Search results for: generative model

Authors: Martin Georgiev, Milena Nanova, Damyan Damov

Abstract:

Architects, engineers, and developers need to analyse and implement a wide spectrum of data in different formats, if they want to produce viable residential developments. Usually, this data comes from a number of different sources and is not well structured. The main objective of this research project is to provide parametric tools working with real geodesic data that can generate residential solutions. Various codes, regulations and design constraints are described by variables and prioritized. In this way, we establish a common workflow for architects, geodesists, and other professionals involved in the building and investment process. This collaborative medium ensures that the generated design variants conform to various requirements, contributing to a more streamlined and informed decision-making process. The quantification of distinctive characteristics inherent to typical residential structures allows a systematic evaluation of the generated variants, focusing on factors crucial to designers, such as daylight simulation, circulation analysis, space utilization, view orientation, etc. Integrating real geodesic data offers a holistic view of the built environment, enhancing the accuracy and relevance of the design solutions. The use of generative algorithms and parametric models offers high productivity and flexibility of the design variants. It can be implemented in more conventional CAD and BIM workflow. Experts from different specialties can join their efforts, sharing a common digital workspace. In conclusion, our research demonstrates that a generative parametric approach based on real geodesic data and collaborative decision-making could be introduced in the early phases of the design process. This gives the designers powerful tools to explore diverse design possibilities, significantly improving the qualities of the building investment during its entire lifecycle.

Keywords: architectural design, residential buildings, urban development, geodesic data, generative design, parametric models, workflow optimization

Procedia PDF Downloads 19

Authors: Brennan Lodge

Abstract:

Amidst a complex regulatory landscape, Retrieval Augmented Generation (RAG) emerges as a transformative tool for Governance Risk and Compliance (GRC) officers. This paper details the application of RAG in synthesizing Large Language Models (LLMs) with external knowledge bases, offering GRC professionals an advanced means to adapt to rapid changes in compliance requirements. While the development for standalone LLM’s (Large Language Models) is exciting, such models do have their downsides. LLM’s cannot easily expand or revise their memory, and they can’t straightforwardly provide insight into their predictions, and may produce “hallucinations.” Leveraging a pre-trained seq2seq transformer and a dense vector index of domain-specific data, this approach integrates real-time data retrieval into the generative process, enabling gap analysis and the dynamic generation of compliance and risk management content. We delve into the mechanics of RAG, focusing on its dual structure that pairs parametric knowledge contained within the transformer model with non-parametric data extracted from an updatable corpus. This hybrid model enhances decision-making through context-rich insights, drawing from the most current and relevant information, thereby enabling GRC officers to maintain a proactive compliance stance. Our methodology aligns with the latest advances in neural network fine-tuning, providing a granular, token-level application of retrieved information to inform and generate compliance narratives. By employing RAG, we exhibit a scalable solution that can adapt to novel regulatory challenges and cybersecurity threats, offering GRC officers a robust, predictive tool that augments their expertise. The granular application of RAG’s dual structure not only improves compliance and risk management protocols but also informs the development of compliance narratives with pinpoint accuracy. It underscores AI’s emerging role in strategic risk mitigation and proactive policy formation, positioning GRC officers to anticipate and navigate the complexities of regulatory evolution confidently.

Keywords: cybersecurity, gen AI, retrieval augmented generation, cybersecurity defense strategies

Procedia PDF Downloads 50

Authors: Esther Ekundayo

Abstract:

The nature of AI-generated works makes it difficult to identify an author. Although, some scholars have suggested that all the players involved in its creation should be allocated authorship according to their respective contribution. From the programmer who creates and designs the AI to the investor who finances the AI and to the user of the AI who most likely ends up creating the work in question. While others suggested that this issue may be resolved by the UK computer-generated works (CGW) provision under Section 9(3) of the Copyright Designs and Patents Act 1988. However, under the UK and Nigerian copyright law, only human-created works are recognised. This is usually assessed based on their originality. This simply means that the work must have been created as a result of its author’s creative and intellectual abilities and not copied. Such works are literary, dramatic, musical and artistic works and are those that have recently been a topic of discussion with regards to generative artificial intelligence (Generative AI). Unlike Nigeria, the UK CDPA recognises computer-generated works and vests its authorship with the human who made the necessary arrangement for its creation . However, making necessary arrangement in the case of Nova Productions Ltd v Mazooma Games Ltd was interpreted similarly to the traditional authorship principle, which requires the skills of the creator to prove originality. Although, some recommend that computer-generated works complicates this issue, and AI-generated works should enter the public domain as authorship cannot be allocated to AI itself. Additionally, the UKIPO recognising these issues in line with the growing AI trend in a public consultation launched in the year 2022, considered whether computer-generated works should be protected at all and why. If not, whether a new right with a different scope and term of protection should be introduced. However, it concluded that the issue of computer-generated works would be revisited as AI was still in its early stages. Conversely, due to the recent developments in this area with regards to Generative AI systems such as ChatGPT, Midjourney, DALL-E and AIVA, amongst others, which can produce human-like copyright creations, it is therefore important to examine the relevant issues which have the possibility of altering traditional copyright principles as we know it. Considering that the UK and Nigeria are both common law jurisdictions but with slightly differing approaches to this area, this research, therefore, seeks to answer the following questions by comparative analysis: 1)Who is the author of an AI-generated work? 2)Is the UK’s CGW provision worthy of emulation by the Nigerian law? 3) Would a sui generis law be capable of protecting AI-generated works and its author under both jurisdictions? This research further examines the possible barriers to the implementation of the new law in Nigeria, such as limited technical expertise and lack of awareness by the policymakers, amongst others.

Keywords: authorship, artificial intelligence (AI), generative ai, computer-generated works, copyright, technology

Procedia PDF Downloads 51

Authors: Xulu Yao, Moi Hoon Yap, Yanlong Zhang

Abstract:

As a branch of artificial neural network, deep learning is widely used in the field of image recognition, but the lack of its dataset leads to imperfect model learning. By analysing the data scale requirements of deep learning and aiming at the application in GUI generation, it is found that the collection of GUI dataset is a time-consuming and labor-consuming project, which is difficult to meet the needs of current deep learning network. To solve this problem, this paper proposes a semi-supervised deep learning model that relies on the original small-scale datasets to produce a large number of reliable data sets. By combining the cyclic neural network with the generated countermeasure network, the cyclic neural network can learn the sequence relationship and characteristics of data, make the generated countermeasure network generate reasonable data, and then expand the Rico dataset. Relying on the network structure, the characteristics of collected data can be well analysed, and a large number of reasonable data can be generated according to these characteristics. After data processing, a reliable dataset for model training can be formed, which alleviates the problem of dataset shortage in deep learning.

Keywords: GUI, deep learning, GAN, data augmentation

Procedia PDF Downloads 148

Authors: Debarag Banerjee, Pooja Singh, Arjun Avadhanam, Saksham Srivastava

Abstract:

Autonomous conversational agents, i.e., chatbots, are becoming an increasingly common mechanism for enterprises to provide support to customers and partners. In order to rate chatbots, especially ones powered by Generative AI tools like Large Language Models (LLMs), we need to be able to accurately assess their performance. This is where chatbot benchmarking becomes important. In this paper, authors propose the use of a benchmark that they call the E2E (End to End) benchmark and show how the E2E benchmark can be used to evaluate the accuracy and usefulness of the answers provided by chatbots, especially ones powered by LLMs. The authors evaluate an example chatbot at different levels of sophistication based on both our E2E benchmark as well as other available metrics commonly used in the state of the art and observe that the proposed benchmark shows better results compared to others. In addition, while some metrics proved to be unpredictable, the metric associated with the E2E benchmark, which uses cosine similarity, performed well in evaluating chatbots. The performance of our best models shows that there are several benefits of using the cosine similarity score as a metric in the E2E benchmark.

Keywords: chatbot benchmarking, end-to-end (E2E) benchmarking, large language model, user centric evaluation.

Procedia PDF Downloads 38

Authors: Shriya Shukla, Lachin Fernando

Abstract:

Pneumonia, a leading cause of mortality in young children globally, presents significant diagnostic challenges, particularly in resource-limited settings. This study presents an approach to diagnosing pediatric pneumonia using Chest X-Ray (CXR) images, employing a lightweight MobileNetV2 model enhanced with synthetic data augmentation. Addressing the challenge of dataset scarcity and imbalance, the study used a Variational Autoencoder-Generative Adversarial Network (VAE-GAN) to generate synthetic CXR images, improving the representation of normal cases in the pediatric dataset. This approach not only addresses the issues of data imbalance and scarcity prevalent in medical imaging but also provides a more accessible and reliable diagnostic tool for early pneumonia detection. The augmented data improved the model’s accuracy and generalization, achieving an overall accuracy of 95% in pneumonia detection. These findings highlight the efficacy of the MobileNetV2 model, offering a computationally efficient yet robust solution well-suited for resource-constrained environments such as mobile health applications. This study demonstrates the potential of synthetic data augmentation in enhancing medical image analysis for critical conditions like pediatric pneumonia.

