The Random Forests ensemble predictor has proven to be well-suited for solving a multitudeof different prediction problems. In this thesis, we propose an extension to the Random Forestframework that allows Random Forests to be constructed for multi-output decision problemswith arbitrary combinations of classification and regression responses, with the goal ofincreasing predictive performance for such multi-output problems. We show that our methodfor combining decision tasks within the same decision tree reduces prediction error for mosttasks compared to single-output decision trees based on the same node impurity metrics, andprovide a comparison of different methods for combining such metrics. / Program: Magisterutbildning i informatik

In the thesis, we use the concept of single-negative metamaterials to reduce the antennas¡¦ coupling. Firstly, the multilayer insulator is proposed to enhance the isolation bandwidth. The isolation bandwidth is broadened by adjusting the individual layer of insulators with close but different operating frequencies. Then, the designed multilayer insulator is inserted in a planar antenna system. Isolation of the MIMO antenna system is below than -20dB. The measured and simulated isolation bandwidth is 8% and 6.9%, respectively. We then design dual-band insulators for dual-band MIMO antenna applications. The proposed dual-band insulator is implemented bystacking the insulators with different operating bands and the isolation of the dual-band MIMO antenna can be improved at both 2.6 and 3.5GHz bands. In the broadband insulator design, the T-shaped branch is proposed to broadenthe operating bandwidth. The measured isolation bandwidth is improved by 12.8% than that of the multilayer insulator. The bandwidth of the proposed broadband insulator can be used in other broadband communication standards.

This dissertation reports the development of a new multi-band multi-output synthesizer, 1/2 dual-injection locked divider, 1/3 injection-locked divider with phase-tuning, and 1/3 injection-locked divider with self-injection using 0.18-micrometer CMOS technology. The synthesizer is used for a multi-band multi-polarization radar system operating in the K- and Ka-band. The synthesizer is a fully integrated concurrent tri-band, tri-output phase-locked loop (PLL) with divide-by-3 injection locked frequency divider (ILFD). A new locking mechanism for the ILFD based on the gain control of the feedback amplifier is utilized to enable tunable and enhanced locking range which facilitates the attainment of stable locking states. The PLL has three concurrent multiband outputs: 3.47-4.313 GHz, 6.94-8.626 GHz and 19.44-21.42-GHz. High second-order harmonic suppression of 62.2 dBc is achieved without using a filter through optimization of the balance between the differential outputs. The proposed technique enables the use of an integer-N architecture for multi-band and microwave systems, while maintaining the benefit of the integer-N architecture; an optimal performance in area and power consumption. The 1/2 dual-ILFD with wide locking range and low-power consumption is analyzed and designed together with a divide-by-2 current mode logic (CML) divider. The 1/2 dual-ILFD enhances the locking range with low-power consumption through optimized load quality factor (QL) and output current amplitude (iOSC) simultaneously. The 1/2 dual-ILFD achieves a locking range of 692 MHz between 7.512 and 8.204 GHz. The new 1/2 dual-ILFD is especially attractive for microwave phase-locked loops and frequency synthesizers requiring low power and wide locking range. The 3.5-GHz divide-by-3 (1/3) ILFD consists of an internal 10.5-GHz Voltage Controlled Oscillator (VCO) functioning as an injection source, 1/3 ILFD core, and output inverter buffer. A phase tuner implemented on an asymmetric inductor is proposed to increase the locking range. The other divide-by-3 ILFD utilizes self-injection technique. The self-injection technique substantially enhances the locking range and phase noise, and reduces the minimum power of the injection signal needed for the 1/3 ILFD. The locking range is increased by 47.8 % and the phase noise is reduced by 14.77 dBc/Hz at 1-MHz offset.

This paper surveys four distinct approaches to frontier estimation of multi-output (and simultaneously multi-input) technologies, when nothing but noisy quantity data are available. Parametrized distributions for inefficiency and noise are necessary for identification of inefficiency, when only cross-sectional data are available. In other respects suitable techniques may differ widely, as is shown. A final technique presented rigorously exploits the possibilities from panel-data by dropping parametrization of distributions as well as functional forms. It is illustrated how this last technique can be coupled with the others to provide a state-of-the-art estimation procedure for this setting. (author's abstract) / Series: Department of Economics Working Paper Series

No description available.

Yes / An adaptive iterative learning control(ILC) approach is proposed for a class of multi-input multi-output (MIMO) uncertain nonlinear systems without prior knowledge about system control gain matrices. The Nussbaum-type gain and the positive definite discrete matrix kernel are proposed for dealing with selection of the unknown control gain and learning of the repeatable uncertainties, respectively. Asymptotic convergence for a trajectory tracking within a finite time interval is achieved through repetitive tracking. Simulations are carried out to show the validity of the proposed control method.

