Deepfake detectors often struggle to generalize to novel forgery types due to biases learned from limited training data. In this paper, we identify a new type of model bias in the frequency domain, termed spectral bias, where detectors overly rely on specific frequency bands, restricting their ability to generalize across unseen forgeries. To address this, we propose FreqDebias, a frequency debiasing framework that mitigates spectral bias through two complementary strategies. First, we introduce a novel Forgery Mixup (Fo-Mixup) augmentation, which dynamically diversifies frequency characteristics of training samples. Second, we incorporate a dual consistency regularization (CR), which enforces both local consistency using class activation maps (CAMs) and global consistency through a von Mises-Fisher (vMF) distribution on a hyperspherical embedding space. This dual CR mitigates over-reliance on certain frequency components by promoting consistent representation learning under both local and global supervision. Extensive experiments show that FreqDebias significantly enhances cross-domain generalization and outperforms state-of-the-art methods in both cross-domain and in-domain settings.

Advanced wireless networks must be highly dynamic and capable of managing heterogeneous service demands. A key feature of these networks is network slicing, which is supported in the next-generation radio access network (RAN) architecture, such as open RAN (O-RAN), by leveraging artificial intelligence (AI) and machine learning (ML) approaches within the ran intelligent controller (RIC) modules. Deep reinforcement learning (DRL) has much potential for managing dynamic networks but often needs to improve when dealing with unstructured, multi-modal data like RF signals and QoS metrics. This kind of data makes it challenging for DRL to grasp the high-level context fully. To tackle this, we're using large language models (LLMs) to give DRL a richer, more meaningful state representation. LLMs add semantic layers to raw data, helping the agent grasp deeper context and think more strategically over the long term. This way, the DRL agent can make smarter decisions even as the environment becomes more complex and changes over time. This paper proposes a task-related state representation that employs LLM to augment multi-agent DRL (MARL) approaches. Simulation results demonstrate that the proposed approach significantly outperforms related baselines.

In recent years, rapid technological advancements and expanded Internet access have led to a significant rise in anomalies within network traffic and time-series data. Prompt detection of these irregularities is crucial for ensuring service quality, preventing financial losses, and maintaining robust security standards. While machine learning algorithms have shown promise in achieving high accuracy for anomaly detection, their performance is often constrained by the specific conditions of their training data. A persistent challenge in this domain is the scarcity of labeled data for anomaly detection in time-series datasets. This limitation hampers the training efficacy of both traditional machine learning and advanced deep learning models. To address this, unsupervised transfer learning emerges as a viable solution, leveraging unlabeled data from a source domain to identify anomalies in an unlabeled target domain. However, many existing approaches still depend on a small amount of labeled data from the target domain. To overcome these constraints, we propose a transfer learning-based model for anomaly detection in multivariate time-series datasets. Unlike conventional methods, our approach does not require labeled data in either the source or target domains. Empirical evaluations on novel intrusion detection datasets demonstrate that our model outperforms existing techniques in accurately identifying anomalies within an entirely unlabeled target domain.

In multimodal learning, dominant modalities often overshadow others, limiting generalization. We propose Modality-Aware Sharpness-Aware Minimization (M-SAM), a model-agnostic framework that applies to many modalities and supports early and late fusion scenarios. In every iteration, M-SAM in three steps optimizes learning. \textbf{First, it identifies the dominant modality} based on modalities' contribution in the accuracy using Shapley. \textbf{Second, it decomposes the loss landscape}, or in another language, it modulates the loss to prioritize the robustness of the model in favor of the dominant modality, and \textbf{third, M-SAM updates the weights} by backpropagation of modulated gradients. This ensures robust learning for the dominant modality while enhancing contributions from others, allowing the model to explore and exploit complementary features that strengthen overall performance. Extensive experiments on four diverse datasets show that M-SAM outperforms the latest state-of-the-art optimization and gradient manipulation methods and significantly balances and improves multimodal learning. The code will be released.

Recent advancements in anomaly detection have shifted focus towards Multi-class Unified Anomaly Detection (MUAD), offering more scalable and practical alternatives compared to traditional one-class-one-model approaches. However, existing MUAD methods often suffer from interclass interference and are highly susceptible to domain shifts, leading to substantial performance degradation in real-world applications. In this paper, we propose a novel robust prompt-driven MUAD framework, called ROADS, to address these challenges. ROADS employs a hierarchical class-aware prompt integration mechanism that dynamically encodes class-specific information into our anomaly detector to mitigate interference among anomaly classes. Additionally, ROADS incorporates a domain adapter to enhance robustness against domain shifts by learning domain-invariant representations. Extensive experiments on MVTec-AD and VISA datasets demonstrate that ROADS surpasses state-of-the-art methods in both anomaly detection and localization, with notable improvements in out-of-distribution settings.

Pre-trained Vision-language (VL) models, such as CLIP, have shown significant generalization ability to downstream tasks, even with minimal fine-tuning. While prompt learning has emerged as an effective strategy to adapt pre-trained VL models for downstream tasks, current approaches frequently encounter severe overfitting to specific downstream data distributions. This overfitting constrains the original behavior of the VL models to generalize to new domains or unseen classes, posing a critical challenge in enhancing the adaptability and generalization of VL models. To address this limitation, we propose Style-Pro, a novel style-guided prompt learning framework that mitigates overfitting and preserves the zero-shot generalization capabilities of CLIP. Style-Pro employs learnable style bases to synthe-size diverse distribution shifts, guided by two specialized loss functions that ensure style diversity and content integrity. Then, to minimize discrepancies between unseen domains and the source domain, Style-Pro maps the unseen styles into the known style representation space as a weighted combination of style bases. Moreover, to maintain consistency between the style-shifted prompted model and the original frozen CLIP, Style-Pro introduces consistency constraints to preserve alignment in the learned embeddings, minimizing deviation during adaptation to down-stream tasks. Extensive experiments across 11 benchmark datasets demonstrate the effectiveness of Style-Pro, consistently surpassing state-of-the-art methods in various settings, including base-to-new generalization, cross-dataset transfer, and domain generalization.

