Advanced Real-time System Research Articles

AN INTEGRATED MACHINE LEARNING FRAMEWORK FOR ACCURATE CARDIOVASCULAR DISEASE PREDICTION

This paper introduces an advanced real-time system designed to predict cardiovascular diseases with integrated machine learning. Cardiovascular diseases, with the highest global mortality rate, have become increasingly prevalent, straining healthcare systems worldwide. These diseases, driven by factors such as high blood pressure, stress, age, gender, and cholesterol levels, have prompted numerous early diagnosis approaches, but their accuracy requires refinement due to the critical nature of cardiovascular diseases. This paper presents the DLCDD (Deep Learning based Cardiovascular Disease Diagnosis) framework, specifically addressing data-related challenges such as missing values and imbalances. The mean replacement technique is employed for handling missing values, while the Synthetic Minority Over-sampling Technique (SMOTE) is utilized to address imbalances in the dataset. In essence, DLCDD represents a significant advance in precise cardiovascular disease prediction, uniting deep learning with cutting-edge data processing and feature selection methods, addressing critical diagnostic challenges.

Deadline-Aware Scheduling for Maximizing Information Freshness in Industrial Cyber-Physical System

Age of Information is an interesting metric that captures the freshness of information in the underlying applications. It is a combination of both packets inter-arrival time and packet transmission delay. In recent times, advanced real-time systems rely on this metric for delivering status updates as timely as possible. This paper aims to accomplish optimal transmission scheduling policy to maintain the information freshness of real-time updates in the industrial cyber-physical systems. Here the coexistence of both cyber and physical units and their individual requirements to provide the quality of service is one of the critical challenges to handle. A greedy scheduling policy called deadline-aware highest latency first has been proposed for this purpose. This paper also gives the analytical proof of its optimality, and finally, the claim is validated by comparing the performance of our algorithm with other scheduling policies by extensive simulations.

Special issue on scheduling and timing analysis for advanced real-time systems

Real-time embedded systems such as those found in automotive, aerospace, and other domains are characterised not only by the need for functional correctness, but also the need for temporal or timing correctness. Typically they continually monitor and respond to stimuli from the environment and the physical systems that they control. In order for such systems to behave correctly, they must not only execute the correct computations, but also do so within predefined time constraints or deadlines on the elapsed time between a stimuli and the corresponding response. Advances in software development methods, hardware technology, and the need to focus on energy efficiency pose significant challenges to the analysis of the overall timing behaviour of real-time systems. With hardware technology continuing to scale through the sub-micron to the deep sub-micron domain (e.g. 35–10nm) factors such as the increased probability of circuit failure causing permanent faults, and increased power consumption and problems of heat dissipation come to the fore. Further, increasing hardware capability has enabled significant increases in the volume and complexity of the software deployed in real-time applications; a trend that is set to continue. As a way of managing this complexity, software is often now produced via Model Based Design methods complemented by automatic code generation. Such an approach poses a severe challenge to the effectiveness of current worst-case execution time analysis techniques, but also opens up opportunities for tracking software

Continuous media communication with dynamic QOS control using ARTS with an FDDI network

Continuous media communication requires timely delivery of data such as digital video and audio packets. Quality of Service (QOS) parameters specify the temporal and spatial characteristic of such continuous media data. To insure timely delivery of continuous media data, the system needs to minimize the communication delay by securing required processor and network resources. We have extended the Capacity-Based Session Reservation Protocol(CBSRP), which was proposed to realizing predictable real-time communications, to support dynamic control of QOS. We have implemented a QOS control scheme by which the network dynamically adjusts the allocations of network bandwidth on a Fiber Distributed Data Interface(FDDI) network. In this paper, we describe the definition of our QOS model, the extension of CBSRP to support dynamic control of QOS, and the implementation and evaluation of extended CBSRP in our distributed systems testbed, Advanced Real-Time System(ARTS).