Accurate 3D object detection from LiDAR data is vital for enhancing road safety, enabling efficient traffic management, and supporting reliable path planning in autonomous navigation systems. However, LiDAR point clouds suffer from inherent challenges such as sparsity, occlusion, and variations in point density, which can significantly impact detection accuracy. To address these challenges, we introduce 3DA-Net, a dual-attention-based network that integrates global and local context for enhanced 3D object detection. We begin by converting raw LiDAR point clouds into structured voxel representations, which are then processed through a hybrid dual-attention encoder. In this encoder, global attention modules capture high-level semantic dependencies across the entire scene, while local attention focuses on fine-grained geometric structures within neighborhoods. This dual-attention mechanism is further strengthened with point-wise and channel-wise attention, which enhances the model’s ability to capture both spatial and contextual information, which is essential for 3D perception. Our design incorporates a custom backbone for robust feature extraction from voxel-based pseudo-image representations, coupled with a feature pyramid network for efficient multi-scale feature learning. Evaluations on the KITTI dataset show that 3DA-Net achieves AP40 scores of 95.91% (easy), 94.78% (moderate), and 91.98% (hard) for cars in bird’s-eye view detection, and 95.83%, 94.58%, and 90.03% in 3D detection, outperforming strong LiDAR-based detection baselines. Significant improvements in pedestrian and cyclist detection further demonstrate the robustness and generalizability of our method in complex driving environments.

The evolution toward Sixth-Generation (6G) wireless networks demands high spectral efficiency, user connectivity, and efficient resource utilization. While dense macro base station deployment improves capacity, it also increases co-channel interference and operational costs. Femtocells serve as a cost-effective means to enhance indoor coverage and spectrum reuse. However, trust and performance concerns often discourage femtocell owners from sharing access, leading to under-utilization. Social ties can enable trusted access and help overcome this limitation. Additionally, Non-Orthogonal Multiple Access (NOMA) improves spectral efficiency by allowing multiple users to share a single subchannel, thereby increasing throughput. Motivated by this, we propose a social-aware, NOMA-enabled heterogeneous network framework to enhance the system throughput by integrating two layers of collaboration: (i) inter-operator collaboration and (ii) social ties among users. Furthermore, a novel social-aware Rate-Difference-Aware Pairing (RDAP) algorithm is proposed to pair the NOMA users. Subsequently, we derive the bounds on power allocation and Successive Interference Cancellation (SIC) imperfection to ensure that the NOMA user rates dominate their Orthogonal Multiple Access (OMA) counterparts. Through extensive simulations, we show the superiority of the proposed social-aware RDAP algorithm over the conventional and socialaware OMA/NOMA baselines, including existing NOMA pairing methods, in terms of throughput, energy efficiency, and spectral efficiency, while reducing user blocking. The impact of power allocation and SIC imperfections is also systematically evaluated.

Federated learning (FL) has emerged as a powerful collaborative learning approach that enables client devices to train a joint machine learning model without sharing private data. However, the decentralized nature of FL makes it highly vulnerable to adversarial attacks from multiple sources. There are diverse FL data poisoning and model poisoning attack methods in the literature. Nevertheless, most of them focus only on the attack’s impact and do not consider the attack budget and attack visibility. These factors are essential to effectively comprehend the adversary’s rationale in designing an attack. Hence, our work highlights the significance of considering these factors by providing an attacker perspective in designing an attack with a low budget, low visibility, and high impact. Also, existing attacks that use total neuron replacement and randomly selected neuron replacement approaches only cater to these factors partially. Therefore, we propose a novel federated learning minimal model replacement attack (FL-MMR) that uses optimal transport (OT) for minimal neural alignment between a surrogate poisoned model and the benign model. Later, we optimize the attack budget in a three-fold adaptive fashion by considering critical learning periods and introducing the replacement map. In addition, we comprehensively evaluate our attack under three threat scenarios using three large-scale datasets: GTSRB, CIFAR10, and EMNIST. We observed that our FL-MMR attack drops global accuracy to$\approx 35\%$less with merely 0.54% total attack budget and lower attack visibility than other attacks. The results confirm that our method aligns closely with the attacker’s viewpoint compared to other methods.

