Search results for: generative model

Authors: Judit Vilarmau

Abstract:

Generative AI is emerging rapidly and transforming higher education in many ways, occasioning new challenges and disrupting traditional models and methods. The studies and authors explored remark on the impact on the ethics, curriculum, and pedagogical methods. Students are increasingly using generative AI for study, as a virtual tutor, and as a resource for generating works and doing assignments. This point is crucial for educators to make sure that students are using generative AI with ethical considerations. Generative AI also has relevant benefits for educators and can help them personalize learning experiences and promote self-regulation. Educators must seek and explore tools like ChatGPT to innovate without forgetting an ethical and pedagogical perspective. Eighteen studies were systematically reviewed, and the findings provide implementation guidelines with pedagogical and ethical considerations.

Keywords: ethics, generative artificial intelligence, guidelines, higher education, pedagogy

Procedia PDF Downloads 37

Authors: Ignitia Motjolopane

Abstract:

Small and medium enterprises (SMEs) play an important role in economies by contributing to economic growth and employment. In the fourth industrial revolution, the convergence of technologies and the changing nature of work created pressures on economies globally. Generative artificial intelligence (AI) may support SMEs in exploring, exploiting, and transforming business models to align with their growth aspirations. SMEs' growth aspirations fall into four categories: subsistence, income, growth, and speculative. Subsistence-oriented firms focus on meeting basic financial obligations and show less motivation for business model innovation. SMEs focused on income, growth, and speculation are more likely to pursue business model innovation to support growth strategies. SMEs' strategic goals link to distinct business model innovation paths depending on whether SMEs are starting a new business, pursuing growth, or seeking profitability. Integrating generative artificial intelligence in start-up SME business model innovation enhances value creation, user-oriented innovation, and SMEs' ability to adapt to dynamic changes in the business environment. The existing literature may lack comprehensive frameworks and guidelines for effectively integrating generative AI in start-up reiterative business model innovation paths. This paper examines start-up business model innovation path with generative artificial intelligence. A theoretical approach is used to examine start-up-focused SME reiterative business model innovation path with generative AI. Articulating how generative AI may be used to support SMEs to systematically and cyclically build the business model covering most or all business model components and analyse and test the BM's viability throughout the process. As such, the paper explores generative AI usage in market exploration. Moreover, market exploration poses unique challenges for start-ups compared to established companies due to a lack of extensive customer data, sales history, and market knowledge. Furthermore, the paper examines the use of generative AI in developing and testing viable value propositions and business models. In addition, the paper looks into identifying and selecting partners with generative AI support. Selecting the right partners is crucial for start-ups and may significantly impact success. The paper will examine generative AI usage in choosing the right information technology, funding process, revenue model determination, and stress testing business models. Stress testing business models validate strong and weak points by applying scenarios and evaluating the robustness of individual business model components and the interrelation between components. Thus, the stress testing business model may address these uncertainties, as misalignment between an organisation and its environment has been recognised as the leading cause of company failure. Generative AI may be used to generate business model stress-testing scenarios. The paper is expected to make a theoretical and practical contribution to theory and approaches in crafting a robust business model innovation path with generative artificial intelligence in start-up SMEs.

Keywords: business models, innovation, generative AI, small medium enterprises

Procedia PDF Downloads 34

Authors: Zhang Shuqi, Liu Dan

Abstract:

For the problems in intelligent network anomaly traffic detection models, such as low detection accuracy caused by the lack of training samples, poor effect with small sample attack detection, a classification model enhancement method, F-ACGAN(Flow Auxiliary Classifier Generative Adversarial Network) which introduces generative adversarial network and adversarial training, is proposed to solve these problems. Generating adversarial data with category labels could enhance the training effect and improve classification accuracy and model robustness. FACGAN consists of three steps: feature preprocess, which includes data type conversion, dimensionality reduction and normalization, etc.; A generative adversarial network model with feature learning ability is designed, and the sample generation effect of the model is improved through adversarial iterations between generator and discriminator. The adversarial disturbance factor of the gradient direction of the classification model is added to improve the diversity and antagonism of generated data and to promote the model to learn from adversarial classification features. The experiment of constructing a classification model with the UNSW-NB15 dataset shows that with the enhancement of FACGAN on the basic model, the classification accuracy has improved by 8.09%, and the score of F1 has improved by 6.94%.