5G technology enhances industries with highspeed, reliable, low-latency communication, revolutionizing mobile broadband and supporting massive IoT connectivity. With the increasing complexity of applications on User Equipment (UE), offloading resource-intensive tasks to robust servers is essential for improving latency and speed. The 3GPP's Multi-access Edge Computing (MEC) framework addresses this challenge by processing tasks closer to the user, highlighting the need for an intelligent controller to optimize task offloading and resource allocation. This paper introduces a novel methodology to efficiently allocate both communication and computational resources among individual UEs. Our approach integrates two critical 5G service imperatives: Ultra-Reliable Low Latency Communication (URLLC) and Massive Machine Type Communication (mMTC), embedding them into the decision-making framework. Central to this approach is the utilization of Proximal Policy Optimization, providing a robust and efficient solution to the challenges posed by the evolving landscape of 5 G technology. The proposed model is evaluated in a simulated 5G MEC environment. The model significantly reduces processing time by$\mathbf{4 \%}$for URLLC users under strict latency constraints and decreases power consumption by$\mathbf{2 6 \%}$for mMTC users, compared to existing baseline models based on the reported simulation results. These improvements showcases the model's adaptability and superior performance in meeting diverse$\mathbf{Q o S}$requirements in 5G networks.

As wireless networks grow to support more complex applications, the Open Radio Access Network (O-RAN) architecture, with its smart RAN Intelligent Controller (RIC) modules, becomes a crucial solution for real-time network data collection, analysis, and dynamic management of network resources including radio resource blocks and downlink power allocation. Utilizing artificial intelligence (AI) and machine learning (ML), O-RAN addresses the variable demands of modern networks with unprecedented efficiency and adaptability. Despite progress in using ML-based strategies for network optimization, challenges remain, particularly in the dynamic allocation of resources in unpredictable environments. This paper proposes a novel Meta Deep Reinforcement Learning (Meta-DRL) strategy, inspired by Model-Agnostic Meta-Learning (MAML), to advance resource block and downlink power allocation in O-RAN. Our approach leverages O-RAN's disaggregated architecture with virtual distributed units (DUs) and meta-DRL strategies, enabling adaptive and localized decision-making that significantly enhances network efficiency. By integrating meta-learning, our system quickly adapts to new network conditions, optimizing resource allocation in real-time. This results in a 19.8% improvement in network management performance over traditional methods, advancing the capabilities of next-generation wireless networks.

Channel Autoencoders (CAEs) have shown significant potential in optimizing the physical layer of a wireless communication system for a specific channel through joint end-to-end training. However, the practical implementation of CAEs faces several challenges, particularly in realistic and dynamic scenarios. Channels in communication systems are dynamic and change with time. Still, most proposed CAE designs assume stationary scenarios, meaning they are trained and tested for only one channel realization without regard for the dynamic nature of wireless communication systems. Moreover, conventional CAEs are designed based on the assumption of having access to a large number of pilot signals, which act as training samples in the context of CAEs. However, in real-world applications, it is not feasible for a CAE operating in real-time to acquire large amounts of training samples for each new channel realization. Hence, the CAE has to be deployable in few-shot learning scenarios where only limited training samples are available. Furthermore, most proposed conventional CAEs lack fast adaptability to new channel realizations, which becomes more pronounced when dealing with a limited number of pilots. To address these challenges, this paper proposes the Online Meta Learning channel AE (OML-CAE) framework for few-shot CAE scenarios with dynamic channels. The OML-CAE framework enhances adaptability to varying channel conditions in an online manner, allowing for dynamic adjustments in response to evolving communication scenarios. Moreover, it can adapt to new channel conditions using only a few pilots, drastically increasing pilot efficiency and making the CAE design feasible in realistic scenarios.

The Distributed Sensing and Computing Over Sparse Environments (DISCOVER) testbed is a pioneering cyberinfrastructure initiative designed to advance research in distributed computing and networking tailored to rural, remote, and sparsely populated regions. Supported by the National Science Foundation (NSF), DISCOVER integrates a network of configurable Internet-of-Things (IoT) nodes—including stationary sensors, drones, and terrestrial rovers—across three key sites: Northern Arizona University (NAU), Clemson University, and Navajo Technical University (NTU). This collaboration offers a unique platform to explore innovative algorithms and methodologies addressing the technical challenges of under-served areas, with an emphasis on environmental and civil disaster response. The testbed enables a wide range of experiments, such as regional-scale data collection, heterogeneous networked services, distributed artificial intelligence (AI), distributed multi-robot control, and communication-aware software for resource-constrained networks. An online portal enhances accessibility, allowing researchers to request resources, upload experimental code, and retrieve data, with pre-integrated deep learning models for applications like human posture detection, object detection, and wildfire detection. This paper outlines the testbed’s architecture, operational sites, supported experiment types, ongoing research efforts, and its educational and outreach impacts, highlighting its role in fostering scientific innovation.

Internet of Vehicles (IoV) systems, while offering significant advancements in transportation efficiency and safety, introduce substantial security vulnerabilities due to their highly interconnected nature. These dynamic systems produce massive amounts of data between vehicles, infrastructure, and cloud services and present a highly distributed framework with a wide attack surface. In considering network-centered attacks on IoV systems, attacks such as Denial-of-Service (DoS) can prohibit the communication of essential physical traffic safety information between system elements, illustrating that the security concerns for these systems go beyond the traditional confidentiality, integrity, and availability concerns of enterprise systems. Given the complexity and volume of data generated by IoV systems, traditional security mechanisms are often inadequate for accurately detecting sophisticated and evolving cyberattacks. Here, we present an unsupervised autoencoder method trained entirely on benign network data for the purpose of unseen attack detection in IoV networks. We leverage a weighted combination of reconstruction and triplet margin loss to guide the autoencoder training and develop a diverse representation of the benign training set. We conduct extensive experiments on recent network intrusion datasets from two different application domains, industrial IoT and home IoT, that represent the modern IoV task. We show that our method performs robustly for all unseen attack types, with roughly 99% accuracy on benign data and between 97% and 100% performance on anomaly data. We extend these results to show that our model is adaptable through the use of transfer learning, achieving similarly high results while leveraging domain features from one domain to another.

