Article
Computer Science, Hardware & Architecture
Ozlem Polat, Cahfer Gungen
Summary: This study proposes a solution for classifying brain tumors in MR images using transfer learning networks and tests the performance of various neural networks under different optimization algorithms. The results show that the proposed transfer learning methods can achieve high performance in classifying the most common brain tumors.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Biotechnology & Applied Microbiology
Jin Li, Peng Wang, Yang Zhou, Hong Liang, Kuan Luan
Summary: The study compared the performance of machine learning, deep learning, and deep transfer learning in automatically classifying colorectal cancer lymph node metastasis, finding that deep transfer learning was the most effective method with an accuracy of 0.7583 and an area under the curve of 0.7941.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2021)
Article
Engineering, Biomedical
Fatima Zulfiqar, Usama Ijaz Bajwa, Yasar Mehmood
Summary: Accurate classification of brain tumor types is crucial for early diagnosis. In this research, a transfer learning-based fine-tuning approach using EfficientNet achieved a test accuracy of 98.86% for brain tumor classification.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Interdisciplinary Applications
Danilo Avola, Andrea Bacciu, Luigi Cinque, Alessio Fagioli, Marco Raoul Marini, Riccardo Taiello
Summary: This study examines the effectiveness of established neural network architectures in the classification of chest-x-rays showing pneumonia symptoms derived from either viral or bacterial sources, using the transfer learning paradigm.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Mathematics
Ashwini Pradhan, Debahuti Mishra, Kaberi Das, Ganapati Panda, Sachin Kumar, Mikhail Zymbler
Summary: The proposed hybrid method ELM-SSA shows superior performance in diagnosing brain diseases compared to traditional methods. Simulation results demonstrate the potential superiority of ELM-SSA in terms of ROC, AUC, and accuracy.
Article
Computer Science, Information Systems
Sohaib Asif, Wenhui Yi, Qurrat Ul Ain, Jin Hou, Tao Yi, Jinhai Si
Summary: This study aims to develop a robust and efficient method for classifying brain tumors using MRI based on transfer learning technique. The experimental results show that the proposed CNN model based on the Xception architecture using ADAM optimizer is better than the other three proposed models, enabling quick and accurate classification of brain tumors.
Article
Oncology
Xianwu Xia, Bin Feng, Jiazhou Wang, Qianjin Hua, Yide Yang, Liang Sheng, Yonghua Mou, Weigang Hu
Summary: This study developed a deep learning model for diagnosing parotid gland tumors using MRI images of 233 patients. The model achieved high accuracy in diagnosing and staging parotid tumors, showing promising potential to assist clinicians in diagnosis. Further validation through larger-scale multicenter studies is recommended.
FRONTIERS IN ONCOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Meghavi Rana, Megha Bhushan
Summary: This study demonstrates the accuracy of transfer learning-based deep learning methods in Computer-Aided Design (CAD) systems for the early detection and analysis of diseases such as lung cancer, brain tumor, and breast cancer. By utilizing pre-trained models, the time for deep learning-based tasks in computer vision can be reduced. The effectiveness of transfer learning models for tumor classification is explained, and the best performing models on a specific dataset are identified.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Plant Sciences
Zhelin Cui, Kanglong Li, Chunyan Kang, Yi Wu, Tao Li, Mingyang Li
Summary: Efficient image recognition is crucial in crop and forest management. This study proposes a modified method that combines prototypical networks and attention mechanisms to address the challenges in plant and disease recognition. The results demonstrate high classification accuracy and the potential applicability of this approach in various domains.
Article
Computer Science, Artificial Intelligence
Soner Civilibal, Kerim Kursat Cevik, Ahmet Bozkurt
Summary: This study investigates the implementation of deep learning approaches, specifically Mask R-CNN, for breast tumor recognition based on thermal images. The results show that the classification and segmentation performances of the proposed method are better than those reported in the literature for similar studies.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
AbdAlRahman Odeh, Ayah Alomar, Shadi Aljawarneh
Summary: This study uses deep learning techniques to analyze X-ray lung images and compares the performance and accuracy of multiple pre-trained models to find the best model for detecting COVID-19 infection.