Keywords: data imbalance, GAN, ACGAN, anomaly detection, adversarial training, data augmentation

Procedia PDF Downloads 72

Authors: Rashmi Malik, Videep Mishra

Abstract:

The practice of generative design has become a transformative approach for an efficient way of generating multiple iterations for any design project. The conventional way of modeling the game elements is very time-consuming and requires skilled artists to design. A 3D modeling tool like 3D S Max, Blender, etc., is used traditionally to create the game library, which will take its stipulated time to model. The study is focused on using the generative design tool to increase the efficiency in game development at the stage of prop and environment generation. This will involve procedural level and customized regulated or randomized assets generation. The paper will present the system design approach using generative tools like Grasshopper (visual scripting) and other scripting tools to automate the process of game library modeling. The script will enable the generation of multiple products from the single script, thus creating a system that lets designers /artists customize props and environments. The main goal is to measure the efficacy of the automated system generated to create a wide variety of game elements, further reducing the need for manual content creation and integrating it into the workflow of AAA and Indie Games.

Keywords: iterative game design, generative design, gaming asset automation, generative game design

Procedia PDF Downloads 38

Authors: Elizabeth Hartney, Keith Borkowsky, Jo Axe, Doug Hamilton

Abstract:

The aim of this research is to develop a grounded theory of educational leadership development, using an approach to initiating and maintaining professional growth in school principals and vice principals termed generative dialogue. The research was conducted in a relatively affluent, urban school district in Western Canada. Generative dialogue interviews were conducted by a team of consultants, and anonymous data in the form of handwritten notes were voluntarily submitted to the research team. The data were transcribed and analyzed using grounded theory. The results indicate that a key focus of educational leadership development is focused on navigating relationships within the school setting and that the generative dialogue process is helpful for principals and vice principals to explore how they might do this. Applicability and limitations of the study are addressed.

Keywords: generative dialogue, school principals, grounded theory, leadership development

Procedia PDF Downloads 302

Authors: Jiawen Wang, Qijun Chen

Abstract:

The performance of most machine-learning methods for image inpainting depends on the quantity and quality of the training samples. However, it is very expensive or even impossible to obtain a great number of training samples in many scenarios. In this paper, an image inpainting model based on a generative adversary network (GAN) is constructed for the cases when the number of training samples is small. Firstly, a feature extraction network (F-net) is incorporated into the GAN network to utilize the available information of the inpainting image. The weighted sum of the extracted feature and the random noise acts as the input to the generative network (G-net). The proposed network can be trained well even when the sample size is very small. Secondly, in the phase of the completion for each damaged image, a genetic algorithm is designed to search an optimized noise input for G-net; based on this optimized input, the parameters of the G-net and F-net are further learned (Once the completion for a certain damaged image ends, the parameters restore to its original values obtained in the training phase) to generate an image patch that not only can fill the missing part of the damaged image smoothly but also has visual semantics.

Keywords: image inpainting, generative adversary nets, genetic algorithm, small-sample size

Procedia PDF Downloads 96

Authors: Aishwarya Rai

Abstract:

This study explores the transformative influence of generative AI on startups, businesses, and industries. We will explore how large businesses can benefit in the area of customer operations, where AI-powered chatbots can improve self-service and agent effectiveness, greatly increasing efficiency. In marketing and sales, generative AI could transform businesses by automating content development, data utilization, and personalization, resulting in a substantial increase in marketing and sales productivity. In software engineering-focused startups, generative AI can streamline activities, significantly impacting coding processes and work experiences. It can be extremely useful in product R&D for market analysis, virtual design, simulations, and test preparation, altering old workflows and increasing efficiency. Zooming into the retail and CPG industry, industry findings suggest a 1-2% increase in annual revenues, equating to $400 billion to $660 billion. By automating customer service, marketing, sales, and supply chain management, generative AI can streamline operations, optimizing personalized offerings and presenting itself as a disruptive force. While celebrating economic potential, we acknowledge challenges like external inference and adversarial attacks. Human involvement remains crucial for quality control and security in the era of generative AI-driven transformative innovation. This talk provides a comprehensive exploration of generative AI's pivotal role in reshaping businesses, recognizing its strategic impact on customer interactions, productivity, and operational efficiency.

