Article
Engineering, Biomedical
S. Sudharson, Turimerla Pratap, Priyanka Kokil
Summary: This paper presents a novel noise level estimation technique for speckle removal in ultrasound images, which accurately estimates the noise level by extracting noise level aware features and training a support vector regression model. Incorporating this technique with advanced despeckling methods results in superior despeckling performance in ultrasound images.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Electrical & Electronic
Umberto Paoletti
Summary: This article proposes a single-channel blind source separation method for decomposing time-domain measurement results of electromagnetic noise into underlying periodic switching noise source signals without any prior knowledge of the sources. The method clusters the time-domain waveforms based on their period and similarity, assigns waveform clusters to each period using a new probabilistic approach, and filters the clusters by removing waveform outliers that are significantly different from the remaining waveforms. The proposed method allows for the determination and ranking of each source's contribution to the spectrum, aiding in the identification of main noise sources and analysis of individual source contributions in complex noisy environments.
IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY
(2023)
Article
Geochemistry & Geophysics
Si Chen, Yue Yuan, Sixiang Wang, Huanhuan Yang, Lingzhi Zhu, Shuning Zhang, Huichang Zhao
Summary: A novel multi-electromagnetic jamming countermeasure for airborne SAR based on maximum SNR blind source separation is proposed in this article. By identifying the real target echo signal and using corresponding imaging methods, high-resolution images of the interested target area are achieved.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Zhenshuo Lei, Qizhe Qu, Hao Chen, Zhaojian Zhang, Gaoqi Dou, Yongliang Wang
Summary: In this paper, a method of mainlobe jamming suppression with space-time multichannel via blind source separation (BSS) is proposed to solve the problem of array radar being seriously affected by complex mainlobe jamming. The proposed method constructs four space-time sum-difference channels to enhance the discriminability of the source signals, and uses the joint approximate diagonalization of eigenmatrices' (JADEs) BSS algorithm to separate the target echo signal from the mixed signal. The simulation results show that the proposed method can effectively suppress interference and extract the target information in the presence of up to three near-mainlobe blanket jamming signals or self-defensive mainlobe deceptive jamming signals.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Ali Abbasian Ardakani, Afshin Mohammadi, Fariborz Faeghi, U. Rajendra Acharya
Summary: This study aims to evaluate 67 denoising filters and select the best one for ultrasound image denoising. A new filter evaluation method, Rank Analysis, was introduced and utilized. The best filter identified was the Spatial correlation (SCorr) filter.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2023)
Article
Engineering, Multidisciplinary
Onur Karaoglu, Hasan Sakir Bilge, Ihsan Uluer
Summary: This study applies deep learning networks to denoise speckle noises in ultrasound images and compares their performance with classical image enhancement algorithms. The results show that the proposed deep learning networks outperform other networks and algorithms in terms of peak signal-to-noise ratio and structural similarity index.
ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH
(2022)
Article
Computer Science, Artificial Intelligence
A. Shamla Beevi, S. Ratheesha, Saidalavi Kalady, Jenu James Chackola
Summary: A deep learning-based denoising model called Convolutional-based improved despeckling autoencoder (CIDAE) is proposed in this paper for denoising transthoracic echocardiographic images. The model is trained with a dataset collected from patients with Regional Wall Motion Abnormality (RWMA). The significance of the proposed CIDAE model for denoising echo images of patients with RWMA and structurally normal hearts is demonstrated through visual and quantitative evaluation.
Article
Engineering, Biomedical
Jieyi Liu, Changchun Li, Liping Liu, Haobo Chen, Hong Han, Bo Zhang, Qi Zhang
Summary: In this study, a US despeckling method based on the CycleGAN is developed to reduce noise in medical ultrasound images, improving disease diagnosis and treatment.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Information Systems
Walid El-Shafai, Amira A. Mahmoud, Anas M. Ali, El-Sayed M. El-Rabaie, Taha E. Taha, Osama F. Zahran, Adel S. El-Fishawy, Naglaa F. Soliman, Amel A. Alhussan, Fathi E. Abd El-Samie
Summary: This paper categorizes and investigates noise reduction techniques for medical images, focusing on single-image denoising methods and exploring various approaches in both spatial and transform domains. A new model based on deep convolutional neural network is proposed, achieving significant improvement over traditional techniques.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Artificial Intelligence
Thavavel Vaiyapuri, Haya Alaskar, Zohra Sbai, Shri Devi
Summary: The paper introduces a multi-objective optimization method for denoising medical images in the wavelet domain, using genetic algorithm to optimize thresholds. This technique can adapt to different types of noise and balance the preservation of diagnostic details with noise reduction.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2021)
Review
Computer Science, Information Systems
Yangyang Li, Dzati Athiar Ramli
Summary: This paper explores the application of diverse TFA methods in BSS systems over the past decade, emphasizing the importance of TFA in handling non-stationary signals. The study covers various influencing factors of TFA methods and aids researchers in selecting techniques aligned with their objectives. Furthermore, it comprehensively reviews contemporary BSS algorithms, categorizing them into three classes, and evaluates the role of commonly used TFA methods in each class, identifying their strengths and limitations. The paper also addresses challenges in implementing BSS algorithms and highlights the central role of TFA in overcoming these challenges and enhancing separation outcomes.
