Showing papers by "Jayanta Kumar Datta published in 2022"

Neuromorphic Spectrum Occupancy Learning in Cognitive Cloud Radio Access System

Abstract: This paper presents a neuromorphic spectrum occupancy learning using convolutional neural networks and long short-term memory, in a cognitive radio enabled cloud radio access system. Cloud radio access networks can prove useful in future generation wireless communication systems, because of their distributed signal processing capability. Owing to its excellent noise immunity property, cyclostationarity-based spectrum sensing is utilized as the method to detect the active sub-bands at the baseband unit. However, the accuracy of sensing is corrupted due to impairments, such as chromatic dispersion, caused by the optical fiber front-haul channel. Hence, application of deep learning techniques like convolutional neural networks and long short-term memory are necessary to compensate for the front-haul channel. Our simulation results indicate that the proposed method can lead to improved signal detection in presence of optical fiber impairment in cloud radio system.

Checkpoint-Based Round-Robin Scheduling Technique Toward Fault-Tolerant Resource Management in Cloud Computing

Abstract: Cloud computing framework is growing with importance in recent times. Public cloud is more challenging than private cloud. Public cloud framework has inherent challenges of security issues, service reliability, and time-constrained requirement for providing service on demand. Resource management is an important aspect under public cloud. Efficient allocation of resources across different service peers or servers is an important aspect toward error management and fault management. This work proposes a modified round-robin mechanism for resource scheduling with multiple checkpoints which take cares of error handling and fault management. Proposed method has been tested on different benchmarks and establishes its robustness.

UWB-OFDM System Model for Breast Cancer Detection

Abstract: This research paper proposes a communication system that can be applied in diagnosis through medical imaging. The objective is to spot abnormalities in breasts with a high level of precision, allowing for diagnostics in the early stages of potential breast cancer. The system was theoretically modeled and simulated with the help of computational calculations. This solution gathers characteristics from different technologies and standards that were combined to model an efficient system which meets the necessary requirements and functions for a feasible and viable proposal for its future implementation. The main contribution of this work is identified in the experimental results through the application of the finite difference method in the time domain (FDTD) where it is shown how a malignant tissue (tumor) reflects to a greater extent the expenditure that falls on said region in compared to healthy tissue made up of fibrous tissue, connective, glandular and adipose tissue. It is also important to highlight the spectral and energy efficiency of OFDM systems, characteristics that directly affect the quality level of the systems. Finally, a simulation of the image formation is performed using an innovative method of spatial filtering under the concept of beamforming.

Deep Neural Network aided Sparse Bayesian Learning for Wireless Access Channel Estimation in mm-Wave Massive MIMO Cloud Radio Access Network Systems

Abstract: Cloud Radio Access Network systems with mmWave Massive MIMO framework can be considered as a potential candidate for next generation wireless communications due to its promise of increased spectral efficiency and distributed signal processing capability. State-of-the-art compressive sensing algorithms like sparse Bayesian learning can exploit the inherent sparsity of the mm-Wave wireless channels to estimate the channel connecting the remote radio head and the user equipment in the wireless access link. The performance of the sparse Bayesian learning based channel estimation can be adversely affected by impairments due to optical fiber based front-haul channel and quantization noise. As a result, it is necessary to compensate for the performance degradation by applying methods which can combat the effects of the front-haul channel. Contemporary research has demonstrated the capability of deep learning algorithms in signal enhancement under low signal-to-noise ratio conditions, such as hybrid beamforming design, channel estimation as well as feedback of channel state in heterogeneous multi-antenna wireless systems. Motivated by their de-noising and signal prediction capabilities, convolutional long short term memory networks are employed in this work to jointly remove the quantization noise and optical fiber impairment due to the front-haul channel, which can improve the performance of sparse Bayesian learning in estimating the wireless access channel at the base-band processing unit. Computer simulation results show that the proposed methodology performs well under low signal-to-noise ratio conditions.

Speech Enhancement using Multi-Microphone Array based Source Separation and Deep Learning

Abstract: Speech Enhancement using tensor decomposition-based source separation and convolutional, bidirectional recurrent neural network (CNN-biRNN) architecture is investigated in this paper. An acoustic receiver comprising uniform linear array (ULA) of microphone sensors is considered, where the ULA performs CANDECOMP/PARAFAC (CP) tensor decomposition to separate the individual speech source signals from the received mixture of multi-channel signals, followed by single channel de-reverberation by a variant of the CNN-biRNN referred to as DenseNet-biLSTM to enhance the target speech signal-of-interest (SOI). While the source separation module based on CP-tensor decomposition is responsible for extracting the target SOI, the subsequent deep learning framework based on DenseNet-biLSTM enhances the extracted SOI by performing de-noising and de-reverberation. It is demonstrated by computer simulations that the proposed approach leads to good performance under multiple interfering speakers and reverberation.