Keywords: generative AI, digital transformation, LLM, artificial intelligence, startups, businesses

Procedia PDF Downloads 30

Authors: Lakshmi Prayaga, Chandra Prayaga. Aaron Wade, Gopi Shankar Mallu, Harsha Satya Pola

Abstract:

Synthetic data generated by Generative Adversarial Networks and Autoencoders is becoming more common to combat the problem of insufficient data for research purposes. However, generating synthetic data is a tedious task requiring extensive mathematical and programming background. Open-source platforms such as the Synthetic Data Vault (SDV) and Mostly AI have offered a platform that is user-friendly and accessible to non-technical professionals to generate synthetic data to augment existing data for further analysis. The SDV also provides for additions to the generic GAN, such as the Gaussian copula. We present the results from two synthetic data sets (CTGAN data and CTGAN with Gaussian Copula) generated by the SDV and report the findings. The results indicate that the ROC and AUC curves for the data generated by adding the layer of Gaussian copula are much higher than the data generated by the CTGAN.

Keywords: synthetic data generation, generative adversarial networks, conditional tabular GAN, Gaussian copula

Procedia PDF Downloads 29

Authors: Hongyu Chen, Li Jiang

Abstract:

Ubiquitous anomalies endanger the security of our system con- stantly. They may bring irreversible damages to the system and cause leakage of privacy. Thus, it is of vital importance to promptly detect these anomalies. Traditional supervised methods such as Decision Trees and Support Vector Machine (SVM) are used to classify normality and abnormality. However, in some case, the abnormal status are largely rarer than normal status, which leads to decision bias of these methods. Generative adversarial network (GAN) has been proposed to handle the case. With its strong generative ability, it only needs to learn the distribution of normal status, and identify the abnormal status through the gap between it and the learned distribution. Nevertheless, existing GAN-based models are not suitable to process data with discrete values, leading to immense degradation of detection performance. To cope with the discrete features, in this paper, we propose an efficient GAN-based model with specifically-designed loss function. Experiment results show that our model outperforms state-of-the-art models on discrete dataset and remarkably reduce the overhead.

Keywords: GAN, discrete feature, Wasserstein distance, multiple intermediate layers

Procedia PDF Downloads 92

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 49

Authors: Han-Yu Cheng

Abstract:

This study aims to explore the impact of AI-generated illustration works on the aesthetic symbol consumption of consumers in Taiwan. The advancement of artificial intelligence drawing has lowered the barriers to entry, enabling more individuals to easily enter the field of illustration. Using Japanese anime style as an example, with the development of Generative Artificial Intelligence (Generative AI), an increasing number of illustration works are being generated by machines, sparking discussions about aesthetics and art consumption. Through surveys and the analysis of consumer perspectives, this research investigates how this influences consumers' aesthetic experiences and the resulting changes in the traditional art market and among creators. The study reveals that among consumers in Taiwan, particularly those interested in Japanese anime style, there is a pronounced interest and curiosity surrounding the emergence of Generative AI. This curiosity is particularly notable among individuals interested in this style but lacking the technical skills required for creating such artworks. These works, rooted in elements of Japanese anime style, find ready acceptance among enthusiasts of this style due to their stylistic alignment. Consequently, they have garnered a substantial following. Furthermore, with the reduction in entry barriers, more individuals interested in this style but lacking traditional drawing skills have been able to participate in producing such works. Against the backdrop of ongoing debates about artistic value since the advent of artificial intelligence (AI), Generative AI-generated illustration works, while not entirely displacing traditional art, to a certain extent, fulfill the aesthetic demands of this consumer group, providing a similar or analogous aesthetic consumption experience. Additionally, this research underscores the advantages and limitations of Generative AI-generated illustration works within this consumption environment.

