Abstract

Edge server-assisted computation offloading enables vehicles to leverage server compute resources to deliver connected services, overcoming the limitations of onboard resources. Understanding the compute workloads of edge servers is crucial for effective resource management and scheduling, yet this task is challenging due to the complex interplay of factors such as vehicle mobility and computation offloading patterns. To address this, we propose an empirical analysis framework that systematically characterizes the compute workloads of edge servers. We begin by formalizing the relationships among three key aspects: local load (generated by vehicles), composite load (imposed on edge servers), and traffic flow (vehicle mobility patterns). Our framework then uses models of the local load and traffic flow as inputs to generate the composite loads on edge servers. Experiments were conducted by injecting between 600 and 5,000 vehicles per hour in two distinct geographical areas, New York City and Tampa. We provide a quantitative analysis demonstrating how the composite loads on edge servers vary with changes in traffic flows, geographical areas, and offloading patterns.

Abstract

Around the world, there are a lot of unreinforced masonry (URM) buildings situated in seismically active areas. Additionally, the majority of these buildings were not built in accordance with seismic code requirements. Buildings made of URM are seismically unsafe and require strengthening, as demonstrated by previous earthquakes. Masonry material exhibits a great deal of variability in its behaviour, and the tensile or flexural capacity of the structural components is one of the key factors in the seismic susceptibility of masonry buildings. The flexural strength and deformability of URM walls can be increased using a variety of retrofitting methods. These can be loosely divided into two categories: “conventional” and “advanced”. The surface treatments (e.g., shotcrete, reinforced plaster, ferrocement overlays, polyurea spray technology), stitching and grout or epoxy injections, re-pointing, reinforced concrete confinement, and post-tensioning fall under the first category. The second category includes the use of seismic wallpaper (i.e., fiber-reinforced polymers—FRP such as epoxy-bonded strips or in situ impregnated fabrics), textile-reinforced mortar composites (mesh/fabric reinforcement in the form of fibre, wire, polypropylene bands, plastic bags, bamboo, etc.), and centre core. The present study reviews the state-of-the-art literature on several methods for reinforcing URM walls subject to lateral earthquake loading. The paper provides a complete overview of retrofitting techniques, including benefits, suitability, applicability, drawbacks, restrictions, sustainability, and consequences on rural communities. In addition, the effectiveness of retrofitting methods is compared using factors including weight, technology (i.e., level of skill required), cost, manpower, and disruption to occupants. The study’s findings will help the policymakers, archaeological survey of India (ASI), various government departments owning low-rise masonry buildings, planners, building owners, architects, structural engineers, consultants, and designers, select an appropriate retrofitting system. Further, the design methodology for retrofitting masonry walls using advanced composites like TRM and FRP is also described in detail, using an explanatory example for seismic in-plane and out-of-plane actions.

Abstract

Certain self-supervised approaches to train image encoders, like CLIP, align images with their text captions. However, these approaches do not have an a priori incentive to learn to associate text inside the image with the semantics of the text. Humans process text visually; our work studies the semantics of text rendered in images. We show that the semantic information captured by image representations can decisively classify the sentiment of sentences and is robust against visual attributes like font and not based on simple character frequency associations.

Abstract

We present a method to compress the final linear layer of language models, reducing memory usage by up to 3.4 x without significant performance loss. By grouping tokens based on Byte Pair Encoding (BPE) merges, we prevent materialisation of the memory-intensive logits tensor. Evaluations on the TinyStories dataset show that our method performs on par with GPT-Neo and GPT2 while significantly improving throughput by up to 3x, making it suitable for low-compute environments.

Abstract

Forensic sketch-to-mugshot matching is a challenging task in face recognition, primarily hindered by the scarcity of annotated forensic sketches and the modality gap between sketches and photographs. To address this, we propose CLIP4Sketch, a novel approach that leverages diffusion models to generate a large and diverse set of sketch images, which helps in enhancing the performance of face recognition systems in sketch-to-mugshot matching. Our method utilizes Denoising Diffusion Probabilistic Models (DDPMs) to generate sketches with explicit control over identity and style. We combine CLIP and Adaface embeddings of a reference mugshot, along with textual descriptions of style, as the conditions to the diffusion model. We demonstrate the efficacy of our approach by generating a comprehensive dataset of sketches corresponding to mugshots and training a face recognition model on our synthetic data. Our results show significant improvements in sketch-to-mugshot matching accuracy over training on an existing, limited amount of real face sketch data, validating the potential of diffusion models in enhancing the performance of face recognition systems across modalities. We also compare our dataset with datasets generated using GAN-based methods to show its superiority.

