Das Chagas Silva Araujo et. al. Frontiers in Artificial Intelligence 8, 1582257 , 2025 2025 Citations: 4
Wireless ECG monitoring system with remote data logging using PSoC and CyFi UU Deshpande, VR Kulkarni Int. J. Adv. Res. Electr. Electron. Instrum. Eng 2 (6), 2770-2778 , 2013 2013 Citations: 4
Image processing based automatic leaf disease detection system using k-means clustering and SVM N Inamdar 2019 Citations: 3
Effect of Cavitation Inducers on Slurry Erosion Resistance of HVOF-Sprayed Stainless-Steel Coatings MG Avalappa, UU Deshpande Frontiers in Materials 12, 1671031 , 2025 2025 Citations: 2
An Integrated Experimental and Machine Learning Approach for Machinability Assessment and Tool Life Prediction in Drilling of 14NiCr10 Alloy Using AlTiN‐Coated Carbide Tools AM Takale, UA Dabade, MG Avalappa, UU Deshpande, M Kumar Engineering Reports 7 (9), e70397 , 2025 2025 Citations: 2
