Academic literature on the topic 'Neural network MLP'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Neural network MLP.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Neural network MLP"
1
Teja, G. Ravi, and M. R. Narasinga Rao. "Image Retrieval System using Fuzzy-Softmax MLP Neural Network." Indian Journal of Applied Research 3, no. 6 (2011): 169–74. http://dx.doi.org/10.15373/2249555x/june2013/57.
Full text
2
Ziółkowski, Jarosław, Mateusz Oszczypała, Jerzy Małachowski, and Joanna Szkutnik-Rogoż. "Use of Artificial Neural Networks to Predict Fuel Consumption on the Basis of Technical Parameters of Vehicles." Energies 14, no. 9 (2021): 2639. http://dx.doi.org/10.3390/en14092639.
Full textAbstract:
This publication presents a multi-faceted analysis of the fuel consumption of motor vehicles and the way human impacts the environment, with a particular emphasis on the passenger cars. The adopted research methodology is based on the use of artificial neural networks in order to create a predictive model on the basis of which fuel consumption of motor vehicles can be determined. A database containing 1750 records, being a set of information on vehicles manufactured in last decade, was used in the process of training the artificial neural networks. The MLP (Multi-Layer Perceptron) 22-10-3 network has been selected from the created neural networks, which was further subjected to an analysis. In order to determine if the predicted values match the real values, the linear Pearson correlation coefficient r and coefficient of determination R2 were used. For the MLP 22-10-3 neural network, the calculated coefficient r was within range 0.93–0.95, while the coefficient of determination R2 assumed a satisfactory value of more than 0.98. Furthermore, a sensitivity analysis of the predictive model was performed, determining the influence of each input variable on prediction accuracy. Then, a neural network with a reduced number of neurons in the input layer (MLP-20-10-3) was built, retaining a quantity of the hidden and output neurons and the activation functions of the individual layers. The MLP 20-10-3 neural network uses similar values of the r and R2 coefficients as the MLP 22-10-3 neural network. For the evaluation of both neural networks, the measures of the ex post prediction errors were used. Depending on the predicted variable, the MAPE errors for the validation sets reached satisfactory values in the range of 5–8% for MLP 22-10-3 and 6–10% for MLP 20-10-3 neural network, respectively. The prediction tool described is intended for the design of passenger cars equipped with internal combustion engines.
3
El-Shafie, A., A. Noureldin, M. Taha, A. Hussain, and M. Mukhlisin. "Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia." Hydrology and Earth System Sciences 16, no. 4 (2012): 1151–69. http://dx.doi.org/10.5194/hess-16-1151-2012.
Full textAbstract:
Abstract. Rainfall is considered as one of the major components of the hydrological process; it takes significant part in evaluating drought and flooding events. Therefore, it is important to have an accurate model for rainfall forecasting. Recently, several data-driven modeling approaches have been investigated to perform such forecasting tasks as multi-layer perceptron neural networks (MLP-NN). In fact, the rainfall time series modeling involves an important temporal dimension. On the other hand, the classical MLP-NN is a static and has a memoryless network architecture that is effective for complex nonlinear static mapping. This research focuses on investigating the potential of introducing a neural network that could address the temporal relationships of the rainfall series. Two different static neural networks and one dynamic neural network, namely the multi-layer perceptron neural network (MLP-NN), radial basis function neural network (RBFNN) and input delay neural network (IDNN), respectively, have been examined in this study. Those models had been developed for the two time horizons for monthly and weekly rainfall forecasting at Klang River, Malaysia. Data collected over 12 yr (1997–2008) on a weekly basis and 22 yr (1987–2008) on a monthly basis were used to develop and examine the performance of the proposed models. Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static and dynamic neural networks. Results showed that the MLP-NN neural network model is able to follow trends of the actual rainfall, however, not very accurately. RBFNN model achieved better accuracy than the MLP-NN model. Moreover, the forecasting accuracy of the IDNN model was better than that of static network during both training and testing stages, which proves a consistent level of accuracy with seen and unseen data.
4
Journal, Baghdad Science. "Using Neural Network with Speaker Applications." Baghdad Science Journal 7, no. 2 (2010): 1076–81. http://dx.doi.org/10.21123/bsj.7.2.1076-1081.
Full textAbstract:
In Automatic Speech Recognition (ASR) the non-linear data projection provided by a one hidden layer Multilayer Perceptron (MLP), trained to recognize phonemes, and has previous experiments to provide feature enhancement substantially increased ASR performance, especially in noise. Previous attempts to apply an analogous approach to speaker identification have not succeeded in improving performance, except by combining MLP processed features with other features. We present test results for the TIMIT database which show that the advantage of MLP preprocessing for open set speaker identification increases with the number of speakers used to train the MLP and that improved identification is obtained as this number increases beyond sixty. We also present a method for selecting the speakers used for MLP training which further improves identification performance.
5
Mazher, Alaa noori, and Samira faris Khlibs. "Using Neural Network with Speaker Applications." Baghdad Science Journal 7, no. 2 (2010): 1076–81. http://dx.doi.org/10.21123/bsj.2010.7.2.1076-1081.
Full textAbstract:
In Automatic Speech Recognition (ASR) the non-linear data projection provided by a one hidden layer Multilayer Perceptron (MLP), trained to recognize phonemes, and has previous experiments to provide feature enhancement substantially increased ASR performance, especially in noise. Previous attempts to apply an analogous approach to speaker identification have not succeeded in improving performance, except by combining MLP processed features with other features. We present test results for the TIMIT database which show that the advantage of MLP preprocessing for open set speaker identification increases with the number of speakers used to train the MLP and that improved identification is obtained as this number increases beyond sixty. We also present a method for selecting the speakers used for MLP training which further improves identification performance.
6
El-Shafie, A., A. Noureldin, M. R. Taha, and A. Hussain. "Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia." Hydrology and Earth System Sciences Discussions 8, no. 4 (2011): 6489–532. http://dx.doi.org/10.5194/hessd-8-6489-2011.
Full textAbstract:
Abstract. Rainfall is considered as one of the major component of the hydrological process, it takes significant part of evaluating drought and flooding events. Therefore, it is important to have accurate model for rainfall forecasting. Recently, several data-driven modeling approaches have been investigated to perform such forecasting task such as Multi-Layer Perceptron Neural Networks (MLP-NN). In fact, the rainfall time series modeling involves an important temporal dimension. On the other hand, the classical MLP-NN is a static and memoryless network architecture that is effective for complex nonlinear static mapping. This research focuses on investigating the potential of introducing a neural network that could address the temporal relationships of the rainfall series. Two different static neural networks and one dynamic neural network namely; Multi-Layer Peceptron Neural network (MLP-NN), Radial Basis Function Neural Network (RBFNN) and Input Delay Neural Network (IDNN), respectively, have been examined in this study. Those models had been developed for two time horizon in monthly and weekly rainfall basis forecasting at Klang River, Malaysia. Data collected over 12 yr (1997–2008) on weekly basis and 22 yr (1987–2008) for monthly basis were used to develop and examine the performance of the proposed models. Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static and dynamic neural network. Results showed that MLP-NN neural network model able to follow the similar trend of the actual rainfall, yet it still relatively poor. RBFNN model achieved better accuracy over the MLP-NN model. Moreover, the forecasting accuracy of the IDNN model outperformed during training and testing stage which prove a consistent level of accuracy with seen and unseen data. Furthermore, the IDNN significantly enhance the forecasting accuracy if compared with the other static neural network model as they could memorize the sequential or time varying patterns.
7
Wongsathan, Rati, and Pasit Pothong. "Heart Disease Classification Using Artificial Neural Networks." Applied Mechanics and Materials 781 (August 2015): 624–27. http://dx.doi.org/10.4028/www.scientific.net/amm.781.624.
Full textAbstract:
Neural Networks (NNs) has emerged as an importance tool for classification in the field of decision making. The main objective of this work is to design the structure and select the optimized parameter in the neural networks to implement the heart disease classifier. Three types of neural networks, i.e. Multi-layered Perceptron Neural Network (MLP-NN), Radial Basis Function Neural Networks (RBF-NN), and Generalized Regression Neural Network (GR-NN) have been used to test the performance of heart disease classification. The classification accuracy obtained by RBFNN gave a very high performance than MLP-NN and GR-NN respectively. The performance of accuracy is very promising compared with the previously reported another type of neural networks.
8
Kovács, László. "Classification Improvement with Integration of Radial Basis Function and Multilayer Perceptron Network Architectures." Mathematics 13, no. 9 (2025): 1471. https://doi.org/10.3390/math13091471.
Full textAbstract:
The radial basis function architecture and the multilayer perceptron architecture are very different approaches to neural networks in theory and practice. Considering their classification efficiency, both have different strengths; thus, the integration of these tools is an interesting but understudied problem domain. This paper presents a novel initialization method based on a distance-weighted homogeneity measure to construct a radial basis function network with fast convergence. The proposed radial basis function network is utilized in the development of an integrated RBF-MLP architecture. The proposed neural network model was tested in various classification tasks and the test results show superiority of the proposed architecture. The RBF-MLP model achieved nearly 40 percent better accuracy in the tests than the baseline MLP or RBF neural network architectures.
