Alok Kumar

The nonlinear power amplifier (NPA) in a cognitive radio (CR) network can degrade sensing performance. While spectrum sensing primarily focuses on the receiver, modeling the transmitter's NPA is crucial to understand its impact on detection. This paper investigates spectrum sensing performance in CR networks assisted by intelligent reconfigurable surfaces (IRS), considering the impact of NPA distortions. A novel multiple‐input single‐output (MISO) IRS‐aided CR system, termed MICR, is proposed. The sensing performance of the proposed MICR system is analyzed in terms of the probabilities of false alarm and detection, considering the effect of IRS elements. The results are presented using receiver operating characteristic (ROC) curves. Furthermore, the impact of various system parameters such as the number of samples, number of IRS elements, IRS position, number of transmitting antennas, and phase shifts is analyzed. Additionally, the effects of line‐of‐sight (LoS) and non–line‐of‐sight (NLoS) propagation are evaluated. The ROC performance using different signal detectors is analyzed. The impact of interference, IRS overhead, and sensing energy on the proposed MICR system is also investigated. Extensive simulations demonstrate that IRS significantly improves the sensing performance of the CR network, both with and without NPA.

The integration of multiple-input multiple-output (MIMO) technology with reconfigurable intelligent surfaces (RIS) in Terahertz (THz) communication systems has emerged as a promising approach to address the challenges and exploit the opportunities in next-generation wireless networks. This technical reviewprovides a systematic state-of-the-art research and developments toward MIMO-based RIS-supported THz communication, systems focus on the potential research opportunities, challenges, and emerging applications of this innovative technology. Further, this paper explores the combined benefits of integrating MIMO with RIS to improve link reliability, along with the associated system-level design challenges. Furthermore, we discuss various aspects of MIMO-based RIS-supported THz communication, such as channel modeling, channel estimation, beamforming techniques, beam split effect resource allocation strategies, and performance evaluation metrics. Moreover, the role of artificial intelligence and machine learning (AI/ML) in the design of RIS-empowered THz wireless communication systems is also discussed.

Corporate libraries gathering business intelligence have to process an overwhelming stream of business news. Automatic categorization of these news articles based on their primary event (‘NewsType’) can significantly aid in better organization and disbursement. We propose an ensemble of a BiLSTM neural network and a Pre-trained Language Model (PLM) based zero-shot classification approach for solving the categorization task. We also show that fine-tuning the NLI model helps in better accuracy on the task. We evaluate our approaches on two datasets while comparing with multiple baselines.

Cognitive radio technology is a potential contender to fulfil the demand of spectrum/bandwidth for a large number of connected devices of the next-generation internet of things (IoT) network. Spectrum sensing is the crucial step of cognitive radio, and its performance is affected by the selection of sensing threshold and cooperation among multiple cognitive users (CUs). The accuracy of spectrum sensing results is a major concern in cognitive radio networks (CRN). Therefore, in this paper, we have minimized the Bayes risk which deals with the spectrum sensing error. In general, the ${k}$ -out-of- ${M}$ fusion rule is employed at fusion center (FC) in the cooperative CRN and optimal ${k}$ and ${M}$ with selection of spectrum sensing threshold results in minimum Bayes risk. Further, we have derived the expression for optimal value of CUs ( ${k}$ and ${M}^{{r}}$ ) in ${k}$ -out-of- ${M}^{{r}}$ rule in the cooperative spectrum sensing (CSS) at all signal-to-noise ratio (SNR) while employing different threshold selection approaches to minimize the Bayes risk at FC. The considered scenario employs multiple antennas at each CU where each CU report to the FC over the perfect/imperfect reporting channel with non-censoring ( ${M}^{{r}}={M}$ ) and censoring ( ${M}^{{r}}={M}^{{c}}$ ) approaches. Further, we have also validated the proposed results with recently reported literature and have shown that the existing expressions are the special case of the proposed generalized expressions.

Automatic question-answer pair generation is gaining importance because of the time being saved when compared to manual creation of questions. It not only saves time but also reduces the effort involved in the manual question generation process. It is useful in many fields such as school assignments, law practicing, self-assessments and many more. Our main objective is to create wh-type questions from a paragraph and find its accurate answer as well. This research work introduces a Question Answer Generation (QAG) system by using a deep learning approach for combining Answer Extraction (AE), Question Generation (QG) and Question Answering (QA) models. This research work aims to use a pre-trained language model - Bidirectional Encoder Representation from Transformers (BERT) and fine-tune it as per the proposed research objective.