Search results for: Chat Generative Pre-training Transformer-3

Authors: Joaquin Ticzon, Christian Demition, Jaime Honra

Abstract:

Additive manufacturing (AM) or 3D printing has been one of the emerging trends present in various industries, particularly in prototyping. This review focuses on the impact of additive manufacturing on a motor vehicle's performance aiming to investigate potential advancements to further revolutionize the way parts are manufactured. One of the most common problems faced in the automotive industry is carbon footprint emissions from motor vehicles, which was stated to be remedied by lightweight; additively manufactured parts helped reduce these emissions due to weight reduction provided by additively manufactured parts. Composed of various techniques for AM as well as materials utilized during the manufacturing process, which differ in terms of the quality and performance it provides during its application on the final product. Given this, the generative design will not be discussed in such a detailed manner because the focus will revolve around the effects on the performance of a vehicle due to additively manufactured parts.

Keywords: additive manufacturing (AM), automotive, computer aided design (CAD), generative design

Procedia PDF Downloads 44

Authors: Andrew Fox, Qingping Yang, Yuanhong Zhao, Tao Zhang

Abstract:

Furniture is a very significant subdivision of architecture and its inherent interior design activities. The furniture industry has developed from an artisan-driven craft industry, whose forerunners saw themselves manifested in their crafts and treasured a sense of pride in the creativity of their designs, these days largely reduced to an anonymous collective mass-produced output. Although a very conservative industry, there is great potential for the implementation of collaborative digital technologies allowing a reconfigured artisan experience to be reawakened in a new and exciting form. The furniture manufacturing industry, in general, has been slow to adopt new methodologies for a design using artificial and rule-based generative design. This tardiness has meant the loss of potential to enhance its capabilities in producing sustainable, flexible, and mass customizable ‘right first-time’ designs. This paper aims to demonstrate the concept methodology for the creation of alternative and inspiring aesthetic structures for robot-based additive manufacturing (RBAM). These technologies can enable the economic creation of previously unachievable structures, which traditionally would not have been commercially economic to manufacture. The integration of these technologies with the computing power of generative design provides the tools for practitioners to create concepts which are well beyond the insight of even the most accomplished traditional design teams. This paper aims to address the problem by introducing generative design methodologies employing the Autodesk Fusion 360 platform. Examination of the alternative methods for its use has the potential to significantly reduce the estimated 80% contribution to environmental impact at the initial design phase. Though predominantly a design methodology, generative design combined with RBAM has the potential to leverage many lean manufacturing and quality assurance benefits, enhancing the efficiency and agility of modern furniture manufacturing. Through a case study examination of a furniture artifact, the results will be compared to a traditionally designed and manufactured product employing the Ecochain Mobius product life cycle analysis (LCA) platform. This will highlight the benefits of both generative design and robot-based additive manufacturing from an environmental impact and manufacturing efficiency standpoint. These step changes in design methodology and environmental assessment have the potential to revolutionise the design to manufacturing workflow, giving momentum to the concept of conceiving a pre-industrial model of manufacturing, with the global demand for a circular economy and bespoke sustainable design at its heart.

Keywords: robot, manufacturing, generative design, sustainability, circular econonmy, product life cycle assessment, furniture

Procedia PDF Downloads 144

Authors: Kuo-Cheng Liu

Abstract:

In the perceptual image coding, the objective is to shape the coding distortion such that the amplitude of distortion does not exceed the error visibility threshold, or to remove perceptually redundant signals from the image. While most researches focus on color image coding, the perceptual-based quantizer developed for luminance signals are always directly applied to chrominance signals such that the color image compression methods are inefficient. In this paper, the internal generative mechanism is integrated into the design of a color image compression method. The internal generative mechanism working model based on the structure-based spatial masking is used to assess the subjective distortion visibility thresholds that are visually consistent to human eyes better. The estimation method of structure-based distortion visibility thresholds for color components is further presented in a locally adaptive way to design quantization process in the wavelet color image compression scheme. Since the lowest subband coefficient matrix of images in the wavelet domain preserves the local property of images in the spatial domain, the error visibility threshold inherent in each coefficient of the lowest subband for each color component is estimated by using the proposed spatial error visibility threshold assessment. The threshold inherent in each coefficient of other subbands for each color component is then estimated in a local adaptive fashion based on the distortion energy allocation. By considering that the error visibility thresholds are estimated using predicting and reconstructed signals of the color image, the coding scheme incorporated with locally adaptive perceptual color quantizer does not require side information. Experimental results show that the entropies of three color components obtained by using proposed IGM-based color image compression scheme are lower than that obtained by using the existing color image compression method at perceptually lossless visual quality.

