Every year, drivers are spending over 3 billions to repair damage on vehicle caused by potholes. Along with the financial disaster, potholes cause frustration in drivers. Also, with the emerging development of automated vehicles, road safety with automation in mind is being a necessity. Deep Learning techniques offer intelligent alternatives to reduce the loss caused by spotting pothole. The world is connected in such a way that the information can be shared in no time. Using the power of connectivity, we can communicate the information of potholes to other vehicles and also the department of Transportation for necessary action. A significant number of research efforts have been done with a view to help detect potholes in the pavements. In this thesis, we have compared two object detection algorithms belonging to two major classes i.e. single shot detectors and two stage detectors using our dataset. Comparing the results in the Faster RCNN and YOLOv5, we concluded that, potholes take a small portion in image which makes potholes detection with YOLOv5 less accurate than the Faster RCNN, but keeping the speed of detection in mind, we have suggested that YOLOv5 will be a better solution for this task. Using the YOLOv5 model and image processing technique, we calculated approximate area of potholes and visualized the shape of potholes. Thus obtained information can be used by the Department of Transportation for planning necessary construction tasks. Also, we can use these information to warn the drivers about the severity of potholes depending upon the shape and area.

Microorganisms exist ubiquitously on Earth, yet their functions and ecological roles remain elusive. Investigating these microbes is accomplished by using culture-dependent and culture-independent methodologies. This study employs both methodologies to characterize: 1) the genomic potential of the novel deep-subsurface bacterial isolate Thermanaerosceptrum fracticalcis strain DRI-13T by combining next-generation and nanopore sequencing technologies and 2) the microbiome of the artificial marine environment for the Hawaiian Bobtail Squid in aquaculture using next-generation sequencing of 16S rRNA gene. Microbial ecology of the deep-subsurface remains understudied in terms of microbial diversity and function. The genomic information of DRI-13T revealed a potential for syntrophic relationships, diverse metabolic potential including prophages/antiviral defenses, and novel methylation motifs. Artificial marine environments housing marine the Hawaiian Bobtail Squid (Euprymna scolopes) contain microorganisms that can directly influence animal and aquaculture health. No studies presently show if bacterial communities of the tank environment correlate with the health and productivity of E. scolopes. This study sought to address this by sampling from a year of unproductive aquaculture yield and comparing the bacterial communities from productive cohorts. Bacterial communities from unproductive samples show less bacterial diversity and abundance coupled with shifts in bacterial composition. Nitrate and pH levels between the tanks were found to be strong influences on determining the bacterial populations of productive and unproductive cohorts.