PEERJ COMPUTER SCIENCE
(2022)
Article
Remote Sensing
Xiangyu Zhao, Jingliang Hu, Lichao Mou, Zhitong Xiong, Xiao Xiang Zhu
Summary: This paper presents a deep transfer model with multiple sub-networks optimized by supervised loss and unsupervised loss. The model improves overall accuracy and average accuracy in climate zone classification. The proposed deep transfer network demonstrates outstanding performance.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)
Article
Engineering, Multidisciplinary
Gonul Sakalli, Hasan Koyuncu
Summary: This study utilizes thermal image analysis to distinguish different conditions of asynchronous motors and transformers. By evaluating deep learning algorithms on 20 different situations, it is found that all tested architectures achieve 100% accuracy.
Article
Geochemistry & Geophysics
Wenpei Jiao, Jianlei Zhang
Summary: This work addresses the challenges of long-tail and few-shot problems in sonar image classification. By introducing a two-stage decoupled training approach and a novel multibalanced sampling method, the balanced ensemble transfer learning (BETL) pipeline is proposed to simultaneously overcome the LTFS problems.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Engineering, Biomedical
Chieh-Te Lin, Sanjay Ghosh, Leighton B. Hinkley, Corby L. Dale, Ana C. S. Souza, Jennifer H. Sabes, Christopher P. Hess, Meredith E. Adams, Steven W. Cheung, Srikantan S. Nagarajan
Summary: This study proposes a deep multi-task multimodal framework for tinnitus classification and severity prediction using structural MRI (sMRI) data. The results demonstrate that our model outperforms existing learning-based and conventional methods in terms of accuracy, sensitivity, specificity, and negative predictive value.
JOURNAL OF NEURAL ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Taranjit Kaur, Tapan Kumar Gandhi
Summary: This paper investigates the use of transfer learning for COVID-19 detection on a small medical imaging dataset. The experimental results show that the transfer learned ResNet50 model outperforms other models and further improvement is achieved through the use of different classifiers and a classifier fusion strategy.
CIRCUITS SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Engineering, Electrical & Electronic
Jyoti Maheshwari, Shiv Dutt Joshi, Tapan K. Gandhi
Summary: Real-time seizure detection using high spatial frequencies is proposed in this article. By analyzing the eigenvalues of the graph Laplacian, the authors construct a sub-band characteristic response vector and analyze it over time to detect seizure and non-seizure brain states. The proposed approach performs well in real-time automated seizure detection without prior training and is independent of sampling rates.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Automation & Control Systems
Himanshu Padole, S. D. Joshi, Tapan K. Gandhi
Summary: In this study, a novel graph signal processing based integrated AD detection model using multimodal deep learning was proposed. The model utilized both static and dynamic brain connectivity features to improve the detection of AD in the early stages.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2022)
Article
Psychology, Multidisciplinary
Priti Gupta, Pragya Shah, Sharon Gilad Gutnick, Marin Vogelsang, Lukas Vogelsang, Kashish Tiwari, Tapan Gandhi, Suma Ganesh, Pawan Sinha
Summary: The study found that individuals who were congenitally blind and underwent visual surgery showed significant improvement in visual memory capacity, reaching a level comparable to a control group with matched visual acuity one year later. This suggests plasticity in visual memory mechanisms in late childhood, but also vulnerability to early deprivation.
PSYCHOLOGICAL SCIENCE
(2022)
Article
Psychology, Developmental
Priti Gupta, Pragya Shah, Swochchhanda Shrestha, Sharon Gilad-Gutnick, Suma Ganesh, Tapan Gandhi, Pawan Sinha
Summary: Judgments of facial attractiveness are affected by early visual deprivation, even newborns are capable of making such judgments. Newly sighted congenitally blind children show individual variability in rating facial attractiveness, possibly due to atypical facial encoding strategies. This suggests that the development of facial attractiveness perception is vulnerable to early visual deprivation.
