system-Level Test (SLT) has been an integral part of integrated circuit test flows for over a decade and continues to be significant. Nevertheless, there is a lack of systematic approaches for generating test programs...
详细信息
ISBN:
(数字)9798350349320
ISBN:
(纸本)9798350349337
system-Level Test (SLT) has been an integral part of integrated circuit test flows for over a decade and continues to be significant. Nevertheless, there is a lack of systematic approaches for generating test programs, specifically focusing on the non-functional aspects of the Device under Test (DUT). Currently, test engineers manually create test suites using commercially available software to simulate the end-user environment of the DUT. This process is challenging and laborious and does not assure adequate control over non-functional properties. This paper proposes to use Large Language Models (LLMs) for SLT program generation. We use a pre-trained LLM and fine-tune it to generate test programs that optimize non-functional properties of the DUT, e.g., instructions per cycle. Therefore, we use Gem5, a microarchitectural simulator, in conjunction with Reinforcement Learning-based training. Finally, we write a prompt to generate C code snippets that maximize the instructions per cycle of the given architecture. In addition, we apply hyperparameter optimization to achieve the best possible results in inference.
system-Level Test (SLT) is essential for testing integrated circuits, focusing on functional and non-functional properties of the Device under Test (DUT). Traditionally, test engineers manually create tests with comme...
详细信息
ISBN:
(数字)9798350366884
ISBN:
(纸本)9798350366891
system-Level Test (SLT) is essential for testing integrated circuits, focusing on functional and non-functional properties of the Device under Test (DUT). Traditionally, test engineers manually create tests with commercial software to simulate the DUT's end-user environment. This process is both time-consuming and offers limited control over non-functional properties. This paper proposes Large Language Models (LLMs) enhanced by Structural Chain of Thought (SCoT) prompting, a temperature schedule, and a pool of previously generated snippets to generate high-quality code snippets for SLT. We repeatedly query the LLM for a better snippet using previously generated snippets as examples, thus creating an iterative optimization loop. This approach can automatically generate snippets for SLT that target specific non-functional properties, reducing time and effort. Our findings show that this approach improves the quality of the generated snippets compared to unstructured prompts containing only a task description.
Within the paradigm of Evolving and Adaptive Intelligent systems, the Electrical Power system (EPS) represents a Critical Infrastructure demanding robust reliability metrics. This study pioneers the application of Var...
详细信息
ISBN:
(数字)9798350366235
ISBN:
(纸本)9798350366242
Within the paradigm of Evolving and Adaptive Intelligent systems, the Electrical Power system (EPS) represents a Critical Infrastructure demanding robust reliability metrics. This study pioneers the application of Variable Neighborhood Search (VNS) heuristic to the Optimal Switch Allocation (OSA) problem in the EPS. Adapting neighborhood structures and local search methods, we consider the joint allocation of Manual Switches and Remote-Controlled switches, addressing interdependencies. Results highlight VNS efficacy in navigating OSA challenges, showcasing its adaptability in an evolving system. Comparative analyses endorse VNS as a valuable tool for addressing EPS reliability within the dynamic landscape of evolving and adaptive intelligent systems.
The key goals in learning Bayesian networks (BNs) from data are to identify significant statistical relationships between variables and to build a Directed Acyclic Graph (DAG) that represents these relationships throu...
详细信息
ISBN:
(数字)9798350366235
ISBN:
(纸本)9798350366242
The key goals in learning Bayesian networks (BNs) from data are to identify significant statistical relationships between variables and to build a Directed Acyclic Graph (DAG) that represents these relationships through Joint Probability Distributions. Most research relies on score-based or conditional test methods for model selection. However, when using real-world data, it can be challenging to identify whether the learned DAG represents the underlying relations inherent in the limited datasets, particularly when evaluating data obtained from multiple independent sources. This study presents a methodology to assess the credible interval for both the existence and direction of each edge within Bayesian networks derived from data. Furthermore, it explores the fusion of models acquired from distinct and independent datasets. This approach enables the Bayesian learning of Bayesian Networks (BNs) from data by treating the uncertainty associated with the existence and orientation of each edge as a random variable. By evaluating the probability of the orientation of each edge, it is possible to suggest the existence of a potential latent variable within the dataset. If an edge exhibits equiprobable directions and is verified to exist, it becomes a plausible hypothesis for a latent variable. The Fast Causal Algorithm, originally introduced by [1], is the foundation of this approach. Finally, by employing a maximum a posteriori estimation, the most prominent edges and their respective orientations are identified and employed to create the leading DAG. We present our findings in simulated datasets with different length sizes. By comparing the structure of the learned DAGs with existing structures and evaluating the inference capabilities of the final BN, we establish that our approach achieves results comparable to the most recent studies in the field, while offering insights into the model’s reliability and improving the use of the data.
Spike detection plays a central role in neural data processing and brain-machine interfaces (BMIs). A challenge for future-generation implantable BMIs is to build a spike detector that features both low hardware cost ...
详细信息
One of the problems faced by engineering and science students is focusing solely on technical knowledge while needing more cultural context. In today's interconnected world, addressing global challenges necessitat...
详细信息
In text mining, Latent Semantic Analysis (LSA) is the popular method to reduce the dimension of document vectors. Since LSA produces a set of topics by statistical information, the meaning of each topic is not *** pro...
详细信息
A Digital Twin for Mobility (DTmob) is based on the digital representation of the real-world transport system. A crucial element underlying the development of such systems is an accurate simulation of traffic flows wi...
详细信息
A Digital Twin for Mobility (DTmob) is based on the digital representation of the real-world transport system. A crucial element underlying the development of such systems is an accurate simulation of traffic flows within the road network, which is generally based on transport demand data in the form of Origin-Destination (O-D) matrices. Estimating demand matrices accurately is a complex challenge, as they are hindered by incomplete data, inaccuracies in transport models and temporal-spatial variability. In this paper we present an integrated methodological approach for the calibration of O-D matrices via the implementation of an iterative calibration procedure incorporating a traffic survey dataset, followed by the assignment procedure performed by a macrosimulation model. This study addresses this issue by employing Nielsen’s Single Path Matrix Estimation Method (SPME) jointly with the macrosimulation tool PTV Visum, developing a script in Python to achieve their integration. We tested it on the real-case study of Catania urban road network (Italy). Several scenarios have been analyzed and evaluated through the GEH statistic as KPI, also providing results with Ordinary Least Square (OLS) method as benchmark. Obtained results prove the validity of our integrated framework as the threshold in terms of the difference between estimated and counted flows was satisfied in all performed analyses. Research findings lay the basis for investigate further calibration algorithms and for exploring the use of real-time data in line with DTmob requirements.
Developing force control mechanisms employing electromagnetics is on the rise in active control applications for flexible mechanical systems like marine engines and shipboard machinery. Electromagnetic control devices...
详细信息
Developing force control mechanisms employing electromagnetics is on the rise in active control applications for flexible mechanical systems like marine engines and shipboard machinery. Electromagnetic control devices offer superior performance indicators compared to traditional mechanical force actuators in terms of longevity, energy efficiency, maintenance requirements, rapid control response, and high operating speeds. This article investigates the use of magnetic actuation and switching power electronics in addressing the stabilization and tracking control challenges encountered in the dynamics of a mechanical system with a single degree of freedom, comprising mass, spring, and damper elements. Particularly, a linear mechanical oscillator is nonlinearly coupled with an electromagnet and its associated driving circuit via the magnetic field. The electromagnetically actuated mechanical system exhibits characteristics of a differentially flat nonlinear system. A control strategy is suggested for the purpose of tracking reference position trajectories using output feedback linearization. The synthetic linearized control signal is subsequently guided to a DC-DC buck converter, able to regulate the system’s input voltage in a wide range of operation, by switching the duty cycle. The converter is described using a precise electrical model of the system, accounting for parasitic resistances in the inductor, capacitor, and switches. An averaged state space approach is utilized to create a mathematical nonlinear model for the converter which is then linearized by employing the Exact Feedback Linearization technique. By applying optimal control theory, the controller's coefficients are fine-tuned for optimal performance. To assess the proposed method's performance, the dynamics of the compensated mechatronic system is simulated using MATLAB/Simulink. The simulation results demonstrate that the proposed control scheme choice for active control of vibrating mechanical system
"Power Consumption Dash Board Using IoT" was developed using a web application. The planned system includes a home energy monitoring system and cloud service notifications. An Internet of Things (IoT) platfo...
详细信息
暂无评论