Search results for: PES (power electronics systems) synchronous machine
15294 Radiomics: Approach to Enable Early Diagnosis of Non-Specific Breast Nodules in Contrast-Enhanced Magnetic Resonance Imaging
Authors: N. D'Amico, E. Grossi, B. Colombo, F. Rigiroli, M. Buscema, D. Fazzini, G. Cornalba, S. Papa
Abstract:
Purpose: To characterize, through a radiomic approach, the nature of nodules considered non-specific by expert radiologists, recognized in magnetic resonance mammography (MRm) with T1-weighted (T1w) sequences with paramagnetic contrast. Material and Methods: 47 cases out of 1200 undergoing MRm, in which the MRm assessment gave uncertain classification (non-specific nodules), were admitted to the study. The clinical outcome of the non-specific nodules was later found through follow-up or further exams (biopsy), finding 35 benign and 12 malignant. All MR Images were acquired at 1.5T, a first basal T1w sequence and then four T1w acquisitions after the paramagnetic contrast injection. After a manual segmentation of the lesions, done by a radiologist, and the extraction of 150 radiomic features (30 features per 5 subsequent times) a machine learning (ML) approach was used. An evolutionary algorithm (TWIST system based on KNN algorithm) was used to subdivide the dataset into training and validation test and to select features yielding the maximal amount of information. After this pre-processing, different machine learning systems were applied to develop a predictive model based on a training-testing crossover procedure. 10 cases with a benign nodule (follow-up older than 5 years) and 18 with an evident malignant tumor (clear malignant histological exam) were added to the dataset in order to allow the ML system to better learn from data. Results: NaiveBayes algorithm working on 79 features selected by a TWIST system, resulted to be the best performing ML system with a sensitivity of 96% and a specificity of 78% and a global accuracy of 87% (average values of two training-testing procedures ab-ba). The results showed that in the subset of 47 non-specific nodules, the algorithm predicted the outcome of 45 nodules which an expert radiologist could not identify. Conclusion: In this pilot study we identified a radiomic approach allowing ML systems to perform well in the diagnosis of a non-specific nodule at MR mammography. This algorithm could be a great support for the early diagnosis of malignant breast tumor, in the event the radiologist is not able to identify the kind of lesion and reduces the necessity for long follow-up. Clinical Relevance: This machine learning algorithm could be essential to support the radiologist in early diagnosis of non-specific nodules, in order to avoid strenuous follow-up and painful biopsy for the patient.Keywords: breast, machine learning, MRI, radiomics
Procedia PDF Downloads 26015293 Real-Time Control of Grid-Connected Inverter Based on labVIEW
Authors: L. Benbaouche, H. E. , F. Krim
Abstract:
In this paper we propose real-time control of grid-connected single phase inverter, which is flexible and efficient. The first step is devoted to the study and design of the controller through simulation, conducted by the LabVIEW software on the computer 'host'. The second step is running the application from PXI 'target'. LabVIEW software, combined with NI-DAQmx, gives the tools to easily build applications using the digital to analog converter to generate the PWM control signals. Experimental results show that the effectiveness of LabVIEW software applied to power electronics.Keywords: real-time control, labview, inverter, PWM
Procedia PDF Downloads 49515292 Prediction of MicroRNA-Target Gene by Machine Learning Algorithms in Lung Cancer Study
Authors: Nilubon Kurubanjerdjit, Nattakarn Iam-On, Ka-Lok Ng
Abstract:
MicroRNAs are small non-coding RNA found in many different species. They play crucial roles in cancer such as biological processes of apoptosis and proliferation. The identification of microRNA-target genes can be an essential first step towards to reveal the role of microRNA in various cancer types. In this paper, we predict miRNA-target genes for lung cancer by integrating prediction scores from miRanda and PITA algorithms used as a feature vector of miRNA-target interaction. Then, machine-learning algorithms were implemented for making a final prediction. The approach developed in this study should be of value for future studies into understanding the role of miRNAs in molecular mechanisms enabling lung cancer formation.Keywords: microRNA, miRNAs, lung cancer, machine learning, Naïve Bayes, SVM
Procedia PDF Downloads 39315291 Optimization of Hate Speech and Abusive Language Detection on Indonesian-language Twitter using Genetic Algorithms
Authors: Rikson Gultom
Abstract:
Hate Speech and Abusive language on social media is difficult to detect, usually, it is detected after it becomes viral in cyberspace, of course, it is too late for prevention. An early detection system that has a fairly good accuracy is needed so that it can reduce conflicts that occur in society caused by postings on social media that attack individuals, groups, and governments in Indonesia. The purpose of this study is to find an early detection model on Twitter social media using machine learning that has high accuracy from several machine learning methods studied. In this study, the support vector machine (SVM), Naïve Bayes (NB), and Random Forest Decision Tree (RFDT) methods were compared with the Support Vector machine with genetic algorithm (SVM-GA), Nave Bayes with genetic algorithm (NB-GA), and Random Forest Decision Tree with Genetic Algorithm (RFDT-GA). The study produced a comparison table for the accuracy of the hate speech and abusive language detection model, and presented it in the form of a graph of the accuracy of the six algorithms developed based on the Indonesian-language Twitter dataset, and concluded the best model with the highest accuracy.Keywords: abusive language, hate speech, machine learning, optimization, social media