9
Lazri, Mourad, Fethi Ouallouche, Karim Labadi, and Soltane Ameur. "Extreme Learning Machine versus Multilayer perceptron for rainfall estimation from MSG Data." E3S Web of Conferences 353 (2022): 01006. http://dx.doi.org/10.1051/e3sconf/202235301006.
Full textAbstract:
The application of artificial neural networks (ANN) in several fields has shown considerable success for classification or regression. Learning algorithms such as artificial neural networks must constantly readjust during the learning phase. This requires a relatively long learning time compared to the size and dimension of the data used. Contrary to these considerations, a new neural network, such as Extreme Learning Machine (ELM) has recently been implemented. The ELM does not care much about the size of the neural network, the hidden layer parameters are randomly generated and remain constant instead of being adjusted during training. In this paper, we will present a comparison between two neural networks, namely ELM and MLP (Multilayer perceptron) implemented for the precipitation estimation from meteorological satellite data. The architecture chosen for the two neural networks consists of an input layer (7 neurons), a hidden layer (8 neurons) and an output layer (7 neurons). The MLP has undergone standard training as soon as the ELM is trained according to the characteristics mentioned above. The results show that MLP prevails over ELM. However, the time cost during learning is too high for MLP compared to ELM.
10
Mohmad Hassim, Yana Mazwin, and Rozaida Ghazali. "Using Artificial Bee Colony to Improve Functional Link Neural Network Training." Applied Mechanics and Materials 263-266 (December 2012): 2102–8. http://dx.doi.org/10.4028/www.scientific.net/amm.263-266.2102.
Full textAbstract:
Artificial Neural Networks have emerged as an important tool for classification and have been widely used to classify non-linearly separable pattern. The most popular artificial neural networks model is a Multilayer Perceptron (MLP) that is able to perform classification task with significant success. However due to the complexity of MLP structure and also problems such as local minima trapping, over fitting and weight interference have made neural network training difficult. Thus, the easy way to avoid these problems is by removing the hidden layers. This paper presents the ability of Functional Link Neural Network (FLNN) in overcoming the complexity structure of MLP, using it single layer architecture and proposes an Artificial Bee Colony (ABC) optimization for training the FLNN. The proposed technique is expected to provide better learning scheme for a classifier in order to get more accurate classification result.
Dissertations / Theses on the topic "Neural network MLP"
1
Freitas, Luciana Paro Scarin [UNESP]. "Discriminação entre pacientes normais e hemiplégicos utilizando plataforma de força e redes neurais." Universidade Estadual Paulista (UNESP), 2011. http://hdl.handle.net/11449/87051.
Full textAbstract:
Made available in DSpace on 2014-06-11T19:22:31Z (GMT). No. of bitstreams: 0
Previous issue date: 2011-12-02Bitstream added on 2014-06-13T19:48:52Z : No. of bitstreams: 1
freitas_lps_me_ilha.pdf: 463364 bytes, checksum: 35c3a3450e5ec638595c65e3a7508c09 (MD5)<br>Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)<br>Neste trabalho descreve-se o desenvolvimento de duas redes neurais que identificam e classificam dados da distribuição do peso corporal na região plantar de pessoas normais e hemiplégicas. Esses dados são experimentais e foram obtidos através da utilização de uma plataforma de força contendo 48 sensores. As arquiteturas utilizadas para esta aplicação foram as redes neurais MLP (Multilayer Perceptron) com o algoritmo retropropagação (backpropagation), e ARTMAP Nebulosa. A escolha de tais arquiteturas se deve ao treinamento (supervisionado) o qual associa de forma direta a distribuição de força plantar com os respectivos pacientes (normais e hemiplégicos). Ambas as arquiteturas, MLP e ARTMAP Nebulosa, conseguiram fazer a discriminação entre quase todas as pessoas normais e hemiplégicos. A rede neural ARTMAP Nebulosa possui a vantagem de efetuar a classificação de forma rápida e eficiente. Esta aplicação é importante nas áreas de Podologia, Posturologia e Podoposturologia, pois propicia ao profissional de saúde uma nova metodologia de diagnóstico<br>This work describes the development of two neural networks that identify and classify data distribution of plantar body weight of normal or hemiplegic individuals. The architectures used for this application were, respectively, MLP neural networks (Multilayer Perceptron) with backpropagation algorithm, and Fuzzy ARTMAP. The choice of such architectures was due to the training (supervised training) which directly associates the distribution of plantar force with the patients (normal or hemiplegic). The input data used for training and diagnosis of the neural networks were obtained from a force plate, with 48 sensors, containing measurements of the weight distribution on the plantar region (right and left) of normal or hemiplegic patients. Both architectures, MLP and Fuzzy ARTMAP, were able to discriminate almost all normal and hemiplegic patients. The Fuzzy ARTMAP neural network was more efficient than MLP neural network in the classification of the patients. This application is important in areas of Podiatry, Posturology and Podoposturology because it can help the health care professionals
2
Freitas, Luciana Paro Scarin. "Discriminação entre pacientes normais e hemiplégicos utilizando plataforma de força e redes neurais /." Ilha Solteira : [s.n.], 2011. http://hdl.handle.net/11449/87051.
Full textAbstract:
Orientador: Marcelo Carvalho Minhoto Teixeira<br>Banca: Aparecido Augusto de Carvalho<br>Banca: Márcio Roberto Covacic<br>Resumo: Neste trabalho descreve-se o desenvolvimento de duas redes neurais que identificam e classificam dados da distribuição do peso corporal na região plantar de pessoas normais e hemiplégicas. Esses dados são experimentais e foram obtidos através da utilização de uma plataforma de força contendo 48 sensores. As arquiteturas utilizadas para esta aplicação foram as redes neurais MLP (Multilayer Perceptron) com o algoritmo retropropagação (backpropagation), e ARTMAP Nebulosa. A escolha de tais arquiteturas se deve ao treinamento (supervisionado) o qual associa de forma direta a distribuição de força plantar com os respectivos pacientes (normais e hemiplégicos). Ambas as arquiteturas, MLP e ARTMAP Nebulosa, conseguiram fazer a discriminação entre quase todas as pessoas normais e hemiplégicos. A rede neural ARTMAP Nebulosa possui a vantagem de efetuar a classificação de forma rápida e eficiente. Esta aplicação é importante nas áreas de Podologia, Posturologia e Podoposturologia, pois propicia ao profissional de saúde uma nova metodologia de diagnóstico<br>Abstract: This work describes the development of two neural networks that identify and classify data distribution of plantar body weight of normal or hemiplegic individuals. The architectures used for this application were, respectively, MLP neural networks (Multilayer Perceptron) with backpropagation algorithm, and Fuzzy ARTMAP. The choice of such architectures was due to the training (supervised training) which directly associates the distribution of plantar force with the patients (normal or hemiplegic). The input data used for training and diagnosis of the neural networks were obtained from a force plate, with 48 sensors, containing measurements of the weight distribution on the plantar region (right and left) of normal or hemiplegic patients. Both architectures, MLP and Fuzzy ARTMAP, were able to discriminate almost all normal and hemiplegic patients. The Fuzzy ARTMAP neural network was more efficient than MLP neural network in the classification of the patients. This application is important in areas of Podiatry, Posturology and Podoposturology because it can help the health care professionals<br>Mestre
3
Zhang, Jiaqi. "Accelerating and Predicting Map Projections with CUDA and MLP." The Ohio State University, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=osu1523394255002174.
Full text
4
Steinholtz, Tim. "Skip connection in a MLP network for Parkinson’s classification." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-303130.
Full textAbstract:
In this thesis, two different architecture designs of a Multi-Layer Perceptron network have been implemented. One architecture being an ordinary MLP, and in the other adding DenseNet inspired skip connections to an MLP architecture. The models were used and evaluated on the classification task, where the goal was to classify if subjects were diagnosed with Parkinson’s disease or not based on vocal features. The models were trained on an openly available dataset for Parkinson’s classification and evaluated on a hold-out set from this dataset and on two datasets recorded in another sound recording environment than the training data. The thesis searched for the answer to two questions; How insensitive models for Parkinson’s classification are to the sound recording environment and how the proposed skip connections in an MLP model could help improve performance and generalization capacity. The thesis results show that the sound environment affects the accuracy. Nevertheless, it concludes that one would be able to overcome this with more time and allow for good accuracy when models are exposed to data from a new sound environment than the training data. As for the question, if the skip connections improve accuracy and generalization, the thesis cannot draw any broad conclusions due to the data that were used. The models had, in general, the best performance with shallow networks, and it is with deeper networks that the skip connections are argued to help improve these attributes. However, when evaluating on the data from a different sound recording environment than the training data, the skip connections had the best performance in two out of three tests.<br>I denna avhandling har två olika arkitektur designer för ett artificiellt flerskikts neuralt nätverk implementerats. En arkitektur som följer konventionen för ett vanlig MLP nätverk, samt en ny arkitektur som introducerar DenseNet inspirerade genvägs kopplingar i MLP nätverk. Modellerna användes och utvärderades för klassificering, vars mål var att urskilja försökspersoner som friska eller diagnostiserade med Parkinsons sjukdom baserat på röst attribut. Modellerna tränades på ett öppet tillgänglig dataset för Parkinsons klassificering och utvärderades på en delmängd av denna data som inte hade använts för träningen, samt två dataset som kommer från en annan ljudinspelnings miljö än datan för träningen. Avhandlingen sökte efter svaret på två frågor; Hur okänsliga modeller för Parkinsons klassificering är för ljudinspelnings miljön och hur de föreslagna genvägs kopplingarna i en MLP-modell kan bidra till att förbättra prestanda och generalisering kapacitet. Resultaten av avhandlingen visar att ljudmiljön påverkar noggrannheten, men drar slutsatsen att med mer tid skulle man troligen kunna övervinna detta och möjliggöra god noggrannhet i nya ljudmiljöer. När det kommer till om genvägs kopplingarna förbättrar noggrannhet och generalisering, är avhandlingen inte i stånd att dra några breda slutsatser på grund av den data som användes. Modellerna hade generellt bästa prestanda med grunda nätverk, och det är i djupare nätverk som genvägs kopplingarna argumenteras för att förbättra dessa egenskaper. Med det sagt, om man bara kollade på resultaten på datan som är ifrån en annan ljudinspelnings miljö så hade genvägs arkitekturen bättre resultat i två av de tre testerna som utfördes.
