Search

In this paper, we explore the integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to enhance automated design and software development in the automotive industry. We present two case studies: a standardization compliance chatbot and a design copilot, both utilizing RAG to provide accurate, context-aware responses. We evaluate four LLMs-GPT-4o, LLAMA3, Mistral, and Mixtral -- comparing their answering accuracy and execution time. Our results demonstrate that while GPT-4 offers superior performance, LLAMA3 and Mistral also show promising capabilities for local deployment, addressing data privacy concerns in automotive applications. This study highlights the potential of RAG-augmented LLMs in improving design workflows and compliance in automotive engineering., Comment: Conference paper accepted in IEEE FLLM 2024

The core of a good model is in its ability to focus only on important information that reflects the basic patterns and consistencies, thus pulling out a clear, noise-free signal from the dataset. This necessitates using a simplified model defined by fewer parameters. The importance of theoretical foundations becomes clear in this context, as this paper relies on established results from the domain of advanced sparse optimization, particularly those addressing nonlinear differentiable functions. The need for such theoretical foundations is further highlighted by the trend that as computational power for training NNs increases, so does the complexity of the models in terms of a higher number of parameters. In practical scenarios, these large models are often simplified to more manageable versions with fewer parameters. Understanding why these simplified models with less number of parameters remain effective raises a crucial question. Understanding why these simplified models with fewer parameters remain effective raises an important question. This leads to the broader question of whether there is a theoretical framework that can clearly explain these empirical observations. Recent developments, such as establishing necessary conditions for the convergence of iterative hard thresholding (IHT) to a sparse local minimum (a sparse method analogous to gradient descent) are promising. The remarkable capacity of the IHT algorithm to accurately identify and learn the locations of nonzero parameters underscores its practical effectiveness and utility. This paper aims to investigate whether the theoretical prerequisites for such convergence are applicable in the realm of neural network (NN) training by providing justification for all the necessary conditions for convergence. Then, these conditions are validated by experiments on a single-layer NN, using the IRIS dataset as a testbed.

The proliferation of deep learning has significantly advanced various fields, yet Human Activity Recognition (HAR) has not fully capitalized on these developments, primarily due to the scarcity of labeled datasets. Despite the integration of advanced Inertial Measurement Units (IMUs) in ubiquitous wearable devices like smartwatches and fitness trackers, which offer self-labeled activity data from users, the volume of labeled data remains insufficient compared to domains where deep learning has achieved remarkable success. Addressing this gap, in this paper, we propose a novel approach to improve wearable sensor-based HAR by introducing a pose-to-sensor network model that generates sensor data directly from 3D skeleton pose sequences. our method simultaneously trains the pose-to-sensor network and a human activity classifier, optimizing both data reconstruction and activity recognition. Our contributions include the integration of simultaneous training, direct pose-to-sensor generation, and a comprehensive evaluation on the MM-Fit dataset. Experimental results demonstrate the superiority of our framework with significant performance improvements over baseline methods., Comment: Accepted in IEEE 6th International Conference on Activity and Behavior Computing (ABC 2024)

We present a prototype of a tool leveraging the synergy of model driven engineering (MDE) and Large Language Models (LLM) for the purpose of software development process automation in the automotive industry. In this approach, the user-provided input is free form textual requirements, which are first translated to Ecore model instance representation using an LLM, which is afterwards checked for consistency using Object Constraint Language (OCL) rules. After successful consistency check, the model instance is fed as input to another LLM for the purpose of code generation. The generated code is evaluated in a simulated environment using CARLA simulator connected to an example centralized vehicle architecture, in an emergency brake scenario.

We propose a novel model- and feature-based approach to development of vehicle software systems, where the end architecture is not explicitly defined. Instead, it emerges from an iterative process of search and optimization given certain constraints, requirements and hardware architecture, while retaining the property of single-system illusion, where applications run in a logically uniform environment. One of the key points of the presented approach is the inclusion of modern generative AI, specifically Large Language Models (LLMs), in the loop. With the recent advances in the field, we expect that the LLMs will be able to assist in processing of requirements, generation of formal system models, as well as generation of software deployment specification and test code. The resulting pipeline is automated to a large extent, with feedback being generated at each step.

