Cybersecurity has become an inevitable concern in the healthcare industry due to the rapid growth of the Internet of Health Things (IoHT). The IoHT is revolutionizing healthcare by enabling remote access to hospital equipment, real-time patient monitoring, and urgent alerts to patients and hospitals. However, the convenience of these systems also makes them vulnerable to cyberattacks, with hackers seeking to disrupt health services or extort money through ransomware attacks. Efficiently detecting multiple threats is a challenging task because IoHT generates large temporal data and system log information. In this article, we propose time-series classification models for the identification of potential cyberattacks in IoHT networks. First, we introduce neighborhood component analysis (NCA) with modifications of the regularization parameter to select the vital input features. With the selected features, we propose two LSTM-based models: 1) directed acyclic graph-based long short-term memory (DAG-LSTM) and 2) projected layer-based long short-term memory (PL-LSTM) for detecting cyberattacks. We evaluate the existing time-series classification models [i.e., gated recurrent unit (GRU), LSTM, and bilinear LSTM (Bi-LSTM)] and proposed models (i.e., DAG-LSTM and PL-LSTM) using real-world IoHT data. We also validate the models by applying a nonparametric statistical test, Friedman test. Our evaluation results show that the proposed DAG-LSTM achieves the highest accuracy with 99.89% training and 92.04% an average testing accuracy.

As the performance and accuracy of machine learning and AI algorithms improve, the demand for adopting computer vision techniques to solve various problems, such as autonomous driving and AI robots, increases. To meet such demand, IoT and edge devices, which are small enough to be adopted in various environments while having sufficient computing capabilities, are being widely adopted. However, as devices are utilized in IoT and edge environments, which have harsh restrictions compared to traditional server environments, they are often limited by low computational and memory resources, in addition to the limited electrical power supply. This necessitates a unique approach for small IoT devices that are required to run complex tasks. In this paper, we propose a concurrent multi-frame processing scheme for real-time object detection algorithms. To do this, we first divide the video into individual frames and group the frames according to the number of cores in the device. Then, we allocate a group of frames per core to perform the object detection, resulting in parallel detection of multiple frames. We implement our scheme in YOLO (You Only Look Once), one of the most popular real-time object detection algorithms, on a state-of-the-art, resource-constrained IoT edge device, Nvidia Jetson Orin Nano, using real-world video and image datasets, including MS-COCO, ImageNet, PascalVOC, DOTA, animal videos, and car-traffic videos. Our evaluation results show that our proposed scheme can improve the diverse aspect of edge performance and improve the runtime, memory consumption, and power usage by up to 445%, 69%, and 73%, respectively. Additionally, it demonstrates improvements of 2.10× over state-of-the-art model optimization.

As data is becoming more and more important, Internet of Things (IoT) devices are widely used to collect information and process data from various industries such as finance, autonomous driving, and smart factories. To address the limited computational power of IoT devices in processing real-time data, both edge computing, which utilizes nearby computers with greater computation capabilities, and cloud computing with even more processing power, are widely adopted solutions. As these systems have heterogeneous software and hardware configurations, it can be challenging to understand the behavior of the application from the perspective of different resources. In this paper, we propose an efficient logging and monitoring system in large-scale, heterogeneous environments for IoT and edge applications. To do this, our scheme first collects system resource usage data from each compute node using the operating system’s native system analysis tool. Then, it consolidates the system resource usage information from multiple nodes into an integrated database which creates a comprehensive view of the system. Finally, our scheme provides global system resource information in terms of specific jobs and nodes, providing a comprehensive understanding of complex heterogeneous hardware/software stacks. Our evaluation, using IoT and Edge workloads in heterogeneous systems, demonstrates the efficiency of logging and monitoring schemes. The average network usage for Windows and Linux is 0.12KB and 1.29KB per second, respectively, resulting in minimal network overhead. In addition, the proposed scheme shows negligible overhead in terms of both runtime (up to 0.73%) and storage (0.0474%).

We propose a secure and scalable file-encryption scheme for cloud systems by integrating Post-Quantum Cryptography (PQC), Quantum Key Distribution (QKD), and Advanced Encryption Standard (AES) within a distributed architecture. While prior studies have primarily focused on secure key exchange or authentication protocols (e.g., layered PQC-QKD key distribution), our scheme extends beyond key management by implementing a distributed encryption architecture that protects large-scale files through integrated PQC, QKD, and AES. To support high-throughput encryption, our proposed scheme partitions the target file into fixed-size subsets and distributes them across slave nodes, each performing parallel AES encryption using a locally reconstructed key from a PQC ciphertext. Each slave node receives a PQC ciphertext that encapsulates the AES key, along with a PQC secret key masked using QKD based on the BB84 protocol, both of which are centrally generated and managed by the master node for secure coordination. In addition, an encryption and transmission pipeline is designed to overlap I/O, encryption, and communication, thereby reducing idle time and improving resource utilization. The master node performs centralized decryption by collecting encrypted subsets, recovering the AES key, and executing decryption in parallel. Our evaluation using a real-world medical dataset shows that the proposed scheme achieves up to 2.37× speedup in end-to-end runtime and up to 8.11× speedup in encryption time over AES (Original). In addition to performance gains, our proposed scheme maintains low communication cost, stable CPU utilization across distributed nodes, and negligible overhead from quantum key management.

The importance of data is becoming more and more prominent as modern applications produce a large amount of data. It is becoming common for applications to produce and process gigabytes or even terabytes of data. To improve the performance of data-intensive applications, the underlying storage systems utilize the I/O characteristics of applications such as access patterns to improve the storage performance. For example, existing storage schemes store frequently accessed data in high performance storage devices such as NVMe SSDs for low latency and stores rarely access data in low performance but high capacity storage devices such as tape storage for cost-efficiency. Thus, as the importance of data arises, it is important to understand the I/O characteristics of applications. In this paper, we propose an access pattern prediction scheme to understand the I/O characteristics of applications and utilize the characteristics for fast I/O processing. Our scheme uses the application history and machine learning algorithm to accurately predict the pattern. To do this, we first utilize a system log to collect access pattern data of applications. Then, by using the logs, we set up a machine learning based prediction model using the long short-term memory (LSTM) algorithm. Finally, when the application is executed repeatedly, we use the prediction model to predict the I/O requests of the application which can be used to improve the storage performance. Evaluation result using a real big data application shows that the proposed scheme can accurately predict the access pattern.

Large-scale quantum circuit simulation on high-performance computing (HPC) systems is crucial for developing and verifying quantum algorithms to overcome the limitations of current noisy quantum computers. However, existing simulators face scalability bottlenecks due to memory limits and communication overhead. Many state-of-the-art approaches rely on static circuit partitioning, which makes it difficult to address the exponential growth in problem size as the number of qubits increases. To overcome these challenges, we present ScaleQsim, a highly scalable quantum circuit simulation framework for large-scale HPC systems. ScaleQsim focuses on providing a unified representation of the full qubit state, yet provides scalability through efficient synchronization and communication. ScaleQsim adopts a novel full state vector partitioning strategy that evenly distributes the full state vector across multiple nodes and GPUs. This distributed structure enables efficient parallel gate execution without costly synchronization, and ScaleQsim applies adaptive kernel configuration, which adjusts execution parameters based on GPU resources and task granularity to enhance simulation efficiency. Our evaluation on a leadership-scale supercomputer with up to 512 GPUs demonstrates that ScaleQsim simulates quantum circuits with up to 42 qubits and outperforms leading SOTA simulators by up to 77.40× across various quantum circuits.