Keywords: pneumonia, MobileNetV2, image classification, GAN, VAE, deep learning

Procedia PDF Downloads 30

Authors: Jacqueline Rose T. Alipo-on, Francesca Isabelle F. Escobar, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar Al Dahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases, which are considered one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis of ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heartbeat types. The dataset used in this work is the synthetic MIT-BIH Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: heartbeat classification, convolutional neural network, electrocardiogram signals, generative adversarial networks, long short-term memory, ResNet-50

Procedia PDF Downloads 85

Authors: Mian Huang, Chi Ma, Junyu Lin, William Lu

Abstract:

Introduction: Bone health attracts more attention recently and an intelligent question and answer (QA) chatbot for osteoporosis is helpful for science popularization. With Generative Pretrained Transformer (GPT) technology developing, we build an osteoporosis corpus dataset and then fine-tune LLaMA, a famous open-source GPT foundation large language model(LLM), on our self-constructed osteoporosis corpus. Evaluated by clinical orthopedic experts, our fine-tuned model outperforms vanilla LLaMA on osteoporosis QA task in Chinese. Three-dimensional quantitative computed tomography (QCT) measured bone mineral density (BMD) is considered as more accurate than DXA for BMD measurement in recent years. We develop an automatic Phantom-less QCT(PL-QCT) that is more efficient for BMD measurement since no need of an external phantom for calibration. Combined with LLM on osteoporosis, our PL-QCT provides efficient and accurate BMD measurement for our chatbot users. Material and Methods: We build an osteoporosis corpus containing about 30,000 Chinese literatures whose titles are related to osteoporosis. The whole process is done automatically, including crawling literatures in .pdf format, localizing text/figure/table region by layout segmentation algorithm and recognizing text by OCR algorithm. We train our model by continuous pre-training with Low-rank Adaptation (LoRA, rank=10) technology to adapt LLaMA-7B model to osteoporosis domain, whose basic principle is to mask the next word in the text and make the model predict that word. The loss function is defined as cross-entropy between the predicted and ground-truth word. Experiment is implemented on single NVIDIA A800 GPU for 15 days. Our automatic PL-QCT BMD measurement adopt AI-associated region-of-interest (ROI) generation algorithm for localizing vertebrae-parallel cylinder in cancellous bone. Due to no phantom for BMD calibration, we calculate ROI BMD by CT-BMD of personal muscle and fat. Results & Discussion: Clinical orthopaedic experts are invited to design 5 osteoporosis questions in Chinese, evaluating performance of vanilla LLaMA and our fine-tuned model. Our model outperforms LLaMA on over 80% of these questions, understanding ‘Expert Consensus on Osteoporosis’, ‘QCT for osteoporosis diagnosis’ and ‘Effect of age on osteoporosis’. Detailed results are shown in appendix. Future work may be done by training a larger LLM on the whole orthopaedics with more high-quality domain data, or a multi-modal GPT combining and understanding X-ray and medical text for orthopaedic computer-aided-diagnosis. However, GPT model gives unexpected outputs sometimes, such as repetitive text or seemingly normal but wrong answer (called ‘hallucination’). Even though GPT give correct answers, it cannot be considered as valid clinical diagnoses instead of clinical doctors. The PL-QCT BMD system provided by Bone’s QCT(Bone’s Technology(Shenzhen) Limited) achieves 0.1448mg/cm2(spine) and 0.0002 mg/cm2(hip) mean absolute error(MAE) and linear correlation coefficient R2=0.9970(spine) and R2=0.9991(hip)(compared to QCT-Pro(Mindways)) on 155 patients in three-center clinical trial in Guangzhou, China. Conclusion: This study builds a Chinese osteoporosis corpus and develops a fine-tuned and domain-adapted LLM as well as a PL-QCT BMD measurement system. Our fine-tuned GPT model shows better capability than LLaMA model on most testing questions on osteoporosis. Combined with our PL-QCT BMD system, we are looking forward to providing science popularization and early morning screening for potential osteoporotic patients.

