<p>Current methods of broadcast herbicide application cause a negative environmental and economic impact. Computer vision methods, specifically those related to object detection, have been reported to aid in site-specific weed management procedures to target apply herbicide on per-weed basis within a field. However, a major challenge to developing a weed detection system is the requirement for properly annotated training data to differentiate between weeds and crops under field conditions. This research involved creating an annotated database of weeds by using UAS-acquired imagery from corn and soybean research plots located in North-central Indiana. A total of 27,828 RGB; 108,398 multispectral; and 23,628 thermal images, were acquired using FLIR Duo Pro R sensor that was attached to a DJI Matrice 600 Pro UAS. An annotated database of 306 RGB images, organized into monocot and dicot weed classes, was used for network training. Two Deep Learning networks namely, DetectNet and You Only Look Once version 3 (YOLO ver3) were subjected to five training stages using four annotated image sets. The precision for weed detection ranged between 3.63-65.37% for monocot and 4.22-45.13% for dicot weed detection. This research has demonstrated a need for creating a large annotated weed database for improving precision of deep learning algorithms through better training of the network.</p>

<p> Roller bearing is one of the machine industry’s common components. The roller bearing operation status is usually related to production efficiency. Failure of bearings during operation will cause downtime and severe economic losses. To prevent this situation, the proposal of effective bearing fault diagnosis methods has become a popular research topic. This thesis research first validates several popular bearing diagnosis methods based on signal processing and machine learning. Second, a novel signal feature extraction method called sparse wavelet packet transform (WPT) decomposition and a corresponding feature learning model called multi-scale and multi-rate convolutional neural network (MSMR-CNN) are proposed. Finally, the proposed method is verified using both Case Western Reserve University (CWRU) dataset and the self-collected dataset. The results demonstrate that our proposed MSMR-CNN method achieves higher performance of bearing fault classification accuracy in comparison with the methods which are recently proposed by the other researchers using machine learning and neural networks .</p>

The topic of the thesis is " Risk management options for accounting errors and accounting fraud". The accounting should correspond to the actual situation, which should be displayed in a comparable manner and with the prescribed accounting methods. All financial statement items must be displayed faithfully and fairly. Honesty is associated with the use of accounting methods. When an entity uses accounting methods correctly, it can be stated that accounting is not only true but also fair. However, there are different valuation methods, and each method can lead to a different result. Therefore, it can be assumed that in practice there may also be purposeful manipulation. The aim of this thesis is to determine by means of detection models whether there are accounting manipulations with accounting statements for companies that have transport as their main activity according to CZ-NACE and at the same time evaluate the ability to detect accounting manipulations of these models. For detection and evaluation of possible accounting manipulations, selected detection models were used - Jones's non-discriminatory accrual, Beneish model and CFEBT model. As a complement to the detection model, the modified Taffler model, and the IN99 model were counted to determine the financial health of the entities in the sample.

Approved for public release; distribution is unlimited / Reissued 30 May 2017 with correction to student's affiliation on title page. / Autonomous vehicle teams have great potential in a wide range of maritime sensing applications, including mine countermeasures (MCM). A key enabler for successfully employing autonomous vehicles in MCM missions is motion planning, a collection of algo-rithms for designing trajectories that vehicles must follow. For maximum utility, these algorithms must consider the capabilities and limitations of each team member. At a minimum, they should incorporate dynamic and operational constraints to ensure trajectories are feasible. Another goal is maximizing sensor performance in the presence of uncertainty. Optimal control provides a useful frame-work for solving these types of motion planning problems with dynamic constraints and di_x000B_erent performance objectives, but they usually require numerical solutions. Recent advances in numerical methods have produced a general mathematical and computational framework for numerically solving optimal control problems with parameter uncertainty—generalized optimal control (GenOC)— thus making it possible to numerically solve optimal search problems with multiple searcher, sensor, and target models. In this dissertation, we use the GenOC framework to solve motion planning problems for di_x000B_erentMCMsearch missions conducted by autonomous surface and underwater vehicles. Physics-based sonar detection models are developed for operationally relevant MCM sensors, and the resulting optimal search trajectories improve mine detection performance over conventional lawnmower survey patterns—especially under time or resource constraints. Simulation results highlight the flexibility of this approach for optimal mo-tion planning and pre-mission analysis. Finally, a novel application of this framework is presented to address inverse problems relating search performance to sensor design, team composition, and mission planning for MCM CONOPS development.

The financial health of a company is important for the decision-making of a financial statement user for various reasons. It may be important for future investors to decide if they can invest in the company. In addition, it may also be important for a bank to decide whether the company can provide a credit. However, there are other cases where the user needs to know if the company is financially health. For this evaluation, there are selected the methods used to detect and evaluate the manipulation of financial statements. As these methods are selected the CFEBT model, the Beneish model and the Jones model of non-discretion accrual. Creditworthy models are used to determine whether the company is making any value for the future and there is any danger of bankruptcy. The creditworthiness index, the Tamari model and the IN05 model are selected as these models. In the diploma thesis, these methods are applied in six companies. There are the parent company named ABC a.s. and its five subsidiaries named with Roman numerals I-V. Names of companies are invention. In the practical part of the diploma thesis, the companies are analysed according to individual models and then there is determined the influence of subsidiaries on the parent company according the correlation coefficient. In the end the hypotheses are confirmed or refuted. The first hypothesis says that the whole consolidation unit is financially health. The second hypothesis assumes that the results of subsidiaries influence the results of parent company positively.

The topic of this diploma thesis is "Creative Accounting Techniques - Aspects of the Presentation of Financial Statements Prepared in Accordance with International Financial Reporting Standards". The aim of this thesis is to assess whether the selected entity has shown indicators of possible creative accounting in the context of publicly available financial statements compiled according to IFRS in comparison with Czech Accounting Standards and the subsequent assessment of acquired differences of both accounting approaches. For such assessment, selected detection models are used the Beneish model, the CFEBT model, and Jones Nondiscretionary Accruals. Moreover, there were calculated other two models Altman's Z-score and the Bonity Index. The diploma thesis is focused on the explanatory power of financial statements for stakeholders (or other external users) which has significant influence on their economic decision making. This work analyses issued and audited financial statements from the user's perspective who does not have any access to more detailed supporting documentation. The diploma thesis is divided into three main parts. The first part is the theoretical over-view of creative accounting. This part describes definitions, history, causes, effects, and techniques of creative accounting, as well as there are mentioned detection models which may help to identify manipulated financial statements. There are also presented bankruptcy and solvency models used for a financial analysis of the selected entity. The second part, methodological, contains the procedures and calculations of selected models used for the further analysis of creative accounting. The third part is devoted to evaluate the results of creative accounting analyses. In conclusion, there is commented the possible occurrence of creative accounting in the entity's financial statements and the explanatory power of both accounting systems.