In a conventional Domain Adaptation (DA) setting, we only have one source and target domain, whereas, in many real-world applications, data is often collected from several related sources in different conditions. This has led to a more practical and challenging knowledge transfer problem called Multi-source Domain Adaptation (MDA). Several methodologies, such as prototype matching, explicit distance discrepancy, adversarial learning, etc., have been considered to tackle the MDA problem in recent years. Among them, the adversarial-based learning framework is a popular methodology for transferring knowledge from multiple sources to target domains using a minmax optimization strategy. Despite the advances in adversarial-based methods, several limitations exist, such as the need for a classifier-aware discrepancy metric to align the domains and the need to consider target samples' consistency and semantic information while aligning the domains. To mitigate these issues, in this work, we propose a novel adversarial learning MDA algorithm, MDAMA, which aligns the target domain with a mixture distribution that consists of source domains. MDAMA uses margin-based discrepancy and augmented intermediate distributions to align the domains effectively. We also propose consistency of target samples by confidence thresholding and transfer of semantic information from multiple source domains to the augmented target domain to further improve the performance of the target domain. We extensively experiment with the MDAMA algorithm on popular real-world MDA datasets such as OfficeHome, Office31, PACS, Office-Caltech, and DomainNet. We evaluate the MDAMA model on these benchmark datasets and demonstrate top performance in all of them.

Infant cry detection is the most important part of automatic cry analysis and diagnosis for continuous infant health and wellness monitoring under various background sounds. Accurate and reliable detection of infant cry events in continuous audio recording is still a challenge in the presence of various mixed sounds and a mixture of sound sources. This paper presents an infant cry detection (Infant-Cry-Detect) method based on sound spectrograms and long short-term memory (LSTM) neural network architecture. The method is evaluated using diverse cry sound patterns and six background sounds in terms of standard performance metrics, model size, and processing time. On the large database having 120931 cry and 149766 non-cry test segments, evaluation results show that the LSTM-based Infant-Cry-Detect method achieved a sensitivity of 98.93%, specificity of 99.26%, and overall accuracy of 99.12% and outperforms other six machine learning based methods. The model has a size of 6.7 MB and a latency of 0.517 ms for processing 1 second audio.

Autonomous vehicles increasingly rely on accurate three-dimensional (3D) object detection for safe navigation. While two-dimensional (2D) methods offer computational efficiency, the shift to 3D detection enhances precision in understanding environments. Point-based and voxel-based approaches are accurate but computationally intensive for onboard deployment. Pillar-based methods like PointPillars provide efficiency but may lack detection accuracy compared to voxel-based approaches. In this paper, we focus on enhancing the performance of PointPillars, a popular pillar-based detector, using LiDAR data. The proposed approach (PointBi-FPN) employs a bi-directional feature pyramid network (Bi-FPN) as a backbone, that aggregates multiscale features in the input data, providing a holistic view of the environment, which is crucial for detecting objects of varying sizes and distances accurately. Bi-FPN improves the model's understanding of complex scenes, making it more robust to occlusions. Through extensive experimentation on the KITTI dataset, the PointBi-FPN approach demonstrates better performance across all three detection benchmarks: BEV (Bird's Eye View), 3D (Three-Dimensional), and AOS (Average Orientation Similarity). Notably, the proposed approach exhibits significant improvements, particularly in accurately detecting objects labeled as “hard” difficulty.

In wireless networks, automatic modulation classification (AMC) is crucial for enabling intelligent signal demodulation, thereby enhancing the system’s adaptability across various applications. Concurrently, the rapid expansion of the Internet of Things (IoT) necessitates scalable network solutions with limited power consumption. Moreover, addressing the Nonline-of-Sight (NLoS) effects in IoT networks, intelligent reflecting surface (IRS) emerges as a promising, cost-effective technology. This article introduces a novel transformer-based deep recurrent architecture (TDRA) for AMC, tailored for IRS-assisted IoT networks, which significantly improves IoT Device (IoTD) performance in NLoS scenarios. In TDRA, the existing recurrent models, long-short-term memory (LSTM), and gated-recurrent-unit (GRU) are suitably revamped with a transformer-based approach and termed as transformer-based LSTM (T-LSTM) and transformer-based GRU (T-GRU). Numerical data sets are generated for IoT applications considering the seven widely used modulation types to train and test the proposed models. Comparative analysis with seven state-of-the-art deep learning models and five machine learning models for AMC demonstrates the superior performance of the proposed models across multiple metrics, including accuracy, R-squared-score, mean-square error, mean-absolute error, precision, recall, and F1-score. Further, the proposed models exhibit notable improvements under various conditions, such as optimized and random IRS phase shifts, with and without IRS-assisted IoT networks, different modulation sequence lengths, and fading channels. Additionally, the time complexity and processing time of the proposed models have been studied to test their suitability for IoTD. The simulation results indicate that the TDRA for AMC in IRS-assisted IoT networks achieves up to 87% higher accuracy compared to without IRS-assisted IoT networks. This significant enhancement underscores the potential of TDRA to revolutionize IoT networks by providing robust, efficient, and scalable solutions for real-world applications.