5
Jin, Xin. "Parallel simulation of neural networks on SpiNNaker universal neuromorphic hardware." Thesis, University of Manchester, 2010. https://www.research.manchester.ac.uk/portal/en/theses/parallel-simulation-of-neural-networks-on-spinnaker-universal-neuromorphic-hardware(d6b8b72a-63c4-44ee-963a-ae349b0e379c).html.
Full textAbstract:
Artificial neural networks have shown great potential and have attracted much research interest. One problem faced when simulating such networks is speed. As the number of neurons increases, the time to simulate and train a network increases dramatically. This makes it difficult to simulate and train a large-scale network system without the support of a high-performance computer system. The solution we present is a "real" parallel system - using a parallel machine to simulate neural networks which are intrinsically parallel applications. SpiNNaker is a scalable massively-parallel computing system under development with the aim of building a general-purpose platform for the parallel simulation of large-scale neural systems. This research investigates how to model large-scale neural networks efficiently on such a parallel machine. While providing increased overall computational power, a parallel architecture introduces a new problem - the increased communication reduces the speedup gains. Modeling schemes, which take into account communication, processing, and storage requirements, are investigated to solve this problem. Since modeling schemes are application-dependent, two different types of neural network are examined - spiking neural networks with spike-time dependent plasticity, and the parallel distributed processing model with the backpropagation learning rule. Different modeling schemes are developed and evaluated for the two types of neural network. The research shows the feasibility of the approach as well as the performance of SpiNNaker as a general-purpose platform for the simulation of neural networks. The linear scalability shown in this architecture provides a path to the further development of parallel solutions for the simulation of extremely large-scale neural networks.
6
Mendes, José da Assunção Gomes. "RECONHECIMENTO DA FALA SUBVOCAL BASEADO EM ELETROMIOGRAFIA DE SUPERFÍCIE (EMG) UTILIZANDO ANÁLISE DE COMPONENTES INDEPENDENTES (ICA) E REDE NEURAL MLP." Universidade Federal do Maranhão, 2007. http://tedebc.ufma.br:8080/jspui/handle/tede/284.
Full textAbstract:
Made available in DSpace on 2016-08-17T14:52:36Z (GMT). No. of bitstreams: 1
Jose da Assuncao Gomes Mendes.pdf: 1427998 bytes, checksum: 6d9df0350d0b7acb752ecadbcfc1825d (MD5)
Previous issue date: 2007-12-19<br>The performance of speech recognition systems is commonly degraded by either
speech-related disabilities or by real-world factors such as the environment s noise
level and reverberation. In this research, we propose a subvocal speech recognition
system based on electromyography (EMG signal) for subvocal acquisition,
Independent Component Analysis (ICA) for feature extraction and Neural Networks
MLP for classification. We have evaluated the system s performance using a
subvocal vowel phonemes database. According to the results, the methodology
proposed obtained a success rate of 93.99%.<br>O desempenho dos sistemas de reconhecimento da fala é comumente degradado
por incapacidades relacionadas com a fala ou por através de fatores do mundo real
tais como nível de ruído do ambiente e reverberação. Nesta pesquisa, nós propomos
um sistema de reconhecimento subvocal da fala. Este sistema é baseado em
Eletromiografia de superfície (sinal EMG) para aquisição de dados subvocais,
Análise de Componentes Independentes (ICA) para extração das características e
Rede Neural MLP para classificação. Nós avaliamos o desempenho do sistema
usando um banco de dados dos fonemas das vogais subvocais. De acordo com os
resultados obtidos, a metodologia proposta obteve uma taxa de sucesso de 93,99%.
7
NINA, Diogo Luis Figueiredo. "Análise de Ocorrências em Transformadores do SDEE usando Redes Neurais Artificiais MLP." Universidade Federal do Maranhão, 2012. http://tedebc.ufma.br:8080/jspui/handle/tede/1863.
Full textAbstract:
Submitted by Maria Aparecida (cidazen@gmail.com) on 2017-08-24T14:18:42Z
No. of bitstreams: 1
Diogo Luis.pdf: 4371869 bytes, checksum: adf1274b2033821c3c2a6cca3766a2e6 (MD5)<br>Made available in DSpace on 2017-08-24T14:18:42Z (GMT). No. of bitstreams: 1
Diogo Luis.pdf: 4371869 bytes, checksum: adf1274b2033821c3c2a6cca3766a2e6 (MD5)
Previous issue date: 2012-10-03<br>Power system operation and maintenance require attention, precise diagnostics
on failure and agility on system recovery. On the other hand, power systems involve high risks, where each operation needs to be carefully planned and executed,
once errors can be fatal. Power system satisfactory operation and maintenance
consist on finding equilibrium between these extremes, acting on a cautious, but
agile, way. For this purpose, we propose the development of an intelligent system
with the ability of detecting abnormal patterns on the electrical signal, providing
support for decisions on Power Distribution System real time operation, from the
analysis of power substation transformers primary and secondary currents, including learning at each new information acquired by the system. The challenge of this
study is to research and develop a method based on ANN for classifying patterns
and providing support for decisions, aiming fault detection and/or fault recovery.
The method di↵erentiates disturbances that will lead to faults from disturbances
generated by transients on power system (for example an undervoltage caused by
powering on an engine). A SCADA supervisory system was developed to contain ANN implementation code and also to provide an interface for Operators,
generating visual and sound alarms and messages guiding system recovery. The
proposed method was evaluated using real data collected from transformers protection digital relays of CEMAR system substations, achieving excellent results.
The ANN developed on this study presented satisfactory performance classifying
signals and detecting faults properly.<br>A operação e manutenção do sistema elétrico requerem atenção, diagnósticos
precisos em caso de falhas e agilidade na recomposição do sistema. Por outro
lado, sistemas elétricos têm um elevado risco, onde cada manobra precisa ser cuidadosamente planejada e executada, pois erros podem ser fatais. A boa operação
e manutenção do sistema elétrico consistem em encontrar o ponto de equilíbrio
entre esses dois extremos, atuando de forma cautelosa, porém ágil. Com esse
intuito, propomos o desenvolvimento de um sistema inteligente dotado da capacidade de detectar padrões anormais no sinal elétrico, fornecendo apoio à decisão
na operação em tempo real do SDEE, a partir da análise das correntes primárias
e secundárias de transformadores de força de subestações de energia elérica, incluindo aprendizado a cada nova informação integrada ao sistema. O desafio deste
estudo é pesquisar e desenvolver um método baseado em RNA para classificação
de padrões e apoio à decisão, visando a detecção e/ou recuperaçao de falhas. O
método diferencia perturbações que culminarão em uma falta de perturbações
geradas por transitórios na rede elétrica (por exemplo o afundamento de tensão
gerado pela partida de uma máquina). Um sistema supervisório SCADA foi desenvolvido para hospedar o código de implementação da RNA, além de fornecer
uma interface para o Operador, gerando alarmes visuais e sonoros e mensagens
orientando a retomada do sistema. O método proposto foi avaliado utilizando-se
dados reais coletados diretamente de relés digitais de proteção de transformadores
de subestações do sistema da CEMAR, obtendo-se excelentes resultados. A RNA
desenvolvida neste estudo apresentou desempenho satisfatório na classificação dos
sinais a ela apresentados, detectando corretamente as faltas.
8
Bhat, Chandrashekhar. "Artificial Neural Network Approach For Characterization Of Acoustic Emission Sources From Complex Noisy Data." Thesis, Indian Institute of Science, 2001. https://etd.iisc.ac.in/handle/2005/251.