Keywords: generative AI, anime aesthetics, Japanese anime illustration, art consumption

Procedia PDF Downloads 39

Authors: Yaowei Hu, Yongkai Wu, Lu Zhang, Xintao Wu

Abstract:

Causal inference from observational data is receiving wide applications in many fields. However, unidentifiable situations, where causal effects cannot be uniquely computed from observational data, pose critical barriers to applying causal inference to complicated real applications. In this paper, we develop a bounding method for estimating the average causal effect (ACE) under unidentifiable situations due to hidden confounders. We propose to parameterize the unknown exogenous random variables and structural equations of a causal model using neural networks and implicit generative models. Then, with an adversarial learning framework, we search the parameter space to explicitly traverse causal models that agree with the given observational distribution and find those that minimize or maximize the ACE to obtain its lower and upper bounds. The proposed method does not make any assumption about the data generating process and the type of the variables. Experiments using both synthetic and real-world datasets show the effectiveness of the method.

Keywords: average causal effect, hidden confounding, bound estimation, generative adversarial learning

Procedia PDF Downloads 143

Authors: Genady Grabarnik, Serge Yaskolko

Abstract:

Generative Artificial Intelligence (AI) has significantly expanded its applicability with the incorporation of Large Language Models (LLMs) and become a technology with promise to automate some areas that were very difficult to automate before. The paper describes the introduction of generative Artificial Intelligence into Introductory Computer and Data Science courses and analysis of effect of such introduction. The generative Artificial Intelligence is incorporated in the educational process two-fold: For the instructors, we create templates of prompts for generation of tasks, and grading of the students work, including feedback on the submitted assignments. For the students, we introduce them to basic prompt engineering, which in turn will be used for generation of test cases based on description of the problems, generating code snippets for the single block complexity programming, and partitioning into such blocks of an average size complexity programming. The above-mentioned classes are run using Large Language Models, and feedback from instructors and students and courses’ outcomes are collected. The analysis shows statistically significant positive effect and preference of both stakeholders.

Keywords: introductory computer and data science education, generative AI, large language models, application of LLMS to computer and data science education

Procedia PDF Downloads 27

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 142

Authors: Simiao Ren, En Wei

Abstract:

Drowning is a significant safety issue worldwide, and a robust computer vision-based alert system can easily prevent such tragedies in swimming pools. However, due to domain shift caused by the visual gap (potentially due to lighting, indoor scene change, pool floor color etc.) between the training swimming pool and the test swimming pool, the robustness of such algorithms has been questionable. The annotation cost for labeling each new swimming pool is too expensive for mass adoption of such a technique. To address this issue, we propose a domain-aware data augmentation pipeline based on Gaussian Poisson Generative Adversarial Network (GP-GAN). Combined with YOLOv8, we demonstrate that such a domain adaptation technique can significantly improve the model performance (from 0.24 mAP to 0.82 mAP) on new test scenes. As the augmentation method only require background imagery from the new domain (no annotation needed), we believe this is a promising, practical route for preventing swimming pool drowning.

Keywords: computer vision, deep learning, YOLOv8, detection, swimming pool, drowning, domain adaptation, generative adversarial network, GAN, GP-GAN

Procedia PDF Downloads 55

Authors: Shryas Bhurat, Aryan Vashistha, Sampreet Dinakar Nayak, Ayush Gupta

Abstract:

As the technology is advancing more towards high computational resources, there is a paradigm shift in the usage of these resources to optimize the design process. This paper discusses the usage of ‘Generative Design using Artificial Intelligence’ to build better models that adapt the operations like selection, mutation, and crossover to generate results. The human mind thinks of the simplest approach while designing an object, but the intelligence learns from the past & designs the complex optimized CAD Models. Generative Design takes the boundary conditions and comes up with multiple solutions with iterations to come up with a sturdy design with the most optimal parameter that is given, saving huge amounts of time & resources. The new production techniques that are at our disposal allow us to use additive manufacturing, 3D printing, and other innovative manufacturing techniques to save resources and design artistically engineered CAD Models. Also, this paper discusses the Genetic Algorithm, the Non-Domination technique to choose the right results using biomimicry that has evolved for current habitation for millions of years. The computer uses parametric models to generate newer models using an iterative approach & uses cloud computing to store these iterative designs. The later part of the paper compares the topology optimization technology with Generative Design that is previously being used to generate CAD Models. Finally, this paper shows the performance of algorithms and how these algorithms help in designing resource-efficient models.