Keywords: internal generative mechanism, structure-based spatial masking, visibility threshold, wavelet domain

Procedia PDF Downloads 251

Authors: Thomas Monahan, Nicolas Gorius, Thanh Nguyen

Abstract:

Exoplanet atmospheric parameters retrieval is a complex, computationally intensive, inverse modeling problem in which an exoplanet’s atmospheric composition is extracted from an observed spectrum. Traditional Bayesian sampling methods require extensive time and computation, involving algorithms that compare large numbers of known atmospheric models to the input spectral data. Runtimes are directly proportional to the number of parameters under consideration. These increased power and runtime requirements are difficult to accommodate in space missions where model size, speed, and power consumption are of particular importance. The use of traditional Bayesian sampling methods, therefore, compromise model complexity or sampling accuracy. The Atmospheric Retrievals conditional Generative Adversarial Network (ARcGAN) is a deep convolutional generative adversarial network that improves on the previous model’s speed and accuracy. We demonstrate the efficacy of artificial intelligence to quickly and reliably predict atmospheric parameters and present it as a viable alternative to slow and computationally heavy Bayesian methods. In addition to its broad applicability across instruments and planetary types, ARcGAN has been designed to function on low power application-specific integrated circuits. The application of edge computing to atmospheric retrievals allows for real or near-real-time quantification of atmospheric constituents at the instrument level. Additionally, edge computing provides both high-performance and power-efficient computing for AI applications, both of which are critical for space missions. With the edge computing chip implementation, ArcGAN serves as a strong basis for the development of a similar machine-learning algorithm to reduce the downlinked data volume from the Compact Ultraviolet to Visible Imaging Spectrometer (CUVIS) onboard the DAVINCI mission to Venus.

Keywords: deep learning, generative adversarial network, edge computing, atmospheric parameters retrieval

Procedia PDF Downloads 173

Authors: Yifan Fan, Xudong Luo, Pingping Lin

Abstract:

An essential task in the field of artificial intelligence is to allow computers to interact with people through natural language. Therefore, researches such as virtual assistants and dialogue systems have received widespread attention from industry and academia. The response generation plays a crucial role in dialogue systems, so to push forward the research on this topic, this paper surveys various methods for response generation. We sort out these methods into three categories. First one includes finite state machine methods, framework methods, and instance methods. The second contains full-text indexing methods, ontology methods, vast knowledge base method, and some other methods. The third covers retrieval methods and generative methods. We also discuss some hybrid methods based knowledge and deep learning. We compare their disadvantages and advantages and point out in which ways these studies can be improved further. Our discussion covers some studies published in leading conferences such as IJCAI and AAAI in recent years.

Keywords: deep learning, generative, knowledge, response generation, retrieval

Procedia PDF Downloads 137

Authors: Sarah Alnafea, Basmah Alalsheikh, Hadab Alkathiri

Abstract:

For over 30 years, AutoCAD, a powerful CAD software developed by Autodesk, has been an imperative need for design in industries such as engineering, building, and architecture. With the emerge of advanced technology, AutoCAD has undergone a revolutionary change with the involvement of artificial intelligence capabilities that have enhanced the productivity and efficiency at work and quality in the design for the users. This paper investigates the role AI in AutoCAD, especially in intelligent automation, generative design, automated design ideas, natural language processing, and predictive analytics. To identify further, A survey among users was also conducted to assess the adoption and satisfaction of AI features and identify areas for improvement. The Competitive standing of AutoCAD is further crosschecked against other AI-enabled CAD software packages, including SolidWorks, Fusion 360, and Rhino.In this paper, an overview of the current impacts of AI in AutoCAD is given, along with some recommendations for the future road of AI development to meet users’ requirements

Keywords: artificail inteligence, natural language proccesing, intelligent automation, generative design

Procedia PDF Downloads 14

Authors: Heeba A. Gurku

Abstract:

Introduction: Cone Beam CT(CBCT) images play an integral part in proper patient positioning in cancer patients undergoing radiation therapy treatment. But these images are low in quality. The purpose of this study is to generate high-quality synthetic CT images from CBCT using generative models. Material and Methods: This study utilized two datasets from The Cancer Imaging Archive (TCIA) 1) Lung cancer dataset of 20 patients (with full view CBCT images) and 2) Pancreatic cancer dataset of 40 patients (only 27 patients having limited view images were included in the study). Cycle Generative Adversarial Networks (GAN) and its variant Attention Guided Generative Adversarial Networks (AGGAN) models were used to generate the synthetic CTs. Models were evaluated by visual evaluation and on four metrics, Structural Similarity Index Measure (SSIM), Peak Signal Noise Ratio (PSNR) Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), to compare the synthetic CT and original CT images. Results: For pancreatic dataset with limited view CBCT images, our study showed that in Cycle GAN model, MAE, RMSE, PSNR improved from 12.57to 8.49, 20.94 to 15.29 and 21.85 to 24.63, respectively but structural similarity only marginally increased from 0.78 to 0.79. Similar, results were achieved with AGGAN with no improvement over Cycle GAN. However, for lung dataset with full view CBCT images Cycle GAN was able to reduce MAE significantly from 89.44 to 15.11 and AGGAN was able to reduce it to 19.77. Similarly, RMSE was also decreased from 92.68 to 23.50 in Cycle GAN and to 29.02 in AGGAN. SSIM and PSNR also improved significantly from 0.17 to 0.59 and from 8.81 to 21.06 in Cycle GAN respectively while in AGGAN SSIM increased to 0.52 and PSNR increased to 19.31. In both datasets, GAN models were able to reduce artifacts, reduce noise, have better resolution, and better contrast enhancement. Conclusion and Recommendation: Both Cycle GAN and AGGAN were significantly able to reduce MAE, RMSE and PSNR in both datasets. However, full view lung dataset showed more improvement in SSIM and image quality than limited view pancreatic dataset.