Keywords: GPT, phantom-less QCT, large language model, osteoporosis

Procedia PDF Downloads 36

Authors: Abdullah Eqal Al Mazrooei

Abstract:

In this work, a new nonlinear model will be introduced. The model is in the state-space form. The nonlinearity of this model is in the state equation where the state vector is multiplied by its self. This technique makes our model generalizes many famous models as Lotka-Volterra model and Lorenz model which have many applications in the real life. We will apply our new model to estimate the wind speed by using a new nonlinear estimator which suitable to work with our model.

Keywords: nonlinear systems, state-space model, Kronecker product, nonlinear estimator

Procedia PDF Downloads 657

Authors: Syed Bilawal Ali Shah

Abstract:

The investigation of the hydrocarbon source rock potential of Eocene-Paleocene formations of Potwar Basin, part of Upper Indus Basin Pakistan, was done using geochemical and petrological techniques. Analysis was performed on forty-five core-cutting samples from two wells. The sequences analysed are Sakesar, Lockhart and Patala formations of Potwar Basin. Patala Formation is one of Potwar Basin's major petroleum-bearing source rocks. The Lockhart Formation samples VR (%Ro) and Tmax data indicate that the formation is early mature to immature for petroleum generation for hydrocarbon generation; samples from the Patala and Sakesar formations, however, have a peak oil generation window and an early maturity (oil window). With 3.37 weight percent mean TOC and HI levels up to 498 mg HC/g TOC, the source rock characteristics of the Sakesar and Patala formations generally exhibit good to very strong petroleum generative potential. The majority of sediments representing Lockhart Formation have 1.5 wt.% mean TOC having fair to good potential with HI values ranging between 203-498 mg HC/g TOC. 1. The analysed sediments of all formations possess primarily mixed Type II/III and Type III kerogen. Analysed sediments indicate that both the Sakesar and Patala formations can possess good oil-generation potential and may act as an oil source rock in the Potwar Basin.

Keywords: Potwar Basin, Patala Shale, Rock-Eval pyrolysis, Indus Basin, VR %Ro

Procedia PDF Downloads 31

Authors: Guolong Zhong, Venkatesh Chennam Vijay, Ilias Oraifige

Abstract:

In the last 20 years, Knowledge Based Engineering (KBE) has shown its advantages in product development in different engineering areas such as automation, mechanical, civil and aerospace engineering in terms of digital design automation and cost reduction by automating repetitive design tasks through capturing, integrating, utilising and reusing the existing knowledge required in various aspects of the product design. However, in primary design stages, the descriptive information of a product is discrete and unorganized while knowledge is in various forms instead of pure data. Thus, it is crucial to have an integrated product model which can represent the entire product information and its associated knowledge at the beginning of the product design. One of the shortcomings of the existing product models is a lack of required knowledge representation in various aspects of product design and its mapping to an interoperable schema. To overcome the limitation of the existing product model and methodologies, two key factors are considered. First, the product model must have well-defined classes that can represent the entire product information and its associated knowledge. Second, the product model needs to be represented in an interoperable schema to ensure a steady data exchange between different product modelling platforms and CAD software. This paper introduced a method to provide a general product model as a generative representation of a product, which consists of the geometry information and non-geometry information, through a product modelling framework. The proposed method for capturing the knowledge from the designers through a knowledge file provides a simple and efficient way of collecting and transferring knowledge. Further, the knowledge schema provides a clear view and format on the data that needed to be gathered in order to achieve a unified knowledge exchange between different platforms. This study used a game-based platform to make product modelling environment accessible for non-engineers. Further the paper goes on to test use case based on the proposed game-based product modelling environment to validate the effectiveness among non-engineers.

Keywords: game-based learning, knowledge based engineering, product modelling, design automation

Procedia PDF Downloads 114

Authors: Entisar A. Elgmati

Abstract:

Recurrent infant diarrhea is studied using daily data collected in Salvador, Brazil over one year and three months. A logistic regression model is fitted instead of Aalen's additive model using the same covariates that were used in the analysis with the additive model. The model gives reasonably similar results to that using additive regression model. In addition, the problem with the estimated conditional probabilities not being constrained between zero and one in additive model is solved here. Also martingale residuals that have been used to judge the goodness of fit for the additive model are shown to be useful for judging the goodness of fit of the logistic model.