Keywords: genetic algorithm, bio mimicry, generative modeling, non-dominant techniques

Procedia PDF Downloads 113

Authors: Thrivikraman Aswathi, S. Advaith

Abstract:

As there can be cases where the use of real data is somehow limited, such as when it is hard to get access to a large volume of real data, we need to go for synthetic data generation. This produces high-quality synthetic data while maintaining the statistical properties of a specific dataset. In the present work, a generative adversarial network (GAN) is trained to produce multivariate time series (MTS) data since the MTS is now being gathered more often in various real-world systems. Furthermore, the GAN-generated MTS data is fed into a transformer-based deep learning architecture that carries out the data categorization into predefined classes. Further, the model is evaluated across various distinct domains by generating corresponding MTS data.

Keywords: GAN, transformer, classification, multivariate time series

Procedia PDF Downloads 83

Authors: Noriki Amano

Abstract:

The final goal of this study is to create another way in which people enjoy music through the performance of 'Wearable Music'. Concretely speaking, we generate colorful costumes in real- time from music and to realize their dressing by projecting them to a person. For this purpose, we propose three methods in this study. First, a method of giving color to music in a three-dimensionally way. Second, a method of generating images of costumes from music. Third, a method of wearing the images of music. In particular, this study stands out from other related work in that we generate images of unique costumes from music and realize to wear them. In this study, we use the technique of generative arts to generate images of unique costumes and project the images to the fog generated around a person from 3-way using projectors. From this study, we can get how to enjoy music as 'wearable'. Furthermore, we are also able to have the prospect of unconventional entertainment based on the fusion between music and costumes.

Keywords: entertainment computing, costumes, music, generative programming

Procedia PDF Downloads 139

Authors: Shola Abidemi Olabode

Abstract:

The technological revolution over the years has impacted journalistic practice. As a matter of fact, journalistic practice has evolved alongside technologies of every generation transforming news and reporting, entertainment, and politics. Alongside these developments, the emergence of new kinds of risks and harms associated with generative AI has become rife with implications for media and journalism. Despite their numerous benefits for research and development, generative AI technologies like ChatGPT introduce new practical, ethical, and regulatory complexities in the practice of media and journalism. This paper presents a preliminary overview of the new kinds of challenges and issues for journalism and media practice in the era of generative AI, the implications for Nigeria, and invites a consideration of methods to mitigate the evolving complexity. It draws mainly on desk-based research underscoring the literature in both developed and developing non-western contexts as a contribution to knowledge.

Keywords: AI, journalism, media, online harms

Procedia PDF Downloads 44

Authors: Ana L. Gonzalez-Celis, Edgardo Ruiz-Carrillo, Karina Reyes-Jarquin, Margarita Chavez-Becerra

Abstract:

Since recent decades, the aging has been viewed from a more positive perspective, where is not only about losses and damage, but also about being on a stage where you can enjoy life and live with well-being and quality of life. The challenge to feel better is to find those resources that seniors have. For that reason, psychological well-being has shown interest in the study of the affect and life satisfaction (hedonic well-being), while from a more recent tradition, focus on the development of capabilities and the personal growth, considering both as the main indicators of the quality of life. A resource that can be used in the later age is generativity, which refers to the ability of older people to develop and grow through activities that contribute with the improvement of the context in which they live and participate. In this way the generative interest is understood as a favourable attitude that contribute to the common benefit while strengthening and enriching the social institutions, to ensure continuity between generations and social development. On the other hand, generative behavior, differentiating from generative interest, is the expression of that attitude reflected in activities that make a social contribution and a benefit for generations to come. Hence the purpose of the research was to test if there is an association between the generative behaviour type and the psychological well-being with their dimensions. For this reason 188 Mexican adults from 60 to 94 years old (M = 69.78), 67% women, 33% men, completed two instruments: The Ryff’s Well-Being Scales to measure psychological well-being with 39 items with two dimensions (Hedonic and Eudaimonic well-being), and the Loyola’s Generative Behaviors Scale, grouped in five categories: Knowledge transmitted to the next generation, things to be remember, creativity, be productive, contribution to the community, and responsibility of other people. In addition, the socio-demographic data sheet was tested, and self-reported health status. The results indicated that the psychological well-being and its dimensions were significantly associated with the presence of generative behavior, where the level of well-being was higher when the frequency of some generative behaviour excelled; finding that the behavior with greater psychological well-being (M = 81.04, SD = 8.18) was "things to be remembered"; while with greater hedonic well-being (M = 73.39, SD = 12.19) was the behavior "responsibility of other people"; and with greater Eudaimonic well-being (M = 84.61, SD = 6.63), was the behavior "things to be remembered”. The most important findings highlight the importance of generative behaviors in adulthood, finding empirical evidence that the generativity in the last stage of life is associated with well-being. However, by finding differences in the types of generative behaviors at the level of well-being, is proposed the idea that generativity is not situated as an isolated construct, but needs other contextualized and related constructs that can simultaneously operate at different levels, taking into account the relationship between the environment and the individual, encompassing both the social and psychological dimension.

Keywords: eudaimonic well-being, generativity, hedonic well-being, Mexican elders, psychological well-being

Procedia PDF Downloads 239

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 42

Authors: Milena Nanova, Radul Shishkov, Damyan Damov, Martin Georgiev

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 places emphasis on algorithmic implementation of the logical constraint and intricacies in residential architecture by exploring the potential of generative design to create visually engaging and contextually harmonious structures. This exploration also contains an analysis of how these designs align with legal building parameters, showcasing the potential for creative solutions within the confines of urban building regulations. Concurrently, our methodology integrates functional, economic, and environmental factors. We investigate how generative design can be utilized to optimize buildings' performance, considering them, aiming to achieve a symbiotic relationship between the built environment and its natural surroundings. Through a blend of theoretical research and practical case studies, this research highlights the multifaceted capabilities of generative design and demonstrates practical applications of our framework. Our findings illustrate the rich possibilities that arise from an algorithmic design approach in the context of a vibrant urban landscape. This study contributes an alternative perspective to residential architecture, suggesting that the future of urban development lies in embracing the complex interplay between computational design innovation, regulatory adherence, and environmental responsibility.

Keywords: generative design, computational design, parametric design, algorithmic modeling

Procedia PDF Downloads 21

Authors: Jindong Gu, Matthias Schubert, Volker Tresp

Abstract:

In many outlier detection tasks, only training data belonging to one class, i.e., the positive class, is available. The task is then to predict a new data point as belonging either to the positive class or to the negative class, in which case the data point is considered an outlier. For this task, we propose a novel corrupted Generative Adversarial Network (CorGAN). In the adversarial process of training CorGAN, the Generator generates outlier samples for the negative class, and the Discriminator is trained to distinguish the positive training data from the generated negative data. The proposed framework is evaluated using an image dataset and a real-world network intrusion dataset. Our outlier-detection method achieves state-of-the-art performance on both tasks.

