Search results for: generative ai

Authors: Milind Patil

Abstract:

Present paper is a discussion on Hindi-Marathi Morphological Analysis and generating rules for Machine Translation on the basis of Machine Readable Dictionary (MRD). This used Transformative Generative Grammar (TGG) rules to design the MRD. As per TGG rules, the suffix of a particular root word is based on its Tense, Aspect, Modality and Voice. That's why the suffix is very important for the word meanings (or root meanings). The Hindi and Marathi Language both have relation with Indo-Aryan language family. Both have been derived from Sanskrit language and their script is 'Devnagari'. But there are lots of differences in terms of semantics and grammatical level too. In Marathi, there are three genders, but in Hindi only two (Masculine and Feminine), the Natural gender is absent in Hindi. Likewise other grammatical categories also differ in their level of use. For MRD the suffixes (or Morpheme) are of particular root word for GNP (Gender, Number and Person) are based on its natural phenomena. A particular Suffix and Morphine change as per the need of person, number and gender. The design of MRD also based on this format. In first, Person, Number, Gender and Tense are key points than root words and suffix of particular Person, Number Gender (PNG). After that the inferences are drawn on the basis of rules that is (V.stem) (Pre.T/Past.T) (x) + (Aux-Pre.T) (x) → (V.Stem.) + (SP.TM) (X).

Keywords: MRD, TGG, stem, morph, morpheme, suffix, PNG, TAM&V, root

Procedia PDF Downloads 325

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 127

Authors: M. Ben Jrad, A. Belhaj Mohamed, S. Riahi, I. Bouazizi, M. Saidi, M. Soussi

Abstract:

The generative potential, depositional environment, thermal maturity and oil seeps of the organic-rich Bou Dabbous Formation (Ypresian) from the thrust belt northwestern Tunisia, were determined by Rock Eval and molecular analyses. The paleo-tectonic units in the area show some similarities with equivalent facies in Mediterranean Sea and Sicilian. The Bou Dabbous Formation displays variable source rock characteristics through the various units Tellian and Numidian nappes Units. Organic matter contents and petroleum potentials are fair to high (reaching 1.95% and 6 kg of HC/t of rock respectively) marine type II kerogen. An increasing SE-NW maturity gradient is well documented in the study area. The Bou Dabbous organic-rich facies are marginally mature stage in the Tellian Unit (Kasseb domain), whilst they are mature-late mature stage within Nefza-Ain Allega tectonic windows. A long and north of Cap Serrat-Ghardimaou Master Fault these facies are overmature. Oil/Oil and Oil/source rock correlation, based on biomarker and carbon isotopic composition, shows a positive genetic correlation between the oil seeps and Bou Dabbous source rock.

Keywords: biomarkers, Bou Dabbous Formation, Northern Tunisia, source rock

Procedia PDF Downloads 486

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 71

Authors: Tamadher Alfahal

Abstract:

Faith and art practice in traditional Islam had a profound rapport that is lost today. From practicing the principles of faith throughout everyday life, art was found as an expressive tool for Islamic revelation, worship, and the contemplative remembrance of God. Today, this rapport between Islamic art and spirituality has diminished; and the cosmological and metaphysical ideas that were the core of creative practices lost their imminence in people's lives. Hence, the cultural and religious practice of Islamic societies became separate from the creative production. In an attempt to revisit this rapport, it is sought to investigate the possibility of creating a set of principles for contemporary Islamic art and design through collaborative practice-led research. The research will aim to regenerate the potentials of Islamic philosophy for creative expressions, particularly in design studies. The outcomes will be manifested through different mediums such as: reflexive mind maps and visuals by the researcher, and various methods of participatory art practice aim to validate the philosophical concepts as design principles as a way to disseminate knowledge. This paper will focus on showcasing the key findings and the research approach for generating philosophical concepts as design principles. Using secondary evidence from literature, it will show examples of transforming textual findings into visuals that will be extensively explored through multidisciplinary collaborative sessions (these are scheduled to be conducted between February and April 2017).

Keywords: creative process, design pedagogy, design thinking, Islamic art, Islamic designs, Islamic philosophy

Procedia PDF Downloads 264

Authors: Xiaolin Zeng, Lei Cheng, Zhirong Li, Xueping Liu

Abstract:

Aiming at the problem of low accuracy and susceptibility to cultural relic diseases in the generation of high-resolution archaeology drawings by current image generation algorithms, an archaeology drawings generation algorithm based on a conditional generative adversarial network is proposed. An attention mechanism is added into the high-resolution image generation network as the backbone network, which enhances the line feature extraction capability and improves the accuracy of line drawing generation. A dual-branch parallel architecture consisting of two backbone networks is implemented, where the semantic translation branch extracts semantic features from orthophotographs of cultural relics, and the gradient screening branch extracts effective gradient features. Finally, the fusion fine-tuning module combines these two types of features to achieve the generation of high-quality and high-resolution archaeology drawings. Experimental results on the self-constructed archaeology drawings dataset of grotto temple statues show that the proposed algorithm outperforms current mainstream image generation algorithms in terms of pixel accuracy (PA), structural similarity (SSIM), and peak signal-to-noise ratio (PSNR) and can be used to assist in drawing archaeology drawings.