Procedia PDF Downloads 12015290 All-Silicon Raman Laser with Quasi-Phase-Matched Structures and Resonators
Authors: Isao Tomita
Abstract:
The principle of all-silicon Raman lasers for an output wavelength of 1.3 μm is presented, which employs quasi-phase-matched structures and resonators to enhance the output power. 1.3-μm laser beams for GE-PONs in FTTH systems generated from a silicon device are very important because such a silicon device can be monolithically integrated with the silicon planar lightwave circuits (Si PLCs) used in the GE-PONs. This reduces the device fabrication processes and time and also optical losses at the junctions between optical waveguides of the Si PLCs and Si laser devices when compared with 1.3-μm III-V semiconductor lasers set on the Si PLCs employed at present. We show that the quasi-phase-matched Si Raman laser with resonators can produce about 174 times larger laser power at 1.3 μm (at maximum) than that without resonators for a Si waveguide of Raman gain 20 cm/GW and optical loss 1.2 dB/cm, pumped at power 10 mW, where the length of the waveguide is 3 mm and its cross-section is (1.5 μm)2.Keywords: All-Silicon Raman Laser, FTTH, GE-PON, Quasi-Phase-Matched Structure, resonator
Procedia PDF Downloads 24515289 Technological Tool-Use as an Online Learner Strategy in a Synchronous Speaking Task
Authors: J. Knight, E. Barberà
Abstract:
Language learning strategies have been defined as thoughts and actions, consciously chosen and operationalized by language learners, to help them in carrying out a multiplicity of tasks from the very outset of learning to the most advanced levels of target language performance. While research in the field of Second Language Acquisition has focused on ‘good’ language learners, the effectiveness of strategy-use and orchestration by effective learners in face-to-face classrooms much less research has attended to learner strategies in online contexts, particular strategies in relation to technological tool use which can be part of a task design. In addition, much research on learner strategies and strategy use has been explored focusing on cognitive, attitudinal and metacognitive behaviour with less research focusing on the social aspect of strategies. This study focuses on how learners mediate with a technological tool designed to support synchronous spoken interaction and how this shape their spoken interaction in the opening of their talk. A case study approach is used incorporating notions from communities of practice theory to analyse and understand learner strategies of dyads carrying out a role play task. The study employs analysis of transcripts of spoken interaction in the openings of the talk along with log files of tool use. The study draws on results of previous studies pertaining to the same tool as a form of triangulation. Findings show how learners gain pre-task planning time through technological tool control. The strategies involving learners’ choices to enter and exit the tool shape their spoken interaction qualitatively, with some cases demonstrating long silences whilst others appearing to start the pedagogical task immediately. Who/what learners orientate to in the openings of the talk: an audience (i.e. the teacher), each other and/or screen-based signifiers in the opening moments of the talk also becomes a focus. The study highlights how tool use as a social practice should be considered a learning strategy in online contexts whereby different usages may be understood in the light of the more usual asynchronous social practices of the online community. The teachers’ role in the community is also problematised as the evaluator of the practices of that community. Results are pertinent for task design for synchronous speaking tasks. The use of community of practice theory supports an understanding of strategy use that involves both metacognition alongside social context revealing how tool-use strategies may need to be orally (socially) negotiated by learners and may also differ from an online language community.Keywords: learner strategy, tool use, community of practice, speaking task
Procedia PDF Downloads 33515288 Distributed System Computing Resource Scheduling Algorithm Based on Deep Reinforcement Learning
Authors: Yitao Lei, Xingxiang Zhai, Burra Venkata Durga Kumar
Abstract:
As the quantity and complexity of computing in large-scale software systems increase, distributed system computing becomes increasingly important. The distributed system realizes high-performance computing by collaboration between different computing resources. If there are no efficient resource scheduling resources, the abuse of distributed computing may cause resource waste and high costs. However, resource scheduling is usually an NP-hard problem, so we cannot find a general solution. However, some optimization algorithms exist like genetic algorithm, ant colony optimization, etc. The large scale of distributed systems makes this traditional optimization algorithm challenging to work with. Heuristic and machine learning algorithms are usually applied in this situation to ease the computing load. As a result, we do a review of traditional resource scheduling optimization algorithms and try to introduce a deep reinforcement learning method that utilizes the perceptual ability of neural networks and the decision-making ability of reinforcement learning. Using the machine learning method, we try to find important factors that influence the performance of distributed system computing and help the distributed system do an efficient computing resource scheduling. This paper surveys the application of deep reinforcement learning on distributed system computing resource scheduling proposes a deep reinforcement learning method that uses a recurrent neural network to optimize the resource scheduling, and proposes the challenges and improvement directions for DRL-based resource scheduling algorithms.Keywords: resource scheduling, deep reinforcement learning, distributed system, artificial intelligence