Article
Chemistry, Analytical
Romoke Grace Akindele, Ming Yu, Paul Shekonya Kanda, Eunice Oluwabunmi Owoola, Ifeoluwapo Aribilola
Summary: The recovery of semantics from corrupted images is a significant challenge in image processing, and noise can obscure features, interfere with analysis, and bias results. In order to address this issue, a algorithm called PixSimWave was developed, which uses regularized pixel similarity detection and adaptive neighborhood filtering to improve the accuracy of noise reduction.
Article
Engineering, Electrical & Electronic
Mingzhan Zhao, Zhiliang Wang, Xinyue Chang, Wei Zhao, Zhimin Zhang
Summary: This paper introduces an algorithm for nonnegative blind source separation (N-BSS) based on the minimum Jaccard index. The proposed method, called dark-point component analysis (DCA), aims to find dark-points without assuming local dominance, full additivity, and sparsity. DCA can also be applied to blind source separation (BSS) with strictly positive sources, yielding the same result as N-BSS.
CIRCUITS SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Energy & Fuels
Guo Wang, Yibin Wang, Yongzhi Min, Wu Lei
Summary: This paper proposes a blind source separation method based on sparse component analysis for handling the problem of interference signals in acoustics-based power transformer fault diagnosis. The method transforms the mixed acoustic signals into the time-frequency domain, extracts single source points, estimates the mixing matrix through clustering, and separates the transformer acoustic signal from the mixed acoustic signals using compressed sensing theory. The simulation and experimental results demonstrate that the proposed method successfully separates the transformer acoustic signal even underdetermination.
Article
Engineering, Electrical & Electronic
Priyanka Arora, Parminder Singh, Akshay Girdhar, Rajesh Vijayvergiya
Summary: This paper presents a performance analysis of various despeckling filters for IVUS images and shows that the CNLM denoising filter outperforms others in terms of preserving edge and feature details.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2023)
Article
Telecommunications
Ritesh Jha, Vandana Bhattacharjee, Abhijit Mustafi
Summary: The study aims at providing solutions for thyroid disease prediction using dimension reduction and data augmentation techniques, achieving a maximum accuracy of 99.95%. Experimental results demonstrate that these techniques can efficiently improve the accuracy of disease prediction.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Article
Optics
Rani Kumari, Abhijit Mustafi
Summary: This paper proposes a multi-parameter image watermarking algorithm using the fractional Fourier transform (FrFT), which utilizes a double transform mechanism to enhance robustness against attacks. The algorithm integrates the Particle Swarm Optimization (PSO) algorithm to determine the optimal fractional domain for embedding by minimizing the RMSE. Performance evaluation tests against standard parameters show improved robustness, imperceptibility, and payload capacity of the algorithm.
Review
Computer Science, Information Systems
R. N. Rathi, A. Mustafi
Summary: This paper reviews a wide range of techniques proposed in the literature for machine recognition of language and text. It discusses the term weighting techniques proposed by researchers, exploring the mathematical foundations of these methods. The term weighting schemes are broadly classified as supervised and statistical methods, and the paper presents numerous examples to highlight the differences between the two categories. The Vector Space Model and its variants, which serve as the basis for many other methods discussed in the paper, are given particular attention.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
R. N. Rathi, A. Mustafi
Summary: In this work, a statistical approach to identify unigram keywords for a document is proposed. The approach does not require pre-training of the model and evaluates terms using relative entropy, displacement, and variance, comparing their effectiveness with term frequency.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Psychology, Multidisciplinary
Ritesh Jha, Vandana Bhattacharjee, Abhijit Mustafi, Sudip Kumar Sahana
Summary: This research focuses on providing a better solution for diagnosing COVID-19 and addressing the issue of limited data for disease prediction models. By developing various machine learning models and applying data augmentation techniques, the authors have achieved improved accuracy in diagnosing COVID-19.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Computer Science, Software Engineering
Ritesh Jha, Vandana Bhattacharjee, Abhijit Mustafi
Summary: Transfer learning is a technique that utilizes knowledge learned from one task to improve learning for another similar task. This article proposes TrFEMNet, a model for classifying medical images, which extracts representations at different levels of hierarchy for improved performance. Experimental results show that TrFEMNet performs comparably to other models in various medical image classification tasks.
SCIENTIFIC PROGRAMMING
(2022)
Article
Telecommunications
Chandana Kumari, Abhijit Mustafi
Summary: This study proposes an efficient color image segmentation method for low-density range images using the RCAB-RDMCNN enhancement technique and RBSHM segmentation algorithm. The proposed method converts LDR images into HSV format, segments the brighter and darker regions using the AMOT algorithm, enhances the image contrast using RCAB-RDMCNN, and performs image segmentation using RBSHM. Experimental results show that the proposed method achieves the highest accuracy rate and outperforms other state-of-the-art methods.
WIRELESS PERSONAL COMMUNICATIONS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
D. Mustafi, G. Sahoo, A. Mustafi
ADVANCES IN COMPUTATIONAL INTELLIGENCE
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
D. Mustafi, G. Sahoo, A. Mustafi
COMPUTATIONAL INTELLIGENCE IN DATA MINING, VOL 1, CIDM 2015
(2016)