Keywords: CT images, CBCT images, cycle GAN, AGGAN

Procedia PDF Downloads 84

Authors: Svenja Pieritz, Jakab Pilaszanovich

Abstract:

Collaborative Problem Solving (CPS) is recognized as being one of the most important skills of the 21st century with having a potential impact on education, job selection, and collaborative systems design. Therefore, CPS has been adopted in several standardized tests, including the Programme for International Student Assessment (PISA) in 2015. A significant challenge of evaluating CPS is the underlying interplay of cognitive and social skills, which requires a more holistic assessment. However, the majority of the existing tests are using a questionnaire-based assessment, which oversimplifies this interplay and undermines ecological validity. Two major difficulties were identified: Firstly, the creation of a controllable, real-time environment allowing natural behaviors and communication between at least two people. Secondly, the development of an appropriate method to collect and synthesize both cognitive and social metrics of collaboration. This paper proposes a more holistic and automated approach to the assessment of CPS. To address these two difficulties, a multiplayer problem-solving game called Sea of Light was developed: An environment allowing students to deploy a variety of measurable collaborative strategies. This controlled environment enables researchers to monitor behavior through the analysis of game actions and chat. The according solution for the statistical model is a combined approach of Natural Language Processing (NLP) and Bayesian network analysis. Social exchanges via the in-game chat are analyzed through NLP and fed into the Bayesian network along with other game actions. This Bayesian network synthesizes evidence to track and update different subdimensions of CPS. Major findings focus on the correlations between the evidences collected through in- game actions, the participants’ chat features and the CPS self- evaluation metrics. These results give an indication of which game mechanics can best describe CPS evaluation. Overall, Sea of Light gives test administrators control over different problem-solving scenarios and difficulties while keeping the student engaged. It enables a more complete assessment based on complex, socio-cognitive information on actions and communication. This tool permits further investigations of the effects of group constellations and personality in collaborative problem-solving.

Keywords: bayesian network, collaborative problem solving, game-based assessment, natural language processing

Procedia PDF Downloads 133

Authors: B. Mombayeva

Abstract:

In the deserts area of south east of Kazakhstan, 16 species of Coleoptera from 6 families and 12 genus of insects damaging Saxaul have been revealed. The vast number of species belong to the Cerambycidae familyCapricorn Beetle (4 species) and Hemlock Borer of Melanophila genus and 3 species of weevils and flea-beetles, and 1 species of coctsinelids and carrion beetle. Some of them cause appreciable harm, and sometimes very heavy damageto saxaul. According to food specialization they are divided into polyphages and - oligophages. According to the confinement to saxaul parts, registered beetles insects mainly feed on generative parts (11 species) and leaves (5 species). 9 species from them feed on roots, leaves and generative organs. They are scarablike beetle’s larvae (Apatophysismongolica Semenov., Tursmenigenavarentzovi Melg., Phytoecia (Opsilla) coerulescens Scopoli., Apatophysismongolica Semenov.), Jewel beetles (Julodis (s. Str.) Variolaris (Pallas), Sphenoptera (s. Str.) cuprina Motschulsky, S. (s. str.) exarata (Fischer), SphenopterapotaniniJak.) and some weevil (Barisartemisiae Hbst.). The larvae eat the roots and the imago - generative organs. Their feeding noticeably has its effect on the condition of saxaul. Beetles also slightlygnaw vegetative organs of plants. Among the harmful species the desert Capricorn Beetle Julodisvariolaris (Pallas) deserved attention. Its larvae live in the soil and cause harm to the roots of Saxaul and other pasture plants. In addition, the larvae of Sphenopterapotanini, S.punctatissima colonize the roots, trunk and branches of Haloxylon. In the spring Saxaul flowers are much damaged by Ladybeetle Bulaealichatchovi.

Keywords: saxaul, coleoptera, insecta, haloxylon

Procedia PDF Downloads 259

Authors: Sheldon Liu, Gordon Wang, Lei Liu, Xuefeng Liu

Abstract:

Anomaly detection, also referred to as one-class classification, plays a crucial role in identifying product images that deviate from the expected distribution. This study introduces Data-centric Anomaly Detection with Diffusion Models (DCADDM), presenting a systematic strategy for data collection and further diversifying the data with image generation via diffusion models. The algorithm addresses data collection challenges in real-world scenarios and points toward data augmentation with the integration of generative AI capabilities. The paper explores the generation of normal images using diffusion models. The experiments demonstrate that with 30% of the original normal image size, modeling in an unsupervised setting with state-of-the-art approaches can achieve equivalent performances. With the addition of generated images via diffusion models (10% equivalence of the original dataset size), the proposed algorithm achieves better or equivalent anomaly localization performance.

