Search results for: adaptive neural controller

Authors: Avent Grange, Frederic Bertrand, Jean-Baptiste Droin, Amandine Marrel, Jean-Henry Ferrasse, Olivier Boutin

Abstract:

CEA and its industrial partners are designing a gas Power Conversion System (PCS) based on a Brayton cycle for the ASTRID Sodium-cooled Fast Reactor. Investigations of control and regulation requirements to operate this PCS during operating, incidental and accidental transients are necessary to adapt core heat removal. To this aim, we developed a methodology to optimize the thermal-hydraulic behavior of the reactor during normal operations, incidents and accidents. This methodology consists of a multi-objective optimization for a specific sequence, whose aim is to increase component lifetime by reducing simultaneously several thermal stresses and to bring the reactor into a stable state. Furthermore, the multi-objective optimization complies with safety and operating constraints. Operating, incidental and accidental sequences use specific regulations to control the thermal-hydraulic reactor behavior, each of them is defined by a setpoint, a controller and an actuator. In the multi-objective problem, the parameters used to solve the optimization are the setpoints and the settings of the controllers associated with the regulations included in the sequence. In this way, the methodology allows designers to define an optimized and specific control strategy of the plant for the studied sequence and hence to adapt PCS piloting at its best. The multi-objective optimization is performed by evolutionary algorithms coupled to surrogate models built on variables computed by the thermal-hydraulic system code, CATHARE2. The methodology is applied to a loss of off-site power sequence. Three variables are controlled: the sodium outlet temperature of the sodium-gas heat exchanger, turbomachine rotational speed and water flow through the heat sink. These regulations are chosen in order to minimize thermal stresses on the gas-gas heat exchanger, on the sodium-gas heat exchanger and on the vessel. The main results of this work are optimal setpoints for the three regulations. Moreover, Proportional-Integral-Derivative (PID) control setting is considered and efficient actuators used in controls are chosen through sensitivity analysis results. Finally, the optimized regulation system and the reactor control procedure, provided by the optimization process, are verified through a direct CATHARE2 calculation.

Keywords: gas power conversion system, loss of off-site power, multi-objective optimization, regulation, sodium fast reactor, surrogate model

Procedia PDF Downloads 282

Authors: Yehjune Heo

Abstract:

As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.

Keywords: anti-spoofing, CNN, fingerprint recognition, loss function, optimizer

Procedia PDF Downloads 109

Authors: Umut Tuğlu Karslı

Abstract:

While, port function had a major role during the antiquity and medieval times, it has started to lose its significance in 19th century. In many port cities, while heavy industrial functions and ports have been moved out of the former port districts, the resulting derelict spaces have been transformed to new waterfront quarters to accommodate commercial, tourism, cultural, residential and public uses. Primary aim of these operations is to revitalize abandoned spaces of historical potential and re-establish a relationship between the city and the coast. Karakoy Port, field of this study, located in the Bosphorus, was surrounded by the city centre in time due to the transformation of urban functions, and as a result it has lost its former significance. While Karakoy has 24 hours lively residential and commercial uses in old times; in early 1980s, became a district of mechanical, plumbing and electronic parts suppliers during the day and a place for homeless at night. Today, activities for revitalization of this region continue in two forms and scales. First of these activities is the "planned transformation projects," which also includes the most important one “Galataport project”, and the second one is "spontaneous transformation," which consists of individual interventions. Galataport project that based on the idea of arranging the area specifically for tourists was prepared in 2005 and became a topic of tremendous public debate. On the other hand, the "spontaneous transformation" that is observed in the Karakoy District starts in 2004 with the foundation of “Istanbul Modern Museum”. Istanbul Modern, the first contemporary arts museum of the city, allowed the cultural integration of old naval warehouses of the port to the daily life. Following this adaptive reuse intervention, the district started to accommodate numerous art galleries, studios, café-workshops and design stores. In this context, this paper briefly examines revitalization studies in obsolete port regions, analyzes the planned and ongoing socio-spatial transformations in the specific case of Karakoy under the subjects of "planned transformation projects" and "spontaneous transformation", and realizes a critical review of the sustainability of the proposals on how to reinstate the district in the active life of Istanbul.

Keywords: port cities, socio-spatial transformation, urban regeneration, urban revitalization

Procedia PDF Downloads 427

Authors: Isaac Kayode Ogunlade

Abstract:

Data acquisition (DAQ) is the process by which physical phenomena from the real world are transformed into an electrical signal(s) that are measured and converted into a digital format for processing, analysis, and storage by a computer. The DAQ is designed using PIC18F4550 microcontroller, communicating with Personal Computer (PC) through USB (Universal Serial Bus). The research deployed initial knowledge of data acquisition system and embedded system to develop a weather data acquisition device using LM35 sensor to measure weather parameters and the use of Artificial Intelligence(Artificial Neural Network - ANN)and statistical approach(Autoregressive Integrated Moving Average – ARIMA) to predict precipitation (rainfall). The device is placed by a standard device in the Department of Meteorology, Federal University of Technology, Akure (FUTA) to know the performance evaluation of the device. Both devices (standard and designed) were subjected to 180 days with the same atmospheric condition for data mining (temperature, relative humidity, and pressure). The acquired data is trained in MATLAB R2012b environment using ANN, and ARIMAto predict precipitation (rainfall). Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Correction Square (R2), and Mean Percentage Error (MPE) was deplored as standardize evaluation to know the performance of the models in the prediction of precipitation. The results from the working of the developed device show that the device has an efficiency of 96% and is also compatible with Personal Computer (PC) and laptops. The simulation result for acquired data shows that ANN models precipitation (rainfall) prediction for two months (May and June 2017) revealed a disparity error of 1.59%; while ARIMA is 2.63%, respectively. The device will be useful in research, practical laboratories, and industrial environments.

Keywords: data acquisition system, design device, weather development, predict precipitation and (FUTA) standard device

Procedia PDF Downloads 66

Authors: Carol Anne Hargreaves

Abstract:

A key issue in stock investment is how to select representative features for stock selection. The objective of this paper is to firstly determine whether an automated stock investment system, using machine learning techniques, may be used to identify a portfolio of growth stocks that are highly likely to provide returns better than the stock market index. The second objective is to identify the technical features that best characterize whether a stock’s price is likely to go up and to identify the most important factors and their contribution to predicting the likelihood of the stock price going up. Unsupervised machine learning techniques, such as cluster analysis, were applied to the stock data to identify a cluster of stocks that was likely to go up in price – portfolio 1. Next, the principal component analysis technique was used to select stocks that were rated high on component one and component two – portfolio 2. Thirdly, a supervised machine learning technique, the logistic regression method, was used to select stocks with a high probability of their price going up – portfolio 3. The predictive models were validated with metrics such as, sensitivity (recall), specificity and overall accuracy for all models. All accuracy measures were above 70%. All portfolios outperformed the market by more than eight times. The top three stocks were selected for each of the three stock portfolios and traded in the market for one month. After one month the return for each stock portfolio was computed and compared with the stock market index returns. The returns for all three stock portfolios was 23.87% for the principal component analysis stock portfolio, 11.65% for the logistic regression portfolio and 8.88% for the K-means cluster portfolio while the stock market performance was 0.38%. This study confirms that an automated stock investment system using machine learning techniques can identify top performing stock portfolios that outperform the stock market.

