Search results for: generative ai

Authors: Colin Schmidt, Adrien Lecossier, Pascal Crubleau, Philippe Blanchard, Simon Richir

Abstract:

Introduction:The widespread availability of artificial intelligence, exemplified by Generative Pre-trained Transformers (GPT) relying on large language models (LLM), has caused a seismic shift in the realm of knowledge. Everyone now has the capacity to swiftly learn how these models can either serve them well or not. Today, conversational AI like ChatGPT is grounded in neural transformer models, a significant advance in natural language processing facilitated by the emergence of renowned LLMs constructed using neural transformer architecture. Inventiveness of an LLM : OpenAI's GPT-3 stands as a premier LLM, capable of handling a broad spectrum of natural language processing tasks without requiring fine-tuning, reliably producing text that reads as if authored by humans. However, even with an understanding of how LLMs respond to questions asked, there may be lurking behind OpenAI’s seemingly endless responses an inventive model yet to be uncovered. There may be some unforeseen reasoning emerging from the interconnection of neural networks here. Just as a Soviet researcher in the 1940s questioned the existence of Common factors in inventions, enabling an Under standing of how and according to what principles humans create them, it is equally legitimate today to explore whether solutions provided by LLMs to complex problems also share common denominators. Theory of Inventive Problem Solving (TRIZ) : We will revisit some fundamentals of TRIZ and how Genrich ALTSHULLER was inspired by the idea that inventions and innovations are essential means to solve societal problems. It's crucial to note that traditional problem-solving methods often fall short in discovering innovative solutions. The design team is frequently hampered by psychological barriers stemming from confinement within a highly specialized knowledge domain that is difficult to question. We presume ChatGPT Utilizes TRIZ 40. Hence, the objective of this research is to decipher the inventive model of LLMs, particularly that of ChatGPT, through a comparative study. This will enhance the efficiency of sustainable innovation processes and shed light on how the construction of a solution to a complex problem was devised. Description of the Experimental Protocol : To confirm or reject our main hypothesis that is to determine whether ChatGPT uses TRIZ, we will follow a stringent protocol that we will detail, drawing on insights from a panel of two TRIZ experts. Conclusion and Future Directions : In this endeavor, we sought to comprehend how an LLM like GPT addresses complex challenges. Our goal was to analyze the inventive model of responses provided by an LLM, specifically ChatGPT, by comparing it to an existing standard model: TRIZ 40. Of course, problem solving is our main focus in our endeavours.

Keywords: artificial intelligence, Triz, ChatGPT, inventiveness, problem-solving

Procedia PDF Downloads 49

Authors: Mohammed Makki, Milad Showkatbakhsh, Aiman Tabony

Abstract:

Computational applications of natural evolutionary processes as problem-solving tools have been well established since the mid-20th century. However, their application within architecture and design has only gained ground in recent years, with an increasing number of academics and professionals in the field electing to utilize evolutionary computation to address problems comprised from multiple conflicting objectives with no clear optimal solution. Recent advances in computer science and its consequent constructive influence on the architectural discourse has led to the emergence of multiple algorithmic processes capable of simulating the evolutionary process in nature within an efficient timescale. Many of the developed processes of generating a population of candidate solutions to a design problem through an evolutionary based stochastic search process are often driven through the application of both environmental and architectural parameters. These methods allow for conflicting objectives to be simultaneously, independently, and objectively optimized. This is an essential approach in design problems with a final product that must address the demand of a multitude of individuals with various requirements. However, one of the main challenges encountered through the application of an evolutionary process as a design tool is the ability for the simulation to maintain variation amongst design solutions in the population while simultaneously increasing in fitness. This is most commonly known as the ‘golden rule’ of balancing exploration and exploitation over time; the difficulty of achieving this balance in the simulation is due to the tendency of either variation or optimization being favored as the simulation progresses. In such cases, the generated population of candidate solutions has either optimized very early in the simulation, or has continued to maintain high levels of variation to which an optimal set could not be discerned; thus, providing the user with a solution set that has not evolved efficiently to the objectives outlined in the problem at hand. As such, the experiments presented in this paper seek to achieve the ‘golden rule’ by incorporating a mathematical fitness criterion for the development of an urban tissue comprised from the superblock as its primary architectural element. The mathematical value investigated in the experiments is the standard deviation factor. Traditionally, the standard deviation factor has been used as an analytical value rather than a generative one, conventionally used to measure the distribution of variation within a population by calculating the degree by which the majority of the population deviates from the mean. A higher standard deviation value delineates a higher number of the population is clustered around the mean and thus limited variation within the population, while a lower standard deviation value is due to greater variation within the population and a lack of convergence towards an optimal solution. The results presented will aim to clarify the extent to which the utilization of the standard deviation factor as a fitness criterion can be advantageous to generating fitter individuals in a more efficient timeframe when compared to conventional simulations that only incorporate architectural and environmental parameters.