Keywords: diffusion models, anomaly detection, data-centric, generative AI

Procedia PDF Downloads 86

Authors: Sultana Razia

Abstract:

The number of children whose social, communication and behavior pattern is affected due to mental and developmental conditions is on the rise. Most of these conditions develop to uncontrollable levels because of ignorance and unaware about their child’s condition. The many myths surrounding mental or developmental conditions are a major cause of families of affected children to develop bitterness and to shy off from seeking appropriate help in time. Several early intervention programs have been put in place, and the number of beneficiaries of these programs is increasing by the day. This research seeks to look into early intervention programs and their effectiveness. The purpose of this study was to investigate the effect of early therapeutic intervention for the children with autism spectrum disorder. Participants were 140 children with autism spectrum disorder from Autism Corner in a selected rehabilitation center of Bangladesh. This study included children who are at age of 18-month to 36-month and who were taking occupational therapy and speech and language therapy from the autism center. They were primarily screened using M-CHAT; however, children with other physical disability or medical conditions excluded. 3-months interventions of 6 sessions per week are a minimum of 45-minutes long per session, one to one interaction followed by parent-led structured home-based therapy were provided. The results indicated that early intensive therapeutic intervention improve understanding, social skills and sensory skills. It can be concluded that therapeutic early intervention a positive effect on diminishing symptoms of Autism Spectrum Disorder.

Keywords: M-CHAT, ASD, sensory cheeklist, OT

Procedia PDF Downloads 79

Authors: Radul Shishkov

Abstract:

This research paper presents an in-depth exploration of the use of generative design in urban residential architecture, with a dual focus on aligning aesthetic values with legal and environmental constraints. The study aims to demonstrate how generative design methodologies can innovate residential building designs that are not only legally compliant and environmentally conscious but also aesthetically compelling. At the core of our research is a specially developed generative design framework tailored for urban residential settings. This framework employs computational algorithms to produce diverse design solutions, meticulously balancing aesthetic appeal with practical considerations. By integrating site-specific features, urban legal restrictions, and environmental factors, our approach generates designs that resonate with the unique character of urban landscapes while adhering to regulatory frameworks. The paper explores how modern digital tools, particularly computational design and algorithmic modelling, can optimize the early stages of residential building design. By creating a basic parametric model of a residential district, the paper investigates how automated design tools can explore multiple design variants based on predefined parameters (e.g., building cost, dimensions, orientation) and constraints. The paper aims to demonstrate how these tools can rapidly generate and refine architectural solutions that meet the required criteria for quality of life, cost efficiency, and functionality. The study utilizes computational design for database processing and algorithmic modelling within the fields of applied geodesy and architecture. It focuses on optimizing the forms of residential development by adjusting specific parameters and constraints. The results of multiple iterations are analyzed, refined, and selected based on their alignment with predefined quality and cost criteria. The findings of this research will contribute to a modern, complex approach to residential area design. The paper demonstrates the potential for integrating BIM models into the design process and their application in virtual 3D Geographic Information Systems (GIS) environments. The study also examines the transformation of BIM models into suitable 3D GIS file formats, such as CityGML, to facilitate the visualization and evaluation of urban planning solutions. 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 investment during its entire lifecycle.

Keywords: algorithmic modeling, architectural design, residential buildings, urban development, generative design, parametric models

Procedia PDF Downloads 18

Authors: Heichia Wang, Yalan Chao

Abstract:

Social inequality is a persistent problem. One of the ways to solve this problem is through education. At present, vulnerable groups are often less geographically accessible to educational resources. However, compared with educational resources, communication equipment is easier for vulnerable groups. Now that information and communication technology (ICT) has entered the field of education, today we can accept the convenience that ICT provides in education, and the mobility that it brings makes learning independent of time and place. With mobile learning, teachers and students can start discussions in an online chat room without the limitations of time or place. However, because liquidity learning is quite convenient, people tend to solve problems in short online texts with lack of detailed information in a lack of convenient online environment to express ideas. Therefore, the ICT education environment may cause misunderstanding between teachers and students. Therefore, in order to better understand each other's views between teachers and students, this study aims to clarify the essays of the analysts and classify the students into several types of learning questions to clarify the views of teachers and students. In addition, this study attempts to extend the description of possible omissions in short texts by using external resources prior to classification. In short, by applying a short text classification, this study can point out each student's learning problems and inform the instructor where the main focus of the future course is, thus improving the ICT education environment. In order to achieve the goals, this research uses convolutional neural network (CNN) method to analyze short discussion content between teachers and students in an ICT education environment. Divide students into several main types of learning problem groups to facilitate answering student problems. In addition, this study will further cluster sub-categories of each major learning type to indicate specific problems for each student. Unlike most neural network programs, this study attempts to extend short texts with external resources before classifying them to improve classification performance. In short, by applying the classification of short texts, we can point out the learning problems of each student and inform the instructors where the main focus of future courses will improve the ICT education environment. The data of the empirical process will be used to pre-process the chat records between teachers and students and the course materials. An action system will be set up to compare the most similar parts of the teaching material with each student's chat history to improve future classification performance. Later, the function of short text classification uses CNN to classify rich chat records into several major learning problems based on theory-driven titles. By applying these modules, this research hopes to clarify the main learning problems of students and inform teachers that they should focus on future teaching.

