In this work, a fully differential Operational Amplifier (OpAmp) with high Gain-Bandwidth (GBW), high linearity and Signal-to-Noise ratio (SNR) has been designed in 65nm CMOS technology with 1.1v supply voltage. The performance of the OpAmp is evaluated using Cadence and Matlab simulations and it satisfies the stringent requirements on the amplifier to be used in a 12-bit pipelined ADC. The open-loop DC-gain of the OpAmp is 72.35 dB with unity-frequency of 4.077 GHz. Phase-Margin (PM) of the amplifier is equal to 76 degree. Applying maximum input swing to the amplifier, it settles within 0.5 LSB error of its final value in less than 4.5 ns. SNR value of the OpAmp is calculated for different input frequencies and amplitudes and it stays above 100 dB for frequencies up to 320MHz. The main focus in this work is the OpAmp design to meet the requirements needed for the 12-bit pipelined ADC. The OpAmp provides enough closed-loop bandwidth to accommodate a high speed ADC (around 300MSPS) with very low gain error to match the accuracy of the 12-bit resolution ADC. The amplifier is placed in a pipelined ADC with 2.5 bit-per-stage (bps) architecture to check for its functionality. Considering only the errors introduced to the ADC by the OpAmp, the Effective Number of Bits (ENOB) stays higher than 11 bit and the SNR is verified to be higher than 72 dB for sampling frequencies up to 320 MHz.

Face detection is a classical application of object detection. There are many practical applications in which face detection is the first step; face recognition, video surveillance, image database management, video coding. This report presents the results of an implementation of the AdaBoost algorithm to train a Strong Classifier to be used for face detection. The AdaBoost algorithm is fast and shows a low false detection rate, two characteristics which are important for face detection algorithms. The application is an implementation of the AdaBoost algorithm with several command-line executables that support testing of the algorithm. The training and detection algorithms are separated from the rest of the application by a well defined interface to allow reuse as a software library. The source code is documented using the JavaDoc-standard, and CppDoc is then used to produce detailed information on classes and relationships in html format. The implemented algorithm is found to produce relatively high detection rate and low false alarm rate, considering the badly suited training data used.

The car has increasingly become more and more intelligent throughout the years. Today's radar and vision based safety systems can warn a driver and brake the vehicle automatically if obstacles are detected. Research projects such as the Google Car have even succeeded in creating fully autonomous cars. The demands to obtain the highest rating in safety tests such as Euro NCAP are also steadily increasing, and as a result, the development of these systems have become more attractive for car manufacturers. In the near future, a car must have a system for detecting, and performing automatic braking for pedestrians to receive the highest safety rating of five stars. The prospect is that the volume of active safety system will increase drastically when the car manufacturers start installing them in not only luxury cars, but also in the regularly priced ones. The use of automatic braking comes with a high demand on the performance of active safety systems, false positives must be avoided at all costs. Dollar et al. [2014] introduced Aggregated Channel Features (ACF) which is based on a 10-channel LUV+HOG feature map. The method uses decision trees learned from boosting and has been shown to outperform previous algorithms in object detection tasks. The rediscovery of neural networks, and especially Convolutional Neural Networks (CNN) has increased the performance in almost every field of machine learning, including pedestrian detection. Recently Yang et al.[2015] combined the two approaches by using the the feature maps from a CNN as input to a decision tree based boosting framework. This resulted in state of the art performance on the challenging Caltech pedestrian data set. This thesis presents an approach to improve the performance of a cascade of boosted classifiers by investigating the impact of using color information for pedestrian detection. The color self similarity feature introduced by Walk et al.[2010] was used to create a version better adapted for boosting. This feature is then used in combination with a gradient based feature at the last step of a cascade. The presented feature increases the performance compared to currently used classifiers at Autoliv, on data recorded by Autoliv and on the benchmark Caltech pedestrian data set. / Bilen har genom åren kommit att bli mer och mer intelligent. Dagens radar- och kamerabaserade säkerhetssystem kan varna och bromsa bilen automatiskt om hider detekteras. Forskningsprojekt såsom Google Car har t.o.m lyckats köra bilar helt autonomt. Kraven för att uppnå den högsta säkerhetsklassningen i t.ex. Euro NCAP blir allt strängare i takt med att dessa system utvecklas och som följd har dessa system blivit attraktivare för biltillverkare. Inom en snart framtid kommer det att krävas att en bil har ett system för att upptäcka och att bromsa automatiskt för fotgängare för att uppnå den högsta klassen, fem stjärnor. Förutsikterna är att produktionsvolymer för aktiva säkerhetsytem kommer att öka drastiskt när biltillverkarna börjar utrusta vanliga bilar och inte enbart lyxmodeller med dessa system. Användningen av aktiv bromsning ställer höga krav på prestanda, felakting aktivering av system måste i högsta grad undvikas. Dollar et al. [2014] presenterade Aggregated Channel Features (ACF) som baseras på en tiokanalig LUV+HOG särdragskarta. Metoden använder beslutsträd på pixelnivå som tas fram genom boosting och överträffade tidigare algoritmer för objektigenkänning. Återupptäkten av neurala nätverker och i synnerlighet Convolutional Neural Networks (CNN) har medfört en ökning i prestanda inom nästan alla fält av maskininlärning, inklusive fotgängardetektion. Nyligen kombinerades dessa två metoder av Yang et al.[2015] genom att särdragskartan från ett CNN användes som insignal till ett beslutsträdsbaserat boostingramverk. Detta ledde till det hittills bästa resultatet på det utmanande Caltech pedestrian dataset. I det här examensarbetet presenteras en metod som kan öka prestandan för en kaskad av boostingklassificerare ämnad för fotgängardetektion. Det färgbaserad särdraget color self similarity, Walk et al.[2010], används för att skapa en version som är bättre lämpad för boosting. Det presenterade särdraget ökade prestandan jämfört med befintliga klassificerare som används av Autoliv på både data inspelat av Autoliv och på Caltech pedestrian dataset.

No description available.

Darbe aprašytas modelis, naudojant aktyvacijos funkcijas su Gauso branduoliais. Vienu atveju buvo paimtos aktyvacijos funkcijos, maksimizuojančios Shannon entropija, kitu – maksimizuojančios Renyi entropiją. Manoma, kad tokio tipo funkