Multimodal feature-optimized approaches for cancer classification using microarray gene expression analysis J. D. Dorathi Jayaseeli, S. S. Saranya, K. Lakshmi, Ramesh Kothapali, Gyeong-Hyu Seok, Gyanendra Prasad Joshi, Woong Cho Scientific Reports, 2025 Uncontrolled abnormal cell growth, referred to as cancer, can result in tumors, other fatal disabilities, and immune system deterioration. Typically, the treatment procedure is longer and extremely expensive owing to its higher recurrence and death rates. Early and precise detection and assessment of cancer are significant for improving patient survival rates. Moreover, initial cancer detection makes the treatment simpler and improves the rate of recovery, leading to a lower mortality rate. Gene expression data plays an important part in cancer classification at the initial phase. Precise cancer classification is a challenging and complex task because of the high-dimensional nature of gene expression data, coupled with the small sample size. With the help of artificial intelligence (AI), researchers have recently developed fundamental models utilizing AI methods to diagnose and predict cancer. These techniques now play a leading role in increasing the precision of survival predictions, cancer susceptibility, and recurrence. This paper presents an Artificial Intelligence-Based Multimodal Approach for Cancer Genomics Diagnosis Using Optimized Significant Feature Selection Technique (AIMACGD-SFST) model. The aim is to develop precise and effective techniques for cancer genomics analysis using advanced computational and analytical techniques. The preprocessing stage comprises min-max normalization, handling missing values, encoding target labels, and splitting the dataset into training and testing sets. Furthermore, the AIMACGD-SFST model employs the coati optimization algorithm (COA) method for feature selection process to choose the related features from the dataset. Finally, the ensemble models, namely deep belief network (DBN), temporal convolutional network (TCN), and variational stacked autoencoder (VSAE) are employed for the classification process. The experimental validation of the AIMACGD-SFST approach is performed under three diverse datasets. The comparison study of the AIMACGD-SFST approach illustrated superior accuracy value of 97.06%, 99.07%, and 98.55% over existing models under diverse datasets.
An integration of ensemble deep learning with hybrid optimization approaches for effective underwater object detection and classification model G. Abirami, S. Nagadevi, J. D. Dorathi Jayaseeli, T. Prabhakara Rao, R S M Lakshmi Patibandla, Rajanikanth Aluvalu, K Srihari Scientific Reports, 2025 Underwater object detection (UOD) is essential in maritime environmental study and underwater species protection. The development of associated technology holds real-world importance. While current object recognition methods have attained an outstanding performance on terrestrial, they are less suitable in underwater conditions because of dual restrictions: the underwater objects are generally smaller, closely spread, and disposed to obstruction features, and underwater embedding tools have temporary storing and computation abilities. Image-based UOD has progressed fast recently, in addition to deep learning (DL) applications and development in computer vision (CV). Investigators utilize DL models to identify possible objects inside an image. Convolutional neural network (CNN) is the major technique of DL, which enhances the learning qualities. In this manuscript, an Underwater Object Detection and Classification Utilizing the Ensemble Deep Learning Approach and Hybrid Optimization Algorithms (UODC-EDLHOA) technique is developed. The UODC-EDLHOA technique mainly detects and classifies underwater objects using advanced DL and hyperparameter models. Initially, the UODC-EDLHOA model involved several levels of pre-processing and noise removal to improve the clearness of the underwater images. The backbone of EfficientNetB7, which has an attention mechanism, is employed for feature extraction. Furthermore, the YOLOv9-based object detection is utilized. For underwater object detection, an ensemble of three techniques, namely deep neural network (DNN), deep belief network (DBN), and long short-term memory (LSTM), is implemented. Finally, the hyperparameter selection uses the hybrid Siberian tiger and sand cat swarm optimization (STSC) methods. Extensive experimentation is conducted on the UOD dataset to illustrate the robust classification performance of the UODC-EDLHOA model. The performance validation of the UODC-EDLHOA model portrayed a superior accuracy value of 92.78% over existing techniques.
An intelligent framework for skin cancer detection and classification using fusion of Squeeze-Excitation-DenseNet with Metaheuristic-driven ensemble deep learning models J. D. Dorathi Jayaseeli, J Briskilal, C. Fancy, V. Vaitheeshwaran, R. S. M. Lakshmi Patibandla, Khasim Syed, Anil Kumar Swain Scientific Reports, 2025 Skin cancer is the most dominant and critical method of cancer, which arises all over the world. Its damaging effects can range from disfigurement to major medical expenditures and even death if not analyzed and preserved timely. Conventional models of skin cancer recognition require a complete physical examination by a specialist, which is time-wasting in a few cases. Computer-aided medicinal analytical methods have gained massive popularity due to their efficiency and effectiveness. This model can assist dermatologists in the initial recognition of skin cancer, which is significant for early diagnosis. An automatic classification model utilizing deep learning (DL) can help doctors perceive the kind of skin lesion and improve the patient's health. The classification of skin cancer is one of the hot topics in the research field, along with the development of DL structure. This manuscript designs and develops a Detection of Skin Cancer Using an Ensemble Deep Learning Model and Gray Wolf Optimization (DSC-EDLMGWO) method. The proposed DSC-EDLMGWO model relies on the recognition and classification of skin cancer in biomedical imaging. The presented DSC-EDLMGWO model initially involves the image preprocessing stage at two levels: contract enhancement using the CLAHE method and noise removal using the wiener filter (WF) model. Furthermore, the proposed DSC-EDLMGWO model utilizes the SE-DenseNet method, which is the fusion of the squeeze-and-excitation (SE) module and DenseNet to extract features. For the classification process, the ensemble of DL models, namely the long short-term memory (LSTM) technique, extreme learning machine (ELM) model, and stacked sparse denoising autoencoder (SSDA) method, is employed. Finally, the gray wolf optimization (GWO) method optimally adjusts the ensemble DL models' hyperparameter values, resulting in more excellent classification performance. The effectiveness of the DSC-EDLMGWO approach is evaluated using a benchmark image database, with outcomes measured across various performance metrics. The experimental validation of the DSC-EDLMGWO approach portrayed a superior accuracy value of 98.38% and 98.17% under HAM10000 and ISIC datasets across other techniques.
Modified Holoentropy based arithmetic coding for ROI based image compression and data transmission Sarath V. Sankaran, J. D. Dorathi Jayaseeli Imaging Science Journal, 2025 This Paper proposes a modified Holoentropy Based Arithmetic coding (AC) for ROI image compression. Here, the ROI extraction is done under two compressions they are lossless and lossy compression. First, the lossless compression on the ROI region is applied using Lembel-Ziv-Welch (LZW). Meanwhile, the lossy compression on the Non-ROI region is applied by using forward transform and Quantization. Then, the modified Holoentropy-based AC is applied to obtain a compressed bit stream in both scenarios. The two compressed bit streams are fused with the label to generate the compressed data. In the decompression phase, inverse LZW, Inverse modified AC, Inverse Quantization and Inverse transform are applied to generate a non-ROI image. The generated RoI image and non-RoI image are fused to obtain the original image. The proposed method has a minimum Mean Squared Error of 0.055, a Peak Signal-to-Noise Ratio (PSNR) of 43.451 dB, and a Structural Similarity Index (SSIM) of 0.975.
Breast Cancer Classification Using Clustering Based Optimized Autoencoder Model Ramya T V, J D Dorathi Jayaseeli 1st IEEE International Conference on Data Science and Intelligent Network Computing Icdsinc 2025, 2025 Breast cancer remains the most general cause of cancer based death among women. Detecting it at an early stage enhances treatment outcomes and chances of recovery. This work presents an automated breast cancer classification model that combines advanced image processing and optimization models using ultrasound (US) and mammography images. At first, median filter is used for noise eradication. This is followed by segmentation using Fuzzy C-Means (FCM) clustering and it is utilized for segmenting lesions. The segmented lesions are classified by the Deep Learning (DL) model Autoencoder(AE) for feature extraction and classification. Then, the Genghis Khan Shark Algorithm (GKSA) is presented for optimizing the hyper parameters of the U-Net. Experimental outcomes are performed on two benchmark datasets and achieved accuracy of 98.9% on US images and 98.7% (Mammogram images). The framework proves to be better and robust to support clinical decision-making in early diagnosis of breast cancer.
Web-Based Framework for Evaluating Clustering Algorithms Across Multiple Datasets Gyanendar Kumar Tiwari, Kshitij Singh, Dorathi Jayaseeli J D Proceedings of the International Conference on Multi Agent Systems for Collaborative Intelligence Icmsci 2025, 2025 This research study develops a web-based framework to compare clustering algorithms based on multiple datasets, assess the performance of algorithmic based on dataset characteristics and clustering objectives. The framework designed to support such widely used algorithms such as KM, DBSCAN and Hierarchical Clustering, offers visual and quantitative analysis for performance comparison. This platform was designed to make it easier for users to try out various algorithms and different parameter settings and thus, help them to choose the best clustering methods for a range of data types. This work impacts that greater understanding of how effective clustering is based on different data structures and application contexts by providing a useful framework for data driven research and analysis.
Candlestick Pattern Detection Using YOLOv11 P. Robert, J.D. Dorathi Jayaseeli, Karthikeyan, P Vijay Anand, Rajasekaran P, Krishna Rathod, Vishnu Haridas Proceedings of 2025 6th International Conference on Communication Computing and Industry 6 0 C2i6 2025, 2025
Network Intrusion Detection System Using Optuna Nishank Parekh, Arzob Sen, P. Rajasekaran, J. D. Dorathi Jayaseeli, P. Robert Proceedings of 5th International Conference on Iot Based Control Networks and Intelligent Systems Icicnis 2024, 2024
Voice Automation Mail System for Visually Impaired D Malathi, S Gopika, Dev Awasthi, Dorathi Jayaseeli Proceedings of the 1st IEEE International Conference on Networking and Communications 2023 Icnwc 2023, 2023
Image Classification Using Federated Averaging Algorithm J. D. Dorathi Jayaseeli, D. Malathi, Batoul Aljaddouh, Feisal Alaswad, Arsh Shah, Dev Choudhary Proceedings 4th IEEE 2023 International Conference on Computing Communication and Intelligent Systems Icccis 2023, 2023
Study and development of graphical authentication system for secure file transmission International Journal of Engineering and Technology Uae, 2018
Object recognition using the principles of deep learning architecture Arpn Journal of Engineering and Applied Sciences, 2017
Electrodermal activity (eda) based wearable device for qunatifying normal and abnormal emotions in humans Arpn Journal of Engineering and Applied Sciences, 2017
Text information extraction and conversion of text to speech Journal of Advanced Research in Dynamical and Control Systems, 2017
Fuzzy filtered neural network approach towards handwritten numeral recognition International Journal of Applied Engineering Research, 2017
An investigation of grammars and their applications in RNA structure prediction International Journal of Pharmacy and Technology, 2016
A survey on road condition monitoring and mitigation International Journal of Applied Engineering Research, 2015
