Abstract

Deep learning assisted diagnosis for assessing the severity of various respiratory infections using chest Computed Tomography (CT) scan images has gained much attention after the COVID-19 pandemic. Major tasks while building such models require an understanding of the characteristic features associated with the disease, patient-to-patient variations and changes associated with disease severity. In this work, an attention-based Convolutional Neural Network (CNN) model with customized bottleneck residual module (Attn-CNN) is proposed for classifying CT images into three classes: COVID-19, Normal, and other Pneumonia. The efficacy of the model is evaluated by carrying out various experiments, such as effect of class imbalance, impact of attention module, generalizability of the model and providing visualization of model’s prediction for the interpretability of results. Comparative performance evaluation with five state-of-the-art deep architectures such as MobileNet, EfficientNet-B7, Inceptionv3, ResNet-50 and VGG-16, and with published models such as COVIDNet-CT, COVNet, COVID-Net CT2, etc. is discussed.

Abstract

No Results Found

Abstract

No Results Found

Abstract

Monuments were built for thousands of years as the most enduring and well-known representations of past civilizations. It is crucial to preserve these because they are national symbols with unique cultural and historical significance. The deterioration of the structures happens as a result of weathering, fire, natural disasters like earthquakes, construction flaws, and numerous other factors. In general, the issue with repairing and reinforcing regular buildings is very different from the issue with restoring monument buildings. The goal of keeping a monumental structure in use may be viewed as secondary in importance and any event as a result of the effort made to fulfil the main task. In the case of monumental buildings, emphasis is placed on the preservation of their aesthetic and historical aspects. Therefore, the restoration strives to protect and highlight the monument’s or building’s aesthetic and historical aspects. Choosing the appropriate material for the restoration depends on how the original structure looks. New materials must be compatible with those already used in the building. The goal of the present study is to provide an overview of the materials used to restore the structural integrity of historic structures and monuments that have been damaged by seismic activity. All of these buildings need extra attention because of their specific historical or architectural value, or because they are significant because they are still standing examples of a former way of life.

Abstract

Masonry structures cover a very wide range of monumental works in space and time, covering almost 6,000 years. The structural assessment of the load-carrying capacity of such old structures depends on several parameters such as: (a) material strength; (b) texture of the structure; (c) geometrical form and dimensions; (d) existing loading and constraints; and (e) expected loadings at failure. Detailed calculations are also required for the structural evaluation using most of the above parameters firstly by considering the gravity loads and secondly by the combination of gravity load and lateral action in areas of high seismicity. However, at the same time, it is equally significant for the structural engineer, who is involved in structural restoration design, to know in depth qualitatively the basic forms and their structural behaviour of monumental buildings. The structural engineer in charge must understand from the beginning, qualitatively, the structural behaviour of a building under consideration to various basic actions so that one can make a preliminary diagnosis of the causes that are responsible for the existing damages (cracks, drifts, settlements, splitting etc.). In this way, one will be in a position to focus on the detailed research, in situ and laboratory, to the critical points of the building, and can conduct the analysis and design using suitable models for a credible safety evaluation. Therefore, an effort is made in the present study to give a qualitative approach to the structural behaviour of the basic structural forms of masonry monumental and historical buildings, where the consequences of the seismic action are traumatic now and then. This article gives an outline and creates background information for further structural evaluation of the monuments.

Abstract

Corrosion creates a significant degradation mechanism in reinforced concrete (RC) structures, which would require a high cost of maintenance and repair in affected buildings. The right methods for structural retrofitting are, therefore, quite pivotal. Modification or rectification for any structure is normally categorized under three major categories: (i) Structural rehabilitation, (ii) Structural refurbishment, and (iii) Structural retrofit. All these activities have a thin but predominant line of differentiation. In contrast, the first two activities relate to enhancing the functional life of a structure that has been damaged under an adverse environment or condition. On the other hand, structural retrofit is an activity where the structure is updated in its basic parameters of sharing the load and supporting the superstructure. It improves the safety and durability of the structure. Further, when corrosion hits the structure, it results in a reduction in many important parameters to the extent that they go below their acceptable limits under national and international standards. It is indeed a perfect blend of structural dynamics or design engineering and functionality of the structure in the right proportion when retrofit action for a corrosion-hit structure is conceptualized and crafted. This paper aims to present and discuss various structural retrofitting methods for RC members affected by corrosion, supported by relevant real-world case studies.