Keywords: architecture, computation, evolution, standard deviation, urban

Procedia PDF Downloads 122

Authors: B. Baran, S. N. Kaptanoglu, M. Ocal, Y. Kagnici, E. Esen, E. Siyez, D. M. Siyez

Abstract:

Infertility is the fact that couples cannot have children despite 1 year of unprotected sexual life. Infertility can be considered as an important problem affecting not only sexual life but also social and psychological conditions of couples. Learning about information about preventable factors related to infertility during university years plays an important role in preventing a possible infertility case in older ages. The possibility to facilitate access to information with the internet has provided the opportunity to reach a broad audience in the diverse learning environments and educational environment. Moreover, the internet has become a basic resource for the 21st-century learners. Providing information about infertility over the internet will enable more people to reach in a short time. When studies conducted abroad about infertility are examined, interactive websites and online education programs come to the fore. In Turkey, while there is no comprehensive online education program for university students, it seems that existing studies are aimed to make more advertisements for doctors or hospitals. In this study, it was aimed to design and develop online infertility prevention education for university students. Mayer’s Multimedia Learning Theory made up the framework for the online learning environment in this study. The results of the needs analysis collected from the university students in Turkey who were selected with sampling to represent the audience for online learning contributed to the design phase. In this study, an infertility prevention online education environment designed as a 4-week education was developed by explaining the theoretical basis and needs analysis results. As a result; in the development of the online environment, different kind of visual aids that will increase teaching were used in the environment of online education according to Mayer’s principles of extraneous processing (coherence, signaling, spatial contiguity, temporal contiguity, redundancy, expectation principles), essential processing (segmenting, pre-training, modality principles) and generative processing (multimedia, personalization, voice principles). For example, the important points in reproductive systems’ expression were emphasized by visuals in order to draw learners’ attention, and the presentation of the information was also supported by the human voice. In addition, because of the limited knowledge of university students in the subject, the issue of female reproductive and male reproductive systems was taught before preventable factors related to infertility. Furthermore, 3D video and augmented reality application were developed in order to embody female and male reproductive systems. In conclusion, this study aims to develop an interactive Online Infertility Prevention Education in which university students can easily access reliable information and evaluate their own level of knowledge about the subject. It is believed that the study will also guide the researchers who want to develop online education in this area as it contains design-stage decisions of interactive online infertility prevention education for university students.

Keywords: infertility, multimedia learning theory, online education, reproductive health

Procedia PDF Downloads 156

Authors: Zhao Gao, Eran Edirisinghe

Abstract:

The production of an accurate sketch of a suspect based on a verbal description obtained from a witness is an essential task for most criminal investigations. The criminal investigation system employs specifically trained professional artists to manually draw a facial image of the suspect according to the descriptions of an eyewitness for subsequent identification. Within the advancement of Deep Learning, Recurrent Neural Networks (RNN) have shown great promise in Natural Language Processing (NLP) tasks. Additionally, Generative Adversarial Networks (GAN) have also proven to be very effective in image generation. In this study, a trained GAN conditioned on textual features such as keywords automatically encoded from a verbal description of a human face using an RNN is used to generate photo-realistic facial images for criminal investigations. The intention of the proposed system is to map corresponding features into text generated from verbal descriptions. With this, it becomes possible to generate many reasonably accurate alternatives to which the witness can use to hopefully identify a suspect from. This reduces subjectivity in decision making both by the eyewitness and the artist while giving an opportunity for the witness to evaluate and reconsider decisions. Furthermore, the proposed approach benefits law enforcement agencies by reducing the time taken to physically draw each potential sketch, thus increasing response times and mitigating potentially malicious human intervention. With publically available 'CelebFaces Attributes Dataset' (CelebA) and additionally providing verbal description as training data, the proposed architecture is able to effectively produce facial structures from given text. Word Embeddings are learnt by applying the RNN architecture in order to perform semantic parsing, the output of which is fed into the GAN for synthesizing photo-realistic images. Rather than the grid search method, a metaheuristic search based on genetic algorithms is applied to evolve the network with the intent of achieving optimal hyperparameters in a fraction the time of a typical brute force approach. With the exception of the ‘CelebA’ training database, further novel test cases are supplied to the network for evaluation. Witness reports detailing criminals from Interpol or other law enforcement agencies are sampled on the network. Using the descriptions provided, samples are generated and compared with the ground truth images of a criminal in order to calculate the similarities. Two factors are used for performance evaluation: The Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). A high percentile output from this performance matrix should attribute to demonstrating the accuracy, in hope of proving that the proposed approach can be an effective tool for law enforcement agencies. The proposed approach to criminal facial image generation has potential to increase the ratio of criminal cases that can be ultimately resolved using eyewitness information gathering.

