Scaling copper interconnects below the 7-nm technology node results in severe resistivity increase due to enhanced electron scattering, necessitating alternative interconnect materials. This work proposes borophene nanoribbons (BNRs) and presents a novel analytical models to evaluate their intrinsic mean free path (MFP), resistance, and effective resistivity under ideal smooth-surface conditions. The model captures quantum transport effects and Fermi-energy-dependent conduction channels for armchair and zigzag BNRs and is benchmarked against graphene and copper. At the 7-nm node and a Fermi energy of 0.3 eV, borophene exhibits an intrinsic MFP comparable to graphene and nearly three orders of magnitude higher than copper. Additionally, borophene achieves up to an 85.5% reduction in effective resistivity compared to copper, while maintaining competitive performance relative to graphene. These findings demonstrate that Fermi-energy tuning significantly enhances borophene’s transport performance, highlighting its strong potential as a scalable and energy-efficient on-chip interconnect material for advanced CMOS technologies.

In planar copper interconnect configurations, surface roughness plays a critical role in determining conductor losses, especially at nanoscale dimensions. This effect becomes most significant in high-performance many-core systems, where interconnect performance often becomes the primary bottleneck. To overcome these drawbacks, in this work, we introduce multilayer borophene nanoribbon (MLBNR) interconnects and develop analytical equivalent circuit models for resistance, capacitance and inductance in armchair and zigzag configurations. Here, the effective mean free path, scattering resistance, kinetic inductance, and quantum capacitance for borophene interconnects at different technology nodes are calculated for the armchair and zigzag cases and compared with graphene. The resistances to top and side contact and inductance and capacitance have also been calculated for the MLBNR interconnect and compared with those of graphene and copper. Simulation is also performed using the industry-standard field electromagnetic (EM) solver to validate the accuracy of our proposed analytical model. In this work, key performance metrics such as delay, energy, and the energy delay product are also calculated. Our findings reveal that the parameters of the borophene nanoribbon interconnects are comparable to those of graphene and significantly outperform those of copper, highlighting the potential of borophene as a promising material for future nanoscale interconnect applications.

The paper presents borophene nanoribbons (BNRs) as a strong candidate for next-generation on-chip interconnects, addressing the scaling, surface roughness, and thermal limitations of copper and the performance constraints of graphene at sub-nanometer technology nodes. Quantum equivalent-circuit models and an analytical mean free path formulation demonstrate that BNRs exhibit higher normalized conductance and lower effective resistivity, particularly with Fermi energy tuning in the range of 0-0.4 eV. Extending this analysis to multilayer BNRs, temperature-aware analytical models for armchair and zigzag configurations reveal low resistance, favorable inductance, and capacitance over a wide temperature range (250-500 K) at the 7 nm node. Benchmarking against graphene and conventional copper interconnects shows that MLBNRs deliver comparable or superior electrical and thermal performance, establishing borophene as a highly promising material for future nanoscale interconnect applications.

In this work, we focus on enhancing performance at the most advanced technology nodes by addressing key challenges like conductances and resistances in traditional VLSI on-chip copper interconnects. To achieve this, we introduce a novel interconnect material: borophene. Borophene, a crystalline form consisting of a monolayer of boron atoms, was theoretically predicted in the mid-1990s and was first synthesized experimentally in 2015. We present equivalent circuit models for interconnects using Borophene Nanoribbons (BNRs), examining both armchair and zigzag configurations. The conductance and resistance of these BNR configurations are benchmarked against those of armchair and zigzag graphene, as well as conventional copper wires. The normalized conductance of borophene and graphene is also analyzed. Our findings reveal that the conductance and normalized conductance of borophene with smooth edges are comparable to graphene, offering greater strength and flexibility, while significantly outperforming copper. The use of borophene in interconnects demonstrates substantial improvements in performance by considerably reducing resistance compared to graphene

Human Action Recognition (HAR) is crucial for monitoring elderly individuals living alone, ensuring timely assistance during distress. This paper presents a HAR framework leveraging image processing and artificial intelligence to enhance performance across key benchmarks, including accuracy, computation speed, memory efficiency, and practical usability. By utilizing skeletal data, recurrent neural networks, and gait classification techniques, the approach achieves improved results on RGB video inputs. The proposed method reduces computation time significantly using Divide and Conquer, Sliding Window, and spatial aspects of Long Short-Term Memory (LSTM) architecture while maintaining low resource requirements for native device compatibility. Testing on the Fall Detection and NTU-RGB datasets demonstrates its effectiveness in handling real-time detection with reduced processing times compared to existing methods.