Procedia PDF Downloads 9815287 Evaluating Reliability Indices in 3 Critical Feeders at Lorestan Electric Power Distribution Company
Authors: Atefeh Pourshafie, Homayoun Bakhtiari
Abstract:
The main task of power distribution companies is to supply the power required by customers in an acceptable level of quality and reliability. Some key performance indicators for electric power distribution companies are those evaluating the continuity of supply within the network. More than other problems, power outages (due to lightning, flood, fire, earthquake, etc.) challenge economy and business. In addition, end users expect a reliable power supply. Reliability indices are evaluated on an annual basis by the specialized holding company of Tavanir (Power Produce, Transmission& distribution company of Iran) . Evaluation of reliability indices is essential for distribution companies, and with regard to the privatization of distribution companies, it will be of particular importance to evaluate these indices and to plan for their improvement in a not too distant future. According to IEEE-1366 standard, there are too many indices; however, the most common reliability indices include SAIFI, SAIDI and CAIDI. These indices describe the period and frequency of blackouts in the reporting period (annual or any desired timeframe). This paper calculates reliability indices for three sample feeders in Lorestan Electric Power Distribution Company and defines the threshold values in a ten-month period. At the end, strategies are introduced to reach the threshold values in order to increase customers' satisfaction.Keywords: power, distribution network, reliability, outage
Procedia PDF Downloads 46115286 Two-Level Separation of High Air Conditioner Consumers and Demand Response Potential Estimation Based on Set Point Change
Authors: Mehdi Naserian, Mohammad Jooshaki, Mahmud Fotuhi-Firuzabad, Mohammad Hossein Mohammadi Sanjani, Ashknaz Oraee
Abstract:
In recent years, the development of communication infrastructure and smart meters have facilitated the utilization of demand-side resources which can enhance stability and economic efficiency of power systems. Direct load control programs can play an important role in the utilization of demand-side resources in the residential sector. However, investments required for installing control equipment can be a limiting factor in the development of such demand response programs. Thus, selection of consumers with higher potentials is crucial to the success of a direct load control program. Heating, ventilation, and air conditioning (HVAC) systems, which due to the heat capacity of buildings feature relatively high flexibility, make up a major part of household consumption. Considering that the consumption of HVAC systems depends highly on the ambient temperature and bearing in mind the high investments required for control systems enabling direct load control demand response programs, in this paper, a recent solution is presented to uncover consumers with high air conditioner demand among large number of consumers and to measure the demand response potential of such consumers. This can pave the way for estimating the investments needed for the implementation of direct load control programs for residential HVAC systems and for estimating the demand response potentials in a distribution system. In doing so, we first cluster consumers into several groups based on the correlation coefficients between hourly consumption data and hourly temperature data using K-means algorithm. Then, by applying a recent algorithm to the hourly consumption and temperature data, consumers with high air conditioner consumption are identified. Finally, demand response potential of such consumers is estimated based on the equivalent desired temperature setpoint changes.Keywords: communication infrastructure, smart meters, power systems, HVAC system, residential HVAC systems
Procedia PDF Downloads 5215285 Metrology-Inspired Methods to Assess the Biases of Artificial Intelligence Systems
Authors: Belkacem Laimouche
Abstract:
With the field of artificial intelligence (AI) experiencing exponential growth, fueled by technological advancements that pave the way for increasingly innovative and promising applications, there is an escalating need to develop rigorous methods for assessing their performance in pursuit of transparency and equity. This article proposes a metrology-inspired statistical framework for evaluating bias and explainability in AI systems. Drawing from the principles of metrology, we propose a pioneering approach, using a concrete example, to evaluate the accuracy and precision of AI models, as well as to quantify the sources of measurement uncertainty that can lead to bias in their predictions. Furthermore, we explore a statistical approach for evaluating the explainability of AI systems based on their ability to provide interpretable and transparent explanations of their predictions.Keywords: artificial intelligence, metrology, measurement uncertainty, prediction error, bias, machine learning algorithms, probabilistic models, interlaboratory comparison, data analysis, data reliability, measurement of bias impact on predictions, improvement of model accuracy and reliability