Unmanned aerial vehicles (UAVs) have enabled numerous inventive solutions to multiple problems, considerably facilitating our daily lives; however, UAVs frequently rely on an open wireless channel for communication, making them susceptible to cyber-physical threats. Also, UAVs cannot execute complicated cryptographic algorithms due to their limited onboard computing capabilities. Balancing high-security levels and minimum computation costs is imperative when developing a security solution for UAVs. Consequently, several proxy signature schemes have been proposed in the literature to fulfill these requirements. Nevertheless, many of these solutions face the issue of high computation costs, and some exhibit security vulnerabilities that could not be more feasible options for UAV communication. Considering these constraints in mind, in this article, we introduce an improvised certificate-based proxy signature scheme (ICPS), which leverages the concept of hyperelliptic curve cryptography (HECC) to meet the security and efficiency requirements of UAV networks. The proposed ICPS scheme offers a range of notable features, including its ability to address key escrow and secret key distribution issues. The proposed ICPS scheme’s security hardness has been evaluated using the widely known security tool, the random oracle model (ROM), proving its resilience against known and unknown cybersecurity threats. Finally, this study conducts a performance comparison of the proposed scheme against existing schemes, emphasizing its outstanding cost-efficiency. Notably, the computation cost is measured at 5.3536 ms and the communication cost at 1120 bits, substantially lower than relevant existing schemes.

Sparse training stands as a landmark approach in addressing the considerable training resource demands imposed by the continuously expanding size of Deep Neural Networks (DNNs). However, the training of a sparse DNN encounters great challenges in achieving optimal generalization ability despite the efforts from the state-of-the-art sparse training methodologies. To unravel the mysterious reason behind the difficulty of sparse training, we connect the network sparsity with neural loss functions structure, and identify the cause of such difficulty lies in chaotic loss surface. In light of such revelation, we propose $S^{2} - SAM$, characterized by a **S**ingle-step **S**harpness_**A**ware **M**inimization that is tailored for **S**parse training. For the first time, $S^{2} - SAM$ innovates the traditional SAM-style optimization by approximating sharpness perturbation through prior gradient information, incurring *zero extra cost*. Therefore, $S^{2} - SAM$ not only exhibits the capacity to improve generalization but also aligns with the efficiency goal of sparse training. Additionally, we study the generalization result of $S^{2} - SAM$ and provide theoretical proof for convergence. Through extensive experiments, $S^{2} - SAM$ demonstrates its universally applicable plug-and-play functionality, enhancing accuracy across various sparse training methods. Code available at https://github.com/jjsrf/SSAM-NEURIPS2024.

The rapid evolution of urban air mobility (UAM) is reshaping the future of transportation by integrating aerial vehicles into urban transit systems. The design of aerial intersections plays a critical role in the phased development of UAM systems to ensure safe and efficient operations in air corridors. This work adapts the concept of rhythmic control of connected and automated vehicles (CAVs) at unsignalized intersections to address complex traffic control problems. This control framework assigns UAM vehicles to different movement groups and significantly reduces the computation of routing strategies to avoid conflicts. In contrast to ground traffic, the objective is to balance three measures: minimizing energy utilization, maximizing intersection flow (throughput), and maintaining safety distances. This optimization method dynamically directs traffic with various demands, considering path assignment distributions and segment-level trajectory coefficients for straight and curved paths as control variables. To the best of our knowledge, this is the first multi-objective optimization approach for unsignalized aerial intersection control using rhythmic control. A sensitivity analysis with respect to inter-platoon safety and straight/left demand balance demonstrates the effectiveness of our method in handling traffic under various scenarios.

This paper investigates an interference-aware joint path planning and power allocation mechanism for a cellular-connected unmanned aerial vehicle (UAV) in a sparse suburban environment. The UAV’s goal is to fly from an initial point and reach a destination point by moving along the cells to guarantee the required quality of service (QoS). In particular, the UAV aims to maximize its uplink throughput and minimize interference to the ground user equipment (UEs) connected to neighboring cellular base stations (BSs), considering both the shortest path and limitations on flight resources. Expert knowledge is used to experience the scenario and define the desired behavior for the sake of the agent (i.e., UAV) training. To solve the problem, an apprenticeship learning method is utilized via inverse reinforcement learning (IRL) based on both Q-learning and deep reinforcement learning (DRL). The performance of this method is compared to learning from a demonstration technique called behavioral cloning (BC) using a supervised learning approach . Simulation and numerical results show that the proposed approach can achieve expert-level performance. We also demonstrate that, unlike the BC technique, the performance of our proposed approach does not degrade in unseen situations.

FlameFinder, a novel deep metric learning (DML) framework, accurately detects RGB-obscured flames using thermal images from firefighter drones during wildfire monitoring. In contrast to RGB, thermal cameras can capture smoke-obscured flame features but they lack absolute thermal reference points, detecting many nonflame hot spots as false positives. This issue suggests that extracting features from both modalities in unobscured cases can reduce the model’s bias to relative thermal gradients. Following this idea, our proposed model utilizes paired thermal-RGB images captured onboard drones for training, learning latent flame features from smoke-free samples. In testing, it identifies flames in smoky patches based on their equivalent thermal-domain distribution, improving performance with supervised and distance-based clustering metrics. The approach includes a flame segmentation method and a DML-aided detection framework with center loss (CL), triplet CL (TCL), and triplet cosine CL (TCCL), to find the optimal cluster representatives for classification. Evaluation of FLAME2 and FLAME3 datasets shows the method’s effectiveness in diverse fire and no-fire scenarios. However, the CL dominates the two other losses, resulting in the model missing features that are sensitive to them. To overcome this issue, an attention mechanism is proposed making nonuniform feature contribution possible and amplifying the critical role of cosine and triplet loss in the DML framework. Plus, the attentive DML shows improved interpretability, class discrimination, and decreased intraclass variance exploiting several other flame-related features. The proposed model surpasses the baseline with a binary classifier by 4.4% in FLAME2 and 7% in FLAME3 datasets for unobscured flame detection accuracy. It also demonstrates enhanced class separation in obscured scenarios compared to fine-tuned VGG19, ResNet18, and three other backbone models tailored for flame detection.