Full textAbstract:
Safety and reliability are prime concerns in aircraft performance due to the involved costs and risk to lives. Despite the best efforts in design methodology, quality evaluation in production and structural integrity assessment in-service, attainment of one hundred percent safety through development and use of a suitable in-flight health monitoring system is still a farfetched goal. And, evolution of such a system requires, first, identification of an appropriate Technique and next its adoption to meet the challenges posed by newer materials (advanced composites), complex structures and the flight environment. In fact, a quick survey of the available Non-Destructive Evaluation (NDE) techniques suggests Acoustic Emission (AE) as the only available method. High merit in itself could be a weakness - Noise is the worst enemy of AE. So, while difficulties are posed due to the insufficient understanding of the basic behavior of composites, growth and interaction of defects and damage under a specified load condition, high in-flight noise further complicates the issue making the developmental task apparently formidable and challenging.
Development of an in-flight monitoring system based on AE to function as an early warning system needs addressing three aspects, viz., the first, discrimination of AE signals from noise data, the second, extraction of required information from AE signals for identification of sources (source characterization) and quantification of its growth, and the third, automation of the entire process. And, a quick assessment of the aspects involved suggests that Artificial Neural Networks (ANN) are ideally suited for solving such a complex problem. A review of the available open literature while indicates a number of investigations carried out using noise elimination and source characterization methods such as frequency filtering and statistical pattern recognition but shows only sporadic attempts using ANN. This may probably be due to the complex nature of the problem involving investigation of a large number of influencing parameters, amount of effort and time to be invested, and facilities required and multi-disciplinary nature of the problem. Hence as stated in the foregoing, the need for such a study cannot be over emphasized.
Thus, this thesis is an attempt addressing the issue of analysis and automation of complex sets of AE data such as AE signals mixed with in-flight noise thus forming the first step towards in-flight monitoring using AE. An ANN can in fact replace the traditional algorithmic approaches used in the past. ANN in general are model free estimators and derive their computational efficiency due to large connectivity, massive parallelism, non-linear analog response and learning capabilities. They are better suited than the conventional methods (statistical pattern recognition methods) due to their characteristics such as classification, pattern matching, learning, generalization, fault tolerance and distributed memory and their ability to process unstructured data sets which may be carrying incomplete information at times and hence chosen as the tool. Further, in the current context, the set of investigations undertaken were in the absence of sufficient a priori information and hence clustering of signals generated by AE sources through self-organizing maps is more appropriate. Thus, in the investigations carried out under the scope of this thesis, at first a hybrid network named "NAEDA" (Neural network for Acoustic Emission Data Analysis) using Kohonen self-organizing feature map (KSOM) and multi-layer perceptron (MLP) that learns on back propagation learning rule was specifically developed with innovative data processing techniques built into the network. However, for accurate pattern recognition, multi-layer back propagation NN needed to be trained with source and noise clusters as input data. Thus, in addition to optimizing the network architecture and training parameters, preprocessing of input data to the network and multi-class clustering and classification proved to be the corner stones in obtaining excellent identification accuracy.
Next, in-flight noise environment of an aircraft was generated off line through carefully designed simulation experiments carried out in the laboratory (Ex: EMI, friction, fretting and other mechanical and hydraulic phenomena) based on the in-flight noise survey carried out by earlier investigators. From these experiments data was acquired and classified into their respective classes through MLP. Further, these noises were mixed together and clustered through KSOM and then classified into their respective clusters through MLP resulting in an accuracy of 95%- 100%
Subsequently, to evaluate the utility of NAEDA for source classification and characterization, carbon fiber reinforced plastic (CFRP) specimens were subjected to spectrum loading simulating typical in-flight load and AE signals were acquired continuously up to a maximum of three designed lives and in some cases up to failure. Further, AE signals with similar characteristics were grouped into individual clusters through self-organizing map and labeled as belonging to appropriate failure modes, there by generating the class configuration. Then MLP was trained with this class information, which resulted in automatic identification and classification of failure modes with an accuracy of 95% - 100%. In addition, extraneous noise generated during the experiments was acquired and classified so as to evaluate the presence or absence of such data in the AE data acquired from the CFRP specimens.
In the next stage, noise and signals were mixed together at random and were reclassified into their respective classes through supervised training of multi-layer back propagation NN. Initially only noise was discriminated from the AE signals from CFRP failure modes and subsequently both noise discrimination and failure mode identification and classification was carried out resulting in an accuracy of 95% - 100% in most of the cases. Further, extraneous signals mentioned above were classified which indicated the presence of such signals in the AE signals obtained from the CFRP specimen.
Thus, having established the basis for noise identification and AE source classification and characterization, two specific examples were considered to evaluate the utility and efficiency of NAEDA. In the first, with the postulation that different basic failure modes in composites have unique AE signatures, the difference in damage generation and progression can be clearly characterized under different loading conditions. To examine this, static compression tests were conducted on a different set of CFRP specimens till failure with continuous AE monitoring and the resulting AE signals were classified through already trained NAEDA. The results obtained shows that the total number of signals obtained were very less when compared to fatigue tests and the specimens failed with hardly any damage growth. Further, NAEDA was able to discriminate the"noise and failure modes in CFRP specimen with the same degree of accuracy with which it has classified such signals obtained from fatigue tests.
In the second example, with the same postulate of unique AE signatures for different failure modes, the differences in the complexion of the damage growth and progression should become clearly evident when one considers specimens with different lay up sequences. To examine this, the data was reclassified on the basis of differences in lay up sequences from specimens subjected to fatigue. The results obtained clearly confirmed the postulation.
As can be seen from the summary of the work presented in the foregoing paragraphs, the investigations undertaken within the scope of this thesis involve elaborate experimentation, development of tools, acquisition of extensive data and analysis. Never the less, the results obtained were commensurate with the efforts and have been fruitful. Of the useful results that have been obtained, to state in specific, the first is, discrimination of simulated noise sources achieved with significant success but for some overlapping which is not of major concern as far as noises are concerned. Therefore they are grouped into required number of clusters so as to achieve better classification through supervised NN. This proved to be an innovative measure in supervised classification through back propagation NN.
The second is the damage characterization in CFRP specimens, which involved imaginative data processing techniques that proved their worth in terms of optimization of various training parameters and resulted in accurate identification through clustering. Labeling of clusters is made possible by marking each signal starting from clustering to final classification through supervised neural network and is achieved through phenomenological correlation combined with ultrasonic imaging.
Most rewarding of all is the identification of failure modes (AE signals) mixed in noise into their respective classes. This is a direct consequence of innovative data processing, multi-class clustering and flexibility of grouping various noise signals into suitable number of clusters.
Thus, the results obtained and presented in this thesis on NN approach to AE signal analysis clearly establishes the fact that methods and procedures developed can automate detection and identification of failure modes in CFRP composites under hostile environment, which could lead to the development of an in-flight monitoring system.
9
Bhat, Chandrashekhar. "Artificial Neural Network Approach For Characterization Of Acoustic Emission Sources From Complex Noisy Data." Thesis, Indian Institute of Science, 2001. http://hdl.handle.net/2005/251.
Full textAbstract:
Safety and reliability are prime concerns in aircraft performance due to the involved costs and risk to lives. Despite the best efforts in design methodology, quality evaluation in production and structural integrity assessment in-service, attainment of one hundred percent safety through development and use of a suitable in-flight health monitoring system is still a farfetched goal. And, evolution of such a system requires, first, identification of an appropriate Technique and next its adoption to meet the challenges posed by newer materials (advanced composites), complex structures and the flight environment. In fact, a quick survey of the available Non-Destructive Evaluation (NDE) techniques suggests Acoustic Emission (AE) as the only available method. High merit in itself could be a weakness - Noise is the worst enemy of AE. So, while difficulties are posed due to the insufficient understanding of the basic behavior of composites, growth and interaction of defects and damage under a specified load condition, high in-flight noise further complicates the issue making the developmental task apparently formidable and challenging.
Development of an in-flight monitoring system based on AE to function as an early warning system needs addressing three aspects, viz., the first, discrimination of AE signals from noise data, the second, extraction of required information from AE signals for identification of sources (source characterization) and quantification of its growth, and the third, automation of the entire process. And, a quick assessment of the aspects involved suggests that Artificial Neural Networks (ANN) are ideally suited for solving such a complex problem. A review of the available open literature while indicates a number of investigations carried out using noise elimination and source characterization methods such as frequency filtering and statistical pattern recognition but shows only sporadic attempts using ANN. This may probably be due to the complex nature of the problem involving investigation of a large number of influencing parameters, amount of effort and time to be invested, and facilities required and multi-disciplinary nature of the problem. Hence as stated in the foregoing, the need for such a study cannot be over emphasized.
Thus, this thesis is an attempt addressing the issue of analysis and automation of complex sets of AE data such as AE signals mixed with in-flight noise thus forming the first step towards in-flight monitoring using AE. An ANN can in fact replace the traditional algorithmic approaches used in the past. ANN in general are model free estimators and derive their computational efficiency due to large connectivity, massive parallelism, non-linear analog response and learning capabilities. They are better suited than the conventional methods (statistical pattern recognition methods) due to their characteristics such as classification, pattern matching, learning, generalization, fault tolerance and distributed memory and their ability to process unstructured data sets which may be carrying incomplete information at times and hence chosen as the tool. Further, in the current context, the set of investigations undertaken were in the absence of sufficient a priori information and hence clustering of signals generated by AE sources through self-organizing maps is more appropriate. Thus, in the investigations carried out under the scope of this thesis, at first a hybrid network named "NAEDA" (Neural network for Acoustic Emission Data Analysis) using Kohonen self-organizing feature map (KSOM) and multi-layer perceptron (MLP) that learns on back propagation learning rule was specifically developed with innovative data processing techniques built into the network. However, for accurate pattern recognition, multi-layer back propagation NN needed to be trained with source and noise clusters as input data. Thus, in addition to optimizing the network architecture and training parameters, preprocessing of input data to the network and multi-class clustering and classification proved to be the corner stones in obtaining excellent identification accuracy.