Keywords: archaeology drawings, digital heritage, image generation, deep learning

Procedia PDF Downloads 60

Authors: Siddharth Sarma, Ayush Majumdar, Nidhi Sabu, Mufaddal Jiruwaala, Shilpa Paygude

Abstract:

Digital Elevation Models (DEMs) are digital representations of the Earth’s topography, which include information about the elevation, slope, aspect, and other terrain attributes. DEMs play a crucial role in various applications, including terrain analysis, urban planning, and environmental modeling. In this paper, TerraEnhance is proposed, a distinct approach for high-resolution DEM generation using Generative Adversarial Networks (GANs) combined with Real-ESRGANs. By learning from a dataset of low-resolution DEMs, the GANs are trained to upscale the data by 10 times, resulting in significantly enhanced DEMs with improved resolution and finer details. The integration of Real-ESRGANs further enhances visual quality, leading to more accurate representations of the terrain. A post-processing layer is introduced, employing high-pass filtering to refine the generated DEMs, preserving important details while reducing noise and artifacts. The results demonstrate that TerraEnhance outperforms existing methods, producing high-fidelity DEMs with intricate terrain features and exceptional accuracy. These advancements make TerraEnhance suitable for various applications, such as terrain analysis and precise environmental modeling.

Keywords: DEM, ESRGAN, image upscaling, super resolution, computer vision

Procedia PDF Downloads 11

Authors: Ana Tsokilauri

Abstract:

The uppermost factor in the regulation of lignin-cellulose activity of decaying white rot or free rot are the substances serving as carbon and nitrogen nutrition of microorganisms and are considered as the most important factor of generative activity of white rot. The research object was Basidiomycete Fungi, peculiar and common in Georgia, and the separation of 10 of them as pure crops. The unidentified pure crops have tasted in order to be determined the potential of synthesis of lignin-degrading enzymes and the substrate of optimal lignocellulose growth. One of the most important aspects of the research conducted on Basidiomycetes was the use of specific lignocellulosic residues for selecting Fungi as a substrate of their growth. In order to increase lignocellulose with the help of substrate, crops were selected from the screening stage that showed good laccase activity. (Dusheti 1; Dusheti 10; Fshavi 5; Fshavi1; Fshavi 8; Fshavi 32; Manglisi 26; Sabaduri20; Dusheti 7; Sabaduri 1 ), Among the selected cultures, the crops with good laccase activity against the following substances, in particular: Dusheti 1- in this case, the rate of enzymatic activity on bran substrate was -105,6 u/ml, mandarin-96,4 u/ml. In case of corn - 102,9 u/ml. In case of Dusheti 7- the indicators were as follows: bananas-121,7 u/ml, mandarin-125,4 u/ml, corn - 117,1 u/ml. In the case of Sanaduri 32, the laccase activity was as follows: pomegranate- 101,2 u/ml. As a result of conducted experiments, the synthesis and activity rates of enzymes depending on plant substrates varied within a fairly wide range, which is still being under research.

Keywords: Lignocellulosic substrate, Basidiomycetes, white-rot basidiomycetes, Laccase

Procedia PDF Downloads 196

Authors: Julian David Rios Acuna

Abstract:

This paper seeks to argue that the phenomenon of ‘paramilitarism’ in Colombia exhibits the role of violence as constitutive of the political process of state formation in the country. In order to do this, it takes as its point of departure a landmark moment in the long history of private armies known as the ‘paramilitary’ in Colombia. In 2001, paramilitary commanders, politicians, and members of the military and other branches of state power singed what is known as the ‘Pact of Ralito.’ In this pact, the paramilitary appropriated constitutional and legal language. The paper argues that this appropriation shows that the paramilitary and the state express the same claim to sovereign power and therefore have the same foundation. More precisely, paramilitary power shows itself to base its power on the same foundation as the legal order, namely, extreme forms of violence where death is generative of power. In this sense, the paper shows how, by sharing its foundation, Colombian paramilitarism exhibits that state power in Colombia can be characterized as necro-power as Achille Mbembe understands it. The paper argues that paramilitarism shows state power as necro-power by constituting itself as a symptom understood, following Zizek, as that which both shows and overthrows its own foundation. In this way, paramilitarism shows the foundation of the state, thereby reconfiguring this very state. This reconfiguration, explicitly based on necro-power, the paper concludes, transforms the state into a form more appropriate to the political demands of neo-liberalism. By exhibiting its foundation in necro-power through paramilitarism, the Colombian State turns from a liberal into a (neo)liberal democracy.