Keywords: ICT education improvement, social equality, short text analysis, convolutional neural network

Procedia PDF Downloads 129

Authors: Weichen Chang

Abstract:

To create a guided teaching method for AI generative drawing design, this paper develops a set of teaching models for AI generative drawing (DCAI), which combines learning modes such as problem-solving, thematic inquiry, phenomenon-based, task-oriented, and DFC . Through the information security AI picture book learning guided programs and content, the application of participatory action research (PAR) and interview methods to explore the dual knowledge of Context and ChatGPT (DCAI) for AI to guide the development of students' AI learning skills. In the interviews, the students highlighted five main learning outcomes (self-study, critical thinking, knowledge generation, cognitive development, and presentation of work) as well as the challenges of implementing the model. Through the use of DCAI, students will enhance their consensus awareness of generative mapping analysis and group cooperation, and they will have knowledge that can enhance AI capabilities in DCAI inquiry and future life. From this paper, it is found that the conclusions are (1) The good use of DCAI can assist students in exploring the value of their knowledge through the power of stories and finding the meaning of knowledge communication; (2) Analyze the transformation power of the integrity and coherence of the story through the context so as to achieve the tension of ‘starting and ending’; (3) Use ChatGPT to extract inspiration, arrange story compositions, and make prompts that can communicate with people and convey emotions. Therefore, new knowledge construction methods will be one of the effective methods for AI learning in the face of artificial intelligence, providing new thinking and new expressions for interdisciplinary design and design education practice.

Keywords: artificial intelligence, task-oriented, contextualization, design education

Procedia PDF Downloads 35

Authors: Vlad Andrei Raducanu, Mariana Lucia Angelescu, Ion Cinca, Vasile Danut Cojocaru, Doina Raducanu

Abstract:

By using smart digital tools, such as generative design (GD) and digital fabrication (DF), problems of high actuality concerning resources optimization (materials, energy, time) can be solved and applications or products of free-form type can be created. In the new digital technology materials are active, designed in response to a set of performance requirements, which impose a total rethinking of old material practices. The article presents the design procedure key steps of a free-form architectural object - a column type one with connections to get an adaptive 3D surface, by using the parametric design methodology and by exploiting the properties of conventional metallic materials. In parametric design the form of the created object or space is shaped by varying the parameters values and relationships between the forms are described by mathematical equations. Digital parametric design is based on specific procedures, as shape grammars, Lindenmayer - systems, cellular automata, genetic algorithms or swarm intelligence, each of these procedures having limitations which make them applicable only in certain cases. In the paper the design process stages and the shape grammar type algorithm are presented. The generative design process relies on two basic principles: the modeling principle and the generative principle. The generative method is based on a form finding process, by creating many 3D spatial forms, using an algorithm conceived in order to apply its generating logic onto different input geometry. Once the algorithm is realized, it can be applied repeatedly to generate the geometry for a number of different input surfaces. The generated configurations are then analyzed through a technical or aesthetic selection criterion and finally the optimal solution is selected. Endless range of generative capacity of codes and algorithms used in digital design offers various conceptual possibilities and optimal solutions for both technical and environmental increasing demands of building industry and architecture. Constructions or spaces generated by parametric design can be specifically tuned, in order to meet certain technical or aesthetical requirements. The proposed approach has direct applicability in sustainable architecture, offering important potential economic advantages, a flexible design (which can be changed until the end of the design process) and unique geometric models of high performance.

Keywords: parametric design, algorithmic procedures, free-form architectural object, sustainable architecture

Procedia PDF Downloads 380

Authors: Wesley Teskey, Vedran Glavas, Julian Wegener

Abstract:

Generating battery cathode microstructures is an important area of research, given the proliferation of the use of automotive batteries. Currently, finite element analysis (FEA) is often used for simulations of battery cathode microstructures before physical batteries can be manufactured and tested to verify the simulation results. Unfortunately, a key drawback of using FEA is that this method of simulation is very slow in terms of computational runtime. Generative AI offers the key advantage of speed when compared to FEA, and because of this, generative AI is capable of evaluating very large numbers of candidate microstructures. Given AI generated candidate microstructures, a subset of the promising microstructures can be selected for further validation using FEA. Leveraging the speed advantage of AI allows for a better final microstructural selection because high speed allows for the evaluation of many more candidate microstructures. For the approach presented, battery cathode 3D candidate microstructures are generated using Gaussian Mixture Models (GMMs) and pix2pix. This approach first uses GMMs to generate a population of spheres (representing the “active material” of the cathode). Once spheres have been sampled from the GMM, they are placed within a microstructure. Subsequently, the pix2pix sweeps over the 3D microstructure (iteratively) slice by slice and adds details to the microstructure to determine what portions of the microstructure will become electrolyte and what part of the microstructure will become binder. In this manner, each subsequent slice of the microstructure is evaluated using pix2pix, where the inputs into pix2pix are the previously processed layers of the microstructure. By feeding into pix2pix previously fully processed layers of the microstructure, pix2pix can be used to ensure candidate microstructures represent a realistic physical reality. More specifically, in order for the microstructure to represent a realistic physical reality, the locations of electrolyte and binder in each layer of the microstructure must reasonably match the locations of electrolyte and binder in previous layers to ensure geometric continuity. Using the above outlined approach, a 10x to 100x speed increase was possible when generating candidate microstructures using AI when compared to using a FEA only approach for this task. A key metric for evaluating microstructures was the battery specific power value that the microstructures would be able to produce. The best generative AI result obtained was a 12% increase in specific power for a candidate microstructure when compared to what a FEA only approach was capable of producing. This 12% increase in specific power was verified by FEA simulation.

Keywords: finite element analysis, gaussian mixture models, generative design, Pix2Pix, structural design

Procedia PDF Downloads 111

Authors: Hussain Sajid, Jung-Hun Shin, Kum-Won Cho

Abstract:

Image super-resolution is the most common computer vision problem with many important applications. Generative adversarial networks (GANs) have promoted remarkable advances in single-image super-resolution (SR) by recovering photo-realistic images. However, high memory requirements of GAN-based SR (mainly generators) lead to performance degradation and increased energy consumption, making it difficult to implement it onto resource-constricted devices. To relieve such a problem, In this paper, we introduce an optimized and highly efficient architecture for SR-GAN (generator) model by utilizing model compression techniques such as Knowledge Distillation and pruning, which work together to reduce the storage requirement of the model also increase in their performance. Our method begins with distilling the knowledge from a large pre-trained model to a lightweight model using different loss functions. Then, iterative weight pruning is applied to the distilled model to remove less significant weights based on their magnitude, resulting in a sparser network. Knowledge Distillation reduces the model size by 40%; pruning then reduces it further by 18%. To accelerate the learning process, we employ the Horovod framework for distributed training on a cluster of 2 nodes, each with 8 GPUs, resulting in improved training performance and faster convergence. Experimental results on various benchmarks demonstrate that the proposed compressed model significantly outperforms state-of-the-art methods in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and image quality for x4 super-resolution tasks.

Keywords: single-image super-resolution, generative adversarial networks, knowledge distillation, pruning

Procedia PDF Downloads 102

Authors: Po-Chun Wang, Yan-Ru Lai, Sophia I. C. Lin, Alvin W. Y. Su

Abstract:

The Generative Theory of Tonal Music (GTTM) provides systematic approaches to recognizing local boundaries of music. The rules have been implemented in some automated melody segmentation algorithms. Besides, there are also deep learning methods with GTTM features applied to boundary detection tasks. However, these studies might face constraints such as a lack of or inconsistent label data. The GTTM database is currently the most widely used GTTM database, which includes manually labeled GTTM rules and local boundaries. Even so, we found some problems with these labels. They are sometimes discrepancies with GTTM rules. In addition, since it is labeled at different times by multiple musicians, they are not within the same scope in some cases. Therefore, in this paper, we examine this database with musicians from the aspect of classical music and relabel the scores. The relabeled database - GTTM Database v2.0 - will be released for academic research usage. Despite the experimental and statistical results showing that the relabeled database is more consistent, the improvement in boundary detection is not substantial. It seems that we need more clues than GTTM rules for boundary detection in the future.

Keywords: dataset, GTTM, local boundary, neural network

Procedia PDF Downloads 149

Authors: Fabrice Setephin Atedjio, Jean-Pierre Lienou, Frederica F. Nelson, Sachin S. Shetty, Charles A. Kamhoua

Abstract:

Malicious users exploit vulnerabilities in computer systems, significantly disrupting their performance and revealing the inadequacies of existing protective solutions. Even machine learning-based approaches, designed to ensure reliability, can be compromised by adversarial attacks that undermine their robustness. This paper addresses two critical aspects of enhancing model reliability. First, we focus on improving model performance and robustness against adversarial threats. To achieve this, we propose a strategy by harnessing deep reinforcement learning. Second, we introduce an approach leveraging generative adversarial networks to counter adversarial attacks effectively. Our results demonstrate substantial improvements over previous works in the literature, with classifiers exhibiting enhanced accuracy in classification tasks, even in the presence of adversarial perturbations. These findings underscore the efficacy of the proposed model in mitigating intrusions and adversarial attacks within the machine-learning landscape.

