Blind Modulation Recognition in Wireless MC-CDMA Systems Using a Support Vector Machine Classifier

Swellings identification from Head and Neck computed tomography image data is an important but time consuming task performed manually by medical experts. Automating this process is challenging due to the high diversity in the appearance of tumor tissues among different patients. In many cases, the task of identifying the location of the tumor in Head and Neck is very complicated. The abnormal tissues have to be removed without causing any lacerations in the adjacent structures during entry or exit from the area subject to the tumor removal operation. This paper deals with a new identification technique for extracting the brain tumors in computed tomography images using Support Vector Machine (SVM). In the training phase, the SVM is used as an identifier to identify the tumor from the brain MRI images. The 2-D images are lexicographic ordered to 1-D signals, and then the Mel Frequency Cepstral Coefficients (MFCCs) are extracted from these 1-D signals or from their transforms. The SVM is then used to match the extracted features in the testing phase to those of the training phase. The method is applied to a set of real data of 20 MRI images with normal and abnormal tumors. Experimental results show that the recognition rate for features extracted from the Discrete Sine Transform (DST) of images contaminated by Additive White Gaussian Noise (AWGN), features extracted from images plus the Discrete Cosine Transform (DCT) of images contaminated by impulsive noise, and features extracted from images plus the DST of images contaminated by speckle noise achieve better performance compared to the existing techniques.

This paper presents a new property called the Duality Theorem for the Discrete Sine Transform (DST). Discrete Sine Transform is a finite — length discrete transform which is related to the renowned Discrete Fourier Transform (DFT) and is quite popular in signal processing arena, but has remained in the oblivion from pure mathematicians. Many of the properties of the Discrete Sine Transform are akin to those of the Discrete Fourier Transform and Discrete Cosine Transform, subject to minor differences. A formal derivation of the Duality Theorem corresponding to the Discrete Sine Transform is given which was hitherto not mentioned or derived in the literature. The usage of Duality Theorem helps in finding the discrete time — domain function from the DST frequency domain and vice versa thereby reducing considerable labour involved in the evaluation of the summation and hence, saves computation time and cost of implementation to a considerable extent. DST finds applications in Image Processing, Signal Processing applications for Communication Systems, and in the numerical solutions of differential equations as well as partial differential equations of mathematics.

Automatic identification of digitally modulated signal has to be able to identify the digitally modulated signal correctly and accurately. Importance of automatic identification of digitally modulated signals are rising increasingly. In this paper an advanced technique is presented, that automatically identifies the multi-user chirp modulated signals in Additive White Gaussian Noise (AWGN) channel. The proposed technique is implementing high order moments (fourth, sixth, and eighth) of detail coefficients of discrete wavelet transform (DWT) as a feature extraction set. Adaptive Neural-Fuzzy Inference System (ANFIS) is proposed as a classifier. The proposed identification procedure is capable of identifying multi-user chirp modulated signals with high accuracy at 0dB, 5dB, and 10dB Signal to Noise Ratio (SNR), over AWGN channel.

Modulation type is one of the most important characteristics used in signal waveform identification for wireless communications. In this paper, a cepstral algorithm for Automatic Digital Modulation Recognition (ADMR) is proposed. This algorithm uses Mel-Frequency Cepstral Coefficients (MFCCs) to extract the features of the modulated signal and a multi-layer feed-forward Artificial Neural Network (ANN) to classify the modulation type and its order. The proposed algorithm is capable of recognizing the modulation scheme with high accuracy in the presence of Additive White Gaussian Noise (AWGN) over a wide Signal-to-Noise Ratio (SNR) range.

A Monte Carlo simulation was conducted to assess the performance of Multi-Carrier Code Division Multiple Access (MC-CDMA) in a sectored cell, in an indoor environment. In each sector, terminal schedule packet transmission using slotted p-persistent Inhibit Sense Multiple Access, while the packets themselves are transmitted using MC-CDMA. The simulated bit error rate performance of MC-CDMA with combining strategies maximal ratio combining (MRC) and equal gain combining (EGC) used in the frequency domain are presented. A comparison is made between analytically determined bit error probability for a single user in an additive white Gaussian noise channel using binary phase shift keying (BPSK), and simulated bit error rate for a single user using MC-CDMA with MRC and EGC. The determination of the number of sectors in a cell is also given. MC-CDMA with diversity combining outperforms BPSK in a non-fading AWGN channel. Further, as the user-number increases, EGC performs better than MRC if these combining strategies are used with MC-CDMA. Finally, the results show the basis for determining the number of sectors in a cell. When using slotted p-persistent ISMA, it is envisaged that only a single user will transmit at a time in a sector.