Keywords: additive model, cumulative probabilities, infant diarrhoea, recurrent event

Procedia PDF Downloads 604

Authors: Qasim Munye, Juned Islam, Haseeb Qureshi, Syed Jung

Abstract:

Lung nodules are commonly identified in computed tomography (CT) scans by experienced radiologists at a relatively late stage. Early diagnosis can greatly increase survival. We propose using a pix2pix conditional generative adversarial network to generate realistic images simulating early-stage lung nodule growth. We have applied deep images prior to 2341 slices from 895 computed tomography (CT) scans from the Lung Image Database Consortium (LIDC) dataset to generate pseudo-healthy medical images. From these images, 819 were chosen to train a pix2pix network. We observed that for most of the images, the pix2pix network was able to generate images where the nodule increased in size and intensity across epochs. To evaluate the images, 400 generated images were chosen at random and shown to a medical student beside their corresponding original image. Of these 400 generated images, 384 were defined as satisfactory - meaning they resembled a nodule and were visually similar to the corresponding image. We believe that this generated dataset could be used as training data for neural networks to detect lung nodules at an early stage or to improve the accuracy of such networks. This is particularly significant as datasets containing the growth of early-stage nodules are scarce. This project shows that the combination of deep image prior and generative models could potentially open the door to creating larger datasets than currently possible and has the potential to increase the accuracy of medical classification tasks.

Keywords: medical technology, artificial intelligence, radiology, lung cancer

Procedia PDF Downloads 39

Authors: Rui Yin, Haojie Wang, Xun Li

Abstract:

Recently, mainstream dense retrieval methods have obtained state-of-the-art results on some datasets and tasks. However, they require large amounts of training data, which is not available in most domains. The severe performance degradation of dense retrievers on new data domains has limited the use of dense retrieval methods to only a few domains with large training datasets. In this paper, we propose an unsupervised domain-adaptive approach based on query generation. First, a generative model is used to generate relevant queries for each passage in the target corpus, and then the generated queries are used for mining negative passages. Finally, the query-passage pairs are labeled with a cross-encoder and used to train a domain-adapted dense retriever. Experiments show that our approach is more robust than previous methods in target domains that require less unlabeled data.

Keywords: dense retrieval, query generation, unsupervised training, text retrieval

Procedia PDF Downloads 37

Authors: Gangmin Li, Fan Yang

Abstract:

Personalized recommendation is crucial for any recommendation system. One of the techniques for personalized recommendation is to identify the intention. Traditional user intention identification uses the user’s selection when facing multiple items. This modeling relies primarily on historical behaviour data resulting in challenges such as the cold start, unintended choice, and failure to capture intention when items are new. Motivated by recent advancements in Large Language Models (LLMs) like ChatGPT, we present an approach for user intention identification by embracing LLMs with Chain-of-Thought (CoT) prompting. We use the initial user profile as input to LLMs and design a collection of prompts to align the LLM's response through various recommendation tasks encompassing rating prediction, search and browse history, user clarification etc. Our tests on real-world datasets demonstrate the improvements in recommendation by explicit user intention identification and, with that intention, merged into a user model.

Keywords: personalized recommendation, generative user modelling, user intention identification, large language models, chain-of-thought prompting

Procedia PDF Downloads 4

Authors: Mechlouch Ridha Fethi

Abstract:

This paper presents a recent mathematical model in political sciences concerning democracy. The model is represented by a logarithmic equation linking the Relative Index of Democracy (RID) to Participation Ratio (PR). Firstly the meanings of the different parameters of the model were presented; and the variation curve of the RID according to PR with different critical areas was discussed. Secondly, the model was applied to a virtual group where we show that the model can be applied depending on the gender. Thirdly, it was observed that the model can be extended to different language models of democracy and that little use to assess the state of democracy for some International organizations like UNO.