This thesis focuses on the design issues of the multiple-output boost full-bridge converter, which is constructed by cascading the boost regulator with the inductor-less full-bridge converter. The design of the boost regulator has been proposed briefly with component selection and compensator design. After that, the inductor-less full-bridge converter is analyzed extensively. In the first place, the operation principle of the inductor-less full-bridge converter is introduced. Later, the effect of parasitic resistance and inductance is analyzed in an L-R series circuit model as step-response, which relates the drop of output voltage to the load current. Then, the effects of the dc blocking capacitor for the unbalanced load condition and unbalanced duty cycle are tackled. The theoretical results are compared with the experimental results and the simulation results to verify the relationship between the output voltage drop and load current. The overall efficiency of the converter is tested under various conditions. The design of the planar transformer is critical to limit the profile of the converter and the leakage phenomenon. A planar transformer fit for the inductor-less full-bridge converter is designed and analyzed in 3D FEA software. An N-port transformer model is proposed to implement the inductance matrix into the leakage inductance matrix for circuit analysis. Based on this N-port model several measurements to extract the parameters in this model are proposed, where only the impedance analyzer is needed. Finally, the effects of trace layout and encapsulation on breakdown voltage in PCB are summarized from experimental results. / Master of Science

Yes / This study estimates output market power in the Chinese banking industry using the multi-output Lerner index. We propose a minimum distance cost function approach, which allows us to determine not only the level of market power but also the non-profit maximizers and efficiency level of Chinese banks. Following the first-stage analysis, we employ the generalized method of moment system estimator to evaluate the impacts of bank innovation and trade openness on market power in a multi-output banking context. In particular, we innovatively propose a causal structure analysis based on Wang and Blei (2019) to validate and verify the robustness of our results. We also assess this relationship for different types of bank ownership in China. The findings suggest that Chinese banks exhibit high market power in loans. Furthermore, the results show that bank innovation and trade openness have a significant negative impact on market power in loans, but a significant positive impact on market power in securities. The results also indicate a significantly negative impact of trade openness on overall market power. We find that higher levels of innovation among state-owned and joint-stock commercial banks improve the overall level of market power. The results suggest that, for all bank ownership types, trade openness has a significant negative impact on market power in loans but a significant positive impact on market power in securities. The impact on the overall level of market power is consistently significant and negative. / The full-text of this article will be released for public view at the end of the publisher embargo on 11 Aug 2025.

Cette thèse traite du problème de l'apprentissage automatique supervisé dans le cas ou l'on considère plusieurs sorties, potentiellement de différent types. Nous proposons d'explorer trois différents axes de recherche en rapport avec ce sujet. Dans un premier temps, nous nous concentrons sur le cas homogène et proposons un cadre théorique pour étudier la consistance des problèmes multi-labels dans le cas de l'utilisation de chaîne de classifieurs. Ensuite, en nous plaçant dans ce cadre, nous proposons une borne de Rademacher sur l'erreur de généralisation pour tous les classifieurs de la chaîne et exposons deux facteurs de dépendance reliant les sorties les unes aux autres. Dans un deuxième temps, nous développons et analysons la performance de modèles en lien avec la théorie proposée. Toujours dans le cadre de l'apprentissage avec plusieurs sorties homogènes, nous proposons un modèle basé sur des réseaux de neurones pour l'analyse de sentiments à grain fin. Enfin, nous proposons un cadre et une étude empirique qui montrent la pertinence de l'apprentissage multi-objectif dans le cas de multiples sorties hétérogènes. / In this thesis, we study the problem of learning with multiple outputs related to different tasks, such as classification and ranking. In this line of research, we explored three different axes. First we proposed a theoretical framework that can be used to show the consistency of multi-label learning in the case of classifier chains, where outputs are homogeneous. Based on this framework, we proposed Rademacher generalization error bound made by any classifier in the chain and exhibit dependency factors relating each output to the others. As a result, we introduced multiple strategies to learn classifier chains and select an order for the chain. Still focusing on the homogeneous multi-output framework, we proposed a neural network based solution for fine-grained sentiment analysis and show the efficiency of the approach. Finally, we proposed a framework and an empirical study showing the interest of learning with multiple tasks, even when the outputs are of different types.

Yes / This paper investigates the stabilisation problem and consider transient optimisation for a class of the multi-input-multi-output (MIMO) semi-linear stochastic systems. A control algorithm is presented via an m-block backstepping controller design where the closed-loop system has been stabilized in a probabilistic sense and the transient performance is optimisable by optimised by searching the design parameters under the given criterion. In particular, the transient randomness and the probabilistic decoupling will be investigated as case studies. Note that the presented control algorithm can be potentially extended as a framework based on the various performance criteria. To evaluate the effectiveness of this proposed control framework, a numerical example is given with simulation results. In summary, the key contributions of this paper are stated as follows: 1) one block backstepping-based output feedback control design is developed to stabilize the dynamic MIMO semi-linear stochastic systems using a linear estimator; 2) the randomness and probabilistic couplings of the system outputs have been minimized based on the optimisation of the design parameters of the controller; 3) a control framework with transient performance enhancement of multi-variable semi-linear stochastic systems has been discussed. / Higher Education Innovation Fund (No. HEIF 2018-2020), De Montfort University, Leicester, UK.