This paper presents asymptotic multiuser efficiency (AME) performance analysis of the decorrelator based successive interference cancellation (DBSIC) DS-CDMA multiuser receiver DBSIC is similar to the conventional SIC receiver except that a decorrelator is used at each detection stage prior to cancellation. AMEs of DBSIC are compared with those of single-user matched filter, optimum, decorrelating and conventional SIC receivers over both additive white Gaussian noise (AWGN) and Rayleigh fading channels. It is shown that over AWGN channels, DBSIC AME is lower than the optimum receiver AME when the interfering user is weaker than the user of interest but approaches the unity optimum receiver AME as the interferer becomes stronger than the user of interest. For all spreading codes cross-correlation considered, DBSIC has a similar AME curve shape as the conventional SIC receiver but has a higher AME which remains positive for all user energy ratios, illustrating its near-far resistance over AWGN channels. The AME of DBSIC is better than that of the decorrelating detector when the interferer is much weaker or slightly stronger than the user of interest and has worse performance when the interferer is not much weaker. It is shown that DBSIC is completely near-far resistant over Rayleigh fading channels with the same AME as the decorrelating scheme for user 1 and as the optimum scheme for user 2, both AMEs being independent of the user energy ratio. This shows that DBSIC is preferable compared to the decorrelating detector, while still being less complex than the optimum scheme over Rayleigh fading channels

The performance of a multicarrier direct sequence code division multiple access (MC-DS-CDMA) system in fading environment has been extensively analysed in the literatures. The analysis that is available in the literatures did not take into account the impact of jamming and channel estimation errors on the performance of the system. In this study, closed-form expressions of the average bit error probability (BEP) of the MC-DS-CDMA system with channel estimation errors in the presence of partial band, broadband and multitone jamming are derived in a Rayleigh fading channel. The analysis shows that the magnitude of the normalised correlation between the actual and the estimated complex fading channel gain, A, greatly affects the performance of the MC-DS-CDMA system. For large signal-to-noise ratio, the average BEP with A=1 and without multiple access interference (MAI) tends to zero. When A≠1, the BEP of the system exhibits an error floor even without MAI. This error floor increases as the number of users increases. It is also shown that increasing the number of the system subcarriers enhances the system performance against jamming.

This paper presents a robust speaker identification method from degraded speech signals. This proposed method depends on the Mel-frequency cepstral coefficients (MFCCs) for feature extraction from the degraded speech and its discrete cosine transform (DCT). It is known that the MFCCs based speech recognition methods are not robust enough in the presence of noise and channel degradation. So, the feature extraction from the DCT of the signal will assist in achieving a higher recognition rate. The artificial neural network (ANN) classification technique is used in the proposed method. The comparison between the proposed method and the method using the MFCCs only for feature extraction from noisy speech signals and telephone-like degraded signals shows that the proposed method improves the recognition rate in the presence of noise or degradation.

Palm print scanning is a widespread method for biometric identity detection which has some advantages over other methods including its simplicity and relatively lower cost. In this study, a novel methods for biometric verification and identification by contactless palm scanning technique is proposed. In the study, Ripplet-I Transform (R-IT) which is a generalized form of Curvelet Transform (CuT), have been used in addition to multi-resolution transforms which were previously used in the literature as palm print verification and identification methods such as Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), Contourlet Transform (CoT). In addition, Principal Component Analysis (PCA) and Local Binary Pattern (LBP) have been utilized to increase the algorithm diversity. In order to investigate the effect of classification methods on the study results and the processing times, Artificial Neural Network (ANN), Euclidean Distance (ED) and Support Vector Machine (SVM) have been used separately for matching in the verification part of study. The performance of Convolutional Neural Network (CNN) as a classifier has also been examined. Verification and identification algorithms proposed in the study have been tested using palm print images of Hong Kong Polytechnic University Contact-free 3D/2D Hand Images Database (Version 1.0). The studies, that were carried out under two main sections yielded interesting results. At the end of the study, AUC (Area Under the ROC Curve) values ranging from 0.550 (Equal Error Rate (EER)= 0.4594) to 0.9875 (EER= 0.0336) were obtained for palm print verification. The highest AUC value without using LBP was obtained as 0.9563 (EER= 0.1096) using R-IT/CuT+DCT+CNN. Study results were showed that CNN is more successful than other classifiers without using LBP. It also has pointed out that the R-IT/CuT provides better results than the DWT and CoT. Using LBP in algorithms has increased success for ED, SVM and ANN. However, it has reduced overall for CNN. The highest AUC value (0.9875 and EER= 0.0336) was provided by the LBP+DWT+ED algorithm for palm print verification. The highest Identification Rate (IR) was achieved by using the LBP+CoT+ED algorithm with 84.444% for for palm print identification.

Block frames called <i>directional analytic discrete cosine frames</i> (DADCFs) are proposed for sparse image representation. In contrast to conventional overlapped frames, the proposed DADCFs require a reduced amount of 1) computational complexity, 2) memory usage, and 3) global memory access. These characteristics are strongly required for current high-resolution image processing. Specifically, we propose two DADCFs based on discrete cosine transform (DCT) and discrete sine transform (DST). The first DADCF is constructed from parallel separable transforms of DCT and DST, where the DST is permuted by row. The second DADCF is also designed based on DCT and DST, while the DST is customized to have no DC leakage property which is a desirable property for image processing. Both DADCFs have rich directional selectivity with slightly different characteristics each other and they can be implemented as non-overlapping block-based transforms, especially they form Parseval block frames with low transform redundancy. We perform experiments to evaluate our DADCFs and compare them with conventional directional block transforms in image recovery.

