Conference Paper

Permanent URI for this collectionhttps://hdl.handle.net/10361/7017

Browse

Now showing 1 - 10 of 10

A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD)
(© 2017 ACM, 2017-01) Ratul, Md Aminur Rab; Raja, Sharif Ahmmad; Uddin, Jia; Department of Computer Science and Engineering
Texture feature extraction consolidated with texture feature detection and feature matching solves many typical problems of image processing and computer vision; such as, texture classification, pattern recognition, object detection, and image segmentation. Through this paper, a new method for texture feature extraction is presented which uses Log-Gabor Filter and Singular Value Decomposition (SVD) algorithm. In the proposed model, sample images are converted to gray level images. And then, to elicit suitable distinctive texture orientation, a 2D Log- Gabor filter with various frequencies and different edges disintegrated with the SVD employ on each converted gray level images. Finally, singular values of SVD used as feature vector for this texture feature extraction model. For training and testing of experimental datasets, Naive Bayes classifier has been used. The Log-Gabor and SVD based feature extraction shows improved performance by exhibiting higher classification accuracy for our tested dataset compare to conventional Gabor and SVD feature extraction method. Furthermore, in order to decrease the computational and time complexity, an NVIDIA GeForce GTX780 GPU is used to implement our proposed model in parallel. The GPU implementation of proposed model showed average 3X speedup for per image than conventional CPU implementation.
A novel modified SFTA approach for feature extraction
(© 2016 IEEE, 9/22/2016) Hasan, Md Junayed; Uddin, Jia; Pinku, Subroto Nag; Department of Computer Science and Engineering
To increase the efficiency of conventional Segmentation Based Fractal Texture Analysis (SFTA), we propose a new approach on SFTA algorithm. We use an optimum multilevel thresholding hybrid method of Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), called HGAPSO with the optimization technique for classification based on grey level range to get more accurate output. Experimental results show that proposed approach exhibits average 2% higher classification accuracy than conventional SFTA for our tested dataset.
An adaptive digital image watermarking scheme with PSO, DWT and XFCM
(© 2017 IEEE, 2017-02) Mitashe, Mashruha Raquib; Habib, Ahnaf Rafid Bin; Razzaque, Anindita; Tanima, Ismat Ara; Uddin, Jia; Department of Computer Science and Engineering
In this paper, a novel adaptive digital image watermarking model based on modified Fuzzy C-means clustering is proposed. For watermark embedding process, we used Discrete Wavelet Transform (DWT). A segmentation technique XieBeni integrated Fuzzy C-means clustering (XFCM) is used to identify the segments of original image to expose suitable locations for embedding watermark. We also pre-processed the host image using Particle Swarm Optimization (PSO) to lend a hand to the clustering process. The goal is to focus on proper segmentation of the image so that the embedded watermark can withstand common image processing attacks and provide security to digital images. Several attacks were performed on the watermarked images and original watermark was extracted. Performance measures like PSNR, MSE, CC were computed to test the extracted watermarks with and without attacks. Experimental results show that the proposed scheme has performed well in terms of imperceptibility and robustness when compared to other watermarking models.
Performance of VoIP networks using MPLS traffic engineering
(© 2012 Trans Tech Publications, 2012) Faisal, Mohammed Fuad Ad; Uddin, Zia; Shil, Shimul; Department of Computer Science and Engineering
The implementation of Voice over Internet Protocol (VoIP) technology is on the increase because of its ability to enhance operating efficiency and reduce infrastructure cost. Voice and data packets traverse over IP networks with fixed maximum capacity. But susceptibility to traffic congestion which results in delay and packet losses is still a major challenge of VoIP technology. Multiprotocol Label Switching Protocol (MPLS) with Traffic Engineering (TE) is an approved standard technology that has the capabilities to minimize network congestion and improve network performance by reducing delay and packet loss to yield a higher throughput. In this paper, we investigate how MPLS Traffic Engineering can be implemented to reduce traffic congestion on VoIP networks.
Performance analysis of multicarrier code division multiple access over rayleigh fading channel
(© 2012 Trans Tech Publications, 2011) Uddin, Jia; Faisal, Mohammed Fuad Ad; Azam, Md. Facihul; Muzahidur Rahman, A. F M; Department of Computer Science and Engineering
Recently, multi-carrier transmission schemes have been introduced into Code Division Multiple Access (CDMA) systems to gain advantages for high data rate transmission as well as security. Due to pseudorandom code there is no chance to Inter Symbol Interference (ISI). There are different techniques to mitigate multipath fading. One of the method is to transmit identical narrowband direct-sequence (DS) waveforms in parallel over a number of sub-channels using frequency diversity. Implementation this multi-carrier modulation technique in CDMA system is known as multi-carrier CDMA (MC-CDMA). In Rayleigh fading channel, due to multi-carrier modulation, when one subcarrier goes deep fade another subcarrier may remain safe. Therefore it combats multi-path fading and signal can be received in low bit error rate.
Impact of background utilization and background traffic on the foreground applications in a wide area network
(© 2012 Springer Science+Business Medi, 2012) Uddin, Zia; Kim, Jongmyon; Department of Computer Science and Engineering