Keywords: machine learning, stock market trading, logistic regression, cluster analysis, factor analysis, decision trees, neural networks, automated stock investment system

Procedia PDF Downloads 131

Authors: Hamed Hedayatnia, Nathan Van Den Bossche

Abstract:

Understanding the ways in which climate change accelerates or slows down the process of material deterioration is the first step towards assessing adaptive approaches for the conservation of historical heritage. Analysis of the climate change effects on the degradation risk assessment parameters like freeze-thaw cycles and wind erosion is also a key parameter when considering mitigating actions. Due to the vulnerability of cultural heritage to climate change, the impact of this phenomenon on material degradation criteria with the focus on brick masonry walls in Timurid heritage, located in Iran, was studied. The Timurids were the final great dynasty to emerge from the Central Asian steppe. Through their patronage, the eastern Islamic world in northwestern of Iran, especially in Mashhad and Herat, became a prominent cultural center. Goharshad Mosque is a mosque in Mashhad of the Razavi Khorasan Province, Iran. It was built by order of Empress Goharshad, the wife of Shah Rukh of the Timurid dynasty in 1418 CE. Choosing an appropriate regional climate model was the first step. The outputs of two different climate model: the 'ALARO-0' and 'REMO,' were analyzed to find out which model is more adopted to the area. For validating the quality of the models, a comparison between model data and observations was done in 4 different climate zones in Iran for a period of 30 years. The impacts of the projected climate change were evaluated until 2100. To determine the material specification of Timurid bricks, standard brick samples from a Timurid mosque were studied. Determination of water absorption coefficient, defining the diffusion properties and determination of real density, and total porosity tests were performed to characterize the specifications of brick masonry walls, which is needed for running HAM-simulations. Results from the analysis showed that the threatening factors in each climate zone are almost different, but the most effective factor around Iran is the extreme temperature increase and erosion. In the north-western region of Iran, one of the key factors is wind erosion. In the north, rainfall erosion and mold growth risk are the key factors. In the north-eastern part, in which our case study is located, the important parameter is wind erosion.

Keywords: brick, climate change, degradation criteria, heritage, Timurid period

Procedia PDF Downloads 101

Authors: Jacques M. Berner, Monja Gerber, Gillian L. Maggs-Kolling, Stuart J. Piketh

Abstract:

The enigmatic melon species, Acanthosicyos horridus Welw. ex Hook. f., locally known as !nara, is endemic to the hyper-arid Namib Desert, where it thrives in sandy dune areas and dry river banks. The Namib Desert is characterized by extreme weather conditions which include high temperatures, very low rainfall, and extremely dry air. Plant and animals that have made the Namib Dessert their home are dependent on non-rainfall water inputs, like fog, dew and water vapor, for survival. Fog is believed to be the most important non-rainfall water input for most of the coastal Namib Desert and is a life line to many Namib plants and animals. It is commonly assumed that the !nara plant is adapted and dependent upon coastal fog events. The !nara plant shares many comparable adaptive features with other organisms that are known to exploit fog as a source of moisture. These include groove-like structures on the stems and the cone-like structures of thorns. These structures are believed to be the driving forces behind directional water flow that allow plants to take advantage of fog events. The !nara-fog interaction was investigated in this study to determine the dependence of !nara on these fog events, as it would illustrate strategies to benefit from non-rainfall water inputs. The direct water uptake capacity of !nara shoots was investigated through absorption tests. Furthermore, the movement and behavior of fluorescent water droplets on a !nara stem were investigated through time-lapse macrophotography. The shoot water potential was measured to investigate the effect of fog on the water status of !nara stems. These tests were used to determine whether the morphology of !nara has evolved to exploit fog as a non-rainfall water input and whether the !nara plant has adapted physiologically in response to fog. Chlorophyll a fluorescence was used to compare the photochemical efficiency of !nara plants on days with fog events to that on non-foggy days. The results indicate that !nara plants do have the ability to take advantage of fog events as commonly believed. However, the !nara plant did not exhibit visible signs of drought stress and this, together with the strong shoot water potential, indicates that these plants are reliant on permanent underground water sources. Chlorophyll a fluorescence data indicated that temperature stress and wind were some of the main abiotic factors influencing the plants’ overall vitality.

Keywords: Acanthosicyos horridus, chlorophyll a fluorescence, fog, foliar absorption, !nara

Procedia PDF Downloads 128

Authors: Md. Rakeb-Ul Islam, Daniel J. Schmidt, Jane M. Hughes

Abstract:

Population connectivity plays an important role in the conservation and recovery of declining species. It affects genetic diversity, adaptive potential and resilience of species in nature. Loss of genetic variation can affect populations by limiting their ability to persist in stressful environmental conditions. Generally, freshwater fishes show higher levels of genetic structuring and subdivision among populations than those inhabiting estuarine or marine environments due to the presence of artificial (e.g. dams) and natural (e.g. mountain ranges) barriers to dispersal in freshwater ecosystems. The Australian smelt (Retropinnidae: Retropinna spp.) is a common freshwater fish species which is widely distributed throughout coastal and inland drainages in South - eastern Australia. These fish are found in a number of habitats from headwaters to lowland sites. They form large shoals in the mid to upper water column and inhabit deep slow – flowing pools as well as shallow fast flowing riffle-runs. Previously, Australian smelt consisted of two described taxa (Retropinna semoni and Retropinna tasmanica), but recently a complex of five or more species has been recognized based on an analysis of allozyme variation. In many area, they spend their entire life cycle within freshwater. Although most populations of the species are thought to be non-diadromous, it is still unclear whether individuals within coastal populations of Australian Retropinna exhibit diadromous migrations or whether fish collected from marine/estuarine environments are vagrants that have strayed out of the freshwater reaches. In this current study, the population structure and genetic differentiation of Australian smelt fish were investigated among eight rivers of South-East Queensland (SEQ), Australia. 11 microsatellite loci were used to examine genetic variation within and among populations. Genetic diversity was very high. Number of alleles ranged from three to twenty. Expected heterozygosity averaged across loci ranged from 0.572 to 0.852. There was a high degree of genetic differentiation among rivers (FST = 0.23), although low levels of genetic differentiation among populations within rivers. These extremely high levels of genetic differentiation suggest that the all smelt in SEQ complete their life history within freshwater, or, if they go to the estuary, they do not migrate to sea. This hypothesis is being tested further with a micro-chemical analysis of their otoliths.