Federated learning (FL) has emerged as a powerful machine learning technique that enables the development of models from decentralized data sources. However, the decentralized nature of FL makes it vulnerable to adversarial attacks. In this survey, we provide a comprehensive overview of the impact of malicious attacks on FL by covering various aspects such as attack budget, visibility, and generalizability, among others. Previous surveys have primarily focused on the multiple types of attacks and defenses but failed to consider the impact of these attacks in terms of their budget, visibility, and generalizability. This survey aims to fill this gap by providing a comprehensive understanding of the attacks' effect by identifying FL attacks with low budgets, low visibility, and high impact. Additionally, we address the recent advancements in the field of adversarial defenses in FL and highlight the challenges in securing FL. The contribution of this survey is threefold: first, it provides a comprehensive and up-to-date overview of the current state of FL attacks and defenses. Second, it highlights the critical importance of considering the impact, budget, and visibility of FL attacks. Finally, we provide ten case studies and potential future directions towards improving the security and privacy of FL systems.

Recently, drones have attracted considerable attention for sensing hostile areas. Multiple drones are deployed to communicate and coordinate sensing and data transfer in the Internet of Drones (IoD) network. Traditionally, multi-hop routing is employed for communication over long distances to increase the network’s lifetime. However, multi-hop routing over large-scale networks leads to energy imbalance and higher data latency. Motivated by this, in this paper, a novel framework of energy-efficient and latency-aware data routing is proposed for Small-World (SW)-IoD networks. We started with an optimization problem formulation in terms of network delay, energy consumption, and reliability. Then, the formulated mixed integer problem is solved by introducing the Small-World Characters (SWC) into the conventional IoD network to form the SW-IoD network. Here, the proposed framework introduces SWC by removing a few existing edges with the least edge weight from the traditional network and introducing the same number of long-range edges with the highest edge weight. We present the simulation results corresponding to packet delivery ratio, network lifetime, and network delay for the performance comparison of the proposed framework with state-of-the-art approaches such as the conventional SWC method, LEACH, Modified LEACH, Canonical Particle Multi-Swarm (PMS) method, and conventional shortest path routing algorithm. We also analyze the effect of the location of the ground control station, the velocity of the drones, and the different heights of layers on the performance of the proposed framework. Through experiments, the superiority of the proposed method is proven to be better when compared to other methods. Finally, the performance evaluation of the proposed model is tested on a network simulator (NS3).

The lifetime of a UAV-assisted wireless network is determined by the amount of energy consumed by the UAVs during flight, data collection, and transmission to the ground station. Routing protocols are commonly used for data transmission in a communication network. However, because of the mobility of UAVs, using a routing protocol with a single communication technology results in higher delay and more energy consumption in a UAV-assisted wireless network. To overcome this, we propose two reinforcement learning (RL) algorithms, Q-learning and deep Q-network (DQN), for energy-efficient data transmission over a hybrid BLE/LTE/Wi-Fi/LoRa UAV-assisted wireless network. We consider BLE, LTE, Wi-Fi, and LoRa for communication over a UAV-GS link. The RL algorithms take any random network as input and learn the best policy to output the network with less energy consumption. The reward/penalty is chosen in such a way that the network with the highest energy consumption is penalized and the one with the lowest is rewarded, thereby minimizing total network energy consumption. Based on learning, it creates a hybrid BLE/LTE/Wi-Fi/LoRa UAV-assisted wireless network by assigning the best communication technology to a UAV-GS link. Further, we compare the performance of proposed RL algorithms with a rule-based algorithm and random hybrid scheme. In addition, we propose a theoretical framework for constructing hybrid network for both free space and free space multipath path loss models. We demonstrate the performance comparison of the proposed work with the conventional shortest path routing algorithm in terms of network energy consumption and average network delay using extensive results. Finally, the effect of the velocity of the UAV and the number of packets on the performance of the proposed framework is analyzed.

