Intelligent transportation systems (ITS) are essential tools for traffic planning, analysis, and forecasting that can utilize the huge amount of traffic data available nowadays. In this work, we aggregated detailed traffic flow sensor data, Waze reports, OpenStreetMap (OSM) features, and weather data, from California Bay Area for 6 months. Using that data, we studied three novel ITS applications using convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The first experiment is an analysis of the relation between roadway shapes and accident occurrence, where results show that the speed limit and number of lanes are significant predictors for major accidents on highways. The second experiment presents a novel method for forecasting congestion severity using crowdsourced data only (Waze, OSM, and weather), without the need for traffic sensor data. The third experiment studies the improvement of traffic flow forecasting using accidents, number of lanes, weather, and time-related features, where results show significant performance improvements when the additional features where used.

Background. Under the current situation, distance education has rapidly become popular among students and teachers. This educational situation has changed the traditional way of teaching in the classroom. Under this kind of circumstance, students will be required to learn independently. But at the same time, it also brings some drawbacks, and teachers cannot obtain the feedback of students’ engagement in real-time. This thesis explores the feasibility of applying a lightweight model to recognize student engagement and the practicality of the model in a distance education environment. Objectives. This thesis aims to develop and apply a lightweight model based on Convolutional Neural Network(CNN) with acceptable performance to recognize the engagement of students in the environment of distance learning. Evaluate and compare the optimized model with selected original and other models in different performance metrics. Methods. This thesis uses experiments and literature review as research methods. The literature review is conducted to select effective CNN-based models for engagement recognition and feasible strategies for optimizing chosen models. These selected and optimized models are trained, tested, evaluated and compared as independent variables in the experiments. The performance of different models is used as the dependent variable. Results. Based on the literature review results, ShuffleNet v2 is selected as the most suitable CNN architecture for solving the task of engagement recognition. Inception v3 and ResNet are used as the classic CNN architecture for comparison. The attention mechanism and replace activation function are used as optimization methods for ShuffleNet v2. The pre-experiment results show that ShuffleNet v2 using the Leaky ReLU function has the highest accuracy compared with other activation functions. The experimental results show that the optimized model performs better in engagement recognition tasks than the baseline ShuffleNet v2 model, ResNet v2 and Inception v3 models. Conclusions. Through the analysis of the experiment results, the optimized ShuffleNet v2 has the best performance and is the most suitable model for real-world applications and deployments on mobile platforms.

Learning to rank is utilized in many scenarios, such as disease-gene association, information retrieval and recommender system. Improving the prediction accuracy of the ranking model is the main target of existing works. Contextual information has a significant influence in the ranking problem, and has been proved effective to increase the prediction performance of ranking models. Then we construct similarities for different types of entities that could utilize contextual information uniformly in an extensible way. Once we have the similarities constructed by contextual information, how to uti- lize them for different types of ranking models will be the task we should tackle. In this thesis, we propose four algorithms for learning to rank with contextual informa- tion. To refine the framework of matrix factorization, we propose an area under the ROC curve (AUC) loss to conquer the sparsity problem. Clustering and sampling methods are used to utilize the contextual information in the global perspective, and an objective function with the optimal solution is proposed to exploit the contex- tual information in the local perspective. Then, for the deep learning framework, we apply the graph convolutional network (GCN) on the ranking problem with the combination of matrix factorization. Contextual information is utilized to generate the input embeddings and graph kernels for the GCN. The third method in this thesis is proposed to directly exploit the contextual information for ranking. Laplacian loss is utilized to solve the ranking problem, which could optimize the ranking matrix directly. With this loss, entities with similar contextual information will have similar ranking results. Finally, we propose a two-step method to solve the ranking problem of the sequential data. The first step in this two-step method is to generate the em- beddings for all entities with a new sampling strategy. Graph neural network (GNN) and long short-term memory (LSTM) are combined to generate the representation of sequential data. Once we have the representation of the sequential data, we could solve the ranking problem of them with pair-wise loss and sampling strategy.

In this dissertation, the design and fabrication of deep-ultraviolet photodetectors were investigated based on gallium oxide and its alloys, through the heterogeneous integration with metallic and other inorganic materials. The crystallographic properties of oxide films grown directly and indirectly on silicon, magnesium oxide, and sapphire are examined, and the challenges that hinder the realization of efficient and reliable deep-ultraviolet photodetectors are described. In recent years, single-crystalline heterojunction photodiodes employing beta-polymorph gallium oxide thin films as the main absorption layers have been studied. However, reports in the literature generally lack a thorough examination of epitaxial growth processes of high-quality single-crystalline beta-polymorph gallium oxide thin films on metals, such as transition metal nitrides. My research was initiated by demonstrating an ultraviolet-C photodetector based on an amorphous aluminum gallium oxide photoconductive layer grown directly on (100)-oriented silicon. The solar-blind photodetector exhibited a peak spectral responsivity of 1.17 A/W. This is the first reported gallium oxide-based photodetector to have been grown and fabricated directly on silicon. The growth of high-quality monoclinic crystals on cubic silicon is a challenging process, which is largely due to the large lattice mismatch that compromises the crystal quality of the oxide layer, and leads to the degradation of device performance. This issue was addressed by growing the material on substrates with metal nitride templates, which resulted in improvements to the oxide crystal quality. Consequently, high optical gain ultraviolet-C photodetectors were fabricated based on a beta-polymorph gallium oxide photoconductive layer grown on magnesium oxide and silicon substrates with titanium nitride templates. The enhanced solar-blind photodetectors exhibited peak spectral responsivity levels as high as 276 A/W. Moreover, thin polymorphic gallium oxide films were grown on c-plane sapphire using pulsed laser deposition for the first time. The stacked thin films, namely epsilon- and beta-polymorph gallium oxide, were sequentially grown under the same conditions. X-ray diffraction measurements and transmission electron microscopy micrographs confirmed a heteroepitaxially grown beta-polymorph gallium oxide on a heterogeneously nucleated epsilon-polymorph gallium oxide polymorphic heterostructure on c-plane sapphire, which had rocking-curve widths of 1.4° (β-Ga2O3 (−603)) and 0.6° (ε-Ga2O3 (006)).