Next, in-flight noise environment of an aircraft was generated off line through carefully designed simulation experiments carried out in the laboratory (Ex: EMI, friction, fretting and other mechanical and hydraulic phenomena) based on the in-flight noise survey carried out by earlier investigators. From these experiments data was acquired and classified into their respective classes through MLP. Further, these noises were mixed together and clustered through KSOM and then classified into their respective clusters through MLP resulting in an accuracy of 95%- 100%
Subsequently, to evaluate the utility of NAEDA for source classification and characterization, carbon fiber reinforced plastic (CFRP) specimens were subjected to spectrum loading simulating typical in-flight load and AE signals were acquired continuously up to a maximum of three designed lives and in some cases up to failure. Further, AE signals with similar characteristics were grouped into individual clusters through self-organizing map and labeled as belonging to appropriate failure modes, there by generating the class configuration. Then MLP was trained with this class information, which resulted in automatic identification and classification of failure modes with an accuracy of 95% - 100%. In addition, extraneous noise generated during the experiments was acquired and classified so as to evaluate the presence or absence of such data in the AE data acquired from the CFRP specimens.
In the next stage, noise and signals were mixed together at random and were reclassified into their respective classes through supervised training of multi-layer back propagation NN. Initially only noise was discriminated from the AE signals from CFRP failure modes and subsequently both noise discrimination and failure mode identification and classification was carried out resulting in an accuracy of 95% - 100% in most of the cases. Further, extraneous signals mentioned above were classified which indicated the presence of such signals in the AE signals obtained from the CFRP specimen.
Thus, having established the basis for noise identification and AE source classification and characterization, two specific examples were considered to evaluate the utility and efficiency of NAEDA. In the first, with the postulation that different basic failure modes in composites have unique AE signatures, the difference in damage generation and progression can be clearly characterized under different loading conditions. To examine this, static compression tests were conducted on a different set of CFRP specimens till failure with continuous AE monitoring and the resulting AE signals were classified through already trained NAEDA. The results obtained shows that the total number of signals obtained were very less when compared to fatigue tests and the specimens failed with hardly any damage growth. Further, NAEDA was able to discriminate the"noise and failure modes in CFRP specimen with the same degree of accuracy with which it has classified such signals obtained from fatigue tests.
In the second example, with the same postulate of unique AE signatures for different failure modes, the differences in the complexion of the damage growth and progression should become clearly evident when one considers specimens with different lay up sequences. To examine this, the data was reclassified on the basis of differences in lay up sequences from specimens subjected to fatigue. The results obtained clearly confirmed the postulation.
As can be seen from the summary of the work presented in the foregoing paragraphs, the investigations undertaken within the scope of this thesis involve elaborate experimentation, development of tools, acquisition of extensive data and analysis. Never the less, the results obtained were commensurate with the efforts and have been fruitful. Of the useful results that have been obtained, to state in specific, the first is, discrimination of simulated noise sources achieved with significant success but for some overlapping which is not of major concern as far as noises are concerned. Therefore they are grouped into required number of clusters so as to achieve better classification through supervised NN. This proved to be an innovative measure in supervised classification through back propagation NN.
The second is the damage characterization in CFRP specimens, which involved imaginative data processing techniques that proved their worth in terms of optimization of various training parameters and resulted in accurate identification through clustering. Labeling of clusters is made possible by marking each signal starting from clustering to final classification through supervised neural network and is achieved through phenomenological correlation combined with ultrasonic imaging.
Most rewarding of all is the identification of failure modes (AE signals) mixed in noise into their respective classes. This is a direct consequence of innovative data processing, multi-class clustering and flexibility of grouping various noise signals into suitable number of clusters.
Thus, the results obtained and presented in this thesis on NN approach to AE signal analysis clearly establishes the fact that methods and procedures developed can automate detection and identification of failure modes in CFRP composites under hostile environment, which could lead to the development of an in-flight monitoring system.
10
Ridhagen, Markus, and Petter Lind. "A comparative study of Neural Network Forecasting models on the M4 competition data." Thesis, Uppsala universitet, Statistiska institutionen, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-445568.
Full textAbstract:
The development of machine learning research has provided statistical innovations and further developments within the field of time series analysis. This study seeks to investigate two different approaches on artificial neural network models based on different learning techniques, and answering how well the neural network approach compares with a basic autoregressive approach, as well as how the artificial neural network models compare to each other. The models were compared and analyzed in regards to the univariate forecast accuracy on 20 randomly drawn time series from two different time frequencies from the M4 competition dataset. Forecasting was made dependent on one time lag (t-1) and forecasted three and six steps ahead respectively. The artificial neural network models outperformed the baseline Autoregressive model, showing notably lower mean average percentage error overall. The Multilayered perceptron models performed better than the Long short-term memory model overall, whereas the Long short-term memory model showed improvement on longer prediction time dimensions. As the training were done univariately on a limited set of time steps, it is believed that the one layered-approach gave a good enough approximation on the data, whereas the added layer couldn’t fully utilize its strengths of processing power. Likewise, the Long short-term memory model couldn’t fully demonstrate the advantagements of recurrent learning. Using the same dataset, further studies could be made with another approach to data processing. Implementing an unsupervised approach of clustering the data before analysis, the same models could be tested with multivariate analysis on models trained on multiple time series simultaneously.
Books on the topic "Neural network MLP"
2
C, Jorgensen Charles, and Ames Research Center, eds. Toward a more robust pruning procedure for MLP networks. National Aeronautics and Space Administration, Ames Research Center, 1998.
Find full text
3
Rhys, Hefin. Machine Learning with R, the Tidyverse, and Mlr. Manning Publications Co. LLC, 2020.
Find full text
4
IEEE Signal Processing Society. 2005 IEEE Workshop on Machine Learning for Signal Processing (Mlsp): Mystic, CT, September 28-30, 2005. IEEE Operations Center, 2005.
Find full text
5
Selverston, Allen. Rhythms and oscillations. Oxford University Press, 2018. http://dx.doi.org/10.1093/oso/9780199674923.003.0021.
Full textAbstract:
The study of identifiable neurons, a common feature of invertebrate nervous systems, has made it possible to construct a detailed cell-to-cell connectivity map using electrophysiological methods that can inspire the design of biomimetic systems. This chapter describes how the analysis of the neural circuitry in the lobster stomatogastric ganglion (STG) has provided some general principles underlying oscillatory and rhythmic behavior in all animals. The rhythmic and oscillatory patterns produced by the two STG central pattern generating (CPG) circuits are a result of two cooperative mechanisms, intrinsically bursting pacemaker neurons and synaptic network properties. Also covered are the major neuromodulatory and neural control mechanisms. The chapter discusses how a deep knowledge of the stomatogastric circuitry has led to the development of electronic neurons for biomimetic devices that can be used for experimental and prosthetic applications The chapter concludes with a section on new techniques that may help with unraveling oscillatory circuits in the brain.
6
Buetefisch, Cathrin M., and Leonardo G. Cohen. Use-dependent changes in TMS measures. Edited by Charles M. Epstein, Eric M. Wassermann, and Ulf Ziemann. Oxford University Press, 2012. http://dx.doi.org/10.1093/oxfordhb/9780198568926.013.0018.
Full textAbstract:
Adult brains maintain the ability to reorganize throughout life. Cortical reorganization or plasticity includes modification of synaptic efficacy as well as neuronal networks that carry behavioural implications. Transcranial magnetic stimulation (TMS) allows for the study of primary motor cortex reorganization in humans. Motor-evoked potential (MEP) amplitudes change in response to practice. This article gives information about the effect of practice on TMS measures such as motor-evoked potential amplitudes, motor maps, paired-pulse measures, and behavioural measures. These changes may be accompanied by down-regulation of activity in nearby body part representations within the same hemisphere and in homonymous regions of the opposite hemisphere, mediated by interhemispheric interactions. There is evidence pointing towards the influence of practice on a distributed network of cortical representations within regions of cerebral hemispheres. This has lead to the formulation of intervention strategies to enhance the training effects by cortical or somatosensory stimulation in health and disease.
7
Butz, Martin V., and Esther F. Kutter. Multisensory Interactions. Oxford University Press, 2017. http://dx.doi.org/10.1093/acprof:oso/9780198739692.003.0010.
