In the last decade, despite rapid advancements in artificial intelligence (AI) transforming many industry practices, construction largely lags in adoption. Recently, the emergence and rapid adoption ...of advanced large language models (LLMs) like OpenAI’s GPT, Google’s PaLM, and Meta’s Llama have shown great potential and sparked considerable global interest. However, the current surge lacks a study investigating the opportunities and challenges of implementing Generative AI (GenAI) in the construction sector, creating a critical knowledge gap for researchers and practitioners. This underlines the necessity to explore the prospects and complexities of GenAI integration. Bridging this gap is fundamental to optimizing GenAI’s early stage adoption within the construction sector. Given GenAI’s unprecedented capabilities to generate human-like content based on learning from existing content, we reflect on two guiding questions: What will the future bring for GenAI in the construction industry? What are the potential opportunities and challenges in implementing GenAI in the construction industry? This study delves into reflected perception in literature, analyzes the industry perception using programming-based word cloud and frequency analysis, and integrates authors’ opinions to answer these questions. This paper recommends a conceptual GenAI implementation framework, provides practical recommendations, summarizes future research questions, and builds foundational literature to foster subsequent research expansion in GenAI within the construction and its allied architecture and engineering domains.
Assessment of interactions of ibuprofen and magnesium trisilicate after co-processing has been carried out by infrared spectroscopy. Dry-state ball-milling and, aqueous state kneading and ...freeze-drying were performed. FTIR spectroscopy of co-processed materials described acid-base reaction between the carboxylic acid containing ibuprofen to a significant extent. Increased absorbance of carboxylate peak accompanied by a consistently reduced absorbance of the carbonyl acid peak was evident. Absorbance of carboxylate peak was more in freeze-dried sample compared to milled product. Intermolecular hydrogen bonding between ibuprofen and magnesium trisilicate in the co-processed material has been suggested. Inhibition of crystal morphology has been noticed in the photomicrographs of both the products. DSC report has shown absence or significantly decreased melting endotherm representing almost complete amorphization of ibuprofen. Release of drug increased greatly after co-processing in comparison to crystalline ibuprofen. Freeze-dried samples have improved drug release more significantly compared to ball-milled samples.
This research investigates the ease with which people in India can access natural disaster videos on YouTube with the goal of raising awareness and empowering the general populace to take action for ...their own safety. The article describes the most common category of calamity for which videos were produced in India. The comments added by viewers in each video’s comment area are analyzed in order to determine the viewers’ intentions and feelings in relation to the available videos. This is done so in order to analyze viewers’ sentiments. For this reason, study makes use of Webometric analyzer to retrieve the pertinent information from YouTube by utilizing the YouTube API key. Furthermore, the R-studio environment was utilized in order to do the sentiment analysis. After the raw data have been collected, they go through a process of manual verification so that the legitimacy and accuracy of the data may be confirmed. Following the application of the criteria for elimination, there were a total of 467 relevant movies and 20,689 comments that were retrieved for further examination. Following a comprehensive investigation, it was discovered that the majority of films were published between the years of 2008 and 2010. When looking at the total amount of videos released on the topic of natural disasters in India, the most notable channels are INDIA TODAY, WION, and NDTV, among others. These channels have the most footage available online. Using the keyword analysis that was performed on the videos’ titles, it was discovered that the majority of the movies in the collection were about cyclones, rather than any of the other kinds of natural disasters that can be found in India.
Over the past decade, deep neural networks have enormously advanced machine perception, especially object classification, object detection, and multimodal scene understanding. But, a major limitation ...of these systems is that they assume a closed-world setting, i.e., the train and the test distribution match exactly. As a result, any input belonging to a category that the system has never seen during training will not be recognized as unknown. However, many real-world applications often need this capability. For example, self-driving cars operate in a dynamic world where the data can change over time due to changes in season, geographic location, sensor types, etc. Handling such changes requires building models with open-world learning capabilities. In open-world learning, the system needs to detect novel examples which are not seen during training and update the system with new knowledge, without retraining from scratch. In this dissertation, we address gaps in the open-world learning literature and develop methods that enable efficient multimodal open-world learning in deep neural networks.
In this technical report, we present our approaches for the continual object detection track of the SODA10M challenge. We adapt ResNet50-FPN as the baseline and try several improvements for the final ...submission model. We find that task-specific replay scheme, learning rate scheduling, model calibration, and using original image scale helps to improve performance for both large and small objects in images. Our team `hypertune28' secured the second position among 52 participants in the challenge. This work will be presented at the ICCV 2021 Workshop on Self-supervised Learning for Next-Generation Industry-level Autonomous Driving (SSLAD).
