The increasing cyber-physical integration in connected and autonomous vehicles (CAVs) has amplified the need for robust intrusion detection systems (IDS) to secure controller area network (CAN) communications. Existing deep learning approaches, such as CNNs and LSTMs, have demonstrated strong potential but often struggle to detect stealthy and sophisticated attacks, primarily due to inadequate temporal modeling and the use of datasets with limited fidelity that do not reflect real-world attack complexities. To address these limitations, we propose an optimized hybrid IDS model that integrates one-dimensional convolutional neural networks (1D-CNN) with bidirectional long short-term memory (BiLSTM) layers. The architecture is specifically designed to extract spatio-temporal features from CAN traffic with minimal complexity, enabling efficient detection of subtle attack patterns. Our model incorporates a time-aware design that allows it to detect attacks as they evolve, even when they occur in localized segments of the payload. It was trained and evaluated using the high-fidelity ORNL ROAD dataset, which includes physically validated fuzzing and targeted CAN ID attacks. The proposed model achieved an accuracy of 99.73%, a Matthews Correlation Coefficient (MCC) of 0.9401, and maintained average low false positive of (≤ 0.00045) and false negative of (≤ 0.00047) rates. It also demonstrated a low average prediction latency of 0.535 milliseconds per CAN frame, highlighting its architectural efficiency. This performance reflects a deliberate design balance between lightweight complexity and high detection accuracy, advancing the development of practical and robust deep learning-based IDS solutions for modern vehicular networks.

Intelligent Transportation Systems (ITS) rely on connected vehicles to overcome problems such as occlusions and potential accidents, due to non-line-of-sight (NLoS) and other perception challenges. These challenges are magnified when explored in conjunction with communication network limitations, such as limited coverage (e.g., base station limitations) or simple packet collisions. Regardless of the reason behind information loss, the successfully received information should be prioritized to allow successful cooperative perception and accident avoidance. We address these issues by proposing a clustering algorithm that considers information relevance to the receivers and requires no extra communication overhead or network infrastructure. Four different information scoring functions are explored to reorganize data based on its perception relevance in the different clusters, with collision awareness being the focal metric for cluster formation. Our proposed technique achieves the best reduction in the number of packets used compared to existing state-of-the-art: ETSI CPM rules, Look Ahead, and Redundancy Mitigation algorithms. Moreover, thanks to its packet prioritization and reordering, the proposed algorithm outperforms these approaches in terms of the number of packets successfully received by more than 25%. Additionally, it achieves 13.1% and 19.8% enhancement in newly perceived objects, compared to the CPM rules, for the urban and highway scenarios, respectively. Lastly, due to a 6X and 5X improvement in information quality, based on the developed information scoring functions, compared to the baselines for the urban and highway scenarios, respectively.

This paper introduces the new paradigm of Mobile Edge Learning "MEL" that enables the implementation of realistic distributed machine learning (DML) tasks on wireless edge nodes while taking into consideration the heterogeneous computing and networking environments. Therefore, a heterogeneity aware (HA) scheme is designed to solve the problem of dynamic task allocation for MEL in a way that maximizes the DML accuracy over wireless heterogeneous nodes or 'learners' while respecting the time constraints. The problem is first formulated as a quadratically-constrained integer linear program (QCILP). Being NP-hard, it is relaxed into a non-convex problem over real variables which can be solved using commercially available numerical solvers. The relaxation also allows us to propose a solution based on deriving the analytical upper bounds of the optimal solution using Lagrangian analysis and Karush-Kuhn-Tucker (KKT) conditions. The merits of the proposed analytical solution are demonstrated by comparing its performance to the numerical approaches and comparing the validation accuracy of the proposed HA scheme to the baseline heterogeneity unaware (HU) equal task allocation approach. Simulation results show that the HA schemes decrease convergence time up-to 56% and increase the final validation accuracy up-to 8%.

Cooperative perception is a widely adopted approach to cope with occlusion and non-line-of-sight limitations of the vehicles' local sensors. It enables vehicles to increase their awareness of the environment by sharing their local perception information with others using Vehicle-to-Everything (V2X) technology, thus, avoiding potential accidents. This paper studies the sensor errors and properties and reflects their impact on redundant information shared over communication while arguing for the cases where redundant information could be accepted. Specifically, three perspectives are evaluated: perception issues due to object detection errors, localization errors due to inaccuracy in the onboard navigation system (NS) and the effect of different perception Field of View (FoV). The system is implemented and evaluated using Simulation of Urban MObility (SUMO) traffic simulator and a centralized basestation that coordinates the CV2X communication. Results confirm that 63% of the missed vehicles due to detection error can be retrieved using the suggested Estimated Error Detection (EED) approach. The drawback is increasing the number of duplicate information sent to the receiver. While this exhausts the communication resources, it is still useful for cases where detection is hindered (e.g., by weather conditions). Moreover, our experiments show that the system becomes less reliable when the positioning error is above 1 meter. Lastly, we analyze the effect of the Field of View (FoV) on the centralized basestation objective value, highlighting the importance of 360° perception although it increases duplicate information (51%), pointing to further research required for mitigating duplicate information.