This paper presents a compact multiband monopole antenna based on substrate integrated waveguide (SIW) technology, designed for millimeter-wave applications including Kaband and 5G FR2 systems. The proposed antenna features a crescent-shaped radiating patch with a slot-fed configuration, enabling the excitation of four distinct resonant modes at 30.63 GHz, 32.21 GHz, 36.83 GHz, and 39.53 GHz. The antenna achieves impedance bandwidths of 5.50% (30.03-31.74 GHz), 3.02% (32.65-33.70 GHz), 5.00% (35.64-37.47 GHz), and 3.17% (38.75-40.00 GHz), respectively. Directional radiation patterns are observed across all bands, with side lobes merging into the main lobe as frequency increases. The SIW-based design ensures low insertion loss, compact form factor, and enhanced radiation efficiency. The reflection coefficient remains below -10 dB over all operational bands, indicating good impedance matching. Due to its planar structure, stable multiband performance, and suitability for mass production, the antenna is well-suited for next-generation mmWave communication and sensing applications.

As interconnect scaling pushes the limits of traditional copper, Multi-Layer Graphene Nanoribbon (MLGNR) has emerged as a promising alternative. However, the optimal insertion of repeaters in MLGNR interconnects is a computationally intensive task, hindering rapid design space exploration. This paper presents a novel surrogate modeling framework that accelerates this process by leveraging a synergistic combination of Particle Swarm Optimization (PSO) and Artificial Neural Networks (ANN). Our method uses three ANNs, one to translate wire design into electrical parameters, another to predict transistor behavior, and a third to fully replace the slower PSO algorithm. Our three-stage approach utilizes a first ANN (ANN1) to map interconnect geometry to Per Unit Length (PUL) parameters, a second (ANN2) to model FinFET driver parasitics from technology parameters, and a third (ANN3) to replace the iterative slower PSO algorithm. Trained on a dataset of 8,000 configurations reflecting realistic process variations, the framework demonstrates exceptional performance. The ANN-based surrogates achieve normalized RMSE values below 3% for parasitic prediction. Most notably, the ANN3 surrogate achieves a realistic speedup of over 300x compared to a direct PSO implementation while maintaining the Power-Delay Product (PDP) prediction error to less than 1%. This enables near-instantaneous prediction of optimal repeater configurations, making it a viable tool for large-scale integrated circuit design.

This work proposed a wideband concentric split ring resonator frequency reconfigurable antenna using the machine learning approach for 5G (sub-6 GHz) and IEEE 802.11ba/Be applications. The concentric split ring resonator and defected ground structures are employed to achieve wide bandwidth. The proposed antenna covers 1-1.2 GHz, 1.2-1.5 GHz, 1.5-1.7 GHz, 3.8-5.2 GHz and 4-5.3 GHz frequency bands. The proposed reconfigurable antenna offers excellent tuning range (99.18%) and total spectrum (99.80%) by using two Positive-Intrinsic-Negative diode (PIN) diodes (with a maximum gain of 6.2 dBi and maximum radiation efficiency of 96%). Six regression ML algorithms such as K-nearest Neighbour (KNN), Decision Tree (DT), Random Forest (RF), Extreme Gradient (XG) Boost, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are employed to optimize the antenna design. Among all ML algorithms, Random Forest (RF) provides the highest accuracy i.e. 99.30% with maximum R2 score and minimum mean square error (MSE) and execution time for all switches configurations. Additionally, 10-fold cross-validation, paired t-test techniques and SHAP analysis are employed to ensure the accuracy of RF model. The antenna characteristics have been investigated using the Ansys HFSS simulator, and it is compared with the experimental results, which found to be in good agreement. These results indicates that the proposed antenna is best suitable for single-band and double-band sub-6 GHz applications such as Global Positioning System (GPS), mobile phones, Wi-Fi, WLAN, WiMAX, 5G and IEEE 802.11 ba/Be communication applications.