Abstract

Portrait sketching involves capturing identity specific attributes of a real face with abstract lines and shades. Unlike photo-realistic images, a good portrait sketch generation method needs selective attention to detail, making the problem challenging. This paper introduces textbf{Portrait Sketching StyleGAN (PS-StyleGAN)}, a style transfer approach tailored for portrait sketch synthesis. We leverage the semantic $W+$ latent space of StyleGAN to generate portrait sketches, allowing us to make meaningful edits, like pose and expression alterations, without compromising identity. To achieve this, we propose the use of Attentive Affine transform blocks in our architecture, and a training strategy that allows us to change StyleGAN's output without finetuning it. These blocks learn to modify style latent code by paying attention to both content and style latent features, allowing us to adapt the outputs of StyleGAN in an inversion-consistent manner. Our approach uses only a few paired examples ($sim 100$) to model a style and has a short training time. We demonstrate PS-StyleGAN's superiority over the current state-of-the-art methods on various datasets, qualitatively and quantitatively.

Abstract

Edge computing allows for reduced latency and operational costs compared to centralized cloud systems. In this context, serverless functions are emerging as a lightweight and effective paradigm for managing computational tasks on edge infrastructures. However, the placement of such functions in constrained edge nodes remains an open challenge. On one hand, it is key to minimize network delays and optimize resource consumption; on the other hand, decisions must be made in a timely manner due to the highly dynamic nature of edge environments. In this paper, we propose POSEIDON, a solution based on Deep Reinforcement Learning for the efficient placement of functions at the edge. POSEIDON leverages Proximal Policy Optimization (PPO) to place functions across a distributed network of nodes under highly dynamic workloads. A comprehensive empirical evaluation demonstrates that POSEIDON significantly reduces execution time, network delay, and resource consumption compared to state-of-the-art methods.

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by challenges in social communication, repetitive behaviors, and restricted interests. Emerging research has emphasized the significance of metabolic dysfunctions in the pathophysiology of ASD, including abnormalities in energy production, mitochondrial dysfunction, and oxidative stress. This study explores metabolic alterations specific to brain tissues, cell types and blood in individuals with ASD by integrating omics data with the human metabolic network. We identified significant brain-specific metabolic changes in ASD, underscoring hypometabolism and reduced glucose utilization. Additionally, alterations in pathways related to fatty acid metabolism, amino acid metabolism, and vitamin metabolism were observed. The analysis of cell-specific metabolic activities in the ASD brain showed alterations in pathways in astrocytes, microglia, and oligodendrocytes. Metabolic gene expression in peripheral blood mononuclear cells (PBMC) samples also showed potential as diagnostic biomarkers. These findings offer insights into metabolic interventions in ASD, as well as potential biomarkers and therapeutic targets for ASD.

Abstract

In the circuit model of quantum computing, amplitude amplification techniques can be used to find solutions to NP-hard problems defined on n-bits in time poly(n)2^{n/2}. In this work, we investigate whether such general statements can be made for adiabatic quantum optimization, as provable results regarding its performance are mostly unknown. Although a lower bound of Ω(2^{n/2}) has existed in such a setting for over a decade, a purely adiabatic algorithm with this running time has been absent. We show that adiabatic quantum optimization using an unstructured search approach results in a running time that matches this lower bound (up to a polylogarithmic factor) for a broad class of classical local spin Hamiltonians. For this, it is necessary to bound the spectral gap throughout the adiabatic evolution and compute beforehand the position of the avoided crossing with sufficient precision so as to adapt the adiabatic schedule accordingly. However, we show that the position of the avoided crossing is approximately given by a quantity that depends on the degeneracies and inverse gaps of the problem Hamiltonian and is NP-hard to compute even within a low additive precision. Furthermore, computing it exactly (or nearly exactly) is #P-hard. Our work indicates a possible limitation of adiabatic quantum optimization algorithms, leaving open the question of whether provable Grover-like speed-ups can be obtained for any optimization problem using this approach.

Abstract

Cyber-physical systems (CPS), robotics, the Internet of Things (IoT), and automotive systems are integral to modern technology. They are characterized by their safety criticality, accuracy, and real-time control requirements. Control software plays a crucial role in achieving these objectives by managing and coordinating the operations of various sub-systems. This paper presents a novel systematic mapping study (SMS) for control software engineering, analyzing 115 peer-reviewed papers. The study identifies, classifies, and maps existing solutions, providing a comprehensive and structured overview for practitioners and researchers. Our contributions include (i) a unique classification of literature into six research themes—engineering phases, engineering approaches, engineering paradigms, engineering artefacts, target application domains, and engineering concerns; (ii) insights into the specificity of approaches to target technologies and phases; (iii) the prominence of model-driven approaches for design and testing; (iv) the lack of end-to-end engineering support in existing approaches; and (v) the emerging role of agile-based methods versus the dominance of waterfallbased methods. This paper’s significance lies in its thorough analysis and the high-level mapping of the solution space, offering new perspectives and a detailed roadmap for future research and innovation in control software engineering. The findings will guide advancements and best practices in the field, underscoring the paper’s impact.