Keywords: one-class classification, outlier detection, generative adversary networks, semi-supervised learning

Procedia PDF Downloads 118

Authors: Kumar Shashvat, Amol P. Bhondekar

Abstract:

In the midst of the five senses, odor is the most reminiscent and least understood. Odor testing has been mysterious and odor data fabled to most practitioners. The delinquent of recognition and classification of odor is important to achieve. The facility to smell and predict whether the artifact is of further use or it has become undesirable for consumption; the imitation of this problem hooked on a model is of consideration. The general industrial standard for this classification is color based anyhow; odor can be improved classifier than color based classification and if incorporated in machine will be awfully constructive. For cataloging of odor for peas, trees and cashews various discriminative approaches have been used Discriminative approaches offer good prognostic performance and have been widely used in many applications but are incapable to make effectual use of the unlabeled information. In such scenarios, generative approaches have better applicability, as they are able to knob glitches, such as in set-ups where variability in the series of possible input vectors is enormous. Generative models are integrated in machine learning for either modeling data directly or as a transitional step to form an indeterminate probability density function. The algorithms or models Linear Discriminant Analysis and Naive Bayes Classifier have been used for classification of the odor of cashews. Linear Discriminant Analysis is a method used in data classification, pattern recognition, and machine learning to discover a linear combination of features that typifies or divides two or more classes of objects or procedures. The Naive Bayes algorithm is a classification approach base on Bayes rule and a set of qualified independence theory. Naive Bayes classifiers are highly scalable, requiring a number of restraints linear in the number of variables (features/predictors) in a learning predicament. The main recompenses of using the generative models are generally a Generative Models make stronger assumptions about the data, specifically, about the distribution of predictors given the response variables. The Electronic instrument which is used for artificial odor sensing and classification is an electronic nose. This device is designed to imitate the anthropological sense of odor by providing an analysis of individual chemicals or chemical mixtures. The experimental results have been evaluated in the form of the performance measures i.e. are accuracy, precision and recall. The investigational results have proven that the overall performance of the Linear Discriminant Analysis was better in assessment to the Naive Bayes Classifier on cashew dataset.

Keywords: odor classification, generative models, naive bayes, linear discriminant analysis

Procedia PDF Downloads 350

Authors: Anika Chebrolu

Abstract:

Mono-targeted drugs can be of limited efficacy against complex diseases. Recently, multi-target drug design has been approached as a promising tool to fight against these challenging diseases. However, the scope of current computational approaches for multi-target drug design is limited. DeepLig presents a de-novo drug discovery platform that uses reinforcement learning to generate and optimize novel, potent, and multitargeted drug candidates against protein targets. DeepLig’s model consists of two networks in interplay: a generative network and a predictive network. The generative network, a Stack- Augmented Recurrent Neural Network, utilizes a stack memory unit to remember and recognize molecular patterns when generating novel ligands from scratch. The generative network passes each newly created ligand to the predictive network, which then uses multiple Graph Attention Networks simultaneously to forecast the average binding affinity of the generated ligand towards multiple target proteins. With each iteration, given feedback from the predictive network, the generative network learns to optimize itself to create molecules with a higher average binding affinity towards multiple proteins. DeepLig was evaluated based on its ability to generate multi-target ligands against two distinct proteins, multi-target ligands against three distinct proteins, and multi-target ligands against two distinct binding pockets on the same protein. With each test case, DeepLig was able to create a library of valid, synthetically accessible, and novel molecules with optimal and equipotent binding energies. We propose that DeepLig provides an effective approach to design multi-targeted drug therapies that can potentially show higher success rates during in-vitro trials.

Keywords: drug design, multitargeticity, de-novo, reinforcement learning

Procedia PDF Downloads 46

Authors: Haoqi Gao, Koichi Ogawara

Abstract:

Retinal vascular segmentation of color fundus is the basis of ophthalmic computer-aided diagnosis and large-scale disease screening systems. Early screening of fundus diseases has great value for clinical medical diagnosis. The traditional methods depend on the experience of the doctor, which is time-consuming, labor-intensive, and inefficient. Furthermore, medical images are scarce and fraught with legal concerns regarding patient privacy. In this paper, we propose a new Generative Adversarial Network based on CycleGAN for retinal fundus images. This method can generate not only synthetic fundus images but also generate corresponding segmentation masks, which has certain application value and challenge in computer vision and computer graphics. In the results, we evaluate our proposed method from both quantitative and qualitative. For generated segmented images, our method achieves dice coefficient of 0.81 and PR of 0.89 on DRIVE dataset. For generated synthetic fundus images, we use ”Toy Experiment” to verify the state-of-the-art performance of our method.

