Browsing by Author "Islam, M.S.,"

Now showing 1 - 5 of 5

AI-Assisted Breast Cancer Diagnosis: Deep Learning on RSNA Mammogram Images for Improved Classification
(Institute of Electrical and Electronics Engineers Inc., 2023-12-15) Islam, M.S.,; Yasmin, S.,; Chowdhury, T.A.,; Sayem, A.,; Mim, K.
Breast cancer remains a significant global health challenge, causing many cancer-related deaths among women. Early detection improves survival rates, but primary prevention remains challenging due to unclear causes. Mammograms, with their ability to detect masses and micro-calcification, serve as the primary screening tool for breast cancer. However, accurate diagnosis can be hindered by poor contrast and fuzzy images of groups and benign glandular tissue. This research aims to enhance early breast cancer diagnosis using deep learning approaches on a newly published RSNA Screening Mammography data set. To increase the accuracy of early breast cancer detection, the researchers concentrated on reprocessing mammography pictures and analyzing breast density. We conducted an experiment using 1081 mammogram images and tested them on several pre-trained models, such as EfficientNetB0, Resnet50, and a conventional 15-layer CNN model. Interestingly, the 15-layer CNN model performed remarkably well, achieving an impressive accuracy of 97.6 per cent. This paper presents a comprehensive investigation into the depth of information within mammography images, highlighting the significance of breast density in the context of breast cancer detection. Additionally, the study explores various data pre-processing techniques to achieve more reliable and accurate results. By delving into these aspects, the research aims to advance breast cancer detection methods, potentially leading to improved outcomes in early diagnosis and treatment.
Design and performance analysis of 1.8 GHz low noise amplifier for wireless receiver application
(Institute of Advanced Engineering and Science, 2017-06) Amin, A.A.,; Islam, M.S.,; Masud, M.A.,; Khan, M.N.H.
In present stereo audio system is a most popular audio system for different purposes. Now a day’s stereo system is commonly used in communication and other purposes. Moreover Normalized Least Mean Square (NLMS) based adaptive filtering is an effective filtering process in case of communication and other applications. However adaptive filtering is an adaptive filter process to cancel out the noise from audio signal successfully. Hence the main objective of this paper is to design a NLMS adaptive filter which cancels out the noise from a noisy wave format stereo audio file. Moreover by varying the order of the adaptive filter (such as 8th, 16th, 32th and 64th), the performance of the NMLS adaptive filtered signal with respect to reference and noisy stereo audio signal are analyzed as well. © 2017 Institute of Advanced Engineering and Science. All rights reserved.
Estimation of optimum number of poles for random signal by Yule-Walker method
(Universitas Ahmad Dahlan, 2017) Al Amin, A.,; Islam, M.S.,; Abdul Al Woadud, K.M.,; Islam, M.J.,; ImrulKayes, M.
The Yule-Walker method is an effective method to estimate the system response or spectrum for random signal. Hence most of the noise and spurious signals are random in nature, so it is very convenient to estimate their spectrum by Yule-Walker method successfully. The Yule-Walker method is an autoregressive process to estimate the poles and errors also based on the number of poles for Wide Sense Stationary (WSS) process as well. Moreover the value of zero will be correspondingly calculated based on the poles in case of all poles model. The main concern of this paper is to analyze the Yule-Walker method and estimate the poles and zero along with the error based on the number of poles for a random signal. Moreover analyze the results to find out the optimum number of poles for least possible error.
Impact of higher order adaptive filtering for stereo system audio signal
(Institute of Advanced Engineering and Science, 2017) Amin, A.A.,; Islam, M.S.,; Masud, M.A.; Khan, M.N.H.
In present stereo audio system is a most popular audio system for different purposes. Now a day’s stereo system is commonly used in communication and other purposes. Moreover Normalized Least Mean Square (NLMS) based adaptive filtering is an effective filtering process in case of communication and other applications. However adaptive filtering is an adaptive filter process to cancel out the noise from audio signal successfully. Hence the main objective of this paper is to design a NLMS adaptive filter which cancels out the noise from a noisy wave format stereo audio file. Moreover by varying the order of the adaptive filter (such as 8th, 16th, 32th and 64th), the performance of the NMLS adaptive filtered signal with respect to reference and noisy stereo audio signal are analyzed as well. © 2017 Institute of Advanced Engineering and Science. All rights reserved.
Suitable beamforming technique for 5G wireless communications
(Institute of Electrical and Electronics Engineers Inc., 2017-01-10) Islam, M.S.,; Jessy, T.,; Hassan, M.S.,; Mondal, K.,; Rahman, T.
5th Generation mobile network (5G) announce the next phase of mobile telecommunications standards beyond the current 4th Generation mobile communication. 5G system will achieve more than 10 Gbps which will implement within 2020. Therefore few major problems have to be solved for getting this super speed. However to achieve this super speed a high frequency wave is required to transmit data through wider bandwidth. Massive MIMO Beamforming (BF) is one of the promising technologies to develop this system and Mm wave can be used to provide higher frequency. Conventional BF is capable to provide CSI (Channel State Information) from the transmitter to the receiver but adaptive BF is not capable to do so. However adaptive BF is very much effective to change it behavior according to the required of the channel. In that case a hybrid BF technology could be very much effective to implement 5G technology which will use both analog and digital BF technology to receive the reference signal without distortion. To find out the best beamforming technique is one the major challenge to implement 5G communication and In this paper the performance of conventional, adaptive and hybrid beamforming technique has been simulated specially for 5G communication to find out the best beamforming technique.