Keywords: diadromous, genetic diversity, microsatellite, otolith

Procedia PDF Downloads 281

Authors: Felix Golla

Abstract:

In an era where technology increasingly intersects with education, the potential of chatbots and ChatGPT agents in enhancing student learning experiences in higher education is both significant and timely. This study explores the integration of these AI-driven tools in educational settings, emphasizing their design and functionality to meet the specific needs of students. Recognizing the gap in literature concerning student-centered AI applications in education, this research offers valuable insights into the role and efficacy of chatbots and ChatGPT agents as educational tools. Employing qualitative research methodologies, the study involved conducting semi-structured interviews with university students. These interviews were designed to gather in-depth insights into the students' experiences and expectations regarding the use of AI in learning environments. The High-Performance Cycle Model, renowned for its focus on goal setting and motivation, served as the theoretical framework guiding the analysis. This model helped in systematically categorizing and interpreting the data, revealing the nuanced perceptions and preferences of students regarding AI tools in education. The major findings of the study indicate a strong preference among students for chatbots and ChatGPT agents that offer personalized interaction, adaptive learning support, and regular, constructive feedback. These features were deemed essential for enhancing student engagement, motivation, and overall learning outcomes. Furthermore, the study revealed that students perceive these AI tools not just as passive sources of information but as active facilitators in the learning process, capable of adapting to individual learning styles and needs. In conclusion, this study underscores the transformative potential of chatbots and ChatGPT agents in higher education. It highlights the need for these AI tools to be designed with a student-centered approach, ensuring their alignment with educational objectives and student preferences. The findings contribute to the evolving discourse on AI in education, suggesting a paradigm shift towards more interactive, responsive, and personalized learning experiences. This research not only informs educators and technologists about the desirable features of educational chatbots but also opens avenues for future studies to explore the long-term impact of AI integration in academic curricula.

Keywords: chatbot design in education, high-performance cycle model application, qualitative research in AI, student-centered learning technologies

Procedia PDF Downloads 39

Authors: Aba-Carina Pârlog

Abstract:

On translating, reading against the grain results in a wrong effect in the TL. Quine’s ocular irradiation plays an important part in the process of understanding and translating a text. The various types of textual radiation must be rendered by the translator by paying close attention to the types of field that produce it. The literary work must be seen as an indirect cause of an expressive effect in the TL that is supposed to be similar to the effect it has in the SL. If the adaptive transformative codes are so flexible that they encourage the translator to repeatedly leave out parts of the original work, then a subversive pattern emerges which changes the entire book. In this case, the translator is a writer per se who decides what goes in and out of the book, how the style is to be ciphered and what elements of ideology are to be highlighted. Figurative language must not be flattened for the sake of clarity or naturalness. The missing figurative elements make the translated text less interesting, less challenging and less vivid which reflects poorly on the writer. There is a close connection between style and the writer’s person. If the writer’s style is very much changed in a translation, the translation is useless as the original writer and his / her imaginative world can no longer be discovered. Then, a different writer appears and his / her creation surfaces. Changing meaning considered as a “negative shift” in translation defines one of the faulty transformative codes used by some translators. It is a dangerous tool which leads to adaptations that sometimes reflect the original less than the reader would wish to. It contradicts the very essence of the process of translation which is that of making a work available in a foreign language. Employing speculative aesthetics at the level of a text indicates the wish to create manipulative or subversive effects in the translated work. This is generally achieved by adding new words or connotations, creating new figures of speech or using explicitations. The irradiation patterns of the original work are neglected and the translator creates new meanings, implications, emphases and contexts. Again s/he turns into a new author who enjoys the freedom of expressing his / her ideas without the constraints of the original text. The stimulus meaning of a text is very important for a translator which is why reading against the grain is unadvisable during the process of translation. By paying attention to the waves of the SL input, a faithful literary work is produced which does not contradict general knowledge about foreign cultures and civilizations. Following personal common sense is essential in the field of translation as well as everywhere else.

Keywords: stimulus meaning, substance of expression, transformative code, translation

Procedia PDF Downloads 427

Authors: Prince Vivek, Vijay K. Bharti, Manishi Mukesh, Ankita Sharma, Om Prakash Chaurasia, Bhuvnesh Kumar

Abstract:

High performance of endurance in equid requires adaptive changes involving physio-biochemical, and molecular responses in an attempt to regain homeostasis. We hypothesized that the identification of the suitable reference genes might be considered for assessing of endurance related traits in pony at high altitude and may ensure for individuals struggling to potent endurance trait in ponies at high altitude. A total of 12 mares of ponies, Zanskar breed, were divided into three groups, group-A (without load), group-B, (60 Kg) and group-C (80 Kg) on backpack loads were subjected to a load carry protocol, on a steep climb of 4 km uphill, and of gravel, uneven rocky surface track at an altitude of 3292 m to 3500 m (endpoint). Blood was collected before and immediately after the load carry on sodium heparin anticoagulant, and the peripheral blood mononuclear cell was separated for total RNA isolation and thereafter cDNA synthesis. Real time-PCR reactions were carried out to evaluate the mRNAs expression profile of a panel of putative internal control genes (ICGs), related to different functional classes, namely glyceraldehyde 3-phosphate dehydrogenase (GAPDH), β₂ microglobulin (β₂M), β-actin (ACTB), ribosomal protein 18 (RS18), hypoxanthine-guanine phosophoribosyltransferase (HPRT), ubiquitin B (UBB), ribosomal protein L32 (RPL32), transferrin receptor protein (TFRC), succinate dehydrogenase complex subunit A (SDHA) for normalizing the real-time quantitative polymerase chain reaction (qPCR) data of native pony’s. Three different algorithms, geNorm, NormFinder, and BestKeeper software, were used to evaluate the stability of reference genes. The result showed that GAPDH was best stable gene and stability value for the best combination of two genes was observed TFRC and β₂M. In conclusion, the geometric mean of GAPDH, TFRC and β₂M might be used for accurate normalization of transcriptional data for assessing endurance related traits in Zanskar ponies during load carrying.