Full textAbstract:
This chapter shows that multiple sensory information sources can generally be integrated in a similar fashion. However, seeing that different modalities are grounded in different frames of reference, integrations will focus on space or on identities. Body-relative spaces integrate information about the body and the surrounding space in body-relative frames of reference, integrating the available information across modalities in an approximately optimal manner. Simple topological neural population encodings are well-suited to generate estimates about stimulus locations and to map several frames of reference onto each other. Self-organizing neural networks are introduced as the basic computation mechanism that enables the learning of such mappings. Multisensory object recognition, on the other hand, is realized most effectively in an object-specific frame of reference – essentially abstracting away from body-relative frames of reference. Cognitive maps, that is, maps of the environment are learned by connecting locations over space and time. The hippocampus strongly supports the learning of cognitive maps, as it supports the generation of new episodic memories, suggesting a strong relation between these two computational tasks. In conclusion, multisensory integration yields internal predictive structures about spaces and object identities, which are well-suited to plan, decide on, and control environmental interactions.
8
Ramani, Ramachandran, ed. Functional MRI. Oxford University Press, 2018. http://dx.doi.org/10.1093/med/9780190297763.001.0001.
Full textAbstract:
Functional MRI with BOLD (Blood Oxygen Level Dependent) imaging is one of the commonly used modalities for studying brain function in neuroscience. The underlying source of the BOLD fMRI signal is the variation in oxyhemoglobin to deoxyhemoglobin ratio at the site of neuronal activity in the brain. fMRI is mostly used to map out the location and intensity of brain activity that correlate with mental activities. In recent years, a new approach to fMRI was developed that is called resting-state fMRI. The fMRI signal from this method does not require the brain to perform any goal-directed task; it is acquired with the subject at rest. It was discovered that there are low-frequency fluctuations in the fMRI signal in the brain at rest. The signals originate from spatially distinct functionally related brain regions but exhibit coherent time-synchronous fluctuations. Several of the networks have been identified and are called resting-state networks. These networks represent the strength of the functional connectivity between distinct functionally related brain regions and have been used as imaging markers of various neurological and psychiatric diseases. Resting-state fMRI is also ideally suited for functional brain imaging in disorders of consciousness and in subjects under anesthesia. This book provides a review of the basic principles of fMRI (signal sources, acquisition methods, and data analysis) and its potential clinical applications.
9
Seeck, Margitta, L. Spinelli, Jean Gotman, and Fernando H. Lopes da Silva. Combination of Brain Functional Imaging Techniques. Edited by Donald L. Schomer and Fernando H. Lopes da Silva. Oxford University Press, 2017. http://dx.doi.org/10.1093/med/9780190228484.003.0046.
Full textAbstract:
Several tools are available to map brain electrical activity. Clinical applications focus on epileptic activity, although electric source imaging (ESI) and electroencephalography-coupled functional magnetic resonance imaging (EEG–fMRI) are also used to investigate non-epileptic processes in healthy subjects. While positron-emission tomography (PET) reflects glucose metabolism, strongly linked with synaptic activity, and single-photon-emission computed tomography (SPECT) reflects blood flow, fMRI (BOLD) signals have a hemodynamic component that is a surrogate signal of neuronal (synaptic) activity. The exact interpretation of BOLD signals is not completely understood; even in unifocal epilepsy, more than one region of positive or negative BOLD is often observed. Co-registration of medical images is essential to answer clinical questions, particularly for presurgical epilepsy evaluations. Multimodal imaging can yield information about epileptic foci and underlying networks. Co-registering MRI, PET, SPECT, fMRI, and ESI (or magnetic source imaging) provides information to estimate the epileptogenic zone and can help optimize surgical results.
10
Zhai, Xiaoming, and Joseph Krajcik, eds. Uses of Artificial Intelligence in STEM Education. Oxford University PressOxford, 2024. http://dx.doi.org/10.1093/oso/9780198882077.001.0001.
Full textAbstract:
Abstract In the age of rapid technological advancements, the integration of artificial intelligence (AI), machine learning (ML), and large language models (LLMs) in science, technology, engineering, and mathematics (STEM) education has emerged as a transformative force, reshaping pedagogical approaches and assessment methodologies. This book, comprising twenty-six chapters, delves deep into the multifaceted realm of AI-driven STEM education. It begins by exploring the challenges and opportunities of AI-based STEM education, emphasizing the intricate balance between human tasks and technological tools. As the chapters unfold, readers learn about innovative AI applications, from automated scoring systems in biology, chemistry, physics, mathematics, and engineering to intelligent tutors and adaptive learning. The book also touches upon the nuances of AI in supporting diverse learners, including students with learning disabilities, and the ethical considerations surrounding AI's growing influence in educational settings. It showcases the transformative potential of AI in reshaping STEM education, emphasizing the need for adaptive pedagogical strategies that cater to diverse learning needs in an AI-centric world. The chapters further delve into the practical applications of AI, from scoring teacher observations and analyzing classroom videos using neural networks to the broader implications of AI for STEM assessment practices. Concluding with reflections on the new paradigm of AI-based STEM education, this book serves as a comprehensive guide for educators, researchers, and policymakers, offering insights into the future of STEM education in an AI-driven world.
Book chapters on the topic "Neural network MLP"
1
Vitabile, Salvatore, Antonio Gentile, G. B. Dammone, and Filippo Sorbello. "MLP Neural Network Implementation on a SIMD Architecture." In Neural Nets. Springer Berlin Heidelberg, 2002. http://dx.doi.org/10.1007/3-540-45808-5_10.
Full text
2
Kordos, Mirosław, and Andrzej Rusiecki. "Improving MLP Neural Network Performance by Noise Reduction." In Theory and Practice of Natural Computing. Springer Berlin Heidelberg, 2013. http://dx.doi.org/10.1007/978-3-642-45008-2_11.
Full text
3
Hu, Fan. "Prediction Application of MLP Feedforward Neural Network Based on SNNS Neural Network Platform." In Atlantis Highlights in Intelligent Systems. Atlantis Press International BV, 2023. http://dx.doi.org/10.2991/978-94-6463-200-2_5.
Full text
4
Guo, Lei, Yumin Zhang, Chengliang Liu, Hong Wang, and Chunbo Feng. "Optimal Actuator Fault Detection via MLP Neural Network for PDFs." In Advances in Neural Networks – ISNN 2005. Springer Berlin Heidelberg, 2005. http://dx.doi.org/10.1007/11427469_88.
Full text
5
Er, Meng Joo, and Fan Liu. "Parameter Tuning of MLP Neural Network Using Genetic Algorithms." In Advances in Soft Computing. Springer Berlin Heidelberg, 2009. http://dx.doi.org/10.1007/978-3-642-01216-7_13.
Full text
6
Bárcena-Humanes, Jose Luis, David Mata-Moya, María Pilar Jarabo-Amores, Nerea del-Rey-Maestre, and Jaime Martín-de-Nicolás. "Sea Clutter Neural Network Classifier: Feature Selection and MLP Design." In Advances in Computational Intelligence. Springer Berlin Heidelberg, 2013. http://dx.doi.org/10.1007/978-3-642-38679-4_58.
Full text
7
Cruz, Isis Bonet, Adolfo Díaz Sardiñas, Rafael Bello Pérez, and Yanetsy Sardiñas Oliva. "Learning Optimization in a MLP Neural Network Applied to OCR." In MICAI 2002: Advances in Artificial Intelligence. Springer Berlin Heidelberg, 2002. http://dx.doi.org/10.1007/3-540-46016-0_31.
Full text
8
Adel, Afia, Ouelmokhtar Hand, Gougam Fawzi, Touzout Walid, Rahmoune Chemseddine, and Benazzouz Djamel. "Gear Fault Detection, Identification and Classification Using MLP Neural Network." In Lecture Notes in Mechanical Engineering. Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-4835-0_18.
Full text
9
Shivappriya, S. N., Rajaguru Harikumar, Krishnamoorthi Maheswari, and Ramasamy Dhivya Praba. "Heart Disease Classification Using Multi-Layer Perceptron (MLP) Neural Network." In Sustainable Digital Technologies for Smart Cities. CRC Press, 2023. http://dx.doi.org/10.1201/9781003307716-14.
Full text
10
Cheng, Bin, Zonggang Li, Jianjun Jiao, and Guanglin An. "MLP Neural Network-Based Precise Localization of Robot Assembly Parts." In Intelligent Robotics and Applications. Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-6480-2_50.
Full textConference papers on the topic "Neural network MLP"
1
Fan, Xingyuan, Yijun Huang, Peiqi Liu, et al. "Fault Detection of Electricity Meters Based on PCA-MLP Neural Network." In 2024 8th International Conference on Electrical, Mechanical and Computer Engineering (ICEMCE). IEEE, 2024. https://doi.org/10.1109/icemce64157.2024.10862455.
Full text
2
Pradhan, Dr Moumita. "PredParkinson-MLP: Parkinson Disease Prediction using Multi Layer Perceptron Neural Network." In 2025 International Conference on Machine Learning and Autonomous Systems (ICMLAS). IEEE, 2025. https://doi.org/10.1109/icmlas64557.2025.10968652.
Full text
3
Matuck, Gustavo R., Joa˜o Roberto Barbosa, Cleverson Bringhenti, and Isaias Lima. "Multiple Faults Detection of Gas Turbine by MLP Neural Network." In ASME Turbo Expo 2009: Power for Land, Sea, and Air. ASMEDC, 2009. http://dx.doi.org/10.1115/gt2009-59964.