Recently-demonstrated high-quality three-dimensional (3D) subsurface laser processing inside crystalline silicon (c-Si) wafers opens a door to a wide range of novel applications in multidisciplinary research areas. Using this technique, a novel maskless micro-pillars with precise control on the surface reflection and coverage are successfully fabricated by etching the laser processed region of c-Si wafer. To achieve this, a particular selective wet chemical etching is developed to follow subsurface laser processing of c-Si to reveal the desired 3D structures with smooth surfaces. Here, we report the development of a novel chromium-free chemical etching recipe based on copper nitrate, which yields substantially smooth surfaces at high etch rate and selectivity on the both laser-processed Si surface and subsurface, i.e., without significant etching of the unmodified Si. Our results show that the etch rate and surface morphology are interrelated and strongly influenced by the composition of the adopted etching solution. After an extensive compositional study performed at room temperature, we identify an etchant with a selectivity of over 1600 times for laser-modified Si with respect to unmodified Si. We also support our findings using density functional theory calculations of HF and Cu adsorption energies, indicating significant diversity on the c-Si and laser-modified surfaces.

This paper outlines a new approach to designing tunable electromagnetic (EM) graphene-based metasurfaces using convolutional neural networks (CNNs). EM metasurfaces have previously been used to manipulate EM waves by adjusting the local phase of subwavelength elements within the wavelength scale, resulting in a variety of intriguing devices. However, the majority of these devices have only been capable of performing a single function, making it difficult to achieve multiple functionalities in a single design. Graphene, as an active material, offers unique properties, such as tunability, making it an excellent candidate for achieving tunable metasurfaces. The proposed procedure involves using two CNNs to design the passive structure of the graphene metasurfaces and predict the chemical potentials required for tunable responses. The CNNs are trained using transfer learning, which significantly reduced the time required to collect the training dataset. The proposed inverse design methodology demonstrates excellent performance in designing reconfigurable EM metasurfaces, which can be tuned to produce multiple functions, making it highly valuable for various applications. The results indicate that the proposed approach is efficient and accurate and provides a promising method for designing reconfigurable intelligent surfaces for future wireless communication systems.

The year 2020 was a challenging year known mainly as the pandemic year. However, the notable event of George Floyd's killing broke many humans' hearts and made them protest on social media and the streets as well. In this research, we studied the hashtag "BlackLivesMatter," and some of its adversary contentions regarding George Floyd's demise in 2020 on Twitter. Based on the extensive aftermath of protests in the United States, we considered an area analysis to compare tweet rates in different groups to some previously studied statistics. The purpose is to investigate how racism content is correlated with life expectancy, poverty, and education. Findings revealed a significant relationship between online color-based contents and some physical world indicators.

Leukemia (blood cancer) is an unusual spread of White Blood Cells or Leukocytes (WBCs) in the bone marrow and blood. Pathologists can diagnose leukemia by looking at a person's blood sample under a microscope. They identify and categorize leukemia by counting various blood cells and morphological features. This technique is time-consuming for the prediction of leukemia. The pathologist's professional skills and experiences may be affecting this procedure, too. In computer vision, traditional machine learning and deep learning techniques are practical roadmaps that increase the accuracy and speed in diagnosing and classifying medical images such as microscopic blood cells. This paper provides a comprehensive analysis of the detection and classification of acute leukemia and WBCs in the microscopic blood cells. First, we have divided the previous works into six categories based on the output of the models. Then, we describe various steps of detection and classification of acute leukemia and WBCs, including Data Augmentation, Preprocessing, Segmentation, Feature Extraction, Feature Selection (Reduction), Classification, and focus on classification step in the methods. Finally, we divide automated detection and classification of acute leukemia and WBCs into three categories, including traditional, Deep Neural Network (DNN), and mixture (traditional and DNN) methods based on the type of classifier in the classification step and analyze them. The results of this study show that in the diagnosis and classification of acute leukemia and WBCs, the Support Vector Machine (SVM) classifier in traditional machine learning models and Convolutional Neural Network (CNN) classifier in deep learning models have widely employed. The performance metrics of the models that use these classifiers compared to the others model are higher.