Keywords: endurance exercise, ubiquitin B (UBB), β₂ microglobulin (β₂M), high altitude, Zanskar ponies, reference gene

Procedia PDF Downloads 112

Authors: David A. Harness

Abstract:

Natural evolution of ATP cognitive systems is to meet AI peer review standards. ATP process of axiom selection from Mizar to prove a conjecture would be further refined, as in all human and machine learning, by solving the real world problem of the proposed AI peer review challenge: Determine which conjecture forms the higher confidence level constructive proof between Standard Model of Physics SU(n) lattice gauge group operation vs. present non-standard 4D GEM EOS SU(n) lattice gauge group spatially extended operation in which the photon and electron are the first two trace angular momentum invariants of a gravitoelectromagnetic (GEM) energy momentum density tensor wavetrain integration spin-stress pressure-volume equation of state (EOS), initiated via 32 lines of Mathematica code. Resulting gravitoelectromagnetic spectrum ranges from compressive through rarefactive of the central cosmological constant vacuum energy density in units of pascals. Said self-adjoint group operation exclusively operates on the stress energy momentum tensor of the Einstein field equations, introducing quantization directly on the 4D spacetime level, essentially reformulating the Yang-Mills virtual superpositioned particle compounded lattice gauge groups quantization of the vacuum—into a single hyper-complex multi-valued GEM U(1) × SU(1,3) lattice gauge group Planck spacetime mesh quantization of the vacuum. Thus the Mizar corpus already contains all of the axioms required for relevant DeepMath premise selection and unambiguous formal natural language parsing in context deep learning.

Keywords: automated theorem proving, constructive quantum field theory, information theory, neural networks

Procedia PDF Downloads 153

Authors: J. DeBoard, R. Dietrich, J. Hughes, K. Yurko, G. Harms

Abstract:

Alzheimer’s disease (AD) is a predominant type of dementia and is likely a major cause of neural network impairment. The pathogenesis of this neurodegenerative disorder has yet to be fully elucidated. There are currently no known cures for the disease, and the best hope is to be able to detect it early enough to impede its progress. Beyond age and genetics, another prevalent risk factor for AD might be traumatic brain injury (TBI), which has similar neurodegenerative hallmarks. Our research focuses on obtaining information and methods to be able to predict when neurodegenerative effects might occur at a clinical level by observation of events at a cellular and molecular level in model mice. First, we wish to introduce our evidence that brain damage can be observed via brain imaging prior to the noticeable loss of neuromuscular control in model mice of AD. We then show our evidence that some blood biomarkers might be able to be early predictors of AD in the same model mice. Thus, we were interested to see if we might be able to predict which mice might show long-term neurodegenerative effects due to differing degrees of TBI and what level of TBI causes further damage and earlier death to the AD model mice. Upon application of TBIs via an apparatus to effectively induce extremely mild to mild TBIs, wild-type (WT) mice and AD mouse models were tested for cognition, neuromuscular control, olfactory ability, blood biomarkers, and brain imaging. Experiments are currently still in process, and more results are therefore forthcoming. Preliminary data suggest that neuromotor control diminishes as well as olfactory function for both AD and WT mice after the administration of five consecutive mild TBIs. Also, seizure activity increases significantly for both AD and WT after the administration of the five TBI treatment. If future data supports these findings, important implications about the effect of TBI on those at risk for AD might be possible.

Keywords: Alzheimer's disease, blood biomarker, neurodegeneration, neuromuscular control, olfaction, traumatic brain injury

Procedia PDF Downloads 114

Authors: M. Bilal Ishfaq, Adnan N. Qureshi

Abstract:

COVID-19 is the most infectious disease these days, it was first reported in Wuhan, the capital city of Hubei in China then it spread rapidly throughout the whole world. Later on 11 March 2020, the World Health Organisation (WHO) declared it a pandemic. Since COVID-19 is highly contagious, it has affected approximately 219M people worldwide and caused 4.55M deaths. It has brought the importance of accurate diagnosis of respiratory diseases such as pneumonia and COVID-19 to the forefront. In this paper, we propose a hybrid approach for the automated detection of COVID-19 using medical imaging. We have presented the hybridization of manually extracted and convolutional features. Our approach combines Haralick texture features and convolutional features extracted from chest X-rays and CT scans. We also employ a minimum redundancy maximum relevance (MRMR) feature selection algorithm to reduce computational complexity and enhance classification performance. The proposed model is evaluated on four publicly available datasets, including Chest X-ray Pneumonia, COVID-19 Pneumonia, COVID-19 CTMaster, and VinBig data. The results demonstrate high accuracy and effectiveness, with 0.9925 on the Chest X-ray pneumonia dataset, 0.9895 on the COVID-19, Pneumonia and Normal Chest X-ray dataset, 0.9806 on the Covid CTMaster dataset, and 0.9398 on the VinBig dataset. We further evaluate the effectiveness of the proposed model using ROC curves, where the AUC for the best-performing model reaches 0.96. Our proposed model provides a promising tool for the early detection and accurate diagnosis of COVID-19, which can assist healthcare professionals in making informed treatment decisions and improving patient outcomes. The results of the proposed model are quite plausible and the system can be deployed in a clinical or research setting to assist in the diagnosis of COVID-19.

Keywords: COVID-19, feature engineering, artificial neural networks, radiology images

Procedia PDF Downloads 46

Authors: Animish Jain

Abstract:

This study deals with using Multiplicative Weight Update within artificial intelligence and machine learning to create models that can diagnose skin cancer using microscopic images of cancer samples. In this study, the multiplicative weight update method is used to take the predictions of multiple models to try and acquire more accurate results. Logistic Regression, Convolutional Neural Network (CNN), and Support Vector Machine Classifier (SVMC) models are employed within the Multiplicative Weight Update system. These models are trained on pictures of skin cancer from the ISIC-Archive, to look for patterns to label unseen scans as either benign or malignant. These models are utilized in a multiplicative weight update algorithm which takes into account the precision and accuracy of each model through each successive guess to apply weights to their guess. These guesses and weights are then analyzed together to try and obtain the correct predictions. The research hypothesis for this study stated that there would be a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The SVMC model had an accuracy of 77.88%. The CNN model had an accuracy of 85.30%. The Logistic Regression model had an accuracy of 79.09%. Using Multiplicative Weight Update, the algorithm received an accuracy of 72.27%. The final conclusion that was drawn was that there was a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The conclusion was made that using a CNN model would be the best option for this problem rather than a Multiplicative Weight Update system. This is due to the possibility that Multiplicative Weight Update is not effective in a binary setting where there are only two possible classifications. In a categorical setting with multiple classes and groupings, a Multiplicative Weight Update system might become more proficient as it takes into account the strengths of multiple different models to classify images into multiple categories rather than only two categories, as shown in this study. This experimentation and computer science project can help to create better algorithms and models for the future of artificial intelligence in the medical imaging field.