Procedia PDF Downloads 9815284 Prediction of Disability-Adjustment Mental Illness Using Machine
Authors: R. M. Krishna Sureddi, V. Kamakshi Prasad, R. Santosh
Abstract:
Machine learning techniques are applied for the analysis of the impact of mental illness on the burden of disease. It is calculated using the disability-adjusted life year (DALY). One DALY represents the loss of the equivalent of one year of full health. DALYs for a disease or health condition are the sum of years of life lost due to premature mortality (YLLs) and years of healthy life lost due to disability (YLDs) due to prevalent cases of the disease or health condition in a population. The critical analysis is done based on the Data sources, machine learning techniques and feature extraction method. The reviewing is done based on major databases. The extracted data is examined using statistical analysis and machine learning techniques were applied. The prediction of the impact of mental illness on the population using machine learning techniques is an alternative approach to the old traditional strategies, which are time-consuming and may not be reliable. The approach makes it necessary for a comprehensive adoption, innovative algorithms, and an understanding of the limitations and challenges. The obtained prediction is a way of understanding the underlying impact of mental illness on the health of the people and it enables us to get a healthy life expectancy. The growing impact of mental illness and the challenges associated with the detection and treatment of mental disorders make it necessary for us to understand the complete effect of it on the majority of the population. Procedia PDF Downloads 1515283 Enhance the Power of Sentiment Analysis
Authors: Yu Zhang, Pedro Desouza
Abstract:
Since big data has become substantially more accessible and manageable due to the development of powerful tools for dealing with unstructured data, people are eager to mine information from social media resources that could not be handled in the past. Sentiment analysis, as a novel branch of text mining, has in the last decade become increasingly important in marketing analysis, customer risk prediction and other fields. Scientists and researchers have undertaken significant work in creating and improving their sentiment models. In this paper, we present a concept of selecting appropriate classifiers based on the features and qualities of data sources by comparing the performances of five classifiers with three popular social media data sources: Twitter, Amazon Customer Reviews, and Movie Reviews. We introduced a couple of innovative models that outperform traditional sentiment classifiers for these data sources, and provide insights on how to further improve the predictive power of sentiment analysis. The modelling and testing work was done in R and Greenplum in-database analytic tools.Keywords: sentiment analysis, social media, Twitter, Amazon, data mining, machine learning, text mining
Procedia PDF Downloads 34315282 Analysis of Roll-Forming for High-Density Wire of Reed
Authors: Yujeong Shin, Seong Jin Cho, Jin Ho Kim
Abstract:
In the textile-weaving machine, the reed is the core component to separate thousands of strands of yarn and to produce the fabric in a continuous high-speed movement. In addition, the reed affects the quality of the fiber. Therefore, the wire forming analysis of the main raw materials of the reed needs to be considered. Roll-forming is a key technology among the manufacturing process of reed wire using textile machine. A simulation of roll-forming line in accordance with the reduction rate is performed using LS-DYNA. The upper roller, fixed roller and reed wire are modeled by finite element. The roller is set to be rigid body and the wire of SUS430 is set to be flexible body. We predict the variation of the cross-sectional shape of the wire depending on the reduction ratio.Keywords: textile machine, reed, rolling, reduction ratio, wire
Procedia PDF Downloads 36715281 Dynamic Performance Analysis of Distribution/ Sub-Transmission Networks with High Penetration of PV Generation
Authors: Cristian F.T. Montenegro, Luís F. N. Lourenço, Maurício B. C. Salles, Renato M. Monaro
Abstract:
More PV systems have been connected to the electrical network each year. As the number of PV systems increases, some issues affecting grid operations have been identified. This paper studied the impacts related to changes in solar irradiance on a distribution/sub-transmission network, considering variations due to moving clouds and daily cycles. Using MATLAB/Simulink software, a solar farm of 30 MWp was built and then implemented to a test network. From simulations, it has been determined that irradiance changes can have a significant impact on the grid by causing voltage fluctuations outside the allowable thresholds. This work discussed some local control strategies and grid reinforcements to mitigate the negative effects of the irradiance changes on the grid.Keywords: reactive power control, solar irradiance, utility-scale PV systems, voltage fluctuations
Procedia PDF Downloads 44915280 Simulation of Wind Solar Hybrid Power Generation for Pumping Station
Authors: Masoud Taghavi, Gholamreza Salehi, Ali Lohrasbi Nichkoohi
Abstract:
Despite the growing use of renewable energies in different fields of application of this technology in the field of water supply has been less attention. Photovoltaic and wind hybrid system is that new topics in renewable energy, including photovoltaic arrays, wind turbines, a set of batteries as a storage system and a diesel generator as a backup system is. In this investigation, first climate data including average wind speed and solar radiation at any time during the year, data collection and analysis are performed in the energy. The wind turbines in four models, photovoltaic panels at the 6 position of relative power, batteries and diesel generator capacity in seven states in the two models are combined hours of operation with renewables, diesel generator and battery bank check and a hybrid system of solar power generation-wind, which is optimized conditions, are presented.Keywords: renewable energy, wind and solar energy, hybrid systems, cloning station
Procedia PDF Downloads 38915279 Assessing the Impact of Low Carbon Technology Integration on Electricity Distribution Networks: Advancing towards Local Area Energy Planning
Authors: Javier Sandoval Bustamante, Pardis Sheikhzadeh, Vijayanarasimha Hindupur Pakka
Abstract:
In the pursuit of achieving net-zero carbon emissions, the integration of low carbon technologies into electricity distribution networks is paramount. This paper delves into the critical assessment of how the integration of low carbon technologies, such as heat pumps, electric vehicle chargers, and photovoltaic systems, impacts the infrastructure and operation of electricity distribution networks. The study employs rigorous methodologies, including power flow analysis and headroom analysis, to evaluate the feasibility and implications of integrating these technologies into existing distribution systems. Furthermore, the research utilizes Local Area Energy Planning (LAEP) methodologies to guide local authorities and distribution network operators in formulating effective plans to meet regional and national decarbonization objectives. Geospatial analysis techniques, coupled with building physics and electric energy systems modeling, are employed to develop geographic datasets aimed at informing the deployment of low carbon technologies at the local level. Drawing upon insights from the Local Energy Net Zero Accelerator (LENZA) project, a comprehensive case study illustrates the practical application of these methodologies in assessing the rollout potential of LCTs. The findings not only shed light on the technical feasibility of integrating low carbon technologies but also provide valuable insights into the broader transition towards a sustainable and electrified energy future. This paper contributes to the advancement of knowledge in power electrical engineering by providing empirical evidence and methodologies to support the integration of low carbon technologies into electricity distribution networks. The insights gained are instrumental for policymakers, utility companies, and stakeholders involved in navigating the complex challenges of energy transition and achieving long-term sustainability goals.Keywords: energy planning, energy systems, digital twins, power flow analysis, headroom analysis
Procedia PDF Downloads 3715278 Single Machine Scheduling Problem to Minimize the Number of Tardy Jobs
Authors: Ali Allahverdi, Harun Aydilek, Asiye Aydilek
Abstract:
Minimizing the number of tardy jobs is an important factor to consider while making scheduling decisions. This is because on-time shipments are vital for lowering cost and increasing customers’ satisfaction. This paper addresses the single machine scheduling problem with the objective of minimizing the number of tardy jobs. The only known information is the lower and upper bounds for processing times, and deterministic job due dates. A dominance relation is established, and an algorithm is proposed. Several heuristics are generated from the proposed algorithm. Computational analysis indicates that the performance of one of the heuristics is very close to the optimal solution, i.e., on average, less than 1.5 % from the optimal solution.Keywords: single machine scheduling, number of tardy jobs, heuristi, lower and upper bounds
Procedia PDF Downloads 55015277 Overview of Resources and Tools to Bridge Language Barriers Provided by the European Union
Authors: Barbara Heinisch, Mikael Snaprud
Abstract:
A common, well understood language is crucial in critical situations like landing a plane. For e-Government solutions, a clear and common language is needed to allow users to successfully complete transactions online. Misunderstandings here may not risk a safe landing but can cause delays, resubmissions and drive costs. This holds also true for higher education, where misunderstandings can also arise due to inconsistent use of terminology. Thus, language barriers are a societal challenge that needs to be tackled. The major means to bridge language barriers is translation. However, achieving high-quality translation and making texts understandable and accessible require certain framework conditions. Therefore, the EU and individual projects take (strategic) actions. These actions include the identification, collection, processing, re-use and development of language resources. These language resources may be used for the development of machine translation systems and the provision of (public) services including higher education. This paper outlines some of the existing resources and indicate directions for further development to increase the quality and usage of these resources.Keywords: language resources, machine translation, terminology, translation