In this article, a compact dual port Multiple Input Multiple Output (MIMO) Coplanar Waveguide (CPW) fed Ultra-Wideband (UWB) antenna for the next generation wireless communication using Machine Learning (ML) optimization is presented. It is designed on an FR4 epoxy substrate of 16 × 30 mm2 with a thickness of 1.6 mm. A bandwidth of 8.7 GHz (2.78–11.48 GHz) is achieved. It is used for 5G New Radio Bands (n78/n46/n47/n77/n48/ n79/n96), Wi-Fi 5, DSRC, Wi-Fi 6, and Vehicle to Infrastructure (V2I), Vehicle to Vehicle (V2V), and Vehicle to Network (V2N) in the entire operating band. The proposed antenna is optimized through the different ML algorithms Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), Random Forest (RF), K-Nearest Neighbor (KNN), and Decision Tree (DT). The DT ML algorithms provide a higher accuracy of 99.92% compared to the remaining ML algorithms. A test and fabrication of the suggested antenna is also done. The findings showed that there was a good correlation between measurement and simulation data for several parameters, including S-parameters, radiation patterns, and MIMO parameters like diversity gain (DG), channel capacity loss (CCL), mean effective gain (MEG), envelope correlation coefficients (ECC), and total active reflection coefficients (TARC). Hence, it is suitable for next-generation wireless communication.

Vehicular Ad Hoc Networks (VANETs), a subclass of Mobile Ad Hoc Networks (MANETs), enable communication among vehicles and between vehicles and roadside infrastructure to enhance traffic safety, efficiency, and passenger comfort. However, VANETs face limitations in terms of geographic coverage and performance during dynamic or emergency conditions. The Internet of Vehicles (IoV) extends VANET capabilities through cloud-based communication, offering real-time information on vehicle speed, location, and route. Despite this advancement, both VANET and IoV encounter challenges related to scalability, reliability, and mobility management. This paper presents a hybrid VANET-IoV framework designed to enhance communication reliability and security in largescale vehicular environments. Network performance is assessed through simulations conducted in NS-2.35 using performance metrics such as average throughput, packet delivery ratio, end-to-end delay, and residual energy. The study evaluates and compares three well-known topology-based routing protocols-AODV, DSDV, and DSR-under varying node densities and vehicle speeds. The proposed approach demonstrates improved network adaptability and efficiency over conventional VANET models.

The Advanced Peripheral Bus (APB4) protocol, a component of the AMBA 4 specification, is designed to connect low-bandwidth peripherals to high-performance system-on-chip (SoC) designs. This paper presents the design, implementation, and verification of the APB4 protocol using Verilog HDL and SystemVerilog-based Universal Verification Methodology (UVM). We extend the standard APB4 protocol by incorporating power gating techniques and burst-mode support to enhance power efficiency and throughput. Simulation and synthesis were performed using Xilinx Vivado and Synopsys VCS, with verification data showing 100% functional coverage and zero protocol violations. Simulation results using ModelSim and Synopsys VCS confirm accurate protocol behavior, while synthesis using Xilinx Vivado and power analysis via XPower Analyzer demonstrate a 66% reduction in dynamic power and 7% area optimization compared to prior APB implementations. This work positions the APB4 protocol as a viable low-power solution for energy-constrained SoC designs, providing a reusable and modular verification infrastructure aligned with modern digital design flows.