Keywords: necro-power, necropolitics, paramilitarism in Colombia, state formation, state power, sovereign power

Procedia PDF Downloads 134

Authors: Ahmed Radwan, Ahmed Abdel Ghaney

Abstract:

This paper delves into the transformative potential of artificial intelligence (AI) in fostering creativity within the domain of architecture education, especially with a specific emphasis on its implications within the Design Studios; the convergence of AI and architectural pedagogy has introduced avenues for redefining the boundaries of creative expression and problem-solving. By harnessing AI-driven tools, students and educators can collaboratively explore a spectrum of design possibilities, stimulate innovative ideation, and engage in multidimensional design processes. This paper investigates the ways in which AI contributes to architectural creativity by facilitating generative design, pattern recognition, virtual reality experiences, and sustainable design optimization. Furthermore, the study examines the balance between AI-enhanced creativity and the preservation of core principles of architectural design/education, ensuring that technology is harnessed to augment rather than replace foundational design skills. Through an exploration of Egypt's architectural heritage and contemporary challenges, this research underscores how AI can synergize with cultural context and historical insights to inspire cutting-edge architectural solutions. By analyzing AI's impact on nurturing creativity among Egyptian architecture students, this paper seeks to contribute to the ongoing discourse on the integration of technology within global architectural education paradigms. It is hoped that this research will guide the thoughtful incorporation of AI in fostering creativity while preserving the authenticity and richness of architectural design education in Egypt and beyond.

Keywords: architecture, artificial intelligence, architecture education, Egypt

Procedia PDF Downloads 79

Authors: Andrei Nosov

Abstract:

This paper discusses the development directions of dialogue systems within the digitalisation of the railway industry, where technologies based on conversational AI are already potentially applied or will be applied. Conversational AI is one of the popular natural language processing (NLP) tasks, as it has great prospects for real-world applications today. At the same time, it is a challenging task as it involves many areas of NLP based on complex computations and deep insights from linguistics and psychology. In this review, we focus on dialogue systems and their implementation in the railway domain. We comprehensively review the state-of-the-art research results on dialogue systems and analyse them from three perspectives: type of problem to be solved, type of model, and type of system. In particular, from the perspective of the type of tasks to be solved, we discuss characteristics and applications. This will help to understand how to prioritise tasks. In terms of the type of models, we give an overview that will allow researchers to become familiar with how to apply them in dialogue systems. By analysing the types of dialogue systems, we propose an unconventional approach in contrast to colleagues who traditionally contrast goal-oriented dialogue systems with open-domain systems. Our view focuses on considering retrieval and generative approaches. Furthermore, the work comprehensively presents evaluation methods and datasets for dialogue systems in the railway domain to pave the way for future research. Finally, some possible directions for future research are identified based on recent research results.

Keywords: digitalisation, railway, dialogue systems, conversational AI, natural language processing, natural language understanding, natural language generation

Procedia PDF Downloads 63

Authors: Yehjune Heo

Abstract:

Fingerprint Anti-Spoofing approaches have been actively developed and applied in real-world applications. One of the main problems for Fingerprint Anti-Spoofing is not robust to unseen samples, especially in real-world scenarios. A possible solution will be to generate artificial, but realistic fingerprint samples and use them for training in order to achieve good generalization. This paper contains experimental and comparative results with currently popular GAN based methods and uses realistic synthesis of fingerprints in training in order to increase the performance. Among various GAN models, the most popular StyleGAN is used for the experiments. The CNN models were first trained with the dataset that did not contain generated fake images and the accuracy along with the mean average error rate were recorded. Then, the fake generated images (fake images of live fingerprints and fake images of spoof fingerprints) were each combined with the original images (real images of live fingerprints and real images of spoof fingerprints), and various CNN models were trained. The best performances for each CNN model, trained with the dataset of generated fake images and each time the accuracy and the mean average error rate, were recorded. We observe that current GAN based approaches need significant improvements for the Anti-Spoofing performance, although the overall quality of the synthesized fingerprints seems to be reasonable. We include the analysis of this performance degradation, especially with a small number of samples. In addition, we suggest several approaches towards improved generalization with a small number of samples, by focusing on what GAN based approaches should learn and should not learn.