Procedia PDF Downloads 31115276 A Design System for Complex Profiles of Machine Members Using a Synthetic Curve
Authors: N. Sateesh, C. S. P. Rao, K. Satyanarayana, C. Rajashekar
Abstract:
This paper proposes a development of a CAD/CAM system for complex profiles of various machine members using a synthetic curve i.e. B-spline. Conventional methods in designing and manufacturing of complex profiles are tedious and time consuming. Even programming those on a computer numerical control (CNC) machine can be a difficult job because of the complexity of the profiles. The system developed provides graphical and numerical representation B-spline profile for any given input. In this paper, the system is applicable to represent a cam profile with B-spline and attempt is made to improve the follower motion.Keywords: plate-cams, cam profile, b-spline, computer numerical control (CNC), computer aided design and computer aided manufacturing (CAD/CAM), R-D-R-D (rise-dwell-return-dwell)
Procedia PDF Downloads 60015275 Unseen Classes: The Paradigm Shift in Machine Learning
Authors: Vani Singhal, Jitendra Parmar, Satyendra Singh Chouhan
Abstract:
Unseen class discovery has now become an important part of a machine-learning algorithm to judge new classes. Unseen classes are the classes on which the machine learning model is not trained on. With the advancement in technology and AI replacing humans, the amount of data has increased to the next level. So while implementing a model on real-world examples, we come across unseen new classes. Our aim is to find the number of unseen classes by using a hierarchical-based active learning algorithm. The algorithm is based on hierarchical clustering as well as active sampling. The number of clusters that we will get in the end will give the number of unseen classes. The total clusters will also contain some clusters that have unseen classes. Instead of first discovering unseen classes and then finding their number, we directly calculated the number by applying the algorithm. The dataset used is for intent classification. The target data is the intent of the corresponding query. We conclude that when the machine learning model will encounter real-world data, it will automatically find the number of unseen classes. In the future, our next work would be to label these unseen classes correctly.Keywords: active sampling, hierarchical clustering, open world learning, unseen class discovery
Procedia PDF Downloads 16015274 DeClEx-Processing Pipeline for Tumor Classification
Authors: Gaurav Shinde, Sai Charan Gongiguntla, Prajwal Shirur, Ahmed Hambaba
Abstract:
Health issues are significantly increasing, putting a substantial strain on healthcare services. This has accelerated the integration of machine learning in healthcare, particularly following the COVID-19 pandemic. The utilization of machine learning in healthcare has grown significantly. We introduce DeClEx, a pipeline that ensures that data mirrors real-world settings by incorporating Gaussian noise and blur and employing autoencoders to learn intermediate feature representations. Subsequently, our convolutional neural network, paired with spatial attention, provides comparable accuracy to state-of-the-art pre-trained models while achieving a threefold improvement in training speed. Furthermore, we provide interpretable results using explainable AI techniques. We integrate denoising and deblurring, classification, and explainability in a single pipeline called DeClEx.Keywords: machine learning, healthcare, classification, explainability
Procedia PDF Downloads 3615273 Combining Shallow and Deep Unsupervised Machine Learning Techniques to Detect Bad Actors in Complex Datasets
Authors: Jun Ming Moey, Zhiyaun Chen, David Nicholson
Abstract:
Bad actors are often hard to detect in data that imprints their behaviour patterns because they are comparatively rare events embedded in non-bad actor data. An unsupervised machine learning framework is applied here to detect bad actors in financial crime datasets that record millions of transactions undertaken by hundreds of actors (<0.01% bad). Specifically, the framework combines ‘shallow’ (PCA, Isolation Forest) and ‘deep’ (Autoencoder) methods to detect outlier patterns. Detection performance analysis for both the individual methods and their combination is reported.Keywords: detection, machine learning, deep learning, unsupervised, outlier analysis, data science, fraud, financial crime
Procedia PDF Downloads 8715272 A Proper Design of Wind Turbine Grounding Systems under Lightning
Authors: M. A. Abd-Allah, Mahmoud N. Ali, A. Said
Abstract:
Lightning Protection Systems (LPS) for wind power generation is becoming an important public issue. A serious damage of blades, accidents where low-voltage and control circuit breakdowns frequently occur in many wind farms. A grounding system is one of the most important components required for appropriate LPSs in wind turbines WTs. Proper design of a wind turbine grounding system is demanding and several factors for the proper and effective implementation must be taken into account. This paper proposed procedure of proper design of grounding systems for a wind turbine was introduced. This procedure depends on measuring of ground current of simulated wind farm under lightning taking into consideration the soil ionization. The procedure also includes the Ground Potential Rise (GPR) and the voltage distributions at ground surface level and Touch potential. In particular, the contribution of mitigating techniques, such as rings, rods and the proposed design were investigated.Keywords: WTs, Lightning Protection Systems (LPS), GPR, grounding system, mitigating techniques