Abstract

Gender bias in machine translation (MT) sys- tems poses a significant challenge to achieving accurate and inclusive translations. This paper examines gender bias in machine translation systems for languages such as Telugu and Kan- nada from the Dravidian family, analyzing how gender inflections affect translation accuracy and neutrality using Google Translate and Chat- GPT. It finds that while plural forms can reduce bias, individual-centric sentences often main- tain the bias due to historical stereotypes. The study evaluates the Chain of Thought process- ing, noting significant bias mitigation from 80% to 4% in Telugu and from 40% to 0% in Kan- nada. It also compares Telugu and Kannada translations, emphasizing the need for language specific strategies to address these challenges and suggesting directions for future research to enhance fairness in both data preparation and prompts during inference.

Abstract

Today’s open-source chip development ecosystem relies on various Electronic Design Automation (EDA) tools, accessible through permissive licenses on GitHub [1]–[3]. As the open-source chip design ecosystem ma- tures, the EDA tool maintainers gradually incorporate customized features to boost the user’s experience. Such is the case of OpenFASoC, an Open-Source, Fully Autonomous SoC Synthesis tool that uses customiz- able Cell-Based Synthesizable Analog Circuits. This process-agnostic tool delivers, through different alter- natives, a framework of integrated open-source tools capable of synthesizing highly optimized, verifiable analog blocks ready for tape-out with reproducible results [4]. The tool also boasts a cloud-based Contin- uous Integration (CI) framework that allows developers to continually collaborate and improve the tool while staying on the latest version. Keywords: Open-Source, Analog Automation, EDA, Cloud, Continuous Integration, IC.

Abstract

Current approaches to Analog Layout Automation apply ML techniques such as Graph Convolutional Neural Networks (GCN) to translate netlist to layout. While these ML approaches have proven to be effective, they lack the powerful reasoning capabilities, an intuitive human interface, and standard evaluation benchmarks that have been improving at a rapid development pace in Large Language Models (LLMs). The GLayout framework introduced in this work translates analog layout into an expressive, technology generic, compact text representation. Then, an LLM is taught to understand analog layout through fine-tuning and in-context learning using Retrieval Augmented Generation (RAG). The LLM is able to successfully layout unseen circuits based on new information provided in-context. We train 3.8, 7, and 22 Billion parameter quantized LLMs on a dataset of less than 50 unique circuits, and text documents providing layout knowledge. The 22B parameter model is tuned in 2 hours on a single NVIDIA A100 GPU. The open-source evaluation set is proposed as an automation benchmark for LLM layout automation tasks, and ranges from 2-transistor circuits to a ΔΣ ADC. The 22B model completes 70% of the tasks in the evaluation set, and passes DRC and LVS verification on 44% of evaluations with verified correct blocks up to 4 transistors in size.

Abstract

Data visualization is key to representing data effectively, especially in large multidimensional datasets. In this paper, we extend the BEADS i.e. breaking cluster into chunks of points and represent each chunk as bead. We do this to study the underlying pattern i.e. shape, size and location of the clusters and visualize them in a manner in which the users understand the distribution of the data points. BEADS cluster visualization system is implemented to represent the high-dimensional shape of a cluster by using standard two-dimensional structures like squares and circles as metaphors. This is achieved by subdividing clusters into smaller chunks, or "beads," using the K-means algorithm and optimizing the lp-norm value to determine the most suitable shape for each bead. The visualization helps comprehend the shape, size and overall placement of clusters in high dimensions. Future work involves finding the best number of beads for each cluster individually and improving the efficiency to speed up the process for large datasets. Instead of K-mean, any other appropriate partitioning algorithm could be used at the user's discretion.