Search results for: generative linguistics

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 104

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 83

Authors: Yinghui Shang, Ziqing Zhou, Rong Han, Hang Wang, Xiaodi Liu, Yong Yang

Abstract:

The design of advanced amorphous solids, such as metallic glasses, with targeted properties through artificial intelligence signifies a paradigmatic shift in physical metallurgy and materials technology. Here, we developed a machine-learning architecture that facilitates the generation of metallic glasses with targeted multifunctional properties. Our architecture integrates the state-of-the-art unsupervised generative adversarial network model with supervised models, allowing the incorporation of general prior knowledge derived from thousands of data points across a vast range of alloy compositions, into the creation of data points for a specific type of composition, which overcame the common issue of data scarcity typically encountered in the design of a given type of metallic glasses. Using our generative model, we have successfully designed copper-based metallic glasses, which display exceptionally high hardness or a remarkably low modulus. Notably, our architecture can not only explore uncharted regions in the targeted compositional space but also permits self-improvement after experimentally validated data points are added to the initial dataset for subsequent cycles of data generation, hence paving the way for the customized design of amorphous solids without human intervention.

Keywords: metallic glass, artificial intelligence, mechanical property, automated generation

Procedia PDF Downloads 22

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. It also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 0.39 m, and more than 90% of the errors are less than 0.82 m. According to numerical results, SRCLoc improves positioning performance and reduces radio map construction costs significantly compared to traditional methods.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 31

Authors: Guanghua Zhang, Fubao Wang, Weijun Duan

Abstract:

Convolution neural network (CNN) has attracted more and more attention on recent years. Especially in the field of computer vision and image classification. However, unsupervised learning with CNN has received less attention than supervised learning. In this work, we use a new powerful tool which is deep convolutional generative adversarial networks (DCGANs) to generate images from Sloan Digital Sky Survey. Training by various star and galaxy images, it shows that both the generator and the discriminator are good for unsupervised learning. In this paper, we also took several experiments to choose the best value for hyper-parameters and which could help to stabilize the training process and promise a good quality of the output.

Keywords: convolution neural network, discriminator, generator, unsupervised learning

Procedia PDF Downloads 242

Authors: Samer Muthana Sarsam, Abdul Samad Shibghatullah, Chit Su Mon, Abd Aziz Alias, Hosam Al-Samarraie

Abstract:

Generative Artificial Intelligence chatbots (GAI chatbots) have emerged as promising tools in various domains, including higher education. However, their specific role within the educational context and the level of legal support for their implementation remain unclear. Therefore, this study aims to investigate the role of Bard, a newly developed GAI chatbot, in higher education. To achieve this objective, English tweets were collected from Twitter's free streaming Application Programming Interface (API). The Latent Dirichlet Allocation (LDA) algorithm was applied to extract latent topics from the collected tweets. User sentiments, including disgust, surprise, sadness, anger, fear, joy, anticipation, and trust, as well as positive and negative sentiments, were extracted using the NRC Affect Intensity Lexicon and SentiStrength tools. This study explored the benefits, challenges, and future implications of integrating GAI chatbots in higher education. The findings shed light on the potential power of such tools, exemplified by Bard, in enhancing the learning process and providing support to students throughout their educational journey.

Keywords: generative artificial intelligence chatbots, bard, higher education, topic modelling, sentiment analysis

Procedia PDF Downloads 55

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 65

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 39 cm, and more than 90% of the errors are less than 82 cm. That is, numerical results proved that, in comparison to traditional methods, the proposed SRCLoc method can significantly improve positioning performance and reduce radio map construction costs.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 47

Authors: Y. Bablu Singh, B. S. Purkayashtha, Chungkham Yashawanta Singh

Abstract:

Morphological analysis forms the basic foundation in NLP applications including syntax parsing Machine Translation (MT), Information Retrieval (IR) and automatic indexing in all languages. It is the field of the linguistics; it can provide valuable information for computer based linguistics task such as lemmatization and studies of internal structure of the words. Computational Morphology is the application of morphological rules in the field of computational linguistics, and it is the emerging area in AI, which studies the structure of words, which are formed by combining smaller units of linguistics information, called morphemes: the building blocks of words. Morphological analysis provides about semantic and syntactic role in a sentence. It analyzes the Manipuri word forms and produces several grammatical information associated with the words. The Morphological Analyzer for Manipuri has been tested on 3500 Manipuri words in Shakti Standard format (SSF) using Meitei Mayek as source; thereby an accuracy of 80% has been obtained on a manual check.

Keywords: morphological analysis, machine translation, computational morphology, information retrieval, SSF

Procedia PDF Downloads 306

Authors: R. A. S. Zacarias

Abstract:

Interlingual is one of the most complex, and engaging one among the several perspectives in lexicography. This is because it involves contacts and contrasts between two or more languages. Considering the fact that translation equivalence goes beyond a mere fixed relation of correspondence, understanding the differences and similarities between linguistic categories by pairs of languages is the basis for effective translations. One of the theoretical approaches that have proved useful in finding improved solutions for enhance translation equivalents for bilingual dictionaries is contrastive linguistics. This paper presents an applied qualitative research based on exploratory and descriptive approaches. This is achieved through an error analysis of students’ errors as well as by a contrastive analysis of Portuguese and English verb systems.