Keywords: democracy, mathematic, modelization, quantification

Procedia PDF Downloads 328

Authors: Thomas Wimmer, Bernhard Weigand

Abstract:

The improvement of gas turbine efficiency is one of the main drivers of research and development in the gas turbine market. This has led to elevated gas turbine inlet temperatures beyond the melting point of the utilized materials. The turbine parts need to be actively cooled in order to withstand these harsh environments. However, the usage of compressor air as coolant decreases the overall gas turbine efficiency. Thus, coolant consumption needs to be minimized in order to gain the maximum advantage from higher turbine inlet temperatures. Therefore, sophisticated cooling designs for gas turbine parts aim to minimize coolant mass flow. New design space is accessible as additive manufacturing is maturing to industrial usage for the creation of hot gas flow path parts. By making use of this technology more efficient cooling schemes can be manufacture. In order to find such cooling schemes a generative design method is being developed. It generates cooling schemes randomly which adhere to a set of rules. These assure the sanity of the design. A huge amount of different cooling schemes are generated and implemented in a simulation environment where it is validated. Criteria for the fitness of the cooling schemes are coolant mass flow, maximum temperature and temperature gradients. This way the whole design space is sampled and a Pareto optimum front can be identified. This approach is applied to a flat plate, which resembles a simplified section of a hot gas flow path part. Realistic boundary conditions are applied and thermal barrier coating is accounted for in the simulation environment. The resulting cooling schemes are presented and compared to representative conventional cooling schemes. Further development of this method can give access to cooling schemes with an even better performance having higher complexity, which makes use of the available design space.

Keywords: additive manufacturing, cooling, gas turbine, heat transfer, heat transfer design, optimization

Procedia PDF Downloads 321

Authors: Le Kang

Abstract:

On the research question of 'how to achieve USR', this contribution reflects the concept of university social responsibility, identify three achievement models of USR as the society - diversified model, the university-cooperation model, the government - compound model, also conduct a case study to explore characteristics of Chinese achievement model of USR. The contribution concludes with discussion of how the university, government and society balance demands and roles, make necessarily strategic adjustment and innovative approach to repair the shortcomings of each achievement model.

Keywords: modern university, USR, achievement model, compound model

Procedia PDF Downloads 719

Authors: Hossam Abdelrahman, Sama Rostom, Reem Yassein, Yara Mohamed, Salma Salah, Nour Awny

Abstract:

In today’s environment, people are becoming increasingly interested in their appearance. However, they are afraid of their unknown appearance after a plastic surgery or treatment. Accidents, burns and genetic problems such as bowing of body parts of people have a negative impact on their mental health with their appearance and this makes them feel uncomfortable and underestimated. The approach presents a revolutionary deep learning-based image inpainting method that analyses the various picture structures and corrects damaged images. In this study, A model is proposed based on the in-painting of medical images with Stable Diffusion Inpainting method. Reconstructing missing and damaged sections of an image is known as image inpainting is a key progress facilitated by deep neural networks. The system uses the input of the user of an image to indicate a problem, the system will then modify the image and output the fixed image, facilitating for the patient to see the final result.

Keywords: generative adversarial network, large mask inpainting, stable diffusion inpainting, plastic surgery

Procedia PDF Downloads 45

Authors: Nubwimana Rachel, Mugabowindekwe Maurice

Abstract:

Trees play a crucial role in maintaining biodiversity and providing various ecological services. Traditional methods of counting trees are time-consuming, and there is a need for more efficient techniques. However, deep learning makes it feasible to identify the multi-scale elements hidden in aerial imagery. This research focuses on the application of deep learning techniques for tree detection and counting in both forest and non-forest areas through the exploration of the deep learning application for automated tree detection and counting using satellite imagery. The objective is to identify the most effective model for automated tree counting. We used different deep learning models such as YOLOV7, SSD, and UNET, along with Generative Adversarial Networks to generate synthetic samples for training and other augmentation techniques, including Random Resized Crop, AutoAugment, and Linear Contrast Enhancement. These models were trained and fine-tuned using satellite imagery to identify and count trees. The performance of the models was assessed through multiple trials; after training and fine-tuning the models, UNET demonstrated the best performance with a validation loss of 0.1211, validation accuracy of 0.9509, and validation precision of 0.9799. This research showcases the success of deep learning in accurate tree counting through remote sensing, particularly with the UNET model. It represents a significant contribution to the field by offering an efficient and precise alternative to conventional tree-counting methods.