Keywords: artificial intelligence, machine learning, multiplicative weight update, skin cancer

Procedia PDF Downloads 51

Authors: Deni̇z Ezgi̇ Gülmez, Mesut Kirca

Abstract:

Nanoporous (np) metals have attracted considerable attention owing to their cellular morphological features at atomistic scale which yield ultra-high specific surface area awarding a great potential to be employed in diverse applications such as catalytic, electrocatalytic, sensing, mechanical and optical. As one of the carbon based nanostructures, fullerenes are also another type of outstanding nanomaterials that have been extensively investigated due to their remarkable chemical, mechanical and optical properties. In this study, the idea of improving the mechanical behavior of nanoporous metals by inclusion of the fullerenes, which offers a new metal-carbon nanocomposite material, is examined and discussed. With this motivation, tensile mechanical behavior of nanoporous metals reinforced with carbon fullerenes is investigated by classical molecular dynamics (MD) simulations. Atomistic models of the nanoporous metals with ultrathin ligaments are obtained through a stochastic process simply based on the intersection of spherical volumes which has been used previously in literature. According to this technique, the atoms within the ensemble of intersecting spherical volumes is removed from the pristine solid block of the selected metal, which results in porous structures with spherical cells. Following this, fullerene units are added into the cellular voids to obtain final atomistic configurations for the numerical tensile tests. Several numerical specimens are prepared with different number of fullerenes per cell and with varied fullerene sizes. LAMMPS code was used to perform classical MD simulations to conduct uniaxial tension experiments on np models filled by fullerenes. The interactions between the metal atoms are modeled by using embedded atomic method (EAM) while adaptive intermolecular reactive empirical bond order (AIREBO) potential is employed for the interaction of carbon atoms. Furthermore, atomic interactions between the metal and carbon atoms are represented by Lennard-Jones potential with appropriate parameters. In conclusion, the ultimate goal of the study is to present the effects of fullerenes embedded into the cellular structure of np metals on the tensile response of the porous metals. The results are believed to be informative and instructive for the experimentalists to synthesize hybrid nanoporous materials with improved properties and multifunctional characteristics.

Keywords: fullerene, intersecting spheres, molecular dynamic, nanoporous metals

Procedia PDF Downloads 221

Authors: D. Bjelica, T. Slavinski, V. Vukimrovic, D. Pavlovic, D. Bodroza, V. Dabetic

Abstract:

Traditional methods and techniques used in higher education may be significantly persuasive on the university students' perception about quality of the teaching process. Students’ satisfaction with the university experience may be affected by chosen educational approaches. Contemporary project management trends recognize agile approaches' beneficial, so modern practice highlights their usage, especially in the IT industry. A key research question concerns the possibility of applying agile methods in youth education. As agile methodology pinpoint iteratively-incremental delivery of results, its employment could be remarkably fruitful in education. This paper demonstrates the agile concept's application in the university students’ education through the continuous delivery of student solutions. Therefore, based on the fundamental values and principles of the agile manifest, paper will analyze students' performance and learned lessons in their encounter with the agile environment. The research is based on qualitative and quantitative analysis that includes sprints, as preparation and realization of student tasks in shorter iterations. Consequently, the performance of student teams will be monitored through iterations, as well as the process of adaptive planning and realization. Grounded theory methodology has been used in this research, as so as descriptive statistics and Man Whitney and Kruskal Wallis test for group comparison. Developed constructs of the model will be showcase through qualitative research, then validated through a pilot survey, and eventually tested as a concept in the final survey. The paper highlights the variability of educational curricula based on university students' feedbacks, which will be collected at the end of every sprint and indicates to university students' satisfaction inconsistency according to approaches applied in education. Values delivered by the lecturers will also be continuously monitored; thus, it will be prioritizing in order to students' requests. Minimal viable product, as the early delivery of results, will be particularly emphasized in the implementation process. The paper offers both theoretical and practical implications. This research contains exceptional lessons that may be applicable by educational institutions in curriculum creation processes, or by lecturers in curriculum design and teaching. On the other hand, they can be beneficial regarding university students' satisfaction increscent in respect of teaching styles, gained knowledge, or even educational content.

Keywords: academic performances, agile, high education, university students' satisfaction

Procedia PDF Downloads 103

Authors: Susan Diamond

Abstract:

Machine Learning workloads have traditionally been run in high-performance computing (HPC) environments, where users log in to dedicated machines and utilize the attached GPUs to run training jobs on huge datasets. Training of large neural network models is very resource intensive, and even after exploiting parallelism and accelerators such as GPUs, a single training job can still take days. Consequently, the cost of hardware is a barrier to entry. Even when upfront cost is not a concern, the lead time to set up such an HPC environment takes months from acquiring hardware to set up the hardware with the right set of firmware, software installed and configured. Furthermore, scalability is hard to achieve in a rigid traditional lab environment. Therefore, it is slow to react to the dynamic change in the artificial intelligent industry. Watson Deep Learning as a service, a cloud-based deep learning platform that mitigates the long lead time and high upfront investment in hardware. It enables robust and scalable sharing of resources among the teams in an organization. It is designed for on-demand cloud environments. Providing a similar user experience in a multi-tenant cloud environment comes with its own unique challenges regarding fault tolerance, performance, and security. Watson Deep Learning as a service tackles these challenges and present a deep learning stack for the cloud environments in a secure, scalable and fault-tolerant manner. It supports a wide range of deep-learning frameworks such as Tensorflow, PyTorch, Caffe, Torch, Theano, and MXNet etc. These frameworks reduce the effort and skillset required to design, train, and use deep learning models. Deep Learning as a service is used at IBM by AI researchers in areas including machine translation, computer vision, and healthcare. 

Keywords: deep learning, machine learning, cognitive computing, model training

Procedia PDF Downloads 185

Authors: Alberto Mínguez-Martínez, Jesús De Vicente Y Oliva

Abstract:

It seems that we live in a world in which the trend in industrial environments is the miniaturization of systems and materials and the fabrication of parts at the micro-and nano-scale. The problem arises when manufacturers want to study the quality of their production. This characteristic is becoming crucial due to the evolution of the industry and the development of Industry 4.0. As Industry 4.0 is based on digital models of production and processes, having accurate measurements becomes capital. At this point, the metrology field plays an important role as it is a powerful tool to ensure more stable production to reduce scrap and the cost of non-conformities. The most extended measuring instruments that allow us to carry out accurate measurements at these scales are optical microscopes, whether they are traditional, confocal, focus variation microscopes, profile projectors, or any other similar measurement system. However, the accuracy of measurements is connected to the traceability of them to the SI unit of length (the meter). The fact of providing adequate traceability to 2D and 3D dimensional measurements at micro-and nano-scale in industrial environments is a problem that is being studied, and it does not have a unique answer. In addition, if commercial material standards for micro-and nano-scale are considered, we can find that there are two main problems. On the one hand, those material standards that could be considered complete and very interesting do not give traceability of dimensional measurements and, on the other hand, their calibration is very expensive. This situation implies that these kinds of standards will not succeed in industrial environments and, as a result, they will work in the absence of traceability. To solve this problem in industrial environments, it becomes necessary to have material standards that are easy to use, agile, adaptive to different forms, cheap to manufacture and, of course, traceable to the definition of meter with simple methods. By using these ‘customized standards’, it would be possible to adapt and design measuring procedures for each application and manufacturers will work with some traceability. It is important to note that, despite the fact that this traceability is clearly incomplete, this situation is preferable to working in the absence of it. Recently, it has been demonstrated the versatility and the utility of using laser technology and other AM technologies to manufacture customized material standards. In this paper, the authors propose to manufacture a customized material standard using an ultraviolet laser system and a method to calibrate it. To conclude, the results of the calibration carried out in an accredited dimensional metrology laboratory are presented.