Keywords: bilingual lexicography, contrastive linguistics, translation equivalent, Portuguese-English

Procedia PDF Downloads 455

Authors: Rongbo Shen, Jianhua Yao, Kezhou Yan, Kuan Tian, Cheng Jiang, Ke Zhou

Abstract:

This study proposes a generative adversarial networks (GAN) framework to perform synthetic sampling in feature space, i.e., feature augmentation, to address the class imbalance problem in medical image analysis. A feature extraction network is first trained to convert images into feature space. Then the GAN framework incorporates adversarial learning to train a feature generator for the minority class through playing a minimax game with a discriminator. The feature generator then generates features for minority class from arbitrary latent distributions to balance the data between the majority class and the minority class. Additionally, a data cleaning technique, i.e., Tomek link, is employed to clean up undesirable conflicting features introduced from the feature augmentation and thus establish well-defined class clusters for the training. The experiment section evaluates the proposed method on two medical image analysis tasks, i.e., mass classification on mammogram and cancer metastasis classification on histopathological images. Experimental results suggest that the proposed method obtains superior or comparable performance over the state-of-the-art counterparts. Compared to all counterparts, our proposed method improves more than 1.5 percentage of accuracy.

Keywords: class imbalance, synthetic sampling, feature augmentation, generative adversarial networks, data cleaning

Procedia PDF Downloads 108

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 39 cm, and more than 90% of the errors are less than 82 cm. That is, numerical results proved that, in comparison to traditional methods, the proposed SRCLoc method can significantly improve positioning performance and reduce radio map construction costs.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 48

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 120

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 223

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 152

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 110

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 63

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 236

Authors: Olufemi Olupe

Abstract:

Within linguistics, various approaches have been adopted to the study of language. One of such approaches is the syntax. The syntax is an aspect of the grammar of the language which deals with how words are put together to form phrases and sentences and how such structures are interpreted in language. Ambiguity, which is also germane in this discourse is about the uncertainty of meaning as a result of the possibility of a phrase or sentence being understood and interpreted in more than one way. In the light of the above, this paper attempts a syntactic study of syntactic ambiguities in The English Language, using the Transformational Generative Grammar (TGG) Approach. In doing this, phrases and sentences were raised with each description followed by relevant analysis. Finding in the work reveals that ambiguity cannot always be disambiguated by the means of syntactic analysis alone without recourse to semantic interpretation. The further finding shows that some syntactical ambiguities structures cannot be analysed on two surface structures in spite of the fact that there are more than one deep structures. The paper concludes that in as much as ambiguity remains in language; it will continue to pose a problem of understanding to a second language learner. Users of English as a second language, must, however, make a conscious effort to avoid its usage to achieve effective communication.

Keywords: language, syntax, semantics, morphology, ambiguity

Procedia PDF Downloads 363

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 64

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 353

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 86

Authors: Valdênia Carvalho e Almeida

Abstract:

The goal of the present study is to investigate the semantic preference of the most frequent adjectives in research articles through a corpus-based analysis of texts published in journals in Applied Linguistics (AL). The corpus used in this study contains texts published in the period from 2014 to 2018 in the three journals: Language Learning and Technology; English for Academic Purposes, and TESOL Quaterly, totaling more than one million words. A corpus-based analysis was carried out on the corpus to identify the most frequent adjectives that co-occurred in the three journals. By observing the concordance lines of the adjectives and analyzing the words they associated with, the semantic preferences of each adjective were determined. Later, the AL corpus analysis was compared to the investigation of the same adjectives in a corpus of Chemistry. This second part of the study aimed to identify possible differences and similarities between the two corpora in relation to the use of the adjectives in research articles from both areas. The results show that there are some preferences which seem to be closely related not only to the academic genre of the texts but also to the specific domain of the discipline and, to a lesser extent, to the context of research in each journal. This research illustrates a possible contribution of Corpus Linguistics to explore the concept of semantic preference in more detail, considering the complex nature of the phenomenon.

Keywords: applied linguistics, corpus linguistics, chemistry, research article, semantic preference

Procedia PDF Downloads 159

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 60

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 117

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 166

Authors: Franklin Thambi Jose.S

Abstract:

Computational Linguistics is a branch of linguistics, which deals with the computer and linguistic levels. It is also said, as a branch of language studies which applies computer techniques to linguistics field. In Computational Linguistics, Natural Language Processing plays an important role. This came to exist because of the invention of Information Technology. In computational syntax, the syntactic analyser breaks a sentence into phrases and clauses and identifies the sentence with the syntactic information. Tamil is one of the major Dravidian languages, which has a very long written history of more than 2000 years. It is mainly spoken in Tamilnadu (in India), Srilanka, Malaysia and Singapore. It is an official language in Tamilnadu (in India), Srilanka, Malaysia and Singapore. In Malaysia Tamil speaking people are considered as an ethnic group. In Tamil syntax, the sentences in Tamil are classified into four for this research, namely: 1. Main Sentence 2. Interrogative Sentence 3. Equational Sentence 4. Elliptical Sentence. In computational syntax, the first step is to provide required information regarding the head and its constituent of each sentence. This information will be incorporated to the system using programming languages. Now the system can easily analyse a given sentence with the criteria or mechanisms given to it. Providing needful criteria or mechanisms to the computer to identify the basic types of sentences using Syntactic parser in Tamil language is the major objective of this paper.

Keywords: tamil, syntax, criteria, sentences, parser

Procedia PDF Downloads 496

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 151

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 104

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 59