We trained a combined deep convolutional neural network to predict seals’ age (3 categories) and gender (2 categories). The entire dataset contains 110 seals with around 489 thousand location records. Most records are continuous and measured in a certain step. We created five convolutional layers for feature representation and established two fully connected structure as age’s and gender’s classifier, respectively. Each classifier consists of three fully connected layers. Treating seals’ latitude and longitude as input, entire deep learning network, which includes 780,000 neurons and 2,097,000 parameters, can reach to 70.72% accuracy rate for predicting seals’ age and simultaneously achieve 79.95% for gender estimation.

Witchweeds and broomrapes are root parasitic weeds that represent one of the main threats to global food security. By drastically reducing host crops’ yield, the parasites are often responsible for enormous economic losses estimated in billions of dollars annually. Parasitic plants rely on a chemical cue in the rhizosphere, indicating the presence of a host plant in proximity. Using this host dependency, research in parasitic plants focuses on understanding the necessary triggers for parasitic seeds germination, to either reduce their germination in presence of crops or provoke germination without hosts (i.e. suicidal germination). For this purpose, a number of synthetic analogs and inhibitors have been developed and their biological activities studied on parasitic plants around the world using various protocols. Current studies are using germination-based bioassays, where pre-conditioned parasitic seeds are placed in the presence of a chemical or plant root exudates, from which the germination ratio is assessed. Although these protocols are very sensitive at the chemical level, the germination rate recording is time consuming, represents a challenging task for researchers, and could easily be sped up leveraging automated seeds detection algorithms. In order to accelerate such protocols, we propose an automatic seed censing tool using computer vision latest development. We use a deep learning approach for object detection with the algorithm Faster R-CNN to count and discriminate germinated from non-germinated seeds. Our method has shown an accuracy of 95% in counting seeds on completely new images, and reduces the counting time by a significant margin, from 5 min to a fraction of second per image. We believe our proposed software 5 “SeedQuant” will be of great help for lab bioassays to perform large scale chemicals screening for parasitic seeds applications.

Neural networks optimizers are dominated by first-order methods, due to their inexpensive computational cost per iteration. However, it has been shown that firstorder optimization is prone to reaching sharp minima when trained with large batch sizes. As the batch size increases, the statistical stability of the problem increases, a regime that is well suited for second-order optimization methods. In this thesis, we study a distributed ellipsoidal trust region model for neural networks. We use a block diagonal approximation of the Hessian, assigning consecutive layers of the network to each process. We solve in parallel for the update direction of each subset of the parameters. We show that our optimizer is fit for large batch training as well as increasing number of processes.

Systems for running distributed deep learning training on the cloud have recently been developed. An important component of a distributed deep learning job handler is its resource allocation scheduler. This scheduler allocates computing resources to parts of a distributed training architecture. In this thesis, a serverless distributed deep learning job handler using Kubernetes was built to compare the job completion time when two different Kubernetes schedulers are used. The default Kubernetes scheduler and a gang-like custom scheduler. These schedulers were compared by performing experiments with different configurations of deep learning models, resource count selection and number of concurrent jobs. No significant difference in job completion time between the schedulers could be found. However, two benefits were found in the gang scheduler compared to the default scheduler. First, prevention of resource deadlocks where one or multiple jobs are locking resources but are unable to start. Second, reduced risk of epoch straggling, where jobs are allocated too few workers to be able to complete epochs in a reasonable time. Thus preventing other jobs from using the resources locked by the straggler job.

The diploma thesis is elaborated within frame of masters study programme 2303T010. The work is submitting design of technology production of the drawn part – the holder. The work is based on the study of problems of the deep drawing process and related calculation was designed drawing in instrument with holder according to drawing documentation 2-5M68-12/00. The lower ejector is using for extrusion component. The drawing instrument make use of standardised components and it is solving forms of customary stool close-set on the crank drawing inclinable press LESP 63 A (producer ŠMERAL Brno, plant Trnava), with nominal tensile force 1000 kN. Drawing punch and drawing die are produced from alloyed instrumental steel 19 573, heat-worked according to drawing documentation.

The thesis solves the efficient production of the sheetmetal cover. The new technological procedure will save two manufacturing operations deep drawing. The deep drawing of the cylindrical vessel with a flange and its following calibration in accordance with the design documentation was choosed. The last stage of the deep drawing is the construcion of the circular cut-out and its bending. By doing so the final shape of the cover will be reached.