This paper presents two deep learning models using a multi-perspective convolutional neural network (CNN) for classifying objects in the context of intelligent transportation systems (ITS). The proposed model categorizes objects accurately, enabling them to make well-informed decisions in multi-object (such as Persons, Trucks, Motorbikes, Cars, and Cyclists.) detection in complex scenarios for automotive applications. The custom backbone model is designed based on experimentation with the VGG backbone network based on the VGG backbone network, incorporating a multilayer prediction head and custom feature extraction blocks for classifying multiple objects in complex scenes. The model is to extract abstract features and features at multiple scales with a custom-designed feature extraction backbone with multiple blocks. The proposed models are lightweight and require fewer computational resources for high classification performance. The automotive publicly available dataset with 19800 images and labels has been used. Results show that when we experimented with the VGG backbone CNN model, the classification accuracy of 99.64% is achieved, and on the other hand, the classification accuracy of custom backbone CNN is 99.46%. The performance of the proposed custom model is also compared to those of pre-trained benchmark models. The experimental findings presented in this paper show that the proposed models achieve higher accuracy than the pre-trained models.

Domain Generalization (DG) techniques have emerged as a popular approach to address the challenges of domain shift in Deep Learning (DL), with the goal of generalizing well to the target domain unseen during the training. In recent years, numerous methods have been proposed to address the DG setting, among which one popular approach is the adversarial learning-based methodology. The main idea behind adversarial DG methods is to learn domain-invariant features by minimizing a discrepancy metric. However, most adversarial DG methods use 0-1 loss based $\mathcal{H}\Delta\mathcal{H}$ divergence metric. In contrast, the margin loss-based discrepancy metric has the following advantages: more informative, tighter, practical, and efficiently optimizable. To mitigate this gap, this work proposes a novel adversarial learning DG algorithm, $\textbf{MADG}$, motivated by a margin loss-based discrepancy metric. The proposed $\textbf{MADG}$ model learns domain-invariant features across all source domains and uses adversarial training to generalize well to the unseen target domain. We also provide a theoretical analysis of the proposed $\textbf{MADG}$ model based on the unseen target error bound. Specifically, we construct the link between the source and unseen domains in the real-valued hypothesis space and derive the generalization bound using margin loss and Rademacher complexity. We extensively experiment with the $\textbf{MADG}$ model on popular real-world DG datasets, VLCS, PACS, OfficeHome, DomainNet, and TerraIncognita. We evaluate the proposed algorithm on DomainBed's benchmark and observe consistent performance across all the datasets.

The widespread use of the Internet of Things (IoT) necessitates large-scale communication among smart IoT devices (IoDs) across a wide geographical area. However, due to the limited radio range and scalability issues of traditional wireless sensor networks, wide-area communication among IoDs is not feasible. As a solution, a low-power wide-area network (LPWAN) is emerging as one of the techniques that can provide long-range communication with minimal power consumption. Nevertheless, the direct data transmission approach will no longer be viable due to its short network lifetime. As such, multihop data routing strategies for LPWANs are proposed in the literature. However, multihop data transmission has several challenges, including increased data latency, energy imbalance, poor bandwidth utilization, and low data throughput. To address these challenges, we propose a novel method that uses the machine learning technique for an energy-efficient and Quality-of-Service (QoS)-aware data transfer based on a recent breakthrough in social networks known as small-world characteristics (SWC). The network having SWC (i.e., low average path length and high average clustering coefficient) uses long-range links to reduce the number of intermediate hops for data transmission. In particular, a$Q$-learning framework is utilized for introducing optimal long-range links between the selected IoDs, resulting in the development of a small-world LPWAN (SW-LPWAN). Furthermore, the performance of the proposed method is computed in terms of energy efficiency and QoS. Moreover, the results are compared with existing data routing techniques, such as low-energy adaptive clustering hierarchy (LEACH), modified LEACH, conventional multihop, and direct data transmission. Specifically, the proposed method maintains 29% more alive nodes, 18% higher residual energy, and 22% higher data throughput compared to the second-best-performing method. As such, the obtained experimental results validate that the proposed method outperforms other existing methods in the context of energy consumption and QoS.