Keywords: retinal vascular segmentations, generative ad-versarial network, cyclegan, fundus images

Procedia PDF Downloads 103

Authors: Muneeb Ullah, Daishihan, Xiadong Young

Abstract:

Deep learning plays a crucial role in identifying COVID-19 and preventing its spread. To improve the accuracy of COVID-19 diagnoses, it is important to have access to a sufficient number of training images of CXRs (chest X-rays) depicting the disease. However, there is currently a shortage of such images. To address this issue, this paper introduces COVID-19 GAN, a model that uses generative adversarial networks (GANs) to generate realistic CXR images of COVID-19, which can be used to train identification models. Initially, a generator model is created that uses digressive channels to generate images of CXR scans for COVID-19. To differentiate between real and fake disease images, an efficient discriminator is developed by combining the dense connectivity strategy and instance normalization. This approach makes use of their feature extraction capabilities on CXR hazy areas. Lastly, the deep regret gradient penalty technique is utilized to ensure stable training of the model. With the use of 4,062 grape leaf disease images, the Leaf GAN model successfully produces 8,124 COVID-19 CXR images. The COVID-19 GAN model produces COVID-19 CXR images that outperform DCGAN and WGAN in terms of the Fréchet inception distance. Experimental findings suggest that the COVID-19 GAN-generated CXR images possess noticeable haziness, offering a promising approach to address the limited training data available for COVID-19 model training. When the dataset was expanded, CNN-based classification models outperformed other models, yielding higher accuracy rates than those of the initial dataset and other augmentation techniques. Among these models, ImagNet exhibited the best recognition accuracy of 99.70% on the testing set. These findings suggest that the proposed augmentation method is a solution to address overfitting issues in disease identification and can enhance identification accuracy effectively.

Keywords: classification, deep learning, medical images, CXR, GAN.

Procedia PDF Downloads 48

Authors: Till Gramberg

Abstract:

In the dynamic world of machine and plant engineering, stagnation in the growth of new product sales compels companies to reconsider their business models. The increasing shift toward service orientation, known as "servitization," along with challenges posed by digitalization and sustainability, necessitates an adaptation of product portfolio management (PPM). Against this backdrop, this study investigates the current challenges and requirements of PPM in this industrial context and develops a framework for the application of generative artificial intelligence (AI) to enhance agility and efficiency in PPM processes. The research approach of this study is based on a mixed-method design. Initially, qualitative interviews with industry experts were conducted to gain a deep understanding of the specific challenges and requirements in PPM. These interviews were analyzed using the Gioia method, painting a detailed picture of the existing issues and needs within the sector. This was complemented by a quantitative online survey. The combination of qualitative and quantitative research enabled a comprehensive understanding of the current challenges in the practical application of machine and plant engineering PPM. Based on these insights, a specific framework for the application of generative AI in PPM was developed. This framework aims to assist companies in implementing faster and more agile processes, systematically integrating dynamic requirements from trends such as digitalization and sustainability into their PPM process. Utilizing generative AI technologies, companies can more quickly identify and respond to trends and market changes, allowing for a more efficient and targeted adaptation of the product portfolio. The study emphasizes the importance of an agile and reactive approach to PPM in a rapidly changing environment. It demonstrates how generative AI can serve as a powerful tool to manage the complexity of a diversified and continually evolving product portfolio. The developed framework offers practical guidelines and strategies for companies to improve their PPM processes by leveraging the latest technological advancements while maintaining ecological and social responsibility. This paper significantly contributes to deepening the understanding of the application of generative AI in PPM and provides a framework for companies to manage their product portfolios more effectively and adapt to changing market conditions. The findings underscore the relevance of continuous adaptation and innovation in PPM strategies and demonstrate the potential of generative AI for proactive and future-oriented business management.

Keywords: servitization, product portfolio management, generative AI, disruptive innovation, machine and plant engineering

Procedia PDF Downloads 28

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 214

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 106