Adaptive predistortion using threshold decomposition‐based piecewise linear modeling

A new adaptive predistortion approach for nonlinear power amplifiers based on the piecewise linear (PWL) approximation of nonlinear functions is presented. The PWL model is obtained using threshold decomposition (TD) of the input‐output characteristics. The TD based PWL model is used to develop a baseband predistorter using both the direct and the indirect learning architectures. The proposed predistorter is proved to provide a better performance in suppressing nonlinear distortion than conventional polynomial predistorters and a reduced hardware complexity as compared to lookup table (LUT) approach. © 2011 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2011.     

Performance Analysis of Machine Learning Algorithms for Classifying Hand Motion-Based EEG Brain Signals

Brain-computer interfaces (BCIs) records brain activity using electroencephalogram (EEG) headsets in the form of EEG signals; these signals can be recorded, processed and classified into different hand movements, which can be used to control other IoT devices. Classification of hand movements will be one step closer to applying these algorithms in real-life situations using EEG headsets. This paper uses different feature extraction techniques and sophisticated machine learning algorithms to classify hand movements from EEG brain signals to control prosthetic hands for amputated persons. To achieve good classification accuracy, denoising and feature extraction of EEG signals is a significant step. We saw a considerable increase in all the machine learning models when the moving average filter was applied to the raw EEG data. Feature extraction techniques like a fast fourier transform (FFT) and continuous wave transform (CWT) were used in this study; three types of features were extracted, i.e., FFT Features, CWT Coefficients and CWT scalogram images. We trained and compared different machine learning (ML) models like logistic regression, random forest, k-nearest neighbors (KNN), light gradient boosting machine (GBM) and XG boost on FFT and CWT features and deep learning (DL) models like VGG-16, DenseNet201 and ResNet50 trained on CWT scalogram images. XG Boost with FFT features gave the maximum accuracy of 88%.     

Enhanced fuzzy-filtered neural networks for material fatigue prognosis

Although fuzzy-filtered neural networks (FFNN) have been used in pattern classification because of their unique characteristics in feature extraction, they usually have poor performance in forecasting applications due to their structure complexities especially in their consequent reasoning part. In this paper, an enhanced FFNN, EFFNN, is proposed for time series forecasting and material fatigue prognosis. A novel neural network scheme is developed to facilitate computation implementation. A new conjugate technique is proposed to improve training efficiency. The effectiveness of the developed EFFNN scheme and the related training technique is demonstrated by a series of simulation tests. The EFFNN is also implemented for material fatigue prognosis. Test results show that the developed EFFNN predictor is an effective forecasting tool; it can capture system dynamics effectively and track system characteristics accurately.     

Holographic antenna concept, analysis, and parameters

The paper describes a new holographic antenna concept that uses a diffraction pattern (hologram) formed on a dielectric substrate and fed by a surface wave. Analytical models and necessary design tools have been developed to investigate the feasibility of this new concept. A demonstration prototype antenna was designed, fabricated, and tested, and the measured radiation patterns at 35 GHz showed good agreement with the theoretical prediction.     

Ring of Masters (ROM): A new ring structure for Bluetooth scatternets with dynamic routing and adaptive scheduling schemes

This paper attempts to address the scatternet problem in Bluetooth through a comprehensive approach. We propose a new decentralized ring structure to combat the formation of traffic bottlenecks. The adopted construction protocol ensures flexibility of node selection and a good level of fault tolerance. The routing protocol combines both simplicity and robustness by taking advantage of the ring structure and relying on the collective memory of piconets to make forwarding and discarding decisions. The intra- and inter-piconet scheduling algorithm, called ROM adaptive scheduling (RAS), dynamically allocates time slots and is responsive to the varying workload conditions. We demonstrate, through analysis and simulations, that the various components of ROM yield a system that has good performance in terms of throughput, latency, delivery, and link utilization.     

Swelling behavior of pH‐ and temperature‐sensitive copolymers containing 2‐hydroxy‐ethyl methacrylate and N‐vinyl‐2‐pyrrolidone crosslinked with new crosslinkers

Copolymers of 2‐hydroxyethyl methacrylate (HEMA) and N‐vinyl‐2‐pyrrolidone (VP) and homopolymers of HEMA and VP were crosslinked in the presence of different mol% of melamine trimethacrylamide (MMAm) and melamine triacrylamide (MAAm) as crosslinkers by bulk radical polymerization. The resultant xerogels were characterized by extracting the soluble fractions and measuring the equilibrium water content. Lower critical solution transition temperatures (LCST) were measured by DSC. The properties of crosslinked HEMA and VP copolymers, VP and HEMA series were evaluated in terms of compositional drift of polymerization, heterogeneous crosslinking, and chemical structure of the relevant components. Soluble fractions of the crosslinked networks were reduced by varying the MAAm and MMAm concentrations. The influence of environmental conditions such as temperature and pH on the swelling behavior of these polymeric gels was investigated. The swelling behaviors of the resulting gels show pH sensitivity. This behavior is explained on the basis that amide groups of VP or crosslinkers could be hydrolyzed to form negatively charged carboxylate ion groups in the produced networks in response to an external pH variation. Copyright © 2004 Society of Chemical Industry     

Microstructure,fluidity, and mechanical properties of semi-solid processed ductile iron

This research is directed towards studying the effect of semi-solid processing (using cooling plate technique) on the microstructure, fluidity, and mechanical properties of ductile iron (DI). Sand mold castings with constant width of 25 mm and length of 150 mm with the thicknesses of 6, 12, 18, and 25 mm were used in this study. Microstructure, fluidity, and tensile strength properties were investigated as a function of fraction of solid. The results indicated that by increasing fraction of solid microstructure becomes finer and more globular. However, increasing primary fraction of solid increases the cementite content in the matrix. Above a certain fraction of solid (f _s = 0.28, f _s = 0.1, and f _s = 0.05 for 25, 18, and 12 mm wall thickness, respectively), the fluidity of semi-solid processed DI decreases steeply. For low fraction of solid (f _s ≤ 0.15), increasing the fraction of solid results in an increment in the tensile strength, comparing with the ordinary DI due to the fine and globular structure formation. Any further increment of fraction of solid (f _s > 0.15) leads to the cementite increment and gas porosity formation, consequently the tensile strength decreased. The fraction of solid of DI and casting wall thickness should be considered in order to obtain the best combination of microstructure, fluidity, and mechanical properties of semi-solid processed DI.