Keywords: industrial environment, material standards, optical measuring instrument, traceability

Procedia PDF Downloads 97

Authors: Cristóbal Moënne-Loccoz, Rodrigo C. Vergara, Vladimir López, Domingo Mery, Diego Cosmelli

Abstract:

Our daily interaction with computational interfaces is plagued of situations in which we go from inexperienced users to experts through self-motivated exploration of the same task. In many of these interactions, we must learn to find our way through a sequence of decisions and actions before obtaining the desired result. For instance, when drawing cash from an ATM machine, choices are presented in a step-by-step fashion so that a specific sequence of actions must be performed in order to produce the expected outcome. But, as they become experts in the use of such interfaces, do users adopt specific search and learning strategies? Moreover, if so, can we use this information to follow the process of expertise development and, eventually, predict future actions? This would be a critical step towards building truly adaptive interfaces that can facilitate interaction at different moments of the learning curve. Furthermore, it could provide a window into potential mechanisms underlying decision-making behavior in real world scenarios. Here we tackle this question using a simple game interface that instantiates a 4-level binary decision tree (BDT) sequential decision-making task. Participants have to explore the interface and discover an underlying concept-icon mapping in order to complete the game. We develop a Hidden Markov Model (HMM)-based approach whereby a set of stereotyped, hierarchically related search behaviors act as hidden states. Using this model, we are able to track the decision-making process as participants explore, learn and develop expertise in the use of the interface. Our results show that partitioning the problem space into such stereotyped strategies is sufficient to capture a host of exploratory and learning behaviors. Moreover, using the modular architecture of stereotyped strategies as a Mixture of Experts, we are able to simultaneously ask the experts about the user's most probable future actions. We show that for those participants that learn the task, it becomes possible to predict their next decision, above chance, approximately halfway through the game. Our long-term goal is, on the basis of a better understanding of real-world decision-making processes, to inform the construction of interfaces that can establish dynamic conversations with their users in order to facilitate the development of expertise.

Keywords: behavioral modeling, expertise acquisition, hidden markov models, sequential decision-making

Procedia PDF Downloads 227

Authors: Anicet Dansou

Abstract:

Textile reinforced concrete (TRC)is increasingly used nowadays in various fields, in particular civil engineering, where it is mainly used for the reinforcement of damaged reinforced concrete structures. TRC is a composite material composed of multi- or uni-axial textile reinforcements coupled with a fine-grained cementitious matrix. The TRC composite is an alternative solution to the traditional Fiber Reinforcement Polymer (FRP) composite. It has good mechanical performance and better temperature stability but also, it makes it possible to meet the criteria of sustainable development better.TRCs are highly anisotropic composite materials with nonlinear hardening behavior; their macroscopic behavior depends on multi-scale mechanisms. The characterization of these materials through numerical simulation has been the subject of many studies. Since TRCs are multiscale material by definition, numerical multi-scale approaches have emerged as one of the most suitable methods for the simulation of TRCs. They aim to incorporate information pertaining to microscale constitute behavior, mesoscale behavior, and macro-scale structure response within a unified model that enables rapid simulation of structures. The computational costs are hence significantly reduced compared to standard simulation at a fine scale. The fine scale information can be implicitly introduced in the macro scale model: approaches of this type are called non-classical. A representative volume element is defined, and the fine scale information are homogenized over it. Analytical and computational homogenization and nested mesh methods belong to these approaches. On the other hand, in classical approaches, the fine scale information are explicitly introduced in the macro scale model. Such approaches pertain to adaptive mesh refinement strategies, sub-modelling, domain decomposition, and multigrid methods This research presents the main principles of numerical multiscale approaches. Advantages and limitations are identified according to several criteria: the assumptions made (fidelity), the number of input parameters required, the calculation costs (efficiency), etc. A bibliographic study of recent results and advances and of the scientific obstacles to be overcome in order to achieve an effective simulation of textile reinforced concrete in civil engineering is presented. A comparative study is further carried out between several methods for the simulation of TRCs used for the structural reinforcement of reinforced concrete structures.

Keywords: composites structures, multiscale methods, numerical modeling, textile reinforced concrete

Procedia PDF Downloads 82

Authors: Raymond Treacy, Paul Humphreys, Ronan McIvor, Trevor Cadden, Alan McKittrick

Abstract:

This study employed event study methodology to examine the role of institutions, resources and dynamic capabilities in the relationship between the Environmental Management System ISO 14001 adoption and firm performance. Utilising financial data from 140 ISO 14001 certified firms and 320 non-certified firms, the results of the study suggested that the UK and Irish manufacturers were not implementing ISO 14001 solely to gain legitimacy. In contrast, the results demonstrated that firms were fully integrating the ISO 14001 standard within their operations as certified firms were able to improve both financial and operating performance when compared to non-certified firms. However, while there were significant and long lasting improvements for employee productivity, manufacturing cost efficiency, return on assets and sales turnover, the sample firms operating cycle and fixed asset efficiency displayed evidence of diminishing returns in the long-run, underlying the observation that no operating advantage based on incremental improvements can be everlasting. Hence, there is an argument for investing in dynamic capabilities which help renew and refresh the resource base and help the firm adapt to changing environments. Indeed, the results of the regression analysis suggest that dynamic capabilities for innovation acted as a moderator in the relationship between ISO 14001 certification and firm performance. This, in turn, will have a significant and symbiotic influence on sustainability practices within the participating organisations. The study not only provides new and original insights, but demonstrates pragmatically how firms can take advantage of environmental management systems as a moderator to significantly enhance firm performance. However, while it was shown that firm innovation aided both short term and long term ROA performance, adaptive market capabilities only aided firms in the short-term at the marketing strategy deployment stage. Finally, the results have important implications for firms operating in an economic recession as the results suggest that firms should scale back investment in R&D while operating in an economic downturn. Conversely, under normal trading conditions, consistent and long term investments in R&D was found to moderate the relationship between ISO 14001 certification and firm performance. Hence, the results of the study have important implications for academics and management alike.