In recent years the advancement in machine learning have solved more and more complex problems. But still these techniques are not commonly used in the industry. One problem is that many of the techniques are black boxes, it is hard to analyse them to make sure that their behaviour is safe. This property makes them unsuitable for safety critical systems. The goal of this thesis is to examine if the deep learning technique Deep Q-network could be used to create a behaviour tree that can solve the same problem. A behaviour tree is a tree representation of a flow structure that is used for representing behaviours, often used in video games or robotics. To solve the problem two simulators are used, one models a cart that shall balance a pole called cart pole, the other is a static world which needs to be navigated called grid world. Inspiration is taken from the learning from demonstration field to use the Deep Q-network as a teacher and then create a decision tree. During the creation of the decision tree two attributes are used for pruning; to look at the trees accuracy or performance. The thesis then compare three techniques, called Naive, BT Espresso, and BT Espresso Simplified. The techniques are used to transform the extracted decision tree into a behaviour tree. When it comes to the performance of the created behaviour trees they all manage to complete the simulator scenarios in the same, or close to, capacity as the trained Deep Q-network. The trees created from the performance pruned decision tree are generally smaller and less complex, but they have worse accuracy. For cart pole the trees created from the accuracy pruned tree has around 10 000 nodes but the performance pruned trees have around 10-20 nodes. The difference in grid world is smaller going from 35-45 nodes to 40-50 nodes. To get the smallest tree with the best performance then the performance pruned tree should be used with the BT Espresso Simplified algorithm. This thesis have shown that it is possible to use knowledge from a trained Deep Q-network model to create a Behaviour tree that can complete the same task. / Under de senaste åren har ett antal framsteg inom maskininlärning gjorts vilket har lett till att mer och mer komplexa problem har kunnat lösas. Dock är dessa tekniker ofta inte använda av industrin. Ett av problemen är att många av de bättre teknikerna beter sig som svarta lådor, det är väldigt svårt att analyser vad de kommer att göra. Denna egenskap gör att de inte är lämpliga att användas i säkerhetskritiska system. Målet med denna avhandling är att undersöka möjligheten att använda den djupa inlärningstekniken djupa q-nätverk kan användas för att skapa ett beteendeträd som är kapabelt att lösa samma problem. Ett beteendeträd är en flödesstruktur som används för att representera beteenden, ofta använt i dataspel eller för robotar. För att undersöka problemet så används två simulatorer, den ena modellerar en vagn som ska balansera en stav och kallas vagnstav (cart pole). Den andra simulatorn är en statisk värld där målet för agenten är att ta sig till en definierad målplats, vilken kallas rutvärld (grid world). För att lösa problemet tas inspiration från ett angränsande fält kallat inlärning från demonstration. Istället för att använda en mänsklig lärare ansätts det djupa q-nätverket som lärare och används för att skapa ett beslutsträd. Beslutsträdet är sedan reducerat genom att kolla på trädets träffsäkerhet eller hur mycket belöning trädet får. Tre tekniker jämförs för att transformera beslutsträdet till ett beteendeträd, teknikerna heter Naiv, BT Espresso och BT Espresso förenklad. Alla skapade beteendeträd lyckas klara av problemet i simulatorn de är skapade för. De hade liknande prestanda som det djupa q-nätverket. När beslutsträden var reducerat på belöning resulterade det i generellt mindre beteendeträd, dock så hade de inte full träffsäkerhet mot det djupa q-nätverket. För vagnstav simulatorn hade beteendeträden som skapats från träffsäkerhets beslutsträden runt 10 000 noder, mot belönings kapade träd som hade runt 10–20 noder. I rutvärlden var skillnaden mindre med 40–50 noder för träd skapade från träffsäkerhet reducerade beslutsträde och 35–45 noder för belöning reducerade beslutsträd. Denna avhandling har påvisat att det går att skapa beteende träd från en tränad djup q-nätverksmodell för ett scenario och om det minsta trädet som klarar scenariot är att önskat bör belönings reducerade beslutsträd användas med BT Espresso förenkling algoritmen.

Background: Avocado (Persea americana) is an economically important tropical fruit considered to be a good source of fatty acids. Despite its importance, the molecular and cellular characterization of biochemical and developmental processes in avocado is limited due to the lack of transcriptome and genomic information. Results: The transcriptomes of seeds, roots, stems, leaves, aerial buds and flowers were determined using different sequencing platforms. Additionally, the transcriptomes of three different stages of fruit ripening (pre-climacteric, climacteric and post-climacteric) were also analyzed. The analysis of the RNAseqatlas presented here reveals strong differences in gene expression patterns between different organs, especially between root and flower, but also reveals similarities among the gene expression patterns in other organs, such as stem, leaves and aerial buds (vegetative organs) or seed and fruit (storage organs). Important regulators, functional categories, and differentially expressed genes involved in avocado fruit ripening were identified. Additionally, to demonstrate the utility of the avocado gene expression atlas, we investigated the expression patterns of genes implicated in fatty acid metabolism and fruit ripening. Conclusions: A description of transcriptomic changes occurring during fruit ripening was obtained in Mexican avocado, contributing to a dynamic view of the expression patterns of genes involved in fatty acid biosynthesis and the fruit ripening process.

No description available.

