Memoria para optar al título de Ingeniero Civil Eléctrico / La enfermedad de Parkinson es un trastorno neurodegenerativo y objeto de interés en la comunidad científica, dado que existe una mayor incidencia luego de los 60 años en promedio y además la población mundial posee una alta esperanza de vida, implicando que existirá una mayor cantidad de casos en el futuro. Los tratamientos actuales para este trastorno se componen de un generador de pulsos yelectrodos, en donde se estimula de manera constante una zona del cuerpo (puede ser un área cerebral o parte de la médula) independiente del estado actual del paciente, lo cual conlleva en algunos efectos secundarios no deseados. El presente trabajo de memoria se enfoca en esta problemática, ya que busca un lazode control para estos tratamientos y corresponde a una de las primeras aproximaciones con aprendizaje de máquinas. En particular, se estudia un clasificador de movimiento con incertidumbre a partir de la actividad neural de un modelo animal de rata de 6-OHDA. De esta manera, se realiza la extracción de movimiento a partir de un video y de señales cerebrales de un modelo animal de Parkinson a través de algoritmos de ventanas deslizantes, generando imágenes de potencia en ciertas bandas de frecuencia con una etiqueta respectiva de movimiento a partir del video. Estas imágenes sirven para entrenar a un clasificador de Deep Learning Bayesiano, el cual puede extraer incertidumbre en la clasificación. Así, al utilizar Deep Learning Bayesiano con la forma de evaluación de MC Dropout se llega a obtener un recall de 80 % para la etiqueta de movimiento y la base de datos consistente en una ventana deslizante de medio segundo. Además, esta arquitectura es superior (para esta base de datos) en comparación a la de Deep Learning y evaluación estándar de dropout. Por otro lado, para estos resultados se tiene que con una mejor clasificación se obtiene una menor incertidumbre, lo cual es una de las ventajas al usar Deep Learning Bayesiano pues permite obtener una medida de confianza en la clasificación al realizar evaluaciones estocásticas. Finalmente, cabe destacar que este trabajo puede usarse como base para obtener una estrategia de control para un circuito cerrado específico para cada paciente, el cual posee incertidumbre en predicciones implicando en la confianza que posee el sistema para cambiar un estado específico. Para generar una nueva estrategia más robusta con incertidumbre, se debería repetir este experimento agregando nuevos biomarcadores o indicadores fisiológicos, además de explorar otros algoritmos para extracción de movimiento para el etiquetado de la base de datos. / FONDECYT

The master’s thesis presents a design for the technology of manufacture of a chandelier hinge from the material ČSN 42 3005 (Cu99.5) with a sheet thickness of 0.5 mm. Due to the spherical shape of the part and the series 40 000 parts per year, the technology of deep drawing was chosen for two drawing operations, while the redrawing is performed by reverse deep drawing. Due to the nature of the component, the additional technology is shearing. The manufacturability of the part was verified using numerical simulation in the PAM-STAMP software. The forming process is performed using three forming tools on three different presses. For the first, combined tool, an LE 160C eccentric press is used. A hydraulic press ZHO100 is applied in the second tool for the reverse drawing, and finally, an eccentric press LEK160 is applied for the shearing in the third operation. With the selected profit value of 25 %, the final price for the component was set at CZK 104.17. The turning point occurs after reaching 16 248 parts.

Indiana University-Purdue University Indianapolis (IUPUI) / Current research in deep learning is primarily focused on using Python as a support language. Go, an emerging language, that has many benefits including native support for concurrency has seen a rise in adoption over the past few years. However, this language is not widely used to develop learning models due to the lack of supporting libraries and frameworks for model development. In this thesis, the use of Go for the development of neural network models in general and convolution neural networks is explored. The proposed study is based on a Go-CUDA implementation of neural network models called GoCuNets. This implementation is then compared to a Go-CPU deep learning implementation that takes advantage of Go's built in concurrency called ConvNetGo. A comparison of these two implementations shows a significant performance gain when using GoCuNets compared to ConvNetGo.