Multihop data routing over a large-scale Internet of Things (IoT) network results in energy imbalance and poor data throughput performance. In addition, data transmission using a large number of hops causes more delay. In light of this, in this work, a novel method of energy and throughput management in a delay-constrained small-world unmanned aerial vehicle (UAV)-IoT network is proposed. The proposed small-world framework optimizes the number of hops required for the data transmission leading to improved energy efficiency and quality of service. The method introduces optimal long-range links between device pairs resulting in low average path length and high clustering coefficient which are called as small-world characteristics. Therefore, in this work, UAVs are deployed to collect the data from IoT devices and forward it to the ground station (GS) utilizing the small world framework. It is shown through results that the network delays corresponding to the proposed method, conventional routing method, low-energy adaptive clustering hierarchy (LEACH) protocol, modified LEACH protocol, and canonical particle multiswarm (CPMS) method are 789.39, 1602.53, 1000.92, 873.63, and 999.79 s, respectively. It is also observed that the number of dead UAVs in case of the proposed method is reduced when compared to other existing methods. It is also noticed that the proposed method results in 100% packet delivery ratio (PDR) dominating LEACH and modified LEACH protocols. Thus, it is shown that the proposed method outperforms the other shortest path methods in terms of network latency, lifetime, and PDR. Further, the effect of location of GS, velocities of UAVs, and hovering heights of UAVs is considered for the performance evaluation of the proposed method. The obtained results validate the significance of utilization of the proposed method over various network scenarios.

In addition to RGB camera sensors, LiDAR (Light Detection and Ranging) plays an important role in autonomous vehicles (AVs) to perceive their surroundings. Deep neural networks (DNNs) are able to achieve cutting-edge 3D object detection and segmentation performance using LiDAR point clouds. LiDAR-enabled autonomous vehicles provide human perception by segmenting LiDAR point clouds into meaningful regions and providing semantic context to the AV user. However, the generation of point clouds to provide semantic segmentation in AVs is not reliable and secure, which may result in traffic accidents. We propose a novel adversarial attack against LiDAR point clouds in autonomous vehicles in this paper. We devised an exchange vanishing adversarial attack (EVAA) to deceive LiDAR point clouds by introducing targeted noise on specific objects (e.g., vehicles and driveways). On two autonomous driving datasets with 3D object annotations, NuScenes and PandaSet, we evaluate the performance of our proposed attack framework. We achieve an attack success rate (ASR) of ≈63% and ASR of ≈29% on both NuScenes and PandaSet datasets, respectively.

The expeditious growth of the Internet of Things (IoT) has accelerated the evolution of multi-access edge computing (MEC). MEC alleviates the challenges of conventional cloud computing, such as high data latency, poor data gathering reliability, increased network cost, and lack of network robustness. The primary objective of MEC is to facilitate a hierarchy of edge servers to address these quality-of-service (QoS) challenges, especially the information propagation issue due to the mobility of IoT devices (IoD). Further, social-relationship among mobile IoD is a critical parameter used to reduce the data transmission delay and queue size at the MEC. Specifically, in this work, a novel socially-aware radio map generation method is proposed to compute the fine-grained and accurate locations of QoS-deprived areas. Firstly, a novel method to compute the social relationship index (SRI) factor is proposed on the basis of current and future encounters among moving IoDs. Then the obtained SRI factor is used to form clusters of mobile IoD. The clusters’ signal to interference plus noise ratio (SINR) is then used to generate the socially-aware radio map. Following that, unmanned aerial vehicles (UAV) use this radio map, which contains rich and serviceable channel information, for 3D beamforming towards the mobile clusters. Using the obtained radio map, Kalman filter-based offline path planning of UAVs is proposed to minimize the UAVs flying distance from the initial to final locations. Furthermore, an optimization problem is formulated to assess the performance of the proposed method. Finally, the performance of the proposed method is compared with the existing methods, taking into account various network parameters such as optimum number of UAVs needed to cover the deployed area, data transmission delay, and received SINR.