Keywords: supply chain management, environmental management systems, quality management, sustainability, firm performance

Procedia PDF Downloads 282

Authors: Ruben L. Tagare, Jr

Abstract:

This study was conducted to determine the parents’ motivating factors for their deaf and mute children to participate in physical and recreational activities. Data were collected from the 17 parents of the deaf and mute children using a specifically designed survey questionnaire as the primary instrument used in the study. Data analysis and interpretation were done with the aid of descriptive statistics, such as frequency, percentage, weighted mean and multiple responses. Most of the respondents were female with a mean average age of 38 years old. The average age of their children was 10 years old. In terms of monthly income, the respondents had an average monthly income of PhP 13,945. Furthermore, most of the respondents lived in the urban area and were all Catholic by faith or religion. As to the factors that parents used to motivate their deaf and mute children to engage in physical and recreational activities, these included the followings: First; to make my child experience and explore more meaningful things through physical and recreational activities; second; to gain other’s respect; third; to build friendship and interact with his peers; fourth; to experience the feeling of belongingness; and fifth: to learn and discover new things. On the other hand, the least chosen factors were: first; to help achieve and maintain a healthy weight; second; to reduce fats and lowering blood pressure; third; to improve balance, coordination and strength; fourth; to improve posture; and fifth; to assist the child in the development of gross motor and fine motor skills. Based on the findings of the study, it is hereby recommended that since the first factor is 'to make my child experience and explore more meaningful things through physical and recreational activities' and the other top factors are more on social aspect, the school should design extra-curricular activities such as theatrical play and other similar activities that the students will find interesting while the parents will be more motivated to engage their children into physical and recreational activities. Also, since the least chosen factors are more on physical aspect, the school should organize or conduct a seminar for the parents to be aware of the benefits of participating in physical and recreational activities for their deaf and mute children. They can also conduct an information campaign to encourage the other parents of deaf and mute children, whom they keep only inside their home to enroll in the school and let their children be exposed to the natural world. Considering that parents are the primary motivators that can best help their children become more interested in physical and recreational activities for their own development, the school should always remain motivated by creating activities for the deaf and mute children with their parents. The study also recommends conducting further study on the level of knowledge/understanding of the parents on the benefits that can be derived from participating in physical and recreational activities.

Keywords: deaf and mute, participation, physical and recreational activities, adaptive PE

Procedia PDF Downloads 159

Authors: Yongjiang Zhang, Kallol Barai, Umesh R. Hodeghatta, Trang Tran, Vikas Dhiman

Abstract:

Detecting water stress on crops early and accurately is crucial to minimize its impact. This study aims to measure water stress in wild blueberry crops non-destructively by analyzing proximal hyperspectral data. The data collection took place in the summer growing season of 2022. A drought experiment was conducted on wild blueberries in the randomized block design in the greenhouse, incorporating various genotypes and irrigation treatments. Hyperspectral data ( spectral range: 400-1000 nm) using a handheld spectroradiometer and leaf water potential data using a pressure chamber were collected from wild blueberry plants. Machine learning techniques, including multiple regression analysis and random forest models, were employed to predict leaf water potential (MPa). We explored the optimal wavelength bands for simple differences (RY1-R Y2), simple ratios (RY1/RY2), and normalized differences (|RY1-R Y2|/ (RY1-R Y2)). NDWI ((R857 - R1241)/(R857 + R1241)), SD (R2188 – R2245), and SR (R1752 / R1756) emerged as top predictors for predicting leaf water potential, significantly contributing to the highest model performance. The base learner models achieved an R-squared value of approximately 0.81, indicating their capacity to explain 81% of the variance. Research is underway to develop a neural vegetation index (NVI) that automates the process of index development by searching for specific wavelengths in the space ratio of linear functions of reflectance. The NVI framework could work across species and predict different physiological parameters.

Keywords: hyperspectral reflectance, water potential, spectral indices, machine learning, wild blueberries, optimal bands

Procedia PDF Downloads 46

Authors: Souvik Phadikar, Nidul Sinha, Rajdeep Ghosh

Abstract:

In brainwaves research using electroencephalogram (EEG) signals, finding the most relevant and effective feature set for identification of activities in the human brain is a big challenge till today because of the random nature of the signals. The feature extraction method is a key issue to solve this problem. Finding those features that prove to give distinctive pictures for different activities and similar for the same activities is very difficult, especially for the number of activities. The performance of a classifier accuracy depends on this quality of feature set. Further, more number of features result in high computational complexity and less number of features compromise with the lower performance. In this paper, a novel idea of the selection of optimal feature set using a heuristically optimized deep autoencoder is presented. Using various feature extraction methods, a vast number of features are extracted from the EEG signals and fed to the autoencoder deep neural network. The autoencoder encodes the input features into a small set of codes. To avoid the gradient vanish problem and normalization of the dataset, a meta-heuristic search algorithm is used to minimize the mean square error (MSE) between encoder input and decoder output. To reduce the feature set into a smaller one, 4 hidden layers are considered in the autoencoder network; hence it is called Heuristically Optimized Deep Autoencoder (HO-DAE). In this method, no features are rejected; all the features are combined into the response of responses of the hidden layer. The results reveal that higher accuracy can be achieved using optimal reduced features. The proposed HO-DAE is also compared with the regular autoencoder to test the performance of both. The performance of the proposed method is validated and compared with the other two methods recently reported in the literature, which reveals that the proposed method is far better than the other two methods in terms of classification accuracy.

Keywords: autoencoder, brainwave signal analysis, electroencephalogram, feature extraction, feature selection, optimization

Procedia PDF Downloads 95

Authors: Aitor Bilbao, Dragos Axinte, John Billingham

Abstract:

The inverse problem in Energy Beam (EB) Processes consists of defining the control parameters, in particular the 2D beam path (position and orientation of the beam as a function of time), to arrive at a prescribed solution (freeform surface). This inverse problem is well understood for conventional machining, because the cutting tool geometry is well defined and the material removal is a time independent process. In contrast, EB machining is achieved through the local interaction of a beam of particular characteristics (e.g. energy distribution), which leads to a surface-dependent removal rate. Furthermore, EB machining is a time-dependent process in which not only the beam varies with the dwell time, but any acceleration/deceleration of the machine/beam delivery system, when performing raster paths will influence the actual geometry of the surface to be generated. Two different EB processes, Abrasive Water Machining (AWJM) and Pulsed Laser Ablation (PLA), are studied. Even though they are considered as independent different technologies, both can be described as time-dependent processes. AWJM can be considered as a continuous process and the etched material depends on the feed speed of the jet at each instant during the process. On the other hand, PLA processes are usually defined as discrete systems and the total removed material is calculated by the summation of the different pulses shot during the process. The overlapping of these shots depends on the feed speed and the frequency between two consecutive shots. However, if the feed speed is sufficiently slow compared with the frequency, then consecutive shots are close enough and the behaviour can be similar to a continuous process. Using this approximation a generic continuous model can be described for both processes. The inverse problem is usually solved for this kind of process by simply controlling dwell time in proportion to the required depth of milling at each single pixel on the surface using a linear model of the process. However, this approach does not always lead to the good solution since linear models are only valid when shallow surfaces are etched. The solution of the inverse problem is improved by using a discrete adjoint optimization algorithm. Moreover, the calculation of the Jacobian matrix consumes less computation time than finite difference approaches. The influence of the dynamics of the machine on the actual movement of the jet is also important and should be taken into account. When the parameters of the controller are not known or cannot be changed, a simple approximation is used for the choice of the slope of a step profile. Several experimental tests are performed for both technologies to show the usefulness of this approach.

Keywords: abrasive waterjet machining, energy beam processes, inverse problem, pulsed laser ablation

Procedia PDF Downloads 257

Authors: Malik Muhammad Arslan, Muneeb Ullah, Dai Shihan, Daniyal Haider, Xiaodong Yang

Abstract:

Chest X-rays are instrumental in the detection and monitoring of a wide array of diseases, including viral infections such as COVID-19, tuberculosis, pneumonia, lung cancer, and various cardiac and pulmonary conditions. To enhance the accuracy of diagnosis, artificial intelligence (AI) algorithms, particularly deep learning models like Convolutional Neural Networks (CNNs), are employed. However, these deep learning models demand a substantial and varied dataset to attain optimal precision. Generative Adversarial Networks (GANs) can be employed to create new data, thereby supplementing the existing dataset and enhancing the accuracy of deep learning models. Nevertheless, GANs have their limitations, such as issues related to stability, convergence, and the ability to distinguish between authentic and fabricated data. In order to overcome these challenges and advance the detection and classification of CXR normal and abnormal images, this study introduces a distinctive technique known as DCWGAN (Diverse Conditional Wasserstein GAN) for generating synthetic chest X-ray (CXR) images. The study evaluates the effectiveness of this Idiosyncratic DCWGAN technique using the ResNet50 model and compares its results with those obtained using the traditional GAN approach. The findings reveal that the ResNet50 model trained on the DCWGAN-generated dataset outperformed the model trained on the classic GAN-generated dataset. Specifically, the ResNet50 model utilizing DCWGAN synthetic images achieved impressive performance metrics with an accuracy of 0.961, precision of 0.955, recall of 0.970, and F1-Measure of 0.963. These results indicate the promising potential for the early detection of diseases in CXR images using this Inimitable approach.

Keywords: CNN, classification, deep learning, GAN, Resnet50

Procedia PDF Downloads 54

Authors: Ajved Ahmed

Abstract:

This research paper explores the intricate relationship between sports activities and disability, aiming to shed light on the multifaceted impacts of sports participation on individuals with disabilities. As the world grapples with the challenges posed by the growing population of people with disabilities, understanding the role of sports in their lives becomes increasingly important. The paper begins by providing a comprehensive overview of the diverse forms of disabilities, emphasizing the wide spectrum of physical, sensory, and cognitive impairments. It then delves into the benefits of sports activities for individuals with disabilities, highlighting the profound physical, psychological, and social advantages that engagement in sports can offer. These benefits encompass improved physical fitness, enhanced self-esteem and mental well-being, increased social integration, and a sense of empowerment and independence. Furthermore, the paper examines the barriers and challenges that individuals with disabilities often encounter when attempting to participate in sports activities, ranging from inaccessible facilities to societal prejudices and stereotypes. It underscores the critical role of inclusive sports programs, adaptive equipment, and policy initiatives in overcoming these barriers and fostering an environment where everyone can enjoy the benefits of sports. Through a comprehensive review of existing research and case studies, the paper also explores specific sports and their suitability for various types of disabilities. It discusses adapted sports like wheelchair basketball, blind soccer, and para-swimming, showcasing how these tailored activities not only accommodate disabilities but also promote excellence and competition at the highest levels. Additionally, the research paper delves into the economic and societal implications of increased sports participation among individuals with disabilities. It explores the potential for greater inclusion in the workforce, reduced healthcare costs, and the fostering of a more inclusive and accepting society. This research paper underscores the profound impact of sports activities on individuals with disabilities, highlighting their potential to improve physical health, mental well-being, and social integration. It calls for continued efforts to break down barriers and promote inclusive sports programs to ensure that everyone, regardless of their abilities, can access the transformative power of sports. Ultimately, this study contributes to a broader understanding of disability and sports, emphasizing the importance of inclusivity and accessibility in creating a more equitable and healthier society.

Keywords: sports and health, sports and disability, curing disability through sports, health benefits of sports

Procedia PDF Downloads 38

Authors: Bikis Muhammed, Sehra Sedigh Sarvestani, Ali R. Hurson, Lasanthi Gamage

Abstract:

Vehicular traffic events have overly complex spatial correlations and temporal interdependencies and are also influenced by environmental events such as weather conditions. To capture these spatial and temporal interdependencies and make more realistic vehicular traffic predictions, graph neural networks (GNN) based traffic prediction models have been extensively utilized due to their capability of capturing non-Euclidean spatial correlation very effectively. However, most of the already existing GNN-based traffic prediction models have some limitations during learning complex and dynamic spatial and temporal patterns due to the following missing factors. First, most GNN-based traffic prediction models have used static distance or sometimes haversine distance mechanisms between spatially separated traffic observations to estimate spatial correlation. Secondly, most GNN-based traffic prediction models have not incorporated environmental events that have a major impact on the normal traffic states. Finally, most of the GNN-based models did not use an attention mechanism to focus on only important traffic observations. The objective of this paper is to study and make real-time vehicular traffic predictions while incorporating the effect of weather conditions. To fill the previously mentioned gaps, our prediction model uses a real-time driving distance between sensors to build a distance matrix or spatial adjacency matrix and capture spatial correlation. In addition, our prediction model considers the effect of six types of weather conditions and has an attention mechanism in both spatial and temporal data aggregation. Our prediction model efficiently captures the spatial and temporal correlation between traffic events, and it relies on the graph attention network (GAT) and Bidirectional bidirectional long short-term memory (Bi-LSTM) plus attention layers and is called GAT-BILSTMA.

Keywords: deep learning, real time prediction, GAT, Bi-LSTM, attention

Procedia PDF Downloads 49

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 59