Procedia PDF Downloads 36615271 Stability of a Self-Excited Machine Due to the Mechanical Coupling
Authors: M. Soltan Rezaee, M. R. Ghazavi, A. Najafi, W.-H. Liao
Abstract:
Generally, different rods in shaft systems can be misaligned based on the mechanical system usages. These rods can be linked together via U-coupling easily. The system is self-stimulated and may cause instabilities due to the inherent behavior of the coupling. In this study, each rod includes an elastic shaft with an angular stiffness and structural damping. Moreover, the mass of shafts is considered via attached solid disks. The impact of the system architecture and shaft mass on the instability of such mechanism are studied. Stability charts are plotted via a method based on Floquet theory. Eventually, the unstable points have been found and analyzed in detail. The results show that stabilizing the driveline is feasible by changing the system characteristics which include shaft mass and architecture.Keywords: coupling, mechanical systems, oscillations, rotating shafts
Procedia PDF Downloads 17215270 Working Title: Estimating the Power Output of Photovoltaics in Kuwait Using a Monte Carlo Approach
Authors: Mohammad Alshawaf, Rahmat Poudineh, Nawaf Alhajeri
Abstract:
The power generated from photovoltaic (PV) modules is non-dispatchable on demand due to the stochastic nature of solar radiation. The random variations in the measured intensity of solar irradiance are due to clouds and, in the case of arid regions, dust storms which decrease the intensity of intensity of solar irradiance. Therefore, modeling PV power output using average, maximum, or minimum solar irradiance values is inefficient to predict power generation reliably. The overall objective of this paper is to predict the power output of PV modules using Monte Carlo approach based the weather and solar conditions measured in Kuwait. Given the 250 Wp PV module used in study, the average daily power output is 1021 Wh/day. The maximum power was generated in April and the minimum power was generated in January 1187 Wh/day and 823 Wh/day respectively. The certainty of the daily predictions varies seasonally and according to the weather conditions. The output predictions were far more certain in the summer months, for example, the 80% certainty range for August is 89 Wh/day, whereas the 80% certainty range for April is 250 Wh/day.Keywords: Monte Carlo, solar energy, variable renewable energy, Kuwait
Procedia PDF Downloads 12515269 2.4 GHz 0.13µM Multi Biased Cascode Power Amplifier for ISM Band Wireless Applications
Authors: Udayan Patankar, Shashwati Bhagat, Vilas Nitneware, Ants Koel
Abstract:
An ISM band power amplifier is a type of electronic amplifier used to convert a low-power radio-frequency signal into a larger signal of significant power, typically used for driving the antenna of a transmitter. Due to drastic changes in telecommunication generations may lead to the requirements of improvements. Rapid changes in communication lead to the wide implementation of WLAN technology for its excellent characteristics, such as high transmission speed, long communication distance, and high reliability. Many applications such as WLAN, Bluetooth, and ZigBee, etc. were evolved with 2.4GHz to 5 GHz ISM Band, in which the power amplifier (PA) is a key building block of RF transmitters. There are many manufacturing processes available to manufacture a power amplifier for desired power output, but the major problem they have faced is about the power it consumed for its proper working, as many of them are fabricated on the GaN HEMT, Bi COMS process. In this paper we present a CMOS Base two stage cascode design of power amplifier working on 2.4GHz ISM frequency band. To lower the costs and allow full integration of a complete System-on-Chip (SoC) we have chosen 0.13µm low power CMOS technology for design. While designing a power amplifier, it is a real task to achieve higher power efficiency with minimum resources. This design showcase the Multi biased Cascode methodology to implement a two-stage CMOS power amplifier using ADS and LTSpice simulating tool. Main source is maximum of 2.4V which is internally distributed into different biasing point VB driving and VB driven as required for distinct stages of two stage RF power amplifier. It shows maximum power added efficiency near about 70.195% whereas its Power added efficiency calculated at 1 dB compression point is 44.669 %. Biased MOSFET is used to reduce total dc current as this circuit is designed for different wireless applications comes under 2.4GHz ISM Band.Keywords: RFIC, PAE, RF CMOS, impedance matching
Procedia PDF Downloads 21315268 New Advanced Medical Software Technology Challenges and Evolution of the Regulatory Framework in Expert Software, Artificial Intelligence, and Machine Learning
Authors: Umamaheswari Shanmugam, Silvia Ronchi
Abstract:
Software, artificial intelligence, and machine learning can improve healthcare through innovative and advanced technologies that can use the large amount and variety of data generated during healthcare services every day; one of the significant advantages of these new technologies is the ability to get experience and knowledge from real-world use and to improve their performance continuously. Healthcare systems and institutions can significantly benefit because the use of advanced technologies improves the efficiency and efficacy of healthcare. Software-defined as a medical device, is stand-alone software that is intended to be used for patients for one or more of these specific medical intended uses: - diagnosis, prevention, monitoring, prediction, prognosis, treatment or alleviation of a disease, any other health conditions, replacing or modifying any part of a physiological or pathological process–manage the received information from in vitro specimens derived from the human samples (body) and without principal main action of its principal intended use by pharmacological, immunological or metabolic definition. Software qualified as medical devices must comply with the general safety and performance requirements applicable to medical devices. These requirements are necessary to ensure high performance and quality and protect patients' safety. The evolution and the continuous improvement of software used in healthcare must consider the increase in regulatory requirements, which are becoming more complex in each market. The gap between these advanced technologies and the new regulations is the biggest challenge for medical device manufacturers. Regulatory requirements can be considered a market barrier, as they can delay or obstacle the device's approval. Still, they are necessary to ensure performance, quality, and safety. At the same time, they can be a business opportunity if the manufacturer can define the appropriate regulatory strategy in advance. The abstract will provide an overview of the current regulatory framework, the evolution of the international requirements, and the standards applicable to medical device software in the potential market all over the world.Keywords: artificial intelligence, machine learning, SaMD, regulatory, clinical evaluation, classification, international requirements, MDR, 510k, PMA, IMDRF, cyber security, health care systems
Procedia PDF Downloads 8115267 Predictive Analysis of Chest X-rays Using NLP and Large Language Models with the Indiana University Dataset and Random Forest Classifier
Authors: Azita Ramezani, Ghazal Mashhadiagha, Bahareh Sanabakhsh
Abstract:
This study researches the combination of Random. Forest classifiers with large language models (LLMs) and natural language processing (NLP) to improve diagnostic accuracy in chest X-ray analysis using the Indiana University dataset. Utilizing advanced NLP techniques, the research preprocesses textual data from radiological reports to extract key features, which are then merged with image-derived data. This improved dataset is analyzed with Random Forest classifiers to predict specific clinical results, focusing on the identification of health issues and the estimation of case urgency. The findings reveal that the combination of NLP, LLMs, and machine learning not only increases diagnostic precision but also reliability, especially in quickly identifying critical conditions. Achieving an accuracy of 99.35%, the model shows significant advancements over conventional diagnostic techniques. The results emphasize the large potential of machine learning in medical imaging, suggesting that these technologies could greatly enhance clinician judgment and patient outcomes by offering quicker and more precise diagnostic approximations.Keywords: natural language processing (NLP), large language models (LLMs), random forest classifier, chest x-ray analysis, medical imaging, diagnostic accuracy, indiana university dataset, machine learning in healthcare, predictive modeling, clinical decision support systems
Procedia PDF Downloads 3215266 The Establishment of RELAP5/SNAP Model for Kuosheng Nuclear Power Plant
Authors: C. Shih, J. R. Wang, H. C. Chang, S. W. Chen, S. C. Chiang, T. Y. Yu
Abstract:
After the measurement uncertainty recapture (MUR) power uprates, Kuosheng nuclear power plant (NPP) was uprated the power from 2894 MWt to 2943 MWt. For power upgrade, several codes (e.g., TRACE, RELAP5, etc.) were applied to assess the safety of Kuosheng NPP. Hence, the main work of this research is to establish a RELAP5/MOD3.3 model of Kuosheng NPP with SNAP interface. The establishment of RELAP5/SNAP model was referred to the FSAR, training documents, and TRACE model which has been developed and verified before. After completing the model establishment, the startup test scenarios would be applied to the RELAP5/SNAP model. With comparing the startup test data and TRACE analysis results, the applicability of RELAP5/SNAP model would be assessed.Keywords: RELAP5, TRACE, SNAP, BWR
Procedia PDF Downloads 41815265 Techniques to Characterize Subpopulations among Hearing Impaired Patients and Its Impact for Hearing Aid Fitting
Authors: Vijaya K. Narne, Gerard Loquet, Tobias Piechowiak, Dorte Hammershoi, Jesper H. Schmidt
Abstract:
BEAR, which stands for better hearing rehabilitation is a large-scale project in Denmark designed and executed by three national universities, three hospitals, and the hearing aid industry with the aim to improve hearing aid fitting. A total of 1963 hearing impaired people were included and were segmented into subgroups based on hearing-loss, demographics, audiological and questionnaires data (i.e., the speech, spatial and qualities of hearing scale [SSQ-12] and the International Outcome Inventory for Hearing-Aids [IOI-HA]). With the aim to provide a better hearing-aid fit to individual patients, we applied modern machine learning techniques with traditional audiograms rule-based systems. Results show that age, speech discrimination scores, and audiogram configurations were evolved as important parameters in characterizing sub-population from the data-set. The attempt to characterize sub-population reveal a clearer picture about the individual hearing difficulties encountered and the benefits derived from more individualized hearing aids.Keywords: hearing loss, audiological data, machine learning, hearing aids
Procedia PDF Downloads 145