As deep convolutional neural networks (DNNs) are widely used in various fields of computer vision, leveraging the overfitting ability of the DNN to achieve video resolution upscaling has become a new trend in the modern video delivery system. By dividing videos into chunks and over-fitting each chunk with a super-resolution model, the server encodes videos before transmitting them to the clients, thus achieving better video quality and transmission efficiency. However, a large number of chunks are expected to ensure good overfitting quality, which substantially increases the storage and consumes more bandwidth resources for data transmission. On the other hand, decreasing the number of chunks through training optimization techniques usually requires high model capacity, which significantly slows down execution speed. To reconcile such, we propose a novel method for high-quality and efficient video resolution upscaling tasks, which leverages the spatial-temporal information to accurately divide video into chunks, thus keeping the number of chunks as well as the model size to minimum. Additionally, we advance our method into a single overfitting model by a data-aware joint training technique. which further reduces the storage requirement with negligible quality drop. We deploy our models on an off-the-shelf mobile phone, and experimental results show that our method achieves real-time video super-resolution with high video quality. Compared with the state-of-the-art, our method achieves 28 fps streaming speed with 41.6 PSNR, which is 14 × faster and 2.29 dB better in the live video resolution upscaling tasks. Code available in https://github.com/coulsonlee/STDO-CVPR2023.git.

As emerging networks such as Open Radio Access Networks (O-RAN) and 5G continue to grow, the demand for various services with different requirements is increasing. Network slicing has emerged as a potential solution to address the different service requirements. However, managing network slices while maintaining quality of services (QoS) in dynamic environments is a challenging task. Utilizing machine learning (ML) approaches for optimal control of dynamic networks can enhance network performance by preventing Service Level Agreement (SLA) violations. This is critical for dependable decision-making and satisfying the needs of emerging networks. Although RL-based control methods are effective for real-time monitoring and controlling network QoS, generalization is necessary to improve decision-making reliability. This paper introduces an innovative attention-based deep RL (ADRL) technique that leverages the O-RAN disaggregated modules and distributed agent cooperation to achieve better performance through effective information extraction and implementing generalization. The proposed method introduces a value-attention network between distributed agents to enable reliable and optimal decision-making. Simulation results demonstrate significant improvements in network performance compared to other DRL baseline methods.

Indoor localization has gained significant attention in recent years due to its various applications in smart homes, industrial automation, and healthcare, especially since more people rely on their wireless devices for location-based services. Deep learning-based solutions have shown promising results in accurately estimating the position of wireless devices in indoor environments using wireless parameters such as Channel State Information (CSI) and Received Signal Strength Indicator (RSSI). However, despite the success of deep learning-based approaches in achieving high localization accuracy, these models suffer from a lack of generalizability and can not be readily-deployed to new environments or operate in dynamic environments without retraining. In this paper, we propose meta-learning-based localization models to address the lack of generalizability that persists in conventionally trained DL-based localization models. Furthermore, since meta-learning algorithms require diverse datasets from several different scenarios, which can be hard to collect in the context of localization, we design and propose a new meta-learning algorithm, TB-MAML (Task Biased Model Agnostic Meta Learning), intended to further improve generalizability when the dataset is limited. Lastly, we evaluate the performance of TB-MAML-based localization against conventionally trained localization models and localization done using other meta-learnina algorithms.

Passive space-borne radiometers operating in the 1400-1427 MHz protected frequency band face radio frequency interference (RFI) from terrestrial sources. With the growth of wireless devices and the appearance of new technologies, the possibility of sharing this spectrum with other technologies would introduce more RFI to these radiometers. This band could be an ideal mid-band frequency for 5G and Beyond, as it offers high capacity and good coverage. Current RFI detection and mitigation techniques at SMAP (Soil Moisture Active Passive) depend on correctly detecting and discarding or filtering the contaminated data leading to the loss of valuable information, especially in severe RFI cases. In this paper, we propose an autoencoder-based RFI mitigation method to remove the dominant RFI caused by potential coexistent terrestrial users (i.e., 5G base station) from the received contaminated signal at the passive receiver side, potentially preserving valuable information and preventing the contaminated data from being discarded1.

Unmanned aerial vehicles (UAVs) have become extremely popular for both military and civilian applications due to their ease of deployment, cost-effectiveness, high maneuverability, and availability. Both applications, however, need reliable communication for command and control (C2) and/or data transmission. Utilizing commercial cellular networks for drone communication can enable beyond visual line of sight (BVLOS) operation, high data rate transmission, and secure communication. However, deployment of cellular-connected drones over commercial LTE/5G networks still presents various challenges such as sparse coverage outside urban areas, and interference caused to the network as the UAV is visible to many towers. Commercial 5G networks can offer various features for aerial user equipment (UE) far beyond what LTE could provide by taking advantage of mmWave, flexible numerology, slicing, and the capability of applying AI-based solutions. Limited experimental data is available to investigate the operation of aerial UEs over current, without any modification, commercial 5G networks, particularly in suburban and NON-URBAN areas. In this paper, we perform a comprehensive study of drone communications over the existing low-band and mid-band 5G networks in a suburban area for different velocities and elevations, comparing the performance against that of LTE. It is important to acknowledge that the network examined in this research is primarily designed and optimized to meet the requirements of terrestrial users, and may not adequately address the needs of aerial users. This paper not only reports the Key Performance Indicators (KPIs) compared among all combinations of the test cases but also provides recommendations for aerial users to enhance their communication quality by controlling their trajectory.

Deep learning-based (DL-based) models have shown to be powerful tools for wireless interference identification (WII). However, one of the key concerns toward using these models in practical systems is that they perform poorly when they are encountered with signals coming from new sources not previously observed during the training phase. In a real-world communication system, the interference identifier will frequently face new unknown signals due to the existence of many wireless transmitters. This renders the conventional DL-based models impractical as a WII tool unless they go through a new training phase. Retraining the model is not only inefficient, but it can also be not feasible in some cases (e.g., at end-user devices) as the training phase consumes time and resources and requires large amounts of data. We present a new approach for data-driven WII systems using meta- learning to address the lack of adaptability in conventional DL-based models to new (not previously seen) signals. We show that by using meta-learning, we are able to identify signals coming from not previously observed technologies and frequencies using just a handful of new samples, a task that is not generally possible with conventional DL models. Finally, we analyze and compare the performance of the presented meta-learning model in multiple different settings using raw I/Q samples and Fast Fourier Transform of I/Q samples. Based on our experiments, we show that the proposed meta-learning scheme outperforms the conventional deep learning models for WII when there are just a few samples available for training1.