In this paper, the implementation of a Support Vector Machine (SVM) is proposed based on automatic system for voice biometric authentication, recognizing the speaker using Mel-Frequency Cepstral Coefficients and the Discrete Cosine Transform. The voice recognition problem can be modeled as a classification problem, where the objective is to obtain the best degree of separability between the classes which represent the voice. Building an automated speech recognition system capable of identifying the speaker, has many techniques using artificial intelligence and general classification at disposal, Support Vector Machines being the one used in this work. The voice samples used are in the Brazilian Portuguese language and had its features extracted through the Discrete Cosine Transform. Extracted features are applied on the Mel-frequency Cepstral Coefficients to create a two-dimensional matrix used as input to the SVM algorithm. This algorithm generates the pattern to be recognized, leading to a reliable speaker identification using few parameters and a small dataset.

The performance of MMSE single‐user detection (SD) and multi‐user detection (MD) STBC multi‐carrier code division multiple access (MC‐CDMA) systems are analysed and compared in the case of two transmit antennas and one or two receive antennas over Rayleigh fading channels and then over the stochastic multiple input multiple output (MIMO) METRA channel model. With two transmit and one receive antennas, MD achieves a gain of roughly 1 dB for non‐full load systems while the same performance is obtained with MD and SD for full load systems. Besides, with two receive antennas, we present a sub‐optimal and an optimal MMSE SD MIMO MC‐CDMA schemes, this last one offering a very good performance. Finally, the very good behaviour of MMSE space‐time block coding (STBC) MC‐CDMA systems is confirmed over the realistic multi element transmit receive antennas (METRA) MIMO channel. Copyright © 2004 AEI

Two three‐dimensional (3D) 16‐ary signal constellations having extended lattice structures are presented in this paper. The theoretical symbol error probabilities (SEPs) of the new constellations in additive white Gaussian noise (AWGN) and Rayleigh fading channel are derived. Computer simulation confirms that the closed‐form expressions for average SEPs of the constellations in the AWGN channel are very accurate. The theoretical SEP upper bounds in the Rayleigh fading channel are very tight. Since the presented constellations have larger minimum Euclidean distance (MED) than the conventional one, error performance can be improved up to 0.9 dB in an AWGN environment. Hence, the proposed constellations and their theoretical analysis can be used as a reference for the development of a wireless communication system with 3D signal constellations.

In the uplink system, different carrier frequency offsets (CFO) of different users at the receiver resulting multiuser interference (MUI) and thus degrade the performance of Multicarrier Code Division Multiple Access (MC-CDMA) system. In the previous study, Modified Minimum Mean Square Error Frequency Domain Equalization (Modified MMSE-FDE) has been proposed by Agnihotri which results in a better performance than the conventional MMSE. However, the achieved Bit Error Rate (BER) is not smaller than 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-2</sup> for Signal to Noise Ratio (SNR) below 20. This paper proposed a new algorithm to improve Modified MMSE-FDE performance in mitigating multiuser interference (MUI) in single cell MC-CDMA system, that is called as Carrier Frequency Offset Estimation-Minimum Mean Square Error Frequency Domain Equalization (CFO Estimation-MMSE FEQ). CFO Estimation-MMSE FEQ takes into account the rest of MUI as well as Modified MMSE-FDE to design equalization coefficient, but CFO Estimation-MMSE FEQ uses CFO estimation that is not on Modified MMSE-FDE. The value of CFO is estimated and regenerated in the receiver and then used to estimate MUI. In order to get signal processing more efficient, CFO Estimation-MMSE FEQ only takes the real trace of equalization coefficient matrix. MC-CDMA with CFO Estimation-MMSE FEQ has better performance than MC-CDMA with Modified MMSE-FDE. However, the complexity of CFO Estimation-MMSE FEQ is higher than Modified MMSE-FDE. By taking only the real trace of equalization coefficient matrix, the complexity of CFO Estimation-MMSE FEQ is getting simpler than taking the whole of equalization coefficient matrix. Furthermore, CFO Estimation-MMSE FEQ that takes only the real trace of equalization coefficient matrix is 2.9 % more efficient than CFO Estimation-MMSE FEQ that takes the whole of equalization coefficient matrix.

The multicarrier code division multiple access (MC-CDMA) system has received a considerable attention from researchers owing to its great potential in achieving high data rates transmission in wireless communications. Due to the detrimental effects of multipath fading the performance of the system degrades. Similarly, the impact of non-orthogonality of spreading codes can exist and cause interference. This paper addresses the performance of multicarrier code division multiple access system under the influence of frequency selective generalized η-µ fading channel and multiple access interference caused by other active users to the desired one. We apply Gaussian approximation technique to analyse the performance of the system. The avearge bit error rate is derived and expressed in Gauss hypergeometic functions. Maximal ratio combining diversity technique is utilized to alleviate the deleterious effect of multipath fading. We observed that the system performance improves when the parameter η increase or decreasse in format 1 or format 2 conditions respectively.