Deep convective clouds (DCCs) play a crucial role in redistributing latent heat, hydrological cycle and in the radiative budget of our climate system. Therefore, their complex evolution processes are in focus of many studies. Changes in the structure of DCCs can delay the onset of precipitation and alter the albedo of clouds. Knowing where in the cloud and under what circumstances the cloud liquid water droplets start to freeze is an important step to improve climate and weather forecast models. The purpose of this planned study is to characterize the impact of aerosol and thermodynamic conditions on the cloud particle growth. Therefore, ground-based cloud side observation of the reflected solar spectral radiation (near infrared) using an imaging spectroradiometer and measurements of the emitted thermal radiation using an infrared camera will be combined. These measurements will be taken at the Amazon Tall Tower Observatory, in the Amazon forest, Brazil. Here, the campaign will be introduced. / Hochreichend konvektive Bewölkung (deep convective clouds, DCCs) spielt eine entscheidende Rolle bei der Umverteilung latenter Wärme, sowie für den Wasserkreislauf und dem Strahlungshaushalt unseres Klimasystems. Aus diesem Grund stehen ihre komplexen Wolkenbildungsprozesse im Fokus vieler Untersuchungen. Veränderungen in der mikrophysikalischen Struktur der DCCs können das Einsetzen der Niederschlagsbildung verzögern. Darüber hinaus verändern sie die Albedo der Wolke. Das Wissen darüber, wo in der Wolke und unter welchen Umständen die Wolkentropfen beginnen zu gefrieren, ist ein wichtiger Schritt zur Verbesserung von Klima- und Wettervorhersagemodellen. Das Ziel der geplanten Untersuchungen besteht in der Charakterisierung des Einflusses von Aerosolpartikeln und thermodynamischer Bedingungen auf den Partikelwachstum und der Phasenumwandlung in Wolken. Hierzu werden bodengebundene Wolkenseitenbeobachtungen der reflektierten solaren Strahlung (nahes infrarot), aufgezeichnet mit Hilfe eines abbildenden Spektrometers, sowie Messungen der emittierten thermischen Strahlung, detektiert mit einer Infrarotkamera, kombiniert. Die entsprechenden Messungen werden am „Amazon Tall Tower Observatory“ im Amazonas Regenwald in Brasilien durchgeführt. Im folgendem wird die zugehörige Kampagne vorgestellt.

In this paper, we try to understand the concept of ’Neural Collapse’ from a mathemati-cal point of view. The survey will be conducted based on [1]. The authors of [1] providea first global optimization landscape analysis of Neural Collapse. Mainly there are threeaspects the authors like to investigate. The first is to add the weight decay on classicalcross-entropy loss to show that the global minimizers are the simplex ETF based onanalysing the Hessian. Secondly, the ’Layer-peeled’ network still preserves the im-portant features of the full network. In other words even simplifying the loss functionthe network does not lose its explainability. Lastly, how the Layer-peeled network canreduce the memory costs and generalization is as good as the full network. Our studydelves into these details on, how the simplified network is defined? How this simplifiednetwork is different from the original network in terms of the loss function, and finallywe understand the theory behind these steps. We also conduct numerical analysis onspecific input, observe and analyze this phenomenon and finally report our results.

Knowing metastasis is the primary cause of cancer-related deaths incentivized research to unravel the complex cellular processes that drive the metastasis. Advancement in technology and specifically the advent of high-throughput sequencing provides knowledge of such processes. This knowledge led to the development of therapeutic and clinical applications. In this regard, predicting metastasis onset has also been explored using artificial intelligence (AI) approaches that are machine learning (ML), and more recently, deep learning (DL). This thesis discusses the revolutionary field of ML/DL and its applications in cancer metastasis prediction. We are raising the question of whether there is a better way to improve the prediction of metastasis? We effectively addressed this by reviewing strides made in this regard in current literature to draw some conclusions based on a comprehensive review. Then, we used this knowledge to develop multiple ML/DL models using different omics data types that can accurately and cost-effectively predict if the cancer is in the metastatic state and suggest the metastasis site. Beyond that, we show the biological functions that the DL model uses to perform the prediction. We proved that ML/DL could improve efficiency and diagnostic accuracy and can be used to develop novel predictors of prognosis despite some existing challenges.

Despite the significant progress in 3D vision in recent years, collecting large amounts of high-quality 3D data remains a challenge. Hence, developing solutions to extract 3D object information efficiently is a significant problem. We aim for an effective shape classification algorithm to facilitate accurate recognition and efficient search of sizeable 3D model databases. This thesis has two contributions in this space: a) a novel meta-learning approach for 3D object recognition and b) propose a new compositional 3D recognition task and dataset. For 3D recognition, we proposed a few-shot semi-supervised meta-learning model based on Pointnet++ representation with a prototypical random walk loss. In particular, we developed the random walk semi-supervised loss that enables fast learning from a few labeled examples by enforcing global consistency over the data manifold and magnetizing unlabeled points around their class prototypes. On the compositional recognition front, we create a large-scale, richly annotated stylized dataset called 3D CoMPaT. This large dataset primarily focuses on stylizing 3D shapes at part-level with compatible materials. We introduce Grounded CoMPaT Recognition as the task of collectively recognizing and grounding compositions of materials on parts of 3D Objects.

No description available.