Key predistribution schemes are promising lightweight solutions to be placed as the cornerstone of key management systems in multihop wireless networks. The intermediate decryption–encryption problem, however, is considered as the security threat of such schemes. Multipath algorithms have been proposed to face such a shortcoming. Alas, these solutions are vulnerable against the node capture attack, where the attacker compromises a fraction of network nodes. In this article, we propose BlocKP, a Blockchain-based solution to increase the resistance of the network against the node capture attack. BlocKP utilizes disjoint key paths for a key-exchange process, where the keying materials form a block at the source side. Each key path step generates the next block of the Blockchain until the keying materials reach the destination. BlocKP is a general framework applicable to any key predistribution schemes. We propose BlocKP in two versions BlocKP-I and BlocKP-II, where the latter enhances the resistance of BlocKP-I using erasure codes at the cost of negligible control traffic. We analytically show that BlocKP improves the resistance of the network against the node capture attack to almost perfect resistance, using just a small number of paths. We evaluate our solution by performing extensive simulations, considering three baseline key predistribution schemes, including probabilistic asymmetric key predistribution (PAKP), strong Steiner trade (SST), and unital key predistribution (UKP). We equipped these schemes with a compatible multipath algorithm to offer end-to-end security. Results show that BlocKP improves the throughput up to 5% and decreases the flow completion time into 20% compared to baseline schemes. It has comparable routing traffic, latency, and throughput with augmented solutions but up to 60% improvement in the resistance against the node capture attack.

ECG databases are usually highly imbalanced due to the abundance of Normal ECG and scarcity of abnormal cases. As such, deep learning classifiers trained on imbalanced datasets usually perform poorly, especially on minor classes. One solution is to generate realistic synthetic ECG signals using Generative Adversarial Networks (GAN) to augment imbalanced datasets. In this study, we combined conditional GAN with WGAN-GP and developed AC-WGAN-GP in 1D form for the first time to be applied on MIT-BIH Arrhythmia dataset. We investigated the impact of data augmentation on arrhythmia classification. Two models were employed for ECG generation: (i) unconditional GAN; Wasserstein GAN with gradient penalty (WGAN-GP) is trained on each class individually; (ii) conditional GAN; one Auxiliary Classifier WGAN-GP (AC-WGAN-GP) model is trained on all classes and then used to generate synthetic beats in all classes. Two scenarios are defined for each case: (a) unscreened; all the generated synthetic beats were used, and (b) screened; only high-quality beats are selected and used, based on their Dynamic Time Warping (DTW) distance to a designated template. The state-of-the-art ResNet classifier (EcgResNet34) is trained on each of the four augmented datasets and the performance metrics (precision/recall/F1-Score micro- and macro-averaged, confusion matrices, multiclass precision-recall curves) were compared with those of the original imbalanced case. We also used a simple metric Net Improvement. All the three metrics show consistently that unconditional GAN with raw generated data creates the best improvements.

Unmanned Aerial Vehicles (UAVs), as a recently emerging technology, enabled a new breed of unprecedented applications in different domains. This technology's ongoing trend is departing from large remotely-controlled drones to networks of small autonomous drones to collectively complete intricate tasks time and cost-effectively. An important challenge is developing efficient sensing, communication, and control algorithms that can accommodate the requirements of highly dynamic UAV networks with heterogeneous mobility levels. Recently, the use of Artificial Intelligence (AI) in learning-based networking has gained momentum to harness the learning power of cognizant nodes to make more intelligent networking decisions by integrating computational intelligence into UAV networks. An important example of this trend is developing learning-powered routing protocols, where machine learning methods are used to model and predict topology evolution, channel status, traffic mobility, and environmental factors for enhanced routing. This paper reviews AI-enabled routing protocols designed primarily for aerial networks, including topology-predictive and self-adaptive learning-based routing algorithms, with an emphasis on accommodating highly-dynamic network topology. To this end, we justify the importance and adaptation of AI into UAV network communications. We also address, with an AI emphasis, the closely related topics of mobility and networking models for UAV networks, simulation tools and public datasets, and relations to UAV swarming, which serve to choose the right algorithm for each scenario. We conclude by presenting future trends, and the remaining challenges in AI-based UAV networking, for different aspects of routing, connectivity, topology control, security and privacy, energy efficiency, and spectrum sharing.1

Internet of Things (IoT) assisted healthcare systems are designed for providing ubiquitous access and recommendations for personal and distributed electronic health services. The heterogeneous IoT platform assists healthcare services with reliable data management through dedicated computing devices. Healthcare services' reliability depends upon the efficient handling of heterogeneous data streams due to variations and errors. A Proportionate Data Analytics (PDA) for heterogeneous healthcare data stream processing is introduced in this manuscript. This analytics method differentiates the data streams based on variations and errors for satisfying the service responses. The classification is streamlined using linear regression for segregating errors from the variations in different time intervals. The time intervals are differentiated recurrently after detecting errors in the stream's variation. This process of differentiation and classification retains a high response ratio for healthcare services through spontaneous regressions. The proposed method's performance is analyzed using the metrics accuracy, identification ratio, delivery, variation factor, and processing time.

Cooperative ad hoc unmanned aerial vehicle (UAV) networks need essential security services to ensure their communication security. Cryptography, as the inseparable tool for providing security services, requires a robust key management system. Alas, the absence of infrastructure in cooperative networks leads to the infeasibility of providing conventional key management systems. Key pre-distribution schemes have shown promising performance in different cooperative networks due to their lightweight nature. However, intermediate decryption-encryption (DE) steps and the lack of key updates are the most concerning issues they suffer from. In this paper, we propose a simple and effective key management algorithm inspired by the idea of key pre-distribution, where it utilizes the highly dynamic UAV node movement in 3D space to provide the key update feature and optimizes the number of intermediate DE steps. Although it is a general model for any mobile ad hoc network, we have selected UAV network as an example domain to show the efficiency of the model given the high mobility. We define the communication density parameter to analytically show that using any highly dynamic random movement pattern leads our algorithm to work effectively. To show the proposed algorithm's effectiveness, we exhaustively analyze its security and performance in the UAV network using the ns-3 network simulator. Results validate our analytical findings and show how the highly dynamic UAV network movement helps our algorithm to provide the key update feature and to optimize the number of DE steps.