Keywords: remote sensing, deep learning, tree counting, image segmentation, object detection, visualization

Procedia PDF Downloads 28

Authors: ShyamKrishna Kirithivasan, Shreyas Battula, Aditi Soori, Richa Ramesh, Ramamoorthy Srinath

Abstract:

The human brain, among the most complex and mysterious aspects of the body, harbors vast potential for extensive exploration. Unraveling these enigmas, especially within neural perception and cognition, delves into the realm of neural decoding. Harnessing advancements in generative AI, particularly in Visual Computing, seeks to elucidate how the brain comprehends visual stimuli observed by humans. The paper endeavors to reconstruct human-perceived visual stimuli using Functional Magnetic Resonance Imaging (fMRI). This fMRI data is then processed through pre-trained deep-learning models to recreate the stimuli. Introducing a new architecture named LatentNeuroNet, the aim is to achieve the utmost semantic fidelity in stimuli reconstruction. The approach employs a Latent Diffusion Model (LDM) - Stable Diffusion v1.5, emphasizing semantic accuracy and generating superior quality outputs. This addresses the limitations of prior methods, such as GANs, known for poor semantic performance and inherent instability. Text conditioning within the LDM's denoising process is handled by extracting text from the brain's ventral visual cortex region. This extracted text undergoes processing through a Bootstrapping Language-Image Pre-training (BLIP) encoder before it is injected into the denoising process. In conclusion, a successful architecture is developed that reconstructs the visual stimuli perceived and finally, this research provides us with enough evidence to identify the most influential regions of the brain responsible for cognition and perception.

Keywords: BLIP, fMRI, latent diffusion model, neural perception.

Procedia PDF Downloads 42

Authors: Zhou Jianhong

Abstract:

Model averaging is a desirable approach to deal with model uncertainty, which, however, has rarely been explored for Poisson regression. In this paper, we propose a model averaging procedure based on an unbiased estimator of the expected Kullback-Leibler distance for the Poisson regression. Simulation study shows that the proposed model average estimator outperforms some other commonly used model selection and model average estimators in some situations. Our proposed methods are further applied to a real data example and the advantage of this method is demonstrated again.

Keywords: model averaging, poission regression, Kullback-Leibler distance, statistics

Procedia PDF Downloads 485

Authors: Yaolin Tian, Shanxiong Chen, Fujia Zhao, Xiaoyu Lin, Hailing Xiong

Abstract:

Ancient books are significant culture inheritors and their background textures convey the potential history information. However, multi-style texture recovery of ancient books has received little attention. Restricted by insufficient ancient textures and complex handling process, the generation of ancient textures confronts with new challenges. For instance, training without sufficient data usually brings about overfitting or mode collapse, so some of the outputs are prone to be fake. Recently, image generation and style transfer based on deep learning are widely applied in computer vision. Breakthroughs within the field make it possible to conduct research upon multi-style texture recovery of ancient books. Under the circumstances, we proposed a network of layout analysis and image fusion system. Firstly, we trained models by using Deep Convolution Generative against Networks (DCGAN) to synthesize multi-style ancient textures; then, we analyzed layouts based on the Position Rearrangement (PR) algorithm that we proposed to adjust the layout structure of foreground content; at last, we realized our goal by fusing rearranged foreground texts and generated background. In experiments, diversified samples such as ancient Yi, Jurchen, Seal were selected as our training sets. Then, the performances of different fine-turning models were gradually improved by adjusting DCGAN model in parameters as well as structures. In order to evaluate the results scientifically, cross entropy loss function and Fréchet Inception Distance (FID) are selected to be our assessment criteria. Eventually, we got model M8 with lowest FID score. Compared with DCGAN model proposed by Radford at el., the FID score of M8 improved by 19.26%, enhancing the quality of the synthetic images profoundly.

Keywords: deep learning, image fusion, image generation, layout analysis

Procedia PDF Downloads 111

Authors: Rui Yin, Haojie Wang, Xun Li

Abstract:

Recently, mainstream dense retrieval methods have obtained state-of-the-art results on some datasets and tasks. However, they require large amounts of training data, which is not available in most domains. The severe performance degradation of dense retrievers on new data domains has limited the use of dense retrieval methods to only a few domains with large training datasets. In this paper, we propose an unsupervised domain-adaptive approach based on query generation. First, a generative model is used to generate relevant queries for each passage in the target corpus, and then, the generated queries are used for mining negative passages. Finally, the query-passage pairs are labeled with a cross-encoder and used to train a domain-adapted dense retriever. We also explore contrastive learning as a method for training domain-adapted dense retrievers and show that it leads to strong performance in various retrieval settings. Experiments show that our approach is more robust than previous methods in target domains that require less unlabeled data.