Keywords: anti-spoofing, CNN, fingerprint recognition, GAN

Procedia PDF Downloads 184

Authors: Mirjana Ruppel, Rajendra Persad, Amit Bahl, Sanja Dogramadzi, Chris Melhuish, Lyndon Smith

Abstract:

Multimodal image registration is a profoundly complex task which is why deep learning has been used widely to address it in recent years. However, two main challenges remain: Firstly, the lack of ground truth data calls for an unsupervised learning approach, which leads to the second challenge of defining a feasible loss function that can compare two images of different modalities to judge their level of alignment. To avoid this issue altogether we implement a generative adversarial network consisting of two registration networks GAB, GBA and two discrimination networks DA, DB connected by spatial transformation layers. GAB learns to generate a deformation field which registers an image of the modality B to an image of the modality A. To do that, it uses the feedback of the discriminator DB which is learning to judge the quality of alignment of the registered image B. GBA and DA learn a mapping from modality A to modality B. Additionally, a cycle-consistency loss is implemented. For this, both registration networks are employed twice, therefore resulting in images ˆA, ˆB which were registered to ˜B, ˜A which were registered to the initial image pair A, B. Thus the resulting and initial images of the same modality can be easily compared. A dataset of liver CT and MRI was used to evaluate the quality of our approach and to compare it against learning and non-learning based registration algorithms. Our approach leads to dice scores of up to 0.80 ± 0.01 and is therefore comparable to and slightly more successful than algorithms like SimpleElastix and VoxelMorph.

Keywords: cycle consistency, deformable multimodal image registration, deep learning, GAN

Procedia PDF Downloads 132

Authors: Shanshan Zhu, Mohammad Nasim

Abstract:

Financial fraud continues to be a major threat to financial institutions across the world, causing colossal money losses and undermining public trust. Fraud prevention techniques, based on hard rules, have become ineffective due to evolving patterns of fraud in recent times. Against such a background, the present study probes into distinct methodologies that exploit emergent AI-driven techniques to further strengthen fraud detection. We would like to compare the performance of generative adversarial networks and graph neural networks with other popular techniques, like gradient boosting, random forests, and neural networks. To this end, we would recommend integrating all these state-of-the-art models into one robust, flexible, and smart system for real-time anomaly and fraud detection. To overcome the challenge, we designed synthetic data and then conducted pattern recognition and unsupervised and supervised learning analyses on the transaction data to identify which activities were fishy. With the use of actual financial statistics, we compare the performance of our model in accuracy, speed, and adaptability versus conventional models. The results of this study illustrate a strong signal and need to integrate state-of-the-art, AI-driven fraud detection solutions into frameworks that are highly relevant to the financial domain. It alerts one to the great urgency that banks and related financial institutions must rapidly implement these most advanced technologies to continue to have a high level of security.

Keywords: AI-driven fraud detection, financial security, machine learning, anomaly detection, real-time fraud detection

Procedia PDF Downloads 44

Authors: Marcus Maia

Abstract:

The present study reports and discusses the use of eye tracking qualitative data in reading workshops in Brazilian middle and high schools and in Generative Syntax and Sentence Processing courses at the undergraduate and graduate levels at the Federal University of Rio de Janeiro, respectively. Both endeavors take the sentential level as the proper object to be metacognitively explored in language education (cf. Chomsky, Gallego & Ott, 2019) to develop innate science forming capacity and knowledge of language. In both projects, non-discrepant qualitative eye tracking data collected and quantitatively analyzed in experimental syntax and psycholinguistic studies carried out in Lapex (Experimental Psycholinguistics Laboratory of the Federal University of Rio de Janeiro) were displayed to students as a point of departure, triggering discussions. Classes would generally start with the display of videos showing eye tracking data, such as gaze plots and heatmaps from several studies in Psycholinguistics and Experimental Syntax that we had already developed in our laboratory. The videos usually triggered discussions with students about linguistic and psycholinguistic issues, such as the reading of sentences for gist, garden-path sentences, syntactic and semantic anomalies, the filled-gap effect, island effects, direct and indirect cause, and recursive constructions, among other topics. Active, problem-solving based methodologies were employed with the objective of stimulating student participation. The communication also discusses the importance of developing full literacy, epistemic vigilance and intellectual self-defense in an infodemic world in the lines of Maia (2022).