Recently, Unmanned Aerial Vehicles (UAVs) present a promising advanced technology that can enhance people life quality and smartness of cities dramatically and increase overall economic efficiency. UAVs have attained a significant interest in supporting many applications such as surveillance, agriculture, communication, transportation, pollution monitoring, disaster management, public safety, healthcare, and environmental preservation. Industry 4.0 applications are conceived of intelligent things that can automatically and collaboratively improve beyond 5G (B5G). Therefore, the Internet of Things (IoT) is required to ensure collaboration between the vast multitude of things efficiently anywhere in real-world applications that are monitored in real-time. However, many IoT devices consume a significant amount of energy when transmitting the collected data from surrounding environments. Due to a drone's capability to fly closer to IoT, UAV technology plays a vital role in greening IoT by transmitting collected data to achieve a sustainable, reliable, eco-friendly Industry 4.0. This survey presents an overview of the techniques and strategies proposed recently to achieve green IoT using UAVs infrastructure for a reliable and sustainable smart world. This survey is different from other attempts in terms of concept, focus, and discussion. Finally, various use cases, challenges, and opportunities regarding green IoT using UAVs are presented.

Wildfires are one of the costliest and deadliest natural disasters in the US, causing damage to millions of hectares of forest resources and threatening the lives of people and animals. Of particular importance are risks to firefighters and operational forces, which highlights the need for leveraging technology to minimize danger to people and property. FLAME (Fire Luminosity Airborne-based Machine learning Evaluation) offers a dataset of aerial images of fires along with methods for fire detection and segmentation which can help firefighters and researchers to develop optimal fire management strategies. This paper provides a fire image dataset collected by drones during a prescribed burning piled detritus in an Arizona pine forest. The dataset includes video recordings and thermal heatmaps captured by infrared cameras. The captured videos and images are annotated, and labeled frame-wise to help researchers easily apply their fire detection and modeling algorithms. The paper also highlights solutions to two machine learning problems: (1) Binary classification of video frames based on the presence [and absence] of fire flames. An Artificial Neural Network (ANN) method is developed that achieved a 76% classification accuracy. (2) Fire detection using segmentation methods to precisely determine fire borders. A deep learning method is designed based on the U-Net up-sampling and down-sampling approach to extract a fire mask from the video frames. Our FLAME method approached a precision of 92%, and recall of 84%. Future research will expand the technique for free burning broadcast fire using thermal images.

Currently, wildfire spread modeling has drawn a lot of attention from the research community since many countries are suffering from severe socioeconomic impacts of wildfires, every year. Fire spread modeling is a key requirement for effective fire management to deploy fire control equipment and forces at the right time and locations, and plan timely evacuations of residential areas. This paper proposes a new data-driven model for fire expansion which uses reference-based image segmentation for vegetation density estimation and incorporates it into the fire heat conduction modeling. Compared with the conventional parameter collection methods at fire scenes, our method relies on topview images taken by unmanned aerial vehicles, which provides significant advantages of flexibility, safety, low cost, and convenience. Our low-complexity and probabilistic model incorporates the terrain slope, vegetation density, and wind factors with adjustable model parameters which can be easily learned from experiments. The proposed model is flexible and applicable to forests with mixed vegetation and different geographical and climate conditions. We evaluate the fire propagation model by comparing the results with the propagation data available for California Rim fire in 2013.

The vast areas of applications for IoTs in future smart cities, smart transportation systems, and so on represent a thriving surface for several security attacks with economic, environmental and societal impacts. This survey paper presents a review of the security challenges of emerging IoT networks and discusses some of the attacks and their countermeasures based on different domains in IoT networks. Most conventional solutions for IoT networks are adopted from communication networks while noting the particular characteristics of IoT networks such as the nodes quantity, heterogeneity, and the limited resources of the nodes, these conventional security methods are not adequate. One challenge towards utilizing common secret key-based cryptographic methods in large-scale IoTs is the problem of secret key generation, distribution, and storage and protecting these secret keys from physical attacks. Physically unclonable functions (PUFs) can be utilized as a possible hardware remedy for identification and authentication in IoTs. Since PUFs extract the unique hardware characteristics, they potentially offer an affordable and practical solution for secret key generation. However, several barriers limit the PUFs’ applications for key generation purposes. We discuss the advantages of PUF-based key generation methods, and we present a survey of state-of-the-art techniques in this domain. We also present a proof-of-concept PUF-based solution for secret key generation using resistive random-access memories (ReRAM) embedded in IoTs.

The high rate of false alarms is a key challenge related to patient care in intensive care units (ICUs) that can result in delayed responses of the medical staff. Several rule-based and machine learning-based techniques have been developed to address this problem. However, the majority of these methods rely on the availability of different physiological signals such as different electrocardiogram (ECG) leads, arterial blood pressure (ABP), and photoplethysmogram (PPG), where each signal is analyzed by an independent processing unit and the results are fed to an algorithm to determine an alarm. That calls for novel methods that can accurately detect the cardiac events by only accessing one signal (e.g., ECG) with a low level of computation and sensors requirement. We propose a novel and robust representation learning framework for ECG analysis that only rely on a single lead ECG signal and yet achieves considerably better performance compared to the state-of-the-art works in this domain, without relying on an expert knowledge. We evaluate the performance of this method using the "2015 Physionet computing in cardiology challenge" dataset. To the best of our knowledge, the best previously reported performance is based on both expert knowledge and machine learning where all available signals of ECG, ABP and PPG are utilized. Our proposed method reaches the performance of 97.3%, 95.5 %, and 90.8 % in terms of sensitivity, specificity, and the challenge's score, respectively for the detection of five arrhythmias when only one single ECG lead signals is used without any expert knowledge.