Energy efficiency has become the new performance criterion in this era of pervasive embedded computing; thus, accelerator-rich multi-processor system-on-chips are commonly used in embedded computing hardware. Once computationally intensive machine learning applications gained much traction, they are now deployed in many application domains due to abundant and cheaply available computational capacity. In addition, there is a growing trend toward developing hardware accelerators for machine learning applications for embedded edge devices where performance and energy efficiency are critical. Although these hardware accelerators frequently use floating-point operations for accuracy, reduced-width floating-point formats are also used to reduce hardware complexity; thus, power consumption while maintaining accuracy. Vectorization concepts can also be used to improve performance, energy efficiency, and memory bandwidth. We propose the design of a vectorized floating-point adder/subtractor that supports arbitrary length floating-point formats with varying exponent and mantissa widths in this article. In comparison to existing designs in the literature, the proposed design is 2.57× area- and 1.56× power-efficient, and it supports true vectorization with no restrictions on exponent and mantissa widths.

Contrary to the World Health Organization’s (WHO) and the medical community’s projections, Covid-19, which started in Wuhan, China, in December 2019, still doesn’t show any signs of progressing to the endemic stage or slowing down any time soon. It continues to wreak havoc on the lives and livelihood of thousands of people every day. There is general agreement that the best way to contain this dangerous virus is through testing and isolation. Therefore, in these epidemic times, developing an automated Covid-19 detection method is of utmost importance. This study uses three different Machine Learning classifiers, such as Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR), along with five Transfer Learning models such as DenseNet121, DenseNet169, ResNet50, ResNet152V2, and Xception as feature extraction methods for identifying Covid-19. Five different datasets are used to assess the models’ performance to generalize. There are encouraging findings, with the best one being the combination of DenseNet121 and DenseNet169 together with SVM and LR.

Non-orthogonal multiple access (NOMA) is a next-generation multiple access technology to improve users’ throughput and spectral efficiency for 5G and beyond cellular networks. Similarly, coordinated multi-point transmission and reception (CoMP) is an existing technology to improve the coverage of cell-edge users. Hence, NOMA with CoMP can potentially enhance the throughput and coverage of the users. However, the order of implementation of CoMP and NOMA can significantly impact the system performance of Ultra-dense networks (UDNs). Motivated by this, we study the performance of the CoMP and NOMA-based UDN by proposing two kinds of user grouping and pairing schemes that differ in the order in which CoMP and NOMA are performed for a group of users. Detailed simulation results are presented, comparing the proposed schemes with the state-of-the-art systems with varying user and base station densities. Through numerical results, we show that the proposed schemes can be used to achieve a suitable coverage-throughout trade-off in UDNs.

Inclusion of massive machine-type-communication (mMTC) devices in 5G cellular Internet of Things (IoT) has significantly raised the issue of network congestion. To address this challenge, a successive interference cancellation-rate splitting random access (SIC-RSRA) mechanism is proposed in this paper. Unlike traditional mechanisms, all selected mMTC devices are allowed to make a finite number of repeated message requests in randomly selected time slots within a radio frame. The gNodeB, on the other hand, applies both intra-slot SIC (utilizing RSRA) and inter-slot SIC to decode messages from a larger number of devices. For the proposed mechanism, the impact of increasing the number of devices as well as the received power difference is investigated. Through extensive simulations, we show that the proposed mechanism outperforms the other mechanisms in terms of number of RACH successes and number of supported devices.

The spectrum cartography finds applications in several areas such as cognitive radios , spectrum aware communications, machine-type communications, Internet of Things , connected vehicles, wireless sensor networks , and radio frequency management systems, etc. This paper presents a survey on state-of-the-art of spectrum cartography techniques for the construction of various radio environment maps (REMs). Following a brief overview on spectrum cartography, various techniques considered to construct the REMs such as channel gain map, power spectral density map, power map, spectrum map, power propagation map, radio frequency map, and interference map are reviewed. In this paper, we compare the performance of the different spectrum cartography methods in terms of mean absolute error , mean square error , normalized mean square error, and root mean square error . The information presented in this paper aims to serve as a practical reference guide for various spectrum cartography methods for constructing different REMs. Finally, some of the open issues and challenges for future research and development are discussed.