Keywords: reading, educational psycholinguistics, eye-tracking, active methodology

Procedia PDF Downloads 66

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 77

Authors: Srinivas Peri, Siva Abhishek Sirivella, Tejaswini Kallakuri, Uzair Ahmad

Abstract:

Smart cities and intelligent transportation systems rely heavily on effective traffic management and infrastructure planning. This research tackles the data scarcity challenge by generating realistically synthetic traffic data from the PeMS-Bay dataset, enhancing predictive modeling accuracy and reliability. Advanced techniques like TimeGAN and GaussianCopula are utilized to create synthetic data that mimics the statistical and structural characteristics of real-world traffic. The future integration of Spatial-Temporal Generative Adversarial Networks (ST-GAN) is anticipated to capture both spatial and temporal correlations, further improving data quality and realism. Each synthetic data generation model's performance is evaluated against real-world data to identify the most effective models for accurately replicating traffic patterns. Long Short-Term Memory (LSTM) networks are employed to model and predict complex temporal dependencies within traffic patterns. This holistic approach aims to identify areas with low vehicle counts, reveal underlying traffic issues, and guide targeted infrastructure interventions. By combining GAN-based synthetic data generation with LSTM-based traffic modeling, this study facilitates data-driven decision-making that improves urban mobility, safety, and the overall efficiency of city planning initiatives.

Keywords: GAN, long short-term memory (LSTM), synthetic data generation, traffic management

Procedia PDF Downloads 15

Authors: Xi Liu, Fan Yuan

Abstract:

In the evolving landscape of physics-based machine learning (PBML), particularly within fluid dynamics and its applications in electromechanical engineering, robot vision, and robot learning, achieving precision and alignment with researchers' specific needs presents a formidable challenge. In response, this work proposes a methodology that integrates neural transformation with a modified smoothed particle hydrodynamics model for generating transformed 3D fluid simulations. This approach is useful for nanoscale science, where the unique and complex behaviors of viscoelastic medium demand accurate neurally-transformed simulations for materials understanding and manipulation. In electromechanical engineering, the method enhances the design and functionality of fluid-operated systems, particularly microfluidic devices, contributing to advancements in nanomaterial design, drug delivery systems, and more. The proposed approach also aligns with the principles of PBML, offering advantages such as multi-fluid stylization and consistent particle attribute transfer. This capability is valuable in various fields where the interaction of multiple fluid components is significant. Moreover, the application of neurally-transformed hydrodynamical models extends to manufacturing processes, such as the production of microelectromechanical systems, enhancing efficiency and cost-effectiveness. The system's ability to perform neural transfer on 3D fluid scenes using a deep learning algorithm alongside physical models further adds a layer of flexibility, allowing researchers to tailor simulations to specific needs across scientific and engineering disciplines.

Keywords: physics-based machine learning, robot vision, robot learning, hydrodynamics

Procedia PDF Downloads 66

Authors: Jinan Fiaidhi, Hashmath Shaik

Abstract:

Breaking the barrier for practicing evidence-based medicine relies on effective methods for rapidly identifying relevant evidence from the body of biomedical literature. An important challenge confronted by medical practitioners is the long time needed to browse, filter, summarize and compile information from different medical resources. Deep learning can help in solving this based on automatic question answering (Q&A) and transformers. However, Q&A and transformer technologies are not trained to answer clinical queries that can be used for evidence-based practice, nor can they respond to structured clinical questioning protocols like PICO (Patient/Problem, Intervention, Comparison and Outcome). This article describes the use of deep learning techniques for Q&A that are based on transformer models like BERT and GPT to answer PICO clinical questions that can be used for evidence-based practice extracted from sound medical research resources like PubMed. We are reporting acceptable clinical answers that are supported by findings from PubMed. Our transformer methods are reaching an acceptable state-of-the-art performance based on two staged bootstrapping processes involving filtering relevant articles followed by identifying articles that support the requested outcome expressed by the PICO question. Moreover, we are also reporting experimentations to empower our bootstrapping techniques with patch attention to the most important keywords in the clinical case and the PICO questions. Our bootstrapped patched with attention is showing relevancy of the evidence collected based on entropy metrics.

Keywords: automatic question answering, PICO questions, evidence-based medicine, generative models, LLM transformers

Procedia PDF Downloads 47

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 69

Authors: Mahdi Bastan, Ali Mohammad Ahmadvand, Fatemeh Soltani Khamsehpour

Abstract:

Health organizations’ sustainable development has nowadays become highly affected by customers’ satisfaction due to significant changes made in the business environment of the healthcare system and emerging of Competitiveness paradigm. In case we look at the hospitals and other health organizations as service providers concerning profit issues, the satisfaction of employees as interior customers, and patients as exterior customers would be of significant importance in health business success. Furthermore, satisfaction rate could be considered in performance assessment of healthcare organizations as a perceived quality measure. Several researches have been carried out in identification of effective factors on patients’ satisfaction in health organizations. However, considering a systemic view, the complex causal relations among many components of healthcare system would be an issue that its acquisition and sustainability requires an understanding of the dynamic complexity, an appropriate cognition of different components, and effective relationships among them resulting ultimately in identifying the generative structure of patients’ satisfaction. Hence, the presenting paper applies system dynamics approaches coherently and methodologically to represent the systemic structure of customers’ satisfaction of a health system involving the constituent components and interactions among them. Then, the results of different policies taken on the system are simulated via developing mathematical models, identifying leverage points, and using scenario making technique and then, the best solutions are presented to improve customers’ satisfaction of the services. The presenting approach supports taking advantage of decision support systems. Additionally, relying on understanding of system behavior Dynamics, the effective policies for improving the health system would be recognized.