Managing energy consumption for computation and communication is a key requirement for flying ad hoc networks (FANET) to prolong the network lifetime. In many applications, the main role of drones is to collect imagery information and relay them to a ground station for further processing and decision making. In this paper, we present a predictive compression policy to maximize the end-to-end image quality penalized by the communication and computation costs. The idea is to predict the number of remaining links to the destination for a given routing algorithm and use it to re-compress image frames at intermediate nodes such that the overall energy consumption is minimized. Numerical results confirm that the performance of this method is within 4% of the global optima and higher than the current fixed-rate policies with a significant margin.

In this paper, we develop a distributed mechanism for spectrum sharing among a network of unmanned aerial vehicles (UAV) and licensed terrestrial networks. This method can provide a practical solution for situations where the UAV network may need external spectrum when dealing with congested spectrum or need to change its operational frequency due to security threats. Here we study a scenario where the UAV network performs a remote sensing mission. In this model, the UAVs are categorized to two clusters of relaying and sensing UAVs. The relay UAVs provide a relaying service for a licensed network to obtain spectrum access for the rest of UAVs that perform the sensing task. We develop a distributed mechanism in which the UAVs locally decide whether they need to participate in relaying or sensing considering the fact that communications among UAVs may not be feasible or reliable. The UAVs learn the optimal task allocation using a distributed reinforcement learning algorithm. Convergence of the algorithm is discussed and simulation results are presented for different scenarios to verify the convergence.

Electrocardiogram (ECG) signal is a common and powerful tool to study heart function and diagnose several abnormal arrhythmias. While there have been remarkable improvements in cardiac arrhythmia classification methods, they still cannot offer acceptable performance in detecting different heart conditions, especially when dealing with imbalanced datasets. In this paper, we propose a solution to address this limitation of current classification approaches by developing an automatic heartbeat classification method using deep convolutional neural networks and sequence to sequence models. We evaluated the proposed method on the MIT-BIH arrhythmia database, considering the intra-patient and inter-patient paradigms, and the AAMI EC57 standard. The evaluation results for both paradigms show that our method achieves the best performance in the literature (a positive predictive value of 96.46% and sensitivity of 100% for the category S, and a positive predictive value of 98.68% and sensitivity of 97.40% for the category F for the intra-patient scheme; a positive predictive value of 92.57% and sensitivity of 88.94% for the category S, and a positive predictive value of 99.50% and sensitivity of 99.94% for the category V for the inter-patient scheme.).

This paper studies the problem of stable node matching for distributed simultaneous wireless information and power transfer in multi-user amplify-and-forward (AF) ad-hoc wireless networks. Particularly, each source node aims to be paired with another node that acts an AF relay to forward its signal to the destination, such that the achievable rate is improved, in return for some payment. In turn, a matching-theoretic solution based on the one-to-one Stable Marriage Matching game is considered, and a distributed polynomial-time complexity algorithm is proposed to pair each source node with its best potential relaying node based on the power-splitting ratios. Simulation results are presented to validate the proposed matching algorithm, and show that it yields sum-utility and sum-payment that are comparable to those of centralized schemes, with the added merits of low-complexity, and network stability.

This paper provides a proof of concept for using SRAM based Physically Unclonable Functions (PUFs) to generate private keys for IoT devices. PUFs are utilized, as there is inadequate protection for secret keys stored in the memory of the IoT devices. We utilize a custom-made Arduino mega shield to extract the fingerprint from SRAM chip on demand. We utilize the concepts of ternary states to exclude the cells which are easily prone to flip, allowing us to extract stable bits from the fingerprint of the SRAM. Using the custom-made software for our SRAM device, we can control the error rate of the PUF to achieve an adjustable memory-based PUF for key generation. We utilize several fuzzy extractor techniques based on using different error correction coding methods to generate secret keys from the SRAM PUF, and study the trade-off between the false authentication rate and false rejection rate of the PUF.

In this paper, we study the problem of spectrum scarcity in a network of unmanned aerial vehicles (UAVs) during mission-critical applications such as disaster monitoring and public safety missions, where the pre-allocated spectrum is not sufficient to offer a high data transmission rate for real-time video-streaming. In such scenarios, the UAV network can lease part of the spectrum of a terrestrial licensed network in exchange for providing relaying service. In order to optimize the performance of the UAV network and prolong its lifetime, some of the UAVs will function as a relay for the primary network while the rest of the UAVs carry out their sensing tasks. Here, we propose a team reinforcement learning algorithm performed by the UAV's controller unit to determine the optimum allocation of sensing and relaying tasks among the UAVs as well as their relocation strategy at each time. We analyze the convergence of our algorithm and present simulation results to evaluate the system throughput in different scenarios.

In parallel to the recent technological advancements and developments, there is a consistent development in the field of Intelligent Transportation Systems (ITS). Though advancements are considered in one side, there is also a negative side of increased road-accidents, traffic jams, and traffic congestions etc. In this paper, to address the above-mentioned problems, dense urban traffic surveillance data analysis and principal component analysis on the vehicular data are performed. This study and analysis provide some findings, which are discussed to come up with various perspectives on the data patterns and analysis to develop a healthy, user-friendly and highly sophisticated environment to the daily commuters in the roadway sector.

We study downlink transmission in a multi-band heterogeneous network comprising unmanned aerial vehicle (UAV) small base stations and ground-based dual mode mmWave small cells within the coverage area of a microwave (μW) macro base station. We formulate a two-layer optimization framework to simultaneously find efficient coverage radius for the UAVs and energy efficient radio resource management for the network, subject to minimum quality-of-service (QoS) and maximum transmission power constraints. The outer layer derives an optimal coverage radius/height for each UAV as a function of the maximum allowed path loss. The inner layer formulates an optimization problem to maximize the system energy efficiency (EE), defined as the ratio between the aggregate user data rate delivered by the system and its aggregate energy consumption (downlink transmission and circuit power). We demonstrate that at certain values of the target SINR τ introducing the UAV base stations doubles the EE. We also show that an increase in τ beyond an optimal EE point decreases the EE.