This paper proposes to maximize the accuracy of a distributed machine learning (ML) model trained on learners connected via the resource-constrained wireless edge. We jointly optimize the number of local/global updates and the task size allocation to minimize the loss while taking into account heterogeneous communication and computation capabilities of each learner. By leveraging existing bounds on the difference between the optimal and actual training loss, we derive an expression for the objective function in terms of the local updates. The resulting convex program is solved to obtain the optimal number of local updates which is used to obtain the total updates and batch sizes for each learner. The merits of the proposed solution, which is heterogeneity aware (HA), are exhibited by comparing its performance to the heterogeneity unaware (HU) approach.

In the age of Big Genomics Data, institutions such as the National Human Genome Research Institute (NHGRI) are challenged in their efforts to share volumes of data between researchers, a process that has been plagued by unreliable transfers and slow speeds. These occur due to throughput bottlenecks of traditional transfer technologies. Two factors that affect the efficiency of data transmission are the channel bandwidth and the amount of data. Increasing the bandwidth is one way to transmit data efficiently, but might not always be possible due to resource limitations. Another way to maximize channel utilization is by decreasing the bits needed for transmission of a dataset. Traditionally, transmission of big genomic data between two geographical locations is done using general-purpose protocols, such as hypertext transfer protocol (HTTP) and file transfer protocol (FTP) secure. In this paper, we present a novel deep learning-based data minimization algorithm that 1) minimizes the datasets during transfer over the carrier channels; 2) protects the data from the man-in-the-middle (MITM) and other attacks by changing the binary representation (content-encoding) several times for the same dataset: we assign different codewords to the same character in different parts of the dataset. Our data minimization strategy exploits the alphabet limitation of DNA sequences and modifies the binary representation (codeword) of dataset characters using deep learning-based convolutional neural network (CNN) to ensure a minimum of code word uses to the high frequency characters at different time slots during the transfer time. This algorithm ensures transmission of big genomic DNA datasets with minimal bits and latency and yields an efficient and expedient process. Our tested heuristic model, simulation, and real implementation results indicate that the proposed data minimization algorithm is up to 99 times faster and more secure than the currently used content-encoding scheme used in HTTP of the HTTP content-encoding scheme and 96 times faster than FTP on tested datasets. The developed protocol in C# will be available to the wider genomics community and domain scientists.

Pneumonia is a high mortality disease that kills 50, 000 people in the United States each year. Children under the age of 5 and older population over the age of 65 are susceptible to serious cases of pneumonia. The United States spend billions of dollars fighting pneumonia-related infections every year. Early detection and intervention are crucial in treating pneumonia related infections. Since chest x-ray is one of the simplest and cheapest methods to diagnose pneumonia, we propose a deep learning algorithm based on convolutional neural networks to identify and classify pneumonia cases from these images. For all three models implemented, we obtained varying classification results and accuracy. Based on the results, we obtained better prediction with average accuracy of (68%) and average specificity of (69%) in contrast to the current state-of-the-art accuracy that is (51%) using the Visual Geometry Group (VGG16 also called OxfordNet), which is a convolutional neural network architecture developed by the Visual Geometry Group of Oxford. By implementing more novel lung segmentation techniques, reducing over fitting, and adding more learning layers, the proposed model has the potential to predict at higher accuracy than human specialists and will help subsidies and reduce the cost of diagnosis across the globe.