This article presents a computer-aided object detection and localization method from lidar 3-D point cloud data. This topic of interest is in the framework of autonomous mooring, where the ship is tied to the rigid structure on-shore (bollard) for autonomous maritime navigation. Using shape and features priors, unlike matching the whole object template to the experimental 3-D point cloud representation of the scene, two customized algorithms: 1) 3-D feature matching (3-DFM) and 2) mixed feature-correspondence matching (MFCM) are presented. The proposed algorithms discriminate and extract the 3-D points corresponding to the noncooperative bollard’s surface from the background, thus capable of classification, localization, and representing it using a unique coordinate in the 3-D world. The proposed algorithms are tested and validated by implementing upon an experimental dataset of 105 scenes where the bollard is at different positions and orientations with respect to lidar mounted on the robotic arm. Statistical and probabilistic-based approaches are taken into account to determine the performance of proposed algorithms. Model parameters’ estimation implies that errors resulting from the 3-DFM algorithm follow homoscedastic bimodal Gaussian distribution with individual Gaussian components having mean 0.03 and 0.09 m, and both have an equal standard deviation of 0.01 m. Furthermore, the posterior component assignment probability is used to identify and cluster the scenes that contribute to relatively larger errors. Finally, an improved algorithm, MFCM, is proposed, whose errors follow unimodal Gaussian distribution with a mean and a standard deviation of 0.03 and 0.01 m, respectively, thus mitigating the shortcomings of the former.

With millions of devices connected together, the Internet of Things (IoT) has become an emerging technology for future wireless networks. The ever-increasing number of smart devices and data hungry applications demand a high Quality-of-Service (QoS) for IoT. In conventional networks, data being sent to cloud for computational purpose leads to poor QoS. In order to address QoS challenges, mobile edge networks have emerged as a promising solution. In edge networks, bringing the networks resources closer to the end devices results in improved QoS. The maneuverability and the ease of versatile deployment coupled with cost efficiency makes unmanned aerial vehicles (UAVs) a promising candidate for future edge networks. The UAVs can act as edge servers to provide computational capabilities and improved services to the edge devices. Due to the flying ability, UAVs can establish better line-of-sight link with the ground devices. In this paper, we consider that the edge devices in the area of interest have to be facilitated with a certain desired QoS, which is based on the notion of outage probability of the wireless link between the UAV and the edge devices. In this context, we first propose a novel method that computes the optimum height at which UAV should hover, resulting in maximum coverage radius with sufficiently small outage probability. Then the geographical area is divided in optimal number of clusters using a novel algorithm based on K-means clustering. The method computes the optimum number of UAVs required for covering the area of interest. Each of the UAVs utilizes 3D beamforming in order to cover its own coverage area. For this purpose, we are taking coordinate transformation of the original area and forming a wide beam to cover the desired area. The obtained results demonstrate the effectiveness of the proposed method when compared to existing methods, which validate the utilization of the proposed method over large scale network applications.

With the increasing number of applications running on a Network-on-Chip (NoC) based System-on-Chip (SoC), there is a need for designing a reconfigurable NoC platform to achieve acceptable performance for all the applications. This paper proposes a novel architecture for implementing a reconfiguration logic to the NoC platform executing multiple applications. The proposed architecture reconfigures SoC modules to the routers in the NoC with the help of tri-state buffers based on the applications running. The overhead in implementing the reconfiguration circuitry is significantly less, approximately 0.9% of the area and 1% of the total power consumed by the router network. The architectures presented in the paper are developed in Verilog HDL, applied to the NoC router platform and simulated for functional verification. The synthesis results show that the proposed tri-state buffer-based reconfiguration logic has better performance in terms of area, power and speed compared with the multiplexer-based reconfiguration logic.

The cellular Internet-of-Things has resulted in the deployment of millions of machine type communication (MTC) devices under the coverage of a single gNodeB (gNB). These massive number of devices should connect to the gNodeB (gNB) via the random access channel (RACH) mechanism. Moreover, the existing RACH mechanisms are inefficient when dealing with such large number of devices. To address this issue, we propose the rate-splitting random access (RSRA) mechanism, which uses rate splitting and decoding in rate-splitting multiple access (RSMA), to improve the RACH success rate. The proposed mechanism divides the message into common and private messages and enhances the decoding performance. We demonstrate, using extensive simulations, that the proposed RSRA mechanism significantly improves the success rate of MTC in cellular IoT networks. We also evaluate the performance of the proposed mechanism with increasing number of devices and received power difference.