With the evolution of Machine Learning, the Internet of Things (IoT), and Big Data Technologies, digital data has increased exponentially. To handle and process such a large bunch of data, high-performance computers are used across various fields. One of the fields has been the financial capital market of stocks, bonds, commodities, foreign exchange, and cryptocurrencies, where supercomputers essentially trade securities with high computational ability and intelligent algorithms. Large financial institutions with significant capital spend a lot of money on programmers and data analysts to develop the best accuracy trading algorithms to drive the overall market. A novice trader or investor with less to no experience in financial markets feels it difficult to search for good trades or stocks to invest their hard-earned money on a short to long-term time horizon. They rely on expert advice for stock recommendations and sometimes end up making significant losses. This paper focuses on developing a universal trend trading indicator that can analyze and predict the overall future trend of any stock, bond, commodity, forex, or cryptocurrency with the highest possible profitability. The historically traded extensive dataset of stock prices and investment reports of large financial institutions worldwide are gathered. Various machine learning and decision-making models are employed to perform technical and fundamental analysis across multiple securities. The output of the trend trading indicator is displayed on charting platforms, which can provide entry-exit levels at which even novice investors can decide where to invest their money. Multi timeframe analysis is deployed to predict short-term, mediumterm, and long-term overall trends, thus increasing the output accuracy. The indicator is helpful for all kinds of retail traders and investors worldwide who struggle to earn profits from financial markets. Our proposed system was able to achieve a profitability of 86.28% annual returns. The entire system, along with the trading orders, is automated so that anyone can earn extra passive income every month from the stock market.

This article presents a dual-band miniaturized Composite Right-Left-Handed Transmission Line (CRLH-TL) in an open-ended terminal, employing the Machine Learning (ML) technique. The CRLH-TL antenna is designed on the FR4 epoxy substrate. The substrate size is 0.31 lambda 0 x 0.09 lambda 0, where lambda 0 is the free space wavelength. The proposed antenna offers dual-band functionality with resonant frequencies at 2.49 GHz and 5.33 GHz. The measured dualband impedance bandwidths are 14.46 % and 14.74 %, with gains of 0.85 dB and 1.67 dB, and radiation efficiencies of 91.78 % and 95.45 % obtained at resonating frequencies of 2.49 GHz and 5.33 GHz, respectively. The proposed antenna also offers bipolar-type radiation patterns in the E-plane, and omnidirectional radiation patterns in the H-plane, along with compactness and constant gain. Several ML methods, including Random Forest (RF), Decision Tree (DT), K-Nearest Neighbour (KNN), Extreme Gradient Boosting (XGB), and Artificial Neural Network (ANN), are used to optimize the antenna. Compared to other ML algorithms, RF ML techniques estimate reflection coefficient S11 with an accuracy of above 98 %. The proposed antenna is utilized in WLAN (5.15-5.35, 5.47-5.725 GHz) and Wi-MAX (5.2-5.8 GHz) microwave applications.

SummaryIn this article, a two‐port multiple‐input multiple‐output (MIMO) hybrid rectangular dielectric resonator antenna (DRA) with machine learning (ML) approach for the n261 5G New Radio (NR) application is presented. The proposed antenna is designed on an RT/duroid 5880 (Ɛr = 2.2) substrate activated by 50 Ω, L‐shaped microstrip slot feeds beneath both DRAs. The isolation is more than 19 dB, and the gain is 10 dBi in the operating frequency range. The proposed antenna is optimized through knowledge‐based neural networks (KBNN), artificial neural networks (ANNs), and ML. The optimal design parameters of the proposed antenna are accomplished using the ML optimization approach, which includes ridge regression, ANNs, and KBNN. KBNN ML techniques provide 96.88% accuracy and correctly predict the S‐parameters of the proposed antenna. The MIMO diversity parameters like envelope correlation coefficient (ECC), diversity gain (DG), total active reflection coefficient (TARC), and channel capacity loss (CCL) are calculated and found within the limits. Hence, the proposed antenna is used for 5G NR mm‐wave application.

