With ongoing advancements in natural language processing (NLP) and deep learning methods, the demand for computational and memory resources has considerably increased, which signifies the determination of efficient and compact models in resource-constrained environments. A comprehensive overview of the most recent advancements in pruning and quantization methods for deep neural networks is provided in this paper. Numerous cutting-edge techniques that harness the complementary advantages of pruning and quantization have been analyzed, highlighting their effectiveness in reducing model size, enhancing computational efficiency, and minimizing memory usage. These techniques include Quantization and Sparsity Aware Fine Tuning, Compression Learning by In-Parallel Pruning-Quantization, GroupReduce, Quantization-Pruned Attention, Structured Pruning, Normalized Linear Quantization (Prune and NLQ), Quantization and Pruning for Sentiment Analysis, an Automatic mixed-precision Quantization approach for BERT compression (AQ-BERT), Mixed Precision Quantization, Unstructured Pruning, and Quantization, and Magnitude Pruning. The datasets utilized, models employed, and outcomes achieved are taken into account within this research. The utilization of pruning and quantization techniques across diverse deep-learning tasks, NLP, and sentiment analysis are also discussed. Moreover, issues such as compatibility with hardware configurations, optimization complexities, accuracy degradation, and other constraints have been analysed. Several challenges and limitations of weight or unit pruning that are utilized for optimizing memory and quantization techniques to enhance precision are explored. The in-depth analysis of these state-of-the-art techniques and experiments provides a broad understanding. Furthermore, strategies to effectively reduce the computational and memory demands of neural networks without compromising their performance are also analysed.

A wideband bandstop frequency selective surface (FSS) for electromagnetic interference reduction applications is presented for S, C and X bands. The proposed FSS is made of convoluted square and circular loop elements which are employed on the opposite surfaces of RO3010 substrate. The overall dimensions of the FSS are reduced to 0.15λ at the center frequency as compared to the conventional loop elements with an overall decrease in the size of more than 90% at the center frequency. It has a bandwidth of 9 GHz to reduce the harmful effects on the human body due to electromagnetic interference (EMI) caused by radio transceivers. It can also be employed as a sub-reflector to enhance the gain and bandwidth of the antennas. Furthermore, it has many advantages in comparison to the designs presented in the latest research. For example, it is low profile, fractional bandwidth is enhanced up to 120%, ensures better angular stability for transverse electric (TE) as well as transverse magnetic (TM) polarized waves. Moreover, an average signal attenuation of more than 30.60 dB and 19.5 dB is ensured in the entire band for TE and TM modes, respectively. Simulation results are obtained using high-frequency structure simulator (HFSS) and validated through experimental results.

Low Power Wide Area Network (LPWAN) technologies have been exponentially growing because of the tremendous growth of the Internet of Things (IoT) devices across the globe. Several LPWAN technologies have been utilized by the researchers to address certain issues like increased number of collisions, retransmissions, delay, and energy consumption. However, Long Range Wide Area Network (LoRaWAN) is the most suitable and attractive technology in terms of delay optimization, low cost and efficient energy consumption. The main issue which arises in LoRaWAN is because of its high packet drop rate due to collision. The reason behind this packet drop rate is the MAC scheme known as Pure Aloha used by LoRaWAN for the transmission of the frames. Long Range (LoRa) End Devices (EDs) initiate communication with Pure Aloha that leads to a high number of retransmissions. These retransmissions further enhance the delay in LoRa networks. This paper aims to optimize the delay in LoRaWAN by using an Adaptive Scheduling Algorithm (ASA) with an unsupervised probabilistic approach called Gaussian Mixture Model (GMM). By using ASA with GMM, the retransmissions are reduced which optimizes the delay in LoRaWAN. The results show that in our approach, Packet Collision Rate (PCR) is reduced by 39% as compared to conventional LoRaWAN. In addition, the Packet Success Ratio (PSR) is also increased by 39% as compared to the conventional LoRaWAN and Dynamic Priority Scheduling Technique (PST). Further, the delay is optimized by 91% and 79%. This research could be effective for the environments where the critical data of patients need to be sent with optimised retransmissions and minimum delay towards gateways.

Regulating the depth of hypnosis during surgery is one of the major objectives of an anesthesia infusion system. Continuous administration of Propofol infusion during surgical procedures is essential but it unduly increases the load of an anesthetist working in a multitasking scenario in the operation theatre. Manual and target controlled infusion systems are not appropriate to handle instabilities like blood pressure and heart rate changes arising due to interpatient and intrapatient variability. Patient safety, large interindividual variability, and less postoperative effects are the main factors motivating automation in anesthesia administration. The idea of automated system for Propofol infusion excites control engineers to come up with more sophisticated systems that can handle optimum delivery of anesthetic drugs during surgery and avoid postoperative effects. A linear control technique is applied initially using three compartmental pharmacokinetic and pharmacodynamic models. Later on, sliding mode control and model predicative control achieve considerable results with nonlinear sigmoid model. Chattering and uncertainties are further improved by employing adaptive fuzzy control andH∞control. The proposed sliding mode control scheme can easily handle the nonlinearities and achieve an optimum hypnosis level as compared to linear control schemes, hence preventing mishaps such as underdosing and overdosing of anesthesia.

Deep neural networks (DNN) are in high demand because of their widespread applications in natural language processing, image processing, and a lot of other domains. However, due to their computational expense, over-parameterization, and large memory requirements, DNN applications often require the use of substantial model resources. This strict requirement of latency and limited memory availability are hurdles in the device deployment of these technologies. Therefore, a common idea could be to mitigate the DNN-based models’ size without any performance degradation using different compression techniques. During the last few years, a great deal of progress has been made in the field of Natural Language Processing (NLP) using deep learning approaches. The objective of this survey paper is to offer a thorough overview of the various pruning methods applied in the context of NLP. In this paper, we review several recent pruning-based schemes used for converting standard networks into their compact and accelerated versions. Traditionally, pruning is a technique for improving latency, reducing model size, and computational complexity which is a viable approach to deal with the above-mentioned challenges. In general, these techniques are divided into two main categories: structural and unstructured pruning methods. Structural pruning methods are further classified into filter, channel, layer, block, and movement pruning. Whereas, neuron, magnitude-based, and iterative pruning lie in the category of unstructured pruning. For each method, we discuss the related metrics and benchmarks. Then recent work on each method is discussed in detail, which provides insightful analysis of the performance, related applications, and pros and cons. Then, a comparative analysis is provided to analyze the differences among approaches. Finally, the paper concludes with possible future directions and some technical challenges.

In this treatise extrinsic information transfer (EXIT) charts are used to design binary self-concatenated convolutional codes employing iterative decoding (SECCC-ID) for communicating over both uncorrelated Rayleigh fading and additive white Gaussian noise (AWGN) channels. Recursive Systematic Convolutional (RSC) codes are selected as constituent codes, an interleaver is used for randomising the extrinsic information exchange of the constituent codes, while a puncturer assists us in increasing the achievable bandwidth efficiency. At the receiver, self-iterative decoding is invoked for exchanging extrinsic information between the hypothetical decoder components. The convergence behaviour of the decoder is analysed with the aid of bit-based EXIT charts. Finally, we propose an attractive system configuration, which is capable of operating within about 1 dB of the information-theoretic limits.