In the last decade, despite rapid advancements in artificial intelligence (AI) transforming many industry practices, construction largely lags in adoption. Recently, the emergence and rapid adoption ...of advanced large language models (LLM) like OpenAI's GPT, Google's PaLM, and Meta's Llama have shown great potential and sparked considerable global interest. However, the current surge lacks a study investigating the opportunities and challenges of implementing Generative AI (GenAI) in the construction sector, creating a critical knowledge gap for researchers and practitioners. This underlines the necessity to explore the prospects and complexities of GenAI integration. Bridging this gap is fundamental to optimizing GenAI's early-stage adoption within the construction sector. Given GenAI's unprecedented capabilities to generate human-like content based on learning from existing content, we reflect on two guiding questions: What will the future bring for GenAI in the construction industry? What are the potential opportunities and challenges in implementing GenAI in the construction industry? This study delves into reflected perception in literature, analyzes the industry perception using programming-based word cloud and frequency analysis, and integrates authors' opinions to answer these questions. This paper recommends a conceptual GenAI implementation framework, provides practical recommendations, summarizes future research questions, and builds foundational literature to foster subsequent research expansion in GenAI within the construction and its allied architecture & engineering domains.
Accurate eye segmentation can improve eye-gaze estimation and support interactive computing based on visual attention; however, existing eye segmentation methods suffer from issues such as ...person-dependent accuracy, lack of robustness, and an inability to be run in real-time. Here, we present the RITnet model, which is a deep neural network that combines U-Net and DenseNet. RITnet is under 1 MB and achieves 95.3% accuracy on the 2019 OpenEDS Semantic Segmentation challenge. Using a GeForce GTX 1080 Ti, RITnet tracks at > 300Hz, enabling real-time gaze tracking applications. Pre-trained models and source code are available
Particle rearrangements, compaction under pressure and in vitro dissolution have been evaluated after melt dispersion of ibuprofen, Avicel and Aerosil. The Cooper–Eaton and Kuno equations were ...utilized for the determination of particle rearrangement and compression behavior from tap density and compact data. Particle rearrangement could be divided into two stages as primary and secondary rearrangement. Transitional tapping between the stages was found to be 20–25 taps in ibuprofen crystalline powder, which was increased up to 45 taps with all formulated powders. Compaction in the rearrangement stages was increased in all the formulations with respect to pure ibuprofen. Significantly increased compaction of ibuprofen under pressure can be achieved using Avicel by melt dispersion technique, which could be beneficial in ibuprofen tablet manufacturing by direct compression. SEM, FTIR and DSC have been utilized for physicochemical characterization of the melt dispersion powder materials. Dissolution of ibuprofen from compacted tablet of physical mixture and melt dispersion particles has also been improved greatly in the following order: Ibc<Ibsmd1<Ibsmd2<Ibsmp10<Ibsmd5<Ibsmd10.
With the advent of multi-modal large language models (MLLMs), datasets used
for visual question answering (VQA) and referring expression comprehension have
seen a resurgence. However, the most ...popular datasets used to evaluate MLLMs
are some of the earliest ones created, and they have many known problems,
including extreme bias, spurious correlations, and an inability to permit
fine-grained analysis. In this paper, we pioneer evaluating recent MLLMs (LLaVA
1.5, LLaVA-NeXT, BLIP2, InstructBLIP, GPT-4V, and GPT-4o) on datasets designed
to address weaknesses in earlier ones. We assess three VQA datasets: 1) TDIUC,
which permits fine-grained analysis on 12 question types; 2) TallyQA, which has
simple and complex counting questions; and 3) DVQA, which requires optical
character recognition for chart understanding. We also study VQDv1, a dataset
that requires identifying all image regions that satisfy a given query. Our
experiments reveal the weaknesses of many MLLMs that have not previously been
reported. Our code is integrated into the widely used LAVIS framework for MLLM
evaluation, enabling the rapid assessment of future MLLMs. Project webpage:
https://kevinlujian.github.io/MLLM_Evaluations/
Humans can incrementally learn to do new visual detection tasks, which is a huge challenge for today's computer vision systems. Incrementally trained deep learning models lack backwards transfer to ...previously seen classes and suffer from a phenomenon known as \("catastrophic forgetting."\) In this paper, we pioneer online streaming learning for object detection, where an agent must learn examples one at a time with severe memory and computational constraints. In object detection, a system must output all bounding boxes for an image with the correct label. Unlike earlier work, the system described in this paper can learn this task in an online manner with new classes being introduced over time. We achieve this capability by using a novel memory replay mechanism that efficiently replays entire scenes. We achieve state-of-the-art results on both the PASCAL VOC 2007 and MS COCO datasets.