<p>  </p> <p>The abundance of heterogeneous data produced and collected each day via multimodal sources may contain hidden events of interest, but in order to extract them the streams of data need to be analyzed with appropriate algorithms, so these events are presented to the end user at the right moment and at the right time. This dissertation proposes a series of algorithms that shape a comprehensive framework for situational knowledge on demand to address this problem. The framework consists of several modules and approaches, each of them is presented in a separate chapter: I begin with video data analysis in streaming video and video at rest for enhanced object detection of real-life surveillance video. For detecting the rare events of interest, I develop a semantic video analysis algorithm which uses an overlay knowledge graph and a semantical network. I show that the usage of the external knowledge for understanding the semantic analysis outperforms other techniques such as transfer learning. </p> <p>The semantical outliers can be used further for improving the algorithm of detecting new objects in the stream of different modalities. I extend the framework with additional modules for natural language data and apply the extended version of the semantic analysis algorithm to define the events of interest from multimodal streaming data. I present a way of combining several feature extractors which can be extended to multiple heterogeneous streams of data in order to efficiently fuse the data based on its semantical similarity, and then show how the serverless architecture of the framework outperforms conventional cloud software architecture. </p> <p>Besides detecting the rare and semantically incompatible events, the semantic analysis can be used for improving the neural networks performance with the data augmentation. The algorithm presented for augmenting the data with the potentially novel objects to circumvent the data drift problem uses the knowledge graph and generative adversarial networks to present the objects to augment the training datasets for supervised learning. I extend the presented framework with a pipeline for generating synthetic novelties to improve the performance of feature extractors and provide the empirical evaluation of the developed method.</p>

<p>  </p> <p>The engine is the heart of the vehicle; any problems with this component will cause significant damage and may even result in the car being junked. The engine repair cost is enormous, and there is no guarantee that the existing engine will be repaired or replaced. Fault diagnosis in engines is critical; there have been numerous techniques and tools used for fault diagnosis in this revolutionary world, which require some extra cost to detect and still cannot detect faults such as knocking. The engine can have several problems but knocking is the major issue that blows up the engine and results in the breakdown of the vehicle. Our research focuses on this key issue which not only costs thousands of dollars but also results in waste. According to experts, at a very early stage, knocking can be detected by human senses, either visually or audibly. The most noticeable feature in detecting engine faults is the knocking sound.  Artificial intelligence deep learning neural networks are well known for their ability to simulate humans; we can utilize this domain to train the networks on sound to detect engine knocking. Many neural networks have been designed for various purposes, one of which is classification. The best widely used and reliable network is the convolution neural network (CNN) which takes input as images and classifies them respectively. Engine sounds have been collected from Google’s Machine Perception research. Our research shows that a prominent feature in building these networks is data. Understanding data and making the most of it is central to data science. A better model is created by meaningful data, not just by designing a complex network. We have used a new algorithmic method of extracting sound and feeding it into all variants of CNN, which we call dependent vehicle sound extraction, in which we use fast Fourier transform (FFT), short-time Fourier transform (STFT), and Mel-frequency cepstral coefficients (MFCCs) for processing input sound signals. We validated the utilization of deep learning networks with a unique dependent vehicle feature extraction technique to detect engine knocking with accurate classification.</p>

<p>Artificial Intelligence driven approaches, especially  based on deep learning algorithms, provided an alternative perspective in summarizing the common features in large-scale and complex datasets and aided the human professions in discovering novel features in cross-domain research. In this dissertation, the author proposed his research of developing AI-driven algorithms to reveal the real relation of complex medical data. The author started to identify the abnormal structures from the radiology images. When the abnormal structure was detected, the author built a model to explore the domain layers or cell phenotype of the specific tissues. Finally, the author evaluated cell-cell communication for the downstream tasks.</p> <p><br></p> <p>In his first research, the author applied IResNet, a two-stage prediction-interpretation Convolution Neural Network, to assist clinicians in the early diagnosis of Autism Spectrum Disorders (ASD). IresNet first predicted the input sMRI scan to one of the two categories: (1) ASD group or (2) Normal Control group, and interpret the prediction using a \textit{post-hoc} approach and visualized the abnormal structures on top of the raw inputs. The proposed method can be applied to other neural diseases such as Alzheimer's Disease. </p> <p><br></p> <p>When the abnormal structure was detected, the author proposed a method to reveal the latent relation at the tissue level. Thus the author proposed SiGra, an unsupervised learning paradigm to identify the domain layers and cellular phenotype in a particular tissue slide based on the corresponding gene expression matrix and the morphology representations. SiGra outperformed other benchmarking algorithms in three different tissue slides from three commercialized single-cell platforms.</p> <p><br></p> <p>At last, the author measured the potential interactions between two cells. The proposed spaCI, measured the correlation of a Ligand-Receptor interaction in the high-dimension latent space and predicted the interactive $L-R$ pair for downstream analysis. </p> <p><br></p> <p>In summary, the author presented three end-to-end AI-driven frameworks to facilitate clinicians and pathologists in better understanding the latent connections of complex diseases and tissues. </p>

No description available.

No description available.

No description available.

No description available.