One of the most chemically adaptable elements is boron which is found in the periodic table between two groups, i.e., metals and nonmetals and may create more than 16 polymorphs that are bulk and made of connected boron polyhedra. Given that boron and carbon are comparable elements, it has been questioned whether two-dimensional (2D) boron could serve as a conceptual starting point for the construction of other boron nanostructures. Using boron as fundamental building blocks, boron nanosheets were synthesized known as borophenes. Borophene is found to be a crystalline form of atomic monolayer boron which was theoretically first predicted in mid-1990s and experimentally synthesized very recently in 2015. In this work, we studied both armchair and zigzag formation of borophene and presented a comparative analysis of their minimum sub-band energy, effective mean free path [Formula: see text], number of conduction channels [Formula: see text], scattering resistance per unit length. The [Formula: see text] for armchair BNR is 3,2,1 for 22[Formula: see text]nm, 13[Formula: see text]nm, 7[Formula: see text]nm, respectively, which is comparatively more than zigzag BNR. We later proposed Top-Contact BNR (TC-BNR) and Side-Contact BNR (SC-BNR). Our analysis shows that SC-BNR offers [Formula: see text] less resistance compared to TC-BNR and it is of the order of SC-GNR. Further, if we compare with copper interconnects, BNR is better in terms of performance and copper can be replaced with BNR due to high bulk mean free paths 300[Formula: see text]nm and 400[Formula: see text]nm compared to copper’s 40[Formula: see text]nm.

In this chapter, we will look at how artificial neural network (ANN) models may be used to design on-chip interconnects for integrated circuits and systems. Conduct of on-chip copper (Cu) interconnect networks is restricted by dispersive processes such as grain boundary scattering, surface roughness scattering, top/bottom surface, and sidewall scattering when minimum interconnect width scales below the 22 nm mark. The resistance of the interconnects, measured over a unit of length, is greatly inflated over the bulk value due to these scattering phenomena. Enhanced signal attenuation, delay, and power loss are all consequences of such extremely resistive interconnects. Augmenting to causing discontinuities in the interconnect line, the migration of copper ions into the dielectric layer increases dielectric conductivity and leakage losses. To prevent copper ions from diffusing away from the copper conductor, a barrier layer is often positioned around it. Recently, many studies have investigated the potential of employing graphene nanoribbons as a replacement barrier material for Cu interlinks. At ambient temperature, the mean free route for electrons in graphene nanoribbons is much greater than in copper. Therefore, in addition to the copper conductor, the barrier layer provides extra low-resistance routes for conducting electrons. It is becoming more important to do SPICE-based simulations of hybrid Cu-Graphene on-chip interconnect networks due to their rising popularity. Simulations of interconnects using SPICE are notoriously time-consuming and computationally intensive. Using surrogate models is one way to deal with the computational overhead of exploring design space. Due to their capacity to mimic the extremely nonlinear input–output correlations of electronic packaging systems, surrogate templates based on machine learning (ML) regression are now quite sought-after. We will also collate the results of our ML-based models to those of our comprehensive EM and SPICE simulations.

This paper reports a novel co-design methodology for signal integrity analysis considering thermal effects. Our analysis focuses on practical high-speed interconnect topologies. To ensure reliable and efficient system design, we introduce an efficient electrical-thermal methodology (EEM) for high-speed PCB interconnects. Using our proposed EEM, we perform electrical-thermal co-simulation to ensure efficient design and performance.

In this paper, a non-planer or 3D Co-planer waveg-uide (CPW) fed, four-port multi input multi output (MIMO) antenna for 2-20GHz ultra-wideband (UWB) applications is presented. Firstly, a single rectangular antenna element is designed. After that by arranging four such antenna elements in cubic order, a 3D MIMO antenna is designed. The proposed MIMO antenna design shows good isolation between its ports without using any decoupling structure. The diversity parameters of the designed antennas are evaluated by investigating Envelope correlation coefficient (ECC), Diversity gain (DG), Mean effective gain (MEG) and Total active reflection coefficient (TARC) values and all show satisfactory results for the entire (2-20GHz) band. This proposed 3D MIMO antenna design is suitable for WLAN, sub-6GHz, 5G mid band, radar and satellite applications.

In this paper, an accurate modeling of on-chip copper interconnects with surface roughness is performed considering the parametric variability. This modeling is highly accurate as per-unit-length parameters of the on-chip rough copper interconnects are extracted via full wave EM solver. Further, a space-mapped artificial neural network (ANN) is developed for accurate prediction of eye height and eye width from the geometrical and material parameters of the rough copper interconnects. The novel space-mapping ANN developed in this work is more efficient in terms of accuracy and requires fewer training samples when compared to conventional ANNs.