Keywords: machine learning, reliability, adversarial attacks, deep-reinforcement learning, robustness

Procedia PDF Downloads 18

Authors: Lucie Bartosova

Abstract:

The rapid advancements in generative artificial intelligence (AI) have introduced transformative possibilities in education, particularly in assessment methodologies. This work provides an overview of the current state of the literature on AI-scoring methodologies for evaluating student-written responses. The focus is on how these innovations can be leveraged within large-scale assessments to address resource constraints such as limited assessors, time, and budget. Drawing from an initiative tied to a language test used for admitting candidates into a pre-service education program in the Faculty of Education at an Ontario university, the review explores the practical and ethical implications of integrating AI-driven tools into assessment processes. These tools are designed to automate the evaluation of learners’ written compositions, provide performance feedback, and support grading procedures. By synthesizing findings from recent research, the review highlights the effectiveness, reliability, and potential biases of AI in scoring, alongside considerations for transparency and fairness. This work emphasizes the dual role of generative AI as both a practical solution for scaling assessments and a subject of critical scrutiny to ensure its responsible implementation. The proposed integration of AI-scoring methodologies in our language test underscores the need to balance innovation with accountability, ensuring that AI tools enhance, rather than compromise, educational equity and rigor. OBJECTIVES OF YOUR RESEARCH To determine which generative AI model is most capable of evaluating written responses for university assessments based on specific criteria and to investigate potential biases within AI models to ensure fair assessments. METHODOLOGIES Evaluating generative AI models to determine their performance in assessing written responses against specific criteria. Collecting responses from previous assessments and annotating them with expert feedback to train and validate the AI models. MAIN CONTRIBUTIONS Introducing a tailored AI model to assess written responses on language tests. Offering a scalable and replicable model that informs broader applications of AI in educational assessments, contributing to policy-making and institutional best practices.

Keywords: artificial intelligence, assessment practices, student written performance, automated essay scoring, language proficiency

Procedia PDF Downloads 9

Authors: P. Karthick, K. Mahesh

Abstract:

Video has become an increasingly significant component of our digital everyday contact. With the advancement of greater contents and shows of the resolution, its significant volume poses serious obstacles to the objective of receiving, distributing, compressing, and revealing video content of high quality. In this paper, we propose the primary beginning to complete a deep video compression model that jointly upgrades all video compression components. The video compression method involves splitting the video into frames, comparing the images using convolutional neural networks (CNN) to remove duplicates, repeating the single image instead of the duplicate images by recognizing and detecting minute changes using generative adversarial network (GAN) and recorded with long short-term memory (LSTM). Instead of the complete image, the small changes generated using GAN are substituted, which helps in frame level compression. Pixel wise comparison is performed using K-nearest neighbours (KNN) over the frame, clustered with K-means, and singular value decomposition (SVD) is applied for each and every frame in the video for all three color channels [Red, Green, Blue] to decrease the dimension of the utility matrix [R, G, B] by extracting its latent factors. Video frames are packed with parameters with the aid of a codec and converted to video format, and the results are compared with the original video. Repeated experiments on several videos with different sizes, duration, frames per second (FPS), and quality results demonstrate a significant resampling rate. On average, the result produced had approximately a 10% deviation in quality and more than 50% in size when compared with the original video.

Keywords: video compression, K-means clustering, convolutional neural network, generative adversarial network, singular value decomposition, pixel visualization, stochastic gradient descent, frame per second extraction, RGB channel extraction, self-detection and deciding system

Procedia PDF Downloads 189

Authors: Arya Prakash Padhi, Anupam Chakrabarti, Rajib Chowdhury

Abstract:

Topology or layout optimization often gives better performing economic structures and is very helpful in the conceptual design phase. But traditionally it is being done in finite element-based optimization schemes which, although gives a good result, is very time-consuming especially in 3D structures. Among other alternatives machine learning, especially deep learning-based methods, have a very good potential in resolving this computational issue. Here convolutional neural network (3D-CNN) based variational auto encoder (VAE) is trained using a dataset generated from commercially available topology optimization code ABAQUS Tosca using solid isotropic material with penalization (SIMP) method for compliance minimization. The encoded data in latent space is then fed to a 3D generative adversarial network (3D-GAN) to generate the outcome in 64x64x64 size. Here the network consists of 3D volumetric CNN with rectified linear unit (ReLU) activation in between and sigmoid activation in the end. The proposed network is seen to provide almost optimal results with significantly reduced computational time, as there is no iteration involved.

Keywords: 3D generative adversarial network, deep learning, structural topology optimization, variational auto encoder

Procedia PDF Downloads 177

Authors: Hamed Alqahtani, Manolya Kavakli-Thorne

Abstract:

The large pose discrepancy is one of the critical challenges in face recognition during video surveillance. Due to the entanglement of pose attributes with identity information, the conventional approaches for pose-independent representation lack in providing quality results in recognizing largely posed faces. In this paper, we propose a practical approach to disentangle the pose attribute from the identity information followed by synthesis of a face using a classifier network in latent space. The proposed approach employs a modified generative adversarial network framework consisting of an encoder-decoder structure embedded with a classifier in manifold space for carrying out factorization on the latent encoding. It can be further generalized to other face and non-face attributes for real-life video frames containing faces with significant attribute variations. Experimental results and comparison with state of the art in the field prove that the learned representation of the proposed approach synthesizes more compelling perceptual images through a combination of adversarial and classification losses.