Chest computed tomography (CT) imaging has become indispensable for staging and managing coronavirus disease 2019 (COVID-19), and current evaluation of anomalies/abnormalities associated with COVID-19 has been performed majorly by the visual score. The development of automated methods for quantifying COVID-19 abnormalities in these CT images is invaluable to clinicians. The hallmark of COVID-19 in chest CT images is the presence of ground-glass opacities in the lung region, which are tedious to segment manually. We propose anamorphic depth embedding-based lightweight CNN, called Anam-Net, to segment anomalies in COVID-19 chest CT images. The proposed Anam-Net has 7.8 times fewer parameters compared to the state-of-the-art UNet (or its variants), making it lightweight capable of providing inferences in mobile or resource constraint (point-of-care) platforms. The results from chest CT images (test cases) across different experiments showed that the proposed method could provide good Dice similarity scores for abnormal and normal regions in the lung. We have benchmarked Anam-Net with other state-of-the-art architectures, such as ENet, LEDNet, UNet++, SegNet, Attention UNet, and DeepLabV3+. The proposed Anam-Net was also deployed on embedded systems, such as Raspberry Pi 4, NVIDIA Jetson Xavier, and mobile-based Android application (CovSeg) embedded with Anam-Net to demonstrate its suitability for point-of-care platforms. The generated codes, models, and the mobile application are available for enthusiastic users at https://github.com/NaveenPaluru/Segmentation-COVID-19.

As the size of the chip is scaling down the density of Intellectual Property (IP) cores integrated on a chip has been increased rapidly. The communication between these IP cores on a chip is highly challenging. To overcome this issue, Network-on-Chip (NoC) has been proposed to provide an efficient and a scalable communication architecture. In the deep sub-micron level NoCs are prone to faults which can occur in any component of NoC. To build a reliable and robust systems, it is necessary to apply efficient fault-tolerant techniques. In this paper, we present a flexible spare core placement in Mesh-of-Tree (MoT) topology using Particle Swarm Optimization (PSO) by considering IP core failures in NoC. We have experimented by considering several application benchmarks reported in the literature. Comparisons have been carried out, (i) by varying the percentage of faults in the MoT network with fixed network size and (ii) by considering the each core has been failed in the given application benchmark. The results show limited overhead in communication cost while providing fault-tolerance.

Due to the increase in the number of processing elements in System-on-Chips (SoCs), communication between the cores is becoming complex. A solution to this issue in SoCs gave rise to a new paradigm called Network-on-Chips (NoCs). In NoCs, communication between different cores is achieved using packet based switching techniques. In the deep sub-micron technology, NoCs are more susceptible to different kinds of faults which can be transient, intermittent and permanent. These faults can occur at any component of NoCs. This paper presents a novel Fault-Tolerant Routing (FTR) technique for Mesh-of-Tree (MoT) topology in the presence of router faults. The proposed technique is compared with routing technique without any faults. The results show improvements interms of the number of data packets reaching to any given destination node from any source node in MoT network in presence of faults.

In this paper, we present the analysis and design of a self-biased single-ended charge sampling amplifier (CSA) in 90nm CMOS for catheter based intravenous ultrasound imaging applications. The proposed CSA is based on a 1V single-ended CMOS inverter-based cascode amplifier. The amplifier achieves a DC gain of 43.7 dB and a unity gain frequency of 1.37 GHz at a power consumption of 385 μW at 37°C - nominal temperature of human body with typical-typical (TT) models defined in the 90nm CMOS technology used for this design. Performance of the self-biased CSA is studied by connecting a single Capacitive Micro machined Ultrasound Transducer (CMUT) to it.

In this paper we present a simple analytical model for the estimation of signal-to-noise ratio (SNR) due to clock jitter for a general charge sampling amplifier. The proposed analytical model is compared with a previously published more complex model. Finally, we compare charge sampling and voltage sampling in terms of SNR due to clock jitter