Wireless communication became an essential tool for information exchange between modern Implantable Medical Devices (IMDs) and hospital servers. In spite of the many advantages of wireless technology, it puts the patients' health and data privacy in serious danger if no proper security mechanism is imployed. We aim to secure these devices while taking into consideration the limitations of these small devices. The IMDs have resources that are relatively simple and sometimes, once implemented in the body, require surgery to be altered. Consequently, common security mechanisms cannot be simply implemented in fear of consuming all the resources dedicated to healthcare needs. A certain balance between security and efficiency must thus be sought in each IMD architecture. In this work, we propose an encryption scheme for IMDs that stores its monitored data for future use. For privacy issues, not all the stored data should be accessed by any device that has access to the IMD. Certain privileges need to be allocated to different people to protect the privacy of the patient. Hence, we propose a new role-based encryption scheme, that both guarantees hierarchical access to personal data based on their role and still satisfies the computational limitations of IMDs. This scheme employs the Chinese Remainder properties to achieve the desired encryption hierarchy. The IMD uses keys form the same key pool for any encryption, and depending on the access rights of the users, the latter will only be able to decrypt the data he is allowed to. This work resulted in a secure scheme that we have proven it can formally protect the stored data. This scheme performs well under statistical analysis and is characterized by a relatively low complexity. Also, this work led to encrypted data with a lossless compression rate that saves on the communication cost.

We propose a real time data analysis solution for in-flight object detection. The presented solution is able to perform typical post-flight processing in real time, with minimal computational and power requirements, which allows its implementation on light-weight Unmanned Aircraft Systems (UAS). It utilizes adaptive segmentation and 3D convolutions that take advantage of the structure of the LiDAR point cloud, to identify vehicles and their respective positions within 3D point cloud segments that may include background clutter.

We revisit the problem of data redundancy in Wireless Sensor Networks (WSNs) from a Collaborative Signal and Information Processing (CSIP) perspective. We propose an Information Processing and Communication Reduction (IPCR) scheme that utilizes spectrum sensing to detect and eliminate data redundancy. IPCR adapts its functionality according to data-space correlations and is independent of spatial and temporal field correlations. Its operation is also independent of the underlying Medium Access Control (MAC) scheme and does not require location information. Compared to spatial/temporal correlation-based signal and information processing techniques, IPCR can achieve up to N-fold reduction in communication complexity, where N is the number of nodes in a neighborhood.

Successful deployment of Wireless Sensor Networks (WSNs) depends on energy efficiency in computations and networking operations. Significant research efforts have been pursued over the last decade to realize techniques aimed at data gathering while prolonging network lifetime. Within data gathering applications, there is a class of applications that do not reconstruct the entire sensing field but mainly focus on monitoring and event/anomaly detection scenarios. In such applications, only representative data values (or distinct within a given threshold) are desired from different geographical (spatial) regions. Utilizing existing data gathering techniques in this type of applications yields communication-inefficient solutions, and therefore expensive in terms of energy cost. In this paper we investigate a cross-layer approach to reduce the number of communication operations in such specialized data gathering/monitoring applications. We explore the use of overhearing at the MAC layer in modifying the behavior of the application layer to realize Dynamic Virtual Clusters (DVCs). DVCs reduce data redundancy and dynamically distribute cluster head responsibilities, thus balancing the load and prolonging the network lifetime. Despite the cost of overhearing, our results show a reduction in the number of communication operations by a factor of up to N-1, where N is the number of nodes in a neighborhood.

In this paper, we propose a Cross-Layer Application-aware Paradigm (CLAP) for designing and simulating Cross-Layer (CL) protocols. CLAP allows each layer to publish its local information to be shared with other layers and subscribe to other layers' shared information via an Information-Layer (I-Layer). The controlling layer, where optimization decisions are made, also utilizes the I-Layer to configure the behavior of other layers according to its current demands and their reported status. The publish/subscribe behavior is achieved by a new API designed as an augmentation to the SIDnet-SWANS simulator. This eliminates the need for bypassing/hacking conventional design hierarchies and simulator architectures, which greatly reduces the design and implementation complexities of CL protocols. CLAP facilitates CL interactions and extends the application layer's awareness and capabilities. This will lead CL protocol design in WSNs to a higher level of awareness via seamless CL information access and sharing, a new dimension of adaptability to operating conditions via continuous reconfiguration, and much simpler implementations.

This paper presents a duty cycling based cross layer MAC protocol for wireless sensor networks (WSNs), referred to as BulkMAC, to support the transmission of multihop multiple packet flows during a single sleep period. We show that without the proposed cross-layered approach, the sensor nodes will spend significant energy and induce longer delays. The proposed protocol cleverly schedules the channel allocation using the upper routing layer information. We implement our protocol in ns2.29 and compare it against RMAC (Routing Enhanced MAC Protocol) and PRMAC (Pipelined-RMAC). On the average, BulkMAC improves data delivery by a factor of 2.26 and 1.67 compared to RMAC and PRMAC, respectively, for data collection in random networks.