Keywords: RNN, GAN, NLP, facial composition, criminal investigation

Procedia PDF Downloads 145

Authors: Ursula Das, Manavjit Singh Dhindsa, Kshirasagar Naik, Marzia Zaman, Richard Purcell, Srinivas Sampalli, Abdul Mutakabbir, Chung-Horng Lung, Thambirajah Ravichandran

Abstract:

Wildland fires, also known as forest fires or wildfires, are exhibiting an alarming surge in frequency in recent times, further adding to its perennial global concern. Forest fires often lead to devastating consequences ranging from loss of healthy forest foliage and wildlife to substantial economic losses and the tragic loss of human lives. Despite the existence of substantial literature on the detection of active forest fires, numerous potential research avenues in forest fire management, such as preventative measures and ancillary effects of forest fires, remain largely underexplored. This paper undertakes a systematic review of these underexplored areas in forest fire research, meticulously categorizing them into distinct phases, namely pre-fire, during-fire, and post-fire stages. The pre-fire phase encompasses the assessment of fire risk, analysis of fuel properties, and other activities aimed at preventing or reducing the risk of forest fires. The during-fire phase includes activities aimed at reducing the impact of active forest fires, such as the detection and localization of active fires, optimization of wildfire suppression methods, and prediction of the behavior of active fires. The post-fire phase involves analyzing the impact of forest fires on various aspects, such as the extent of damage in forest areas, post-fire regeneration of forests, impact on wildlife, economic losses, and health impacts from byproducts produced during burning. A comprehensive understanding of the three stages is imperative for effective forest fire management and mitigation of the impact of forest fires on both ecological systems and human well-being. Artificial intelligence and machine learning (AI/ML) methods have garnered much attention in the cyber-physical systems domain in recent times leading to their adoption in decision-making in diverse applications including disaster management. This paper explores the current state of AI/ML applications for managing the activities in the aforementioned phases of forest fire. While conventional machine learning and deep learning methods have been extensively explored for the prevention, detection, and management of forest fires, a systematic classification of these methods into distinct AI research domains is conspicuously absent. This paper gives a comprehensive overview of the state of forest fire research across more recent and prominent AI/ML disciplines, including big data, classical machine learning, computer vision, explainable AI, generative AI, natural language processing, optimization algorithms, and time series forecasting. By providing a detailed overview of the potential areas of research and identifying the diverse ways AI/ML can be employed in forest fire research, this paper aims to serve as a roadmap for future investigations in this domain.

Keywords: artificial intelligence, computer vision, deep learning, during-fire activities, forest fire management, machine learning, pre-fire activities, post-fire activities

Procedia PDF Downloads 57

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations of previous approaches, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with attention mechanism. In a previous work on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: transformers, generative ai, gene expression design, classification

Procedia PDF Downloads 48

Authors: Jessica Ho

Abstract:

AI has helped government, businesses and industries transform the way they do things. AI is used in automating tasks to improve decision-making and efficiency. AI is embedded in sensors and used in automation to help save time and eliminate human errors in repetitive tasks. Today, we saw the growth in AI using the collection of vast amounts of data to forecast with greater accuracy, inform decision-making, adapt to changing market conditions and offer more personalised service based on consumer habits and preferences. Government around the world share the opportunity to leverage these disruptive technologies to improve productivity while reducing costs. In addition, these intelligent solutions can also help streamline government processes to deliver more seamless and intuitive user experiences for employees and citizens. This is a critical challenge for NSW Government as we are unable to determine the risk that is brought by the unprecedented pace of adoption of AI solutions in government. Government agencies must ensure that their use of AI complies with relevant laws and regulatory requirements, including those related to data privacy and security. Furthermore, there will always be ethical concerns surrounding the use of AI, such as the potential for bias, intellectual property rights and its impact on job security. Within NSW’s public sector, agencies are already testing AI for crowd control, infrastructure management, fraud compliance, public safety, transport, and police surveillance. Citizens are also attracted to the ease of use and accessibility of AI solutions without requiring specialised technical skills. This increased accessibility also comes with balancing a higher risk and exposure to the health and safety of citizens. On the other side, public agencies struggle with keeping up with this pace while minimising risks, but the low entry cost and open-source nature of generative AI led to a rapid increase in the development of AI powered apps organically – “There is an AI for That” in Government. Other challenges include the fact that there appeared to be no legislative provisions that expressly authorise the NSW Government to use an AI to make decision. On the global stage, there were too many actors in the regulatory space, and a sovereign response is needed to minimise multiplicity and regulatory burden. Therefore, traditional corporate risk and governance framework and regulation and legislation frameworks will need to be evaluated for AI unique challenges due to their rapidly evolving nature, ethical considerations, and heightened regulatory scrutiny impacting the safety of consumers and increased risks for Government. Creating an effective, efficient NSW Government’s governance regime, adapted to the range of different approaches to the applications of AI, is not a mere matter of overcoming technical challenges. Technologies have a wide range of social effects on our surroundings and behaviours. There is compelling evidence to show that Australia's sustained social and economic advancement depends on AI's ability to spur economic growth, boost productivity, and address a wide range of societal and political issues. AI may also inflict significant damage. If such harm is not addressed, the public's confidence in this kind of innovation will be weakened. This paper suggests several AI regulatory approaches for consideration that is forward-looking and agile while simultaneously fostering innovation and human rights. The anticipated outcome is to ensure that NSW Government matches the rising levels of innovation in AI technologies with the appropriate and balanced innovation in AI governance.

Keywords: artificial inteligence, machine learning, rules, governance, government

Procedia PDF Downloads 58