Full textAbstract:
This paper describes a procedure to measure the performance of detection and isolation of multiple faults in gas turbines using artificial neural network and optimization techniques. It is on a particular form of artificial neural networks, the traditional multi-layer perceptron (MLP). Error back-propagation and different activation functions are used. The main goal is to recognize single, double and triple faults in a turboshaft engine, whose performance data were output from a gas turbine simulator program, tuned to represent the engine running at an existing power station. MLP network is a nonlinear interpolation function usually made of input layer, hidden-layer and output-layer, with different neuronal units, but in this work, only one hidden-layer was used. Weights were altered by error back-propagation from the initial values established from a seed fixed between 0 and 1. The activation function in the MLP algorithm is the sigmoid function. The best moment to stop the training process and avoid the over fitting problem was chosen by cross-validation. Optimization of convergence error was achieved using the momentum criteria and reducing the oscillation problem in all nets trained. Several configurations of the neural network have been compared and evaluated, using several noise graduations incorporated to the data, aiming at finding the network most suitable to detect and isolate multiple faults in gas turbines. Based on the results obtained it is inferred that the procedure reported herein may be applied to actual systems in order to assist in maintenance programs, at least.
4
Lacrama, Dan L., Vasile Gherhes, Florin Alexa, and Tiberiu M. Karnyanszky. "Automatic survey processing using a MLP neural net." In 2010 10th Symposium on Neural Network Applications in Electrical Engineering (NEUREL 2010). IEEE, 2010. http://dx.doi.org/10.1109/neurel.2010.5644092.
Full text
5
Salah, Latifa Belhaj, and Fathi Fourati. "Deep MLP neural network control of bioreactor." In 2019 10th International Renewable Energy Congress (IREC). IEEE, 2019. http://dx.doi.org/10.1109/irec.2019.8754572.
Full text
6
Yashwanth, Talla, K. Ashwini, Gandla Shiva Chaithanya, and Arshiya Tabassum. "Network Intrusion Detection using Auto-encoder Neural Networks and MLP." In 2024 Third International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE). IEEE, 2024. http://dx.doi.org/10.1109/icdcece60827.2024.10548660.
Full text
7
Mat Darus, I. Z., M. O. Tokhi, and S. Z. Mohd. Hashim. "Non-Linear System Identification of Flexible Plate Structures Using Neural Networks." In ASME 7th Biennial Conference on Engineering Systems Design and Analysis. ASMEDC, 2004. http://dx.doi.org/10.1115/esda2004-58200.
Full textAbstract:
This paper investigates the utilisation of feedforward and recurrent neural networks for dynamic modelling of a flexible plate structure. Neuro-modelling techniques are used for non-parametric identification of the flexible plate structure based on one-step-ahead prediction. A multi layer perceptron (MLP) and Elman neural networks are designed to characterise the dynamic behaviour of the flexible plate. Results of the modelling techniques are validated through a range of tests including input/output mapping, training and test validation, mean-squared error and correlation tests. Results are presented in both time and frequency domains. Comparative performance assessments of both neuro-modelling approaches in terms of mean-squared error and estimation of the resonance modes of the system are carried out. It is noted that both techniques have been able to detect the first five vibration modes of the system successfully. Investigations also signify the advantage of a recurrent Elman network over an MLP feedforward network in modelling the flexible plate structure.
8
Motato, Eliot, and Clark Radcliffe. "Recursive Assembly of Multi-Layer Perceptron Neural Networks." In ASME 2014 Dynamic Systems and Control Conference. American Society of Mechanical Engineers, 2014. http://dx.doi.org/10.1115/dscc2014-5997.
Full textAbstract:
The objective of this paper is to present a methodology to modularly connect Multi-Layer Perceptron (MLP) neural network models describing static port-based physical behavior. The MLP considered in this work are characterized for an standard format with a single hidden layer with sigmoidal activation functions. Since every port is defined by an input-output pair, the number of outputs of the proposed neural network format is equal to the number of its inputs. This work extends the Model Assembly Method (MAM) used to connect transfer function models and Volterra models to multi-layer perceptron neural networks.
9
Meng Joo Er and Fan Liu. "Genetic Algorithms for MLP Neural Network parameters optimization." In 2009 Chinese Control and Decision Conference (CCDC). IEEE, 2009. http://dx.doi.org/10.1109/ccdc.2009.5192353.
Full text
10
Jarrar, Manel, Asma Kerkeni, Asma Ben Abdallah, and Mohamed Hedi Bedoui. "MLP Neural Network Classifier for Medical Image Segmentation." In 2016 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV). IEEE, 2016. http://dx.doi.org/10.1109/cgiv.2016.26.
Full textReports on the topic "Neural network MLP"
1
Ramakrishnan, Aravind, Fangyu Liu, Angeli Jayme, and Imad Al-Qadi. Prediction of Pavement Damage under Truck Platoons Utilizing a Combined Finite Element and Artificial Intelligence Model. Illinois Center for Transportation, 2024. https://doi.org/10.36501/0197-9191/24-030.
Full textAbstract:
For robust pavement design, accurate damage computation is essential, especially for loading scenarios such as truck platoons. Studies have developed a framework to compute pavement distresses as function of lateral position, spacing, and market-penetration level of truck platoons. The established framework uses a robust 3D pavement model, along with the AASHTOWare Mechanistic–Empirical Pavement Design Guidelines (MEPDG) transfer functions to compute pavement distresses. However, transfer functions include high variability and lack physical significance. Therefore, as an improvement to effectively predict permanent deformation, this study utilized a conventional Burger’s model, incorporating a nonlinear power-law dashpot, in lieu of a transfer function. Key components, including stress increments and the Jacobian, were derived for implementation in ABAQUS as a user subroutine. Model parameters were determined through asphalt concrete (AC) flow number and dynamic modulus tests. Using a nonlinear power-law dashpot, the model accurately characterized rutting under varying conditions. The Burger’s model was both verified and validated to check the accuracy of implementation and representative of the actual behavior, respectively. Initially developed in 1D domain, the validated Burger’s model was integrated into the robust 3D finite element (FE) pavement model to predict permanent deformation. A new load-pass approach (LPA) enabled reduction in computational domain and cost, along with implementing transient loads more efficiently. The combined integration of the LPA and the Burger’s model into the pavement model effectively captured the rutting progression per loading cycle. Moreover, a graph neural network (GNN) was established to extend the prediction power of the framework, while strategically limiting the FE numerical matrix. The FE model data was transformed into a graph structure, converting FE model components into corresponding graph nodes and edges. The GNN-based pavement simulator (GPS) was developed to model 3D pavement responses, integrating three key components: encoder, processor, and decoder. The GPS model employed two-layer multilayer perceptrons (MLP) for the encoder and decoder, while utilizing graph network (GN) technology for the processor. Validation occurred through two case studies—OneStep and Rollout—with results compared against FE model data as ground truth. Results demonstrated that the GPS model provides an accurate and computationally efficient alternative to traditional 3D pavement FE simulations.
2
Kirichek, Galina, Vladyslav Harkusha, Artur Timenko, and Nataliia Kulykovska. System for detecting network anomalies using a hybrid of an uncontrolled and controlled neural network. [б. в.], 2020. http://dx.doi.org/10.31812/123456789/3743.
Full textAbstract:
In this article realization method of attacks and anomalies detection with the use of training of ordinary and attacking packages, respectively. The method that was used to teach an attack on is a combination of an uncontrollable and controlled neural network. In an uncontrolled network, attacks are classified in smaller categories, taking into account their features and using the self- organized map. To manage clusters, a neural network based on back-propagation method used. We use PyBrain as the main framework for designing, developing and learning perceptron data. This framework has a sufficient number of solutions and algorithms for training, designing and testing various types of neural networks. Software architecture is presented using a procedural-object approach. Because there is no need to save intermediate result of the program (after learning entire perceptron is stored in the file), all the progress of learning is stored in the normal files on hard disk.
3
Alwan, Iktimal, Dennis D. Spencer, and Rafeed Alkawadri. Comparison of Machine Learning Algorithms in Sensorimotor Functional Mapping. Progress in Neurobiology, 2023. http://dx.doi.org/10.60124/j.pneuro.2023.30.03.
Full textAbstract:
Objective: To compare the performance of popular machine learning algorithms (ML) in mapping the sensorimotor cortex (SM) and identifying the anterior lip of the central sulcus (CS). Methods: We evaluated support vector machines (SVMs), random forest (RF), decision trees (DT), single layer perceptron (SLP), and multilayer perceptron (MLP) against standard logistic regression (LR) to identify the SM cortex employing validated features from six-minute of NREM sleep icEEG data and applying standard common hyperparameters and 10-fold cross-validation. Each algorithm was tested using vetted features based on the statistical significance of classical univariate analysis (p<0.05) and extended () 17 features representing power/coherence of different frequency bands, entropy, and interelectrode-based distance. The analysis was performed before and after weight adjustment for imbalanced data (w). Results: 7 subjects and 376 contacts were included. Before optimization, ML algorithms performed comparably employing conventional features (median CS accuracy: 0.89, IQR [0.88-0.9]). After optimization, neural networks outperformed others in means of accuracy (MLP: 0.86), the area under the curve (AUC) (SLPw, MLPw, MLP: 0.91), recall (SLPw: 0.82, MLPw: 0.81), precision (SLPw: 0.84), and F1-scores (SLPw: 0.82). SVM achieved the best specificity performance. Extending the number of features and adjusting the weights improved recall, precision, and F1-scores by 48.27%, 27.15%, and 39.15%, respectively, with gains or no significant losses in specificity and AUC across CS and Function (correlation r=0.71 between the two clinical scenarios in all performance metrics, p<0.001). Interpretation: Computational passive sensorimotor mapping is feasible and reliable. Feature extension and weight adjustments improve the performance and counterbalance the accuracy paradox. Optimized neural networks outperform other ML algorithms even in binary classification tasks. The best-performing models and the MATLAB® routine employed in signal processing are available to the public at (Link 1).