Some of the main challenges towards utilizing conventional cryptographic techniques in Internet of Things (IoT) include the need for generating secret keys for such a large-scale network, distributing the generated keys to all the devices, key storage as well as the vulnerability to security attacks when an adversary gets physical access to the devices. In this paper, a novel secret key generation method is proposed for IoTs that utilize the intrinsic randomness embedded in the devices' memories introduced in the manufacturing process. A fuzzy extractor structure using serially concatenated BCHPolar codes is proposed to generate reproducible keys from a ReRAM-based ternary-state Physical Unclonable Functions (PUFs) for device authentication and secret key generation. The main concern in deploying PUF-based key generation methods is the leakage of information about the secret keys from the publicly available helper data. The fuzzy extractor proposed in this paper ensures much less mutual information between the generated keys and the helper data. The experimental results show that our proposed scheme is capable of generating notably stronger keys compared to existing techniques, while utilizing a significantly lower number of helper data bits. The failure probability when a low complex Successive Cancellation decoder is implemented in the proposed fuzzy extractor structure is 10-8, which was further increased to 10-10, when a complex iterative belief propagation decoder was used.11This project is partially supported by Arizona Board of Regents under Grant # 1003330.

This paper considers the problem of delay-optimal bundling of the input symbols into transmit packets in the entry point of a wireless sensor network such that the link delay is minimized under an arbitrary arrival rate and a given channel error rate. The proposed policy exploits the variable packet length feature of contemporary communications protocols in order to minimize the link delay via packet length regularization. This is performed through concrete characterization of the end-to-end link delay for zero-error tolerance system with first come first serve (FCFS) queuing discipline and automatic repeat request (ARQ) re-transmission mechanism. The derivations are provided for an uncoded system as well as a coded system with a given bit error rate. The proposed packetization policy provides an optimal packetization interval that minimizes the end-to-end delay for a given channel with certain bit error probability. This algorithm can also be used for near-optimal bundling of input symbols for dynamic channel conditions provided that the channel condition varies slowly over time with respect to symbol arrival rate. This algorithm complements the current network-based delay-optimal routing and scheduling algorithms in order to further reduce the end-to-end delivery time. Moreover, the proposed method is employed to solve the problem of energy efficiency maximization under an average delay constraint by recasting it as a convex optimization problem.

The Smart home has gained widespread attention due to its flexible integration into everyday life. This next generation green home system, transparently unifies various home appliances, smart sensors and wireless communication technologies. It can integrate diversified physical sensed information and control various consumer home devices, with the support of active sensor networks having both sensor and actuator components. Although smart homes are gaining popularity due to their energy saving and better living benefits, there is no standardized design for smart homes. In this paper, we put forward a concept by designing and implementing a smart home system which can classify and predict the state of the home based on historical data. We set up a wireless sensor network and collected months of data. By employing supervised machine learning technique, we were able to establish patterns and use the acquired information as a vital cog in our control system algorithm, thereby improving the intelligence of the home. We created a system capable of running with minimal human supervision, an attribute which makes our system an asset for senior care scenarios. Our system also caters to the safety of the home owner.

The capability to estimate driver's intention leads to the development of advanced driver assistance systems that can assist the drivers in complex situations. Developing precise driver behavior models near intersections can considerably reduce the number of accidents at road intersections. In this study, the problem of driver behavior modeling near a road intersection is investigated using support vector machines (SVMs) based on the hybrid-state system (HSS) framework. In the HSS framework, the decisions of the driver are represented as a discrete-state system and the vehicle dynamics are represented as a continuous-state system. The proposed modeling technique utilizes the continuous observations from the vehicle and estimates the driver's intention at each time step using a multi-class SVM approach. Statistical methods are used to extract features from continuous observations. This allows for the use of history in estimating the current state. The developed algorithm is trained and tested successfully using naturalistic driving data collected from a sensor-equipped vehicle operated in the streets of Columbus, OH and provided by the Ohio State University. The proposed framework shows a promising accuracy of above 97% in estimating the driver's intention when approaching an intersection.

In this paper1, we propose a distributed fair-efficient power allocation game model for two-hop relay networks. The system model consists of N-parallel source-relay-destination links, where each source node sends its packets to its corresponding destination via a preassigned relay node using half-duplex Amplify-and-Forward (AF) relaying method. The previously reported works only account for the efficiency of system throughput, however in this paper we incorporate fairness into this problem and propose a distributed game model that balances the fairness and efficiency objectives.

In conventional two-tiered Wireless Sensor Networks (WSN), sensors in each cluster transmit observed data to a fusion center via an intermediate supernode. This structure is vulnerable to supernode failure. A double supernode system model with a new coding scheme is proposed to monitor a binary data source. A Distributed Joint Source Channel Code (D-JSCC) is proposed for sensors inside a cluster that provides two advantages of low complexity transmitters and scalability to a large number of sensors. In order to setup a robust communication channel from sensors to the data fusion center, Distributed Space-Time Block Coding (D-STBC) is employed at two supernodes prior to relaying that results in additional diversity gain. DeModulate and Forward (DMF) relaying mode is chosen to enable packet reformatting at the supernodes, which is not possible in widely used Amplify and Forward (AF) mode. The optimum power allocation for the two-hop multiple DMF relaying is calculated to minimize the system Bit Error Rate (BER). An upper bound is derived for the system end-to-end BER by analyzing a basic decoder operation over the system model. The simulation results validate this upper bound and also demonstrate considerable improvement in the system BER for the proposed coding scheme.

In this paper, problem of throughput optimization in relay networks where all users transmit their packets on a multiple-access channel is studied by introducing a new Markovian game theoretical solution. Despite the previously reported works, in the proposed model, simultaneously transmitted packets on a multiple-access channel are not always discarded. In this article, the possibility of capturing one of these packets is considered. Both cases of cooperative and non-cooperative stochastic game solutions are investigated and compared. The main objective is to maximize the system throughput with minimum transmission delay and power consumption cost. Effect of different packet error rates due to possible collision occurrence is considered in the game definition that improves system performance further. Performance of the proposed non-cooperative game model approaches the cooperative case, however the non-cooperative game model adds less signaling load to the system, therefore it is more likely to be used in practical applications.