DEVELOPMENTAL SCIENCE
(2023)
Article
Multidisciplinary Sciences
Amita Giri, Lalan Kumar, Nilesh Kurwale, Tapan K. Gandhi
Summary: This study presents a brain source localization method based on anatomical harmonics basis, which reduces the computational cost and increases the accuracy by reducing dimensionality and increasing the contribution of source eigenvalues. The proposed method shows good performance on both simulated data and clinical EEG data.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Artificial Intelligence
Debanjan Konar, Siddhartha Bhattacharyya, Tapan K. Gandhi, Bijaya K. Panigrahi, Richard Jiang
Summary: This article presents a new shallow 3D self-supervised tensor neural network called 3D quantum-inspired self-supervised tensor neural network (3D-QNet) for volumetric segmentation of medical images. The network consists of input, intermediate, and output layers interconnected using a third-order neighborhood-based topology. Each layer contains quantum neurons designated by qubits or quantum bits. The network incorporates tensor decomposition in quantum formalism for faster convergence and achieves promising results in semantic segmentation.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Multidisciplinary Sciences
Caterina A. Pedersini, Nathaniel P. Miller, Tapan K. Gandhi, Sharon Gilad-Gutnick, Vidur Mahajan, Pawan Sinha, Bas Rokers
Summary: The visual system develops abnormally when visual input is absent or degraded during a critical period early in life. Recent evidence shows that congenitally blind adolescents can recover both low-level and higher-level visual function following surgery. The structural integrity of late-visual pathways is associated with improvements in face perception.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2023)
Article
Engineering, Electrical & Electronic
Raghav Dev, Sandeep Kumar, Tapan Kumar Gandhi
Summary: In this letter, a novel approach for detecting the transition of EEG microstates of the human brain has been proposed. The proposed method uses graph theory and spectral analysis to construct a spatiotemporal graph and detect the transition of the microstates. Experimental results on two datasets show that the proposed method outperforms state-of-the-art methods in terms of accuracy.
IEEE SENSORS LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Chandra Bhushan Kumar, Arnab Kumar Mondal, Manvir Bhatia, Bijaya Ketan Panigrahi, Tapan Kumar Gandhi
Summary: Sleep apnea is a common sleep disorder that can have serious health consequences. Polysomnography is an effective method for diagnosis, but it is time-consuming. This study proposes a self-supervised learning approach using ECG signals for detecting sleep apnea.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Shipra Madan, Anirudra Diwakar, Santanu Chaudhury, Tapan Gandhi
Summary: In this study, an automated approach using chest X-rays for the classification of Viral, Bacterial, and Fungal pneumonia is proposed. By employing Siamese Networks and visual explanations, our model demonstrates remarkable improvement in performance with few training samples, and exhibits powerful generalization capability.
INTELLIGENT HUMAN COMPUTER INTERACTION, IHCI 2021
(2022)
Article
Engineering, Electrical & Electronic
Amita Giri, Lalan Kumar, Tapan Gandhi
Summary: The study explores the applications of motor imagery and motor execution in neuro-rehabilitation and motor power augmentation, revealing significant differences in response time, activation magnitude, and cortical source distribution between the two. Different frameworks for enhanced brain computer interface applications have been developed based on these differences. Decoding subject's intent using cortical source domain processing increases accuracy in MI and ME scenarios, outperforming existing techniques.
IEEE SENSORS LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Shiva Azimi, Rohan Wadhawan, Tapan K. Gandhi
Summary: In the past decade, high-throughput plant phenotyping techniques utilizing image analysis and machine learning have been successful in identifying and quantifying plant health and diseases. To address the issue of early detection and recovery, a deep learning pipeline for analyzing plant visual changes induced by stress has been proposed.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Biomedical
Taranjit Kaur, Tapan K. Gandhi, Bijaya K. Panigrahi
Summary: The study utilizes deep learning techniques in diagnosing COVID-19 from CT images, proposing an expert model based on deep features and PF-BAT optimized FKNN classifier with high validation accuracy. The proposed model can assist clinicians in timely and accurate identification of the coronavirus, aiding in patient management and speedy recovery.
IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE
(2021)
Proceedings Paper
Computer Science, Information Systems
Sakshi Ahuja, B. K. Panigrahi, Tapan Gandhi, Utkarsh Gautam
Summary: A deep learning-based CAD tool was proposed for the classification and localization of brain tumors, achieving an accuracy of 98.72% and a recall rate of 99.56% through training and evaluation on the CE-MRI brain dataset.
2021 11TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING, DATA SCIENCE & ENGINEERING (CONFLUENCE 2021)
(2021)