Keywords: customer satisfaction, healthcare, scenario, simulation, system dynamics

Procedia PDF Downloads 416

Authors: Etim, Victoria Enefiok, Dada, Oluseyi Akintunde, Bassey Okon

Abstract:

Phonological disorder is a serious and disturbing issue to many parents and teachers. Efforts towards resolving the problem have been undermined by other specific disabilities which were hidden to many regular and special education teachers. It is against this background that this study was motivated to provide data on the prevalence of phonological disorders in children with specific language impairment (CWSLI) as the first step towards critical intervention. The study was a survey of 15 CWSLI from St. Louise Inclusive schools, Ikot Ekpene in Akwa Ibom State of Nigeria. Phonological Processes Diagnostic Scale (PPDS) with 17 short sentences, which cut across the five phonological processes that were examined, were validated by experts in test measurement, phonology and special education. The respondents were made to read the sentences with emphasis on the targeted sounds. Their utterances were recorded and analyzed in the language laboratory using Praat Software. Data were also collected through friendly interactions at different times from the clients. The theory of generative phonology was adopted for the descriptive analysis of the phonological processes. Data collected were analyzed using simple percentage and composite bar chart for better understanding of the result. The study found out that CWSLI exhibited the five phonological processes under investigation. It was revealed that 66.7%, 80%, 73.3%, 80%, and 86.7% of the respondents have severe deficit in fricative stopping, velar fronting, liquid gliding, final consonant deletion and cluster reduction, respectively. It was therefore recommended that a nationwide survey should be carried out to have national statistics of CWSLI with phonological deficits and develop intervention strategies for effective therapy to remediate the disorder.

Keywords: language disorders, phonology, phonological processes, specific language impairment

Procedia PDF Downloads 193

Authors: Dongqi Li, Yunjia Huang, Tomo Inoue, Kohei Inoue

Abstract:

With urbanization, urban cultural heritage is facing the impact and destruction of modernization and urbanization. Many historical areas are losing their historical information and regional cultural characteristics, so it is necessary to carry out systematic color planning for historical areas in conservation. As an early focus on urban color planning, Japan has a systematic approach to urban color planning. Hence, this paper selects five merchant towns from the category of important traditional building preservation areas in Japan as the subject of this study to explore the color structure and emotion of this type of historic area. First, the image semantic segmentation method identifies the buildings, roads, and landscape environments. Their color data were extracted for color composition and emotion analysis to summarize their common features. Second, the obtained Internet evaluations were extracted by natural language processing for keyword extraction. The correlation analysis of the color structure and keywords provides a valuable reference for conservation decisions for this historic area in the town. This paper also combines the color structure and Internet evaluation results with generative adversarial networks to generate predicted images of color structure improvements and color improvement schemes. The methods and conclusions of this paper can provide new ideas for the digital management of environmental colors in historic districts and provide a valuable reference for the inheritance of local traditional culture.

Keywords: historic districts, color planning, semantic segmentation, natural language processing

Procedia PDF Downloads 89

Authors: Aminah Muchdar

Abstract:

To increase the genetic diversity of soybean in order to adapt to agroecology in Indonesia conducted ways including introduction, cross, mutation and genetic transformation. The purpose of this research is to obtain early maturity soybean mutant lines, large seed tolerant to drought with high yield potential. This study consisted of two stages: the first is sensitivity of gamma rays carried out in the Laboratory BATAN. The genetic variety used is Anjasmoro. The method seeds irradiated with gamma rays at a rate of activity with the old ci 1046.16976 irradiation 0-71 minutes. Irradiation doses of 0, 100, 200, 300, 400, 500, 600, 700, 800, 900 and 1000gy. The results indicated all seeds irradiated with doses of 0 - 1000gy, just a dose of 200 and 300gy are able to show the percentage of germination, plant height, number of leaves, number of normal sprouts and green leaves of the best and can be continued for a second trial in order to assemble and to get mutants which is expected. The result of second stage of soybean M2 Population irradiated with diversity Gamma Irradiation performed that in the form of soybean planting, the seed planted is the first derivative of the M2 irradiated seeds. The result after the age of 30ADP has already showing growth and development of plants that vary when compared to its parent, both in terms of plant height, number of leaves, leaf shape and leaf forage level. In the generative phase, a plant that has been irradiated 200 and 300 gy seen some plants flower form packs, but not formed pods, there is also a form packs of flowers, but few pods produce soybean morphological characters such as plant height, number of branches, pods, days to flowering, harvesting, seed weight and seed number.