In the real scenarios, network utilization widely depends on the background traffic and the number of active users. This paper presents the effect of background traffic on the QoS of foreground traffic by varying the utilization of LAN devices, server, and bandwidth. We designed a WAN (Wide Area Network) using the OPNET simulator, which consists of different Local Area Networks (LANs) located in different cities. We considered a foreground GSM quality voice traffic, and FTP heavy and video conference background traffic. The experimental results demonstrated that the channel bandwidth utilization has much effect on the QoS of foreground traffic. In addition, heavy background traffic highly affects the QoS of foreground traffic due to the network congestion.
FIR filter design using modified lanczos window function
(© 2012 Advanced Materials Research, 2012) Samad, Md. Abdus; Uddin, Jia; Ahmed, Md. Razu; ; Department of Computer Science and Engineering
Attenuated side lobe peak in the range of around ~-45dB is required in many applications of signal processing and measurements. However, the problem is usual window based FIR filter design lies in its side lobes amplitudes that are higher than the requirement of application. We propose a modified Lanczos window function by heuristic by examining the Lanczos window, which has better performance like equiripple, minimum side lobe compared to the several commonly used windows. The proposed window has slightly larger main lobe width of the commonly used Hamming window, while featuring 5.1-18.5 dB smaller side lobe peak. The proposed modified Lanczos window maintains its maximum side lobe peak about -55.2-51.9 dB compared to -39-36.7 dB of Hamming window for M= 10-14, while offering roughly equal main lobe width. Our simulated results also show significant performance upgrading of the proposed modified Lanczos window compared to the Kaiser, Gaussian, and Lanczos windows. The proposed modified Lanczos window also shows better performance than Dolph-Chebyshev window. Finally, the example of designed low pass FIR filter confirms the efficiency of the proposed modified Lanczos window.
Automated irrigation system using solar power
(© 2012 IEEE, 2012) Uddin, Jia; Reza, S.M. Taslim; Newaz, Qader; Uddin, Jamal; Islam, Touhidul; Kim, Jong-Myon; Department of Computer Science and Engineering
This paper proposes a model of variable rate automatic microcontroller based irrigation system. Solar power is used as only the source of power to control the overall system. Sensors are placed on the paddy field and these sensors continuously sense the water level and give the message to the farmer informing the water level. Without visiting the paddy fields, farmers can get the information about the water level. Based on the water level, a farmer can control the motor by sending a message from his cellular phone even from a remote place. However, if the water level reaches to the danger level; the motor will automatically start without confirmation of farmer to ensure the proper water level in the site. At the end of this paper, a complete hardware implementation of this proposed automated irrigation system is presented.
Network design and performance analysis of geographical routing protocol in mobile Ad-Hoc networks
(© 2013 IEEE, 2013) Alam, Abu Hasnat Md. Riadul; Khan, Md. Atiqur Rahaman; Uddin, Jia; Department of Computer Science and Engineering
In this research we have explored the consequences of increase in number of nodes on the overall performance of Geographical Routing Protocol (GRP) which is at present covering an enormous demand in the field of Mobile Ad-Hoc Networks (MANETs). To think about a wireless network without having any sorts of infrastructures, MANETs are such examples which are usually set up to serve a specified or special purpose on a temporary basis within a certain passage of time. Due to its lots of applications in the various fields of human endeavor, the immense significance of it can hardly be expressed in words in modern times. Thus, before deploying any mobile network, a proficient routing protocol has become a fundamental and vital issue. In order to observe the performance of GRP protocol, we have carried out simulation by varying the number of mobile nodes in different network scenarios using the OPNET (Optimized Network Engineer Tool) Modeler 14.0. The experimental results demonstrate that for a fixed size network area with varying network density, the GRP routing protocol shows comparatively lower delay than AODV routing protocol. But it shows inverse characteristics curve for throughput and load compare to the AODV. However, from any network always expects less delay and concurrently want large throughput. Therefore, till now no routing protocol shows optimum performance in all MANET scenarios.
Accelerating a Bellman-Ford routing algorithm using GPU
(© 2014 Springer Verlag, 2014) Jeong, In-Kyu; Uddin, Jia; Kang, Myeongsu; Kim, Cheol-Hong; Kim, Jong-Myon; Department of Computer Science and Engineering
This paper presents a graphics processing unit (GPU)-based implementation of the Bellman-Ford (BF) routing algorithm used in distance-vector routing protocols. In the proposed GPU-based approach, multiple threads concurrently run in numerous streaming processors in the GPU to update the routing information instead of computing the individual vertex distances one-by-one, where an individual vertex distance is considered as a single thread. This paper compares the performance and energy consumption of the GPU-based approach with those of the equivalent central processing unit (CPU) implementation for varying the number of vertices. Experiment results show that the proposed approach outperforms the equivalent sequential CPU implementation in terms of execution time by exploiting massive parallelism inherent in the BF routing algorithm.

Browse

Recent Submissions