Keywords: disentanglement, face detection, generative adversarial networks, video surveillance

Procedia PDF Downloads 131

Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli

Abstract:

Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are playing an increasingly important role in automated customer service. These models, which are able to recognize complex relationships between input and output sequences, are crucial for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the focus of the model during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the domain of chatbots using the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Utilizing the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k=3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k=3). These results emphasize the crucial influence of selecting an appropriate attention-scoring function in improving the performance of seq2seq models for chatbots. Particularly, the model that integrates tanh activation proves to be a promising approach to improve the quality of chatbots in the customer support context.

Keywords: attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence

Procedia PDF Downloads 79

Authors: Agastya Pratap Singh

Abstract:

This review paper examines the emerging applications of generative adversarial networks (GANs) in the fields of image recognition and anomaly detection. With the rapid growth of digital image data, the need for efficient and accurate methodologies to identify and classify images has become increasingly critical. GANs, known for their ability to generate realistic data, have gained significant attention for their potential to enhance traditional image recognition systems and improve anomaly detection performance. The paper systematically analyzes various GAN architectures and their modifications tailored for image recognition tasks, highlighting their strengths and limitations. Additionally, it delves into the effectiveness of GANs in detecting anomalies in diverse datasets, including medical imaging, industrial inspection, and surveillance. The review also discusses the challenges faced in training GANs, such as mode collapse and stability issues, and presents recent advancements aimed at overcoming these obstacles.

Keywords: generative adversarial networks, image recognition, anomaly detection, synthetic data generation, deep learning, computer vision, unsupervised learning, pattern recognition, model evaluation, machine learning applications

Procedia PDF Downloads 32

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 55

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 105

Authors: Armineh Nourbakhsh, Sameena Shah, Carolyn Rose

Abstract:

Layout-aware language models have been used to create multimodal representations for documents that are in image form, achieving relatively high accuracy in document understanding tasks. However, the large number of parameters in the resulting models makes building and using them prohibitive without access to high-performing processing units with large memory capacity. We propose an alternative approach that can create efficient representations without the need for a neural visual backbone. This leads to an 80% reduction in the number of parameters compared to the smallest SOTA model, widely expanding applicability. In addition, our layout embeddings are pre-trained on spatial and visual cues alone and only fused with text embeddings in downstream tasks, which can facilitate applicability to low-resource of multi-lingual domains. Despite using 2.5% of training data, we show competitive performance on two form understanding tasks: semantic labeling and link prediction.

Keywords: layout understanding, form understanding, multimodal document understanding, bias-augmented attention

Procedia PDF Downloads 154

Authors: Christoph Linse, Thomas Martinetz

Abstract:

Recent findings have shown that Neural Networks generalize also in over-parametrized regimes with zero training error. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in the domain of fine-grained image classification. We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regularization or pretraining. We train the architectures ResNet018, ResNet101 and VGG19 on subsets of the difficult benchmark datasets Caltech101, CUB_200_2011, FGVCAircraft, Flowers102 and StanfordCars with 100 classes and more, perform a comprehensive comparative study and draw implications for the practical application of CNNs. Finally, we show that VGG19 with 140 million weights learns to distinguish airplanes and motorbikes with up to 95% accuracy using only 20 training samples per class.

Keywords: convolutional neural networks, fine-grained image classification, generalization, image recognition, over-parameterized, small data sets

Procedia PDF Downloads 91

Authors: Agastya Pratap Singh

Abstract:

Generative Adversarial Networks (GANs) have emerged as powerful tools in the fields of image recognition and anomaly detection due to their ability to model complex data distributions and generate realistic images. This systematic review explores recent advancements and applications of GANs in both image recognition and anomaly detection tasks. We discuss various GAN architectures, such as DCGAN, CycleGAN, and StyleGAN, which have been tailored to improve accuracy, robustness, and efficiency in visual data analysis. In image recognition, GANs have been used to enhance data augmentation, improve classification models, and generate high-quality synthetic images. In anomaly detection, GANs have proven effective in identifying rare and subtle abnormalities across various domains, including medical imaging, cybersecurity, and industrial inspection. The review also highlights the challenges and limitations associated with GAN-based methods, such as instability during training and mode collapse, and suggests future research directions to overcome these issues. Through this review, we aim to provide researchers with a comprehensive understanding of the capabilities and potential of GANs in transforming image recognition and anomaly detection practices.

Keywords: generative adversarial networks, image recognition, anomaly detection, DCGAN, CycleGAN, StyleGAN, data augmentation

Procedia PDF Downloads 27