Keywords: gamma ray, genetic mutation, irradiation, soybean

Procedia PDF Downloads 403

Authors: Xiaochen Mu

Abstract:

Due to the diversity of stakeholders and the ambiguity of ownership boundaries, the current protection models for Artificial Intelligence Generated Content (AIGC) have many disadvantages. In response to this situation, there are three different protection models worldwide. The United States Copyright Office stipulates that works autonomously generated by artificial intelligence ‘lack’ the element of human creation, and non-human AI cannot create works. To protect and promote investment in the field of artificial intelligence, UK legislation, through Section 9(3) of the CDPA, designates the author of AI-generated works as ‘the person by whom the arrangements necessary for the creation of the work are undertaken.’ China neither simply excludes the work attributes of AI-generated content based on the lack of a natural person subject as the sole reason, nor does it generalize that AIGC should or should not be protected. Instead, it combines specific case circumstances and comprehensively evaluates the degree of originality of AIGC and the contributions of natural persons to AIGC. In China's first AI drawing case, the court determined that the image in question was the result of the plaintiff's design and selection through inputting prompt words and setting parameters, reflecting the plaintiff's intellectual investment and personalized expression, and should be recognized as a work in the sense of copyright law. Despite opposition, the ruling also established the feasibility of the AIGC copyright protection path. The recognition of the work attributes of AIGC will not lead to overprotection that hinders the overall development of the AI industry. Just as with the legislation and regulation of AI by various countries, there is a need for a balance between protection and development. For example, the provisional agreement reached on the EU AI Act, based on a risk classification approach, seeks a dynamic balance between copyright protection and the development of the AI industry.

Keywords: generative artificial intelligence, originality, works, copyright

Procedia PDF Downloads 46

Authors: Nurhayati Br Tarigan, Rizkita Rachmi Esyanti

Abstract:

Stevia (Stevia rebaudiana Bertoni) has a great potential to be used as a natural sweetener because it contains steviol glycoside, which is approximately 100 - 300 times sweeter than sucrose, yet low calories. Vegetative and generative propagation of S. rebaudiana is inefficient to produce stevia biomass and stevioside. One of alternative for stevia propagation is in vitro shoot culture. This research was conducted to optimize the best medium for shoot growth and to compare the bioconversion efficiency and stevioside production of S. rebaudiana shoot culture cultivated in thin layer culture (TLC), recipient for automated temporary immersion system (TIS RITA®) bioreactor, and bubble column bioreactor. The result showed that 1 ppm of Kinetin produced a healthy shoot and the highest number of leaves compared to BAP. Shoots were then cultivated in TLC, TIS RITA® bioreactor, and bubble column bioreactor. Growth medium efficiency was determined by yield and productivity. TLC produced the highest growth medium efficiency of S. rebaudiana, the yield was 0.471 ± 0.117 gbiomass.gsubstrate-1, and the productivity was 0.599 ± 0.122 gbiomass.Lmedium-1.day-1. While TIS RITA® bioreactor produced the lowest yield and productivity, 0.182 ± 0.024 gbiomass.gsubstrate-1 and 0.041 ± 0.0002 gbiomass.Lmedium-1.day-1 respectively. The yield of bubble column bioreactor was 0.354 ± 0.204 gbiomass.gsubstrate-1 and the productivity was 0,099 ± 0,009 gbiomass.Lmedium-1.day-1. The stevioside content from the highest to the lowest was obtained from stevia shoot which was cultivated on TLC, TIS RITA® bioreactor, and bubble column bioreactor; the content was 93,44 μg/g, 42,57 μg/g, and 23,03 μg/g respectively. All three systems could be used to produce stevia shoot biomass, but optimization on the number of nutrition and oxygen intake was required in each system.