4
Pasupuleti, Murali Krishna. Quantum Intelligence: Machine Learning Algorithms for Secure Quantum Networks. National Education Services, 2025. https://doi.org/10.62311/nesx/rr925.
Full textAbstract:
Abstract: As quantum computing and quantum communication technologies advance, securing quantum networks against emerging cyber threats has become a critical challenge. Traditional cryptographic methods are vulnerable to quantum attacks, necessitating the development of AI-driven security solutions. This research explores the integration of machine learning (ML) algorithms with quantum cryptographic frameworks to enhance Quantum Key Distribution (QKD), post-quantum cryptography (PQC), and real-time threat detection. AI-powered quantum security mechanisms, including neural network-based quantum error correction (QEC), deep learning-driven anomaly detection, and reinforcement learning for adaptive encryption, provide a self-learning security model for quantum communication systems. The study also examines quantum blockchain integration, AI-optimized quantum network traffic management, and secure quantum biometric authentication as emerging trends in AI-enhanced quantum cybersecurity. Additionally, it evaluates industry adoption, policy considerations, and global quantum security initiatives across China, the US, the EU, and India. By addressing scalability, automation, and real-time quantum security monitoring, this research provides a roadmap for leveraging AI in next-generation secure quantum networks to enable fault-tolerant, self-healing cybersecurity frameworks. Keywords: Quantum intelligence, machine learning, secure quantum networks, AI-driven quantum cryptography, quantum key distribution, post-quantum cryptography, neural network-based quantum error correction, deep learning anomaly detection, reinforcement learning in quantum security, AI-driven quantum authentication, quantum blockchain security, quantum biometric authentication, quantum-enhanced AI cybersecurity, real-time quantum security monitoring, AI-optimized quantum routing, scalable quantum encryption, quantum cybersecurity policy, AI-powered post-quantum security, self-healing quantum networks, AI-driven quantum forensics.
5
Goulet Coulombe, Philippe, Massimiliano Marcellino, and Dalibor Stevanovic. Panel Machine Learning with Mixed-Frequency Data: Monitoring State-Level Fiscal Variables. CIRANO, 2025. https://doi.org/10.54932/qgja3449.
Full textAbstract:
We study the nowcasting of U.S. state-level fiscal variables using machine learning (ML) models and mixed-frequency predictors within a panel framework. Neural networks with continuous and categorical embeddings consistently outperform both linear and nonlinear alternatives, especially when combined with pooled panel structures. These architectures flexibly capture differences across states while benefiting from shared patterns in the panel structure. Forecast gains are especially large for volatile variables like expenditures and deficits. Pooling enhances forecast stability, and ML models are better suited to handle cross-sectional nonlinearities. Results show that predictive improvements are broad-based and that even a few high frequency state indicators contribute substantially to forecast accuracy. Our findings highlight the complementarity between flexible modeling and cross-sectional pooling, making panel neural networks a powerful tool for timely and accurate fiscal monitoring in heterogeneous settings.
6
Naseem, Shahid. Hand written digits classification and recognition using convolutional neural networks by implementing the techniques of MLP and SVM. Peeref, 2023. http://dx.doi.org/10.54985/peeref.2303p8226220.
Full text
7
Mbani, Benson, Timm Schoening, and Jens Greinert. Automated and Integrated Seafloor Classification Workflow (AI-SCW). GEOMAR, 2023. http://dx.doi.org/10.3289/sw_2_2023.
Full textAbstract:
The Automated and Integrated Seafloor Classification Workflow (AI-SCW) is a semi-automated underwater image processing pipeline that has been customized for use in classifying the seafloor into semantic habitat categories. The current implementation has been tested against a sequence of underwater images collected by the Ocean Floor Observation System (OFOS), in the Clarion-Clipperton Zone of the Pacific Ocean. Despite this, the workflow could also be applied to images acquired by other platforms such as an Autonomous Underwater Vehicle (AUV), or Remotely Operated Vehicle (ROV). The modules in AI-SCW have been implemented using the python programming language, specifically using libraries such as scikit-image for image processing, scikit-learn for machine learning and dimensionality reduction, keras for computer vision with deep learning, and matplotlib for generating visualizations. Therefore, AI-SCW modularized implementation allows users to accomplish a variety of underwater computer vision tasks, which include: detecting laser points from the underwater images for use in scale determination; performing contrast enhancement and color normalization to improve the visual quality of the images; semi-automated generation of annotations to be used downstream during supervised classification; training a convolutional neural network (Inception v3) using the generated annotations to semantically classify each image into one of pre-defined seafloor habitat categories; evaluating sampling strategies for generation of balanced training images to be used for fitting an unsupervised k-means classifier; and visualization of classification results in both feature space view and in map view geospatial co-ordinates. Thus, the workflow is useful for a quick but objective generation of image-based seafloor habitat maps to support monitoring of remote benthic ecosystems.
8
Irudayaraj, Joseph, Ze'ev Schmilovitch, Amos Mizrach, Giora Kritzman, and Chitrita DebRoy. Rapid detection of food borne pathogens and non-pathogens in fresh produce using FT-IRS and raman spectroscopy. United States Department of Agriculture, 2004. http://dx.doi.org/10.32747/2004.7587221.bard.
Full textAbstract:
Rapid detection of pathogens and hazardous elements in fresh fruits and vegetables after harvest requires the use of advanced sensor technology at each step in the farm-to-consumer or farm-to-processing sequence. Fourier-transform infrared (FTIR) spectroscopy and the complementary Raman spectroscopy, an advanced optical technique based on light scattering will be investigated for rapid and on-site assessment of produce safety. Paving the way toward the development of this innovative methodology, specific original objectives were to (1) identify and distinguish different serotypes of Escherichia coli, Listeria monocytogenes, Salmonella typhimurium, and Bacillus cereus by FTIR and Raman spectroscopy, (2) develop spectroscopic fingerprint patterns and detection methodology for fungi such as Aspergillus, Rhizopus, Fusarium, and Penicillium (3) to validate a universal spectroscopic procedure to detect foodborne pathogens and non-pathogens in food systems. The original objectives proposed were very ambitious hence modifications were necessary to fit with the funding. Elaborate experiments were conducted for sensitivity, additionally, testing a wide range of pathogens (more than selected list proposed) was also necessary to demonstrate the robustness of the instruments, most crucially, algorithms for differentiating a specific organism of interest in mixed cultures was conceptualized and validated, and finally neural network and chemometric models were tested on a variety of applications. Food systems tested were apple juice and buffer systems. Pathogens tested include Enterococcus faecium, Salmonella enteritidis, Salmonella typhimurium, Bacillus cereus, Yersinia enterocolitis, Shigella boydii, Staphylococus aureus, Serratiamarcescens, Pseudomonas vulgaris, Vibrio cholerae, Hafniaalvei, Enterobacter cloacae, Enterobacter aerogenes, E. coli (O103, O55, O121, O30 and O26), Aspergillus niger (NRRL 326) and Fusarium verticilliodes (NRRL 13586), Saccharomyces cerevisiae (ATCC 24859), Lactobacillus casei (ATCC 11443), Erwinia carotovora pv. carotovora and Clavibacter michiganense. Sensitivity of the FTIR detection was 103CFU/ml and a clear differentiation was obtained between the different organisms both at the species as well as at the strain level for the tested pathogens. A very crucial step in the direction of analyzing mixed cultures was taken. The vector based algorithm was able to identify a target pathogen of interest in a mixture of up to three organisms. Efforts will be made to extend this to 10-12 key pathogens. The experience gained was very helpful in laying the foundations for extracting the true fingerprint of a specific pathogen irrespective of the background substrate. This is very crucial especially when experimenting with solid samples as well as complex food matrices. Spectroscopic techniques, especially FTIR and Raman methods are being pursued by agencies such as DARPA and Department of Defense to combat homeland security. Through the BARD US-3296-02 feasibility grant, the foundations for detection, sample handling, and the needed algorithms and models were developed. Successive efforts will be made in transferring the methodology to fruit surfaces and to other complex food matrices which can be accomplished with creative sampling methods and experimentation. Even a marginal success in this direction will result in a very significant breakthrough because FTIR and Raman methods, in spite of their limitations are still one of most rapid and nondestructive methods available. Continued interest and efforts in improving the components as well as the refinement of the procedures is bound to result in a significant breakthrough in sensor technology for food safety and biosecurity.