Keywords: dense retrieval, query generation, contrastive learning, unsupervised training

Procedia PDF Downloads 61

Authors: L. Madouni, M. Ould Ouali, N. E. Hannachi

Abstract:

Two constitutive models for concrete are available in ABAQUS/Explicit, the Brittle Cracking Model and the Concrete Damaged Plasticity Model, and their suitability and limitations are well known. The aim of the present paper is to implement a damage-friction concrete constitutive model and to evaluate the performance of this model by comparing the predicted response with experimental data. The constitutive formulation of this material model is reviewed. In order to have consistent results, the parameter identification and calibration for the model have been performed. Several numerical simulations are presented in this paper, whose results allow for validating the capability of the proposed model for reproducing the typical nonlinear performances of concrete structures under different monotonic and cyclic load conditions. The results of the evaluation will be used for recommendations concerning the application and further improvements of the investigated model.

Keywords: Abaqus, concrete, constitutive model, numerical simulation

Procedia PDF Downloads 330

Authors: Arslan Murtaza

Abstract:

Model Driven Architecture (MDA) is technique presented by OMG (Object Management Group) for software development in which different models are proposed and converted them into code. The main plan is to identify task by using PIM (Platform Independent Model) and transform it into PSM (Platform Specific Model) and then converted into code. In this review paper describes some challenges and issues that are faced in MDA, type and transformation of models (e.g. CIM, PIM and PSM), and evaluation of MDA-based methodologies.

Keywords: OMG, model driven rrchitecture (MDA), computation independent model (CIM), platform independent model (PIM), platform specific model(PSM), MDA-based methodologies

Procedia PDF Downloads 414

Authors: Mohamed Rabhi, Kouider Halim Benrahou

Abstract:

The rheological properties of the carbonyl-methylcellulose (CMC), of different concentrations (25000, 50000, 60000, 80000 and 100000 ppm) and different temperatures were studied. We found that the rheological behavior of all CMC solutions presents a pseudo-plastic behavior, it follows the model of Ostwald-de Waele. The objective of this work is the modeling of flow by the CMC Cross model. The Cross model gives us the variation of the viscosity according to the shear rate. This model allowed us to adjust more clearly the rheological characteristics of CMC solutions. A comparison between the Cross model and the model of Ostwald was made. Cross the model fitting parameters were determined by a numerical simulation to make an approach between the experimental curve and those given by the two models. Our study has shown that the model of Cross, describes well the flow of "CMC" for low concentrations.

Keywords: CMC, rheological modeling, Ostwald model, cross model, viscosity

Procedia PDF Downloads 355

Authors: Viet-Hung Truong, Seung-Eock Kim

Abstract:

Rain–wind induced vibration of inclined cable is a special aerodynamic phenomenon because it is easily influenced by many factors, especially the distribution of rivulet and wind velocity. This paper proposes a new 3D model of inclined cable, based on single degree-of-freedom model. Aerodynamic forces are firstly established and verified with the existing results from a 2D model. The 3D model of inclined cable is developed. The 3D model is then applied to assess the effects of wind velocity distribution and the continuity of rivulets on the cable. Finally, an inclined cable model with small sag is investigated.

Keywords: 3D model, rain - wind induced vibration, rivulet, analytical model

Procedia PDF Downloads 458

Authors: Pouya Vakili

Abstract:

The aim of present paper is to have a rough comparison between language proficiency and communicative competence, moreover, how different scholars in the field of second language acquisition/assessment have defined competence in different paradigms. Researchers differ, however, in how they view 'competence'. Those who are dealing with generative tradition associated with Chomsky have defined it as linguistic competence (knowledge of the grammar of L2). Other researchers have adopted a broader perspective that is examining how learners acquire communicative competence (knowledge of both the L2 grammar and of how this system is put to use in actual communication).

Keywords: communicative competence, competence, language proficiency, linguistic competence

Procedia PDF Downloads 452

Authors: Go Bong Choi, Shin Je Lee, Sung Jin Yoo, Gibaek Lee, Jong Min Lee

Abstract:

In South Korea, it is difficult to obtain data for statistical pipe assessment. In this paper, to address these issues, we find that various statistical model presented before is how data mixed with noise and are whether apply in South Korea. Three major type of model is studied and if data is presented in the paper, we add noise to data, which affects how model response changes. Moreover, we generate data from model in paper and analyse effect of noise. From this we can find robustness and applicability in Korea of each model.

Keywords: proportional hazard model, survival model, water main deterioration, ecological sciences

Procedia PDF Downloads 702