Keywords: bubble column, growth medium efficiency, Stevia rebaudiana, stevioside, TIS RITA®, TLC

Procedia PDF Downloads 270

Authors: Mark Salisbury

Abstract:

The arrival of artificially intelligent avatars and the automation they bring is worrying many of us, not only for our livelihood but for the jobs that may be lost to our kids. We worry about what our place will be as human beings in this new economy where much of it will be conducted online in the metaverse – in a network of 3D virtual worlds – working with intelligent machines. The Future of Leadership was written to address these fears and show what our place will be – the right place – in this new economy of AI avatars, automation, and 3D virtual worlds. But to be successful in this new economy, our job will be to bring wisdom to our workplace and the marketplace. And we will use AI avatars and 3D virtual worlds to do it. However, this book is about more than AI and the avatars that we will work with in the metaverse. It’s about building Organizational intelligence (OI) -- the capability of an organization to comprehend and create knowledge relevant to its purpose; in other words, it is the intellectual capacity of the entire organization. To increase organizational intelligence requires a new kind of knowledge worker, a wisdom worker, that requires a new kind of leadership. This book begins your story for how to become a leader of wisdom workers and be successful in the emerging wisdom economy. After this presentation, conference participants will be able to do the following: Recognize the characteristics of the new generation of wisdom workers and how they differ from their predecessors. Recognize that new leadership methods and techniques are needed to lead this new generation of wisdom workers. Apply personal and professional values – personal integrity, belief in something larger than yourself, and keeping the best interest of others in mind – to improve your work performance and lead others. Exhibit an attitude of confidence, courage, and reciprocity of sharing knowledge to increase your productivity and influence others. Leverage artificial intelligence to accelerate your ability to learn, augment your decision-making, and influence others.Utilize new technologies to communicate with human colleagues and intelligent machines to develop better solutions more quickly.

Keywords: metaverse, generative artificial intelligence, automation, leadership, organizational intelligence, wisdom worker

Procedia PDF Downloads 45

Authors: Hiromi Takafuji

Abstract:

Flight attendant:FA is one of popular occupation, especially in Asian countries, and the decision to be hired is made after clearing a high multiplier. On the other hand, immediately after joining the company, they experience unique stress due to the fact that the organization requires them to perform security and customer service duties in a highly specialized and limited space and time. As a result, despite the high level of difficulty in joining the company, many new recruits retire early at a high rate. It is commonly said that 30% of new graduates leave the company within three years in Japan and speculated that Reality Shock:RS is one of the causes of this. RS is that newcomers experience refers to the stress caused by the difference between pre-employment expectations and post-employment reality. The purpose of this study was to elucidate the mechanism by which the expertise required of new FA and the expectation of expertise held by each of them cause reality shock, which affects motivation and the decision to leave. This study identified the professionalism required of new FA and the impact of that expectation for professionalism on RS through an exploratory study of the experiences and psychological processes of FA who left within three years. Semi-structured in-depth interviews were conducted with five FA who left a major Japanese airline at an early stage, and their experiences were categorized, integrated, and classified by qualitative content analysis. They were chosen under a number of controlled conditions. Then two major findings emerged: first, that pre-employment expectations defining RS were hierarchical, and second, that training amplified expectations of professionalism, which strongly influenced early turnover. From these, this study generated a model of RS generative process model of FA that expectations are hierarchical and influential. This could contribute to the prevention of mental health deterioration by reality shock among new FA.

Keywords: reality shock, flight attendant, early turnover, qualitative study

Procedia PDF Downloads 82

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 155

Authors: Ningfei Xiao, Simon Twose, Hannah Hopewell

Abstract:

In urban settings worldwide, artists and researchers have drawn from shamanic healing, providing insightful responses to the environment. This project is a transdisciplinary creative research project where architecture and art practice draw from shamanic healing and provide the potential to expand knowledge of public space and inspire more aesthetic explorations of public spatial visions. The research started from the encounters with the Ewengki/Evenki shaman tribe in settlement areas of northern China in 2019 and extended through the partnerships with Maori artists in Poneke Aotearoa, New Zealand, in 2023. Based on the learnings and collaborations with female indigenous tradition practitioners and the healing that the researcher received from the land, a spatial installation exhibition was developed in this project. Indigenous practices are intricately woven with contemporary technology, merging visuals, soundscapes, and other non-visual aesthetics influenced by the researcher's personal experiences of embodied shamanic healing with brainwave generative technology. This synthesis seeks to ritualize and reimagine future public spaces, encompassing streetscapes and greenscapes from China to Aotearoa, and fostering connections between urbanized human body, mind, spirit, and land. In doing so, the project presents a feminist posthuman inquiry into how individuals perceive materiality within the context of a future city. Grounded in creative research and embodied methodologies, this paper focuses on the conceptual and autoethnographic aspects of visual-non-visual aesthetics and their creative representation. Through the exploration of aesthetics beyond the visual realm within urban and spatial contexts, this project showcases the spatial installation exhibition as an example of shamanic influence and related response to public space through embodied artistry and transdisciplinary creative inquiry.

Keywords: aesthetic, embodiment, visual and/or non-visual, spatial installation, shamanic healing, public space

Procedia PDF Downloads 62