In this paper the simplified double-spherical harmonics SDPN, approximation of the neutron transport equation is proposed. The SDPN equations are derived from the multi-group DPN equations for N=1,2,3 (comparable to the SP3, SP5, and SP7 equations, respectively), and are converted into the form of second order multi-group diffusion equations. The finite element method with the variational approach is then used to numerically solve these equations. The computational performance of the SDPN method is compared with the SPN on several fixed-source and criticality test problems. The results show that the SDPN formulation generally results in parameters like criticality eigenvalue, disadvantage factors, absorption rate, etc. more accurately than the SPN, even up to an order of magnitude more precise, while the computational effort is the same for both methods., Comment: 25 pages, 9 figures, 11 tables

Spatial patterns of elevated wall shear stress and pressure due to blood flow past aortic stenosis (AS) are studied using GPU-accelerated patient-specific computational fluid dynamics. Three cases of moderate AS, one with a dilated ascending aorta and two within the normal range (root diameter less than 4cm) are simulated for physiological beat cycle waveforms obtained from echocardiography data. The computational framework is built based on sharp-interface Immersed Boundary Method, where aortic geometries segmented from CT angiograms are integrated into a high-order incompressible Navier-Stokes solver. We show that even though the wall shear stress is elevated and oscillatory due to turbulence in the ascending aorta for all the cases, its spatial distribution is significantly more focused for the case with dilation than those without dilation. This focal area is linked to aortic valve jet impingement on the outer curvature of the ascending aorta, and has been shown in vivo using 4D flow MRI of aortic stenosis patients with aortic dilation (van Ooij et al., J. Am. Heart Assoc., 6(9), 2017). We show that this focal area also accommodates a persistent pocket of high pressure, which is likely to have contributed to the dilation process through an increased wall-normal forcing. The cases without dilation, on the contrary, showed a rather oscillatory pressure behaviour, with no persistent pressure buildup effect. We further argue that a more proximal branching of the aortic arch could explain the lack of a focal area of elevated wall shear stress and pressure, because it interferes with the impingement process due to fluid suction effects. These phenomena are further illustrated using an idealized aortic geometry. We finally show that a restored inflow condition eliminates the focal area of elevated wall shear stress and pressure zone from the ascending aorta.

In recent years, the existence of a significant cross-impact between Cloud computing and Internet of Things (IoT) has lead to a dichotomy that gives raise to Cloud-Assisted IoT (CAIoT) and IoT-Based Cloud (IoTBC). Although it is pertinent to study both technologies, this paper focuses on CAIoT, and especially its security issues, which are inherited from both Cloud computing and IoT. This study starts with reviewing existing relevant surveys, noting their shortcomings, which motivate a comprehensive survey in this area. We proceed to highlight existing approaches towards the design of Secure CAIoT (SCAIoT) along with related security challenges and controls. We develop a layered architecture for SCAIoT. Furthermore, we take a look at what the future may hold for SCAIoT with a focus on the role of Artificial Intelligence(AI)., Comment: The authors metadata field and some parts of paper during replacement has been updated in the new version

Adopting cryptography has given rise to a significant evolution in Artificial Intelligence (AI). This paper studies the path and stages of this evolution. We start with reviewing existing relevant surveys, noting their shortcomings, especially the lack of a close look at the evolution process and solid future roadmap. These shortcomings justify the work of this paper. Next, we identify, define and discuss five consequent stages in the evolution path, including Crypto-Sensitive AI, Crypto-Adapted AI, Crypto-Friendly AI, Crypto-Enabled AI, Crypto-Protected AI. Then, we establish a future roadmap for further research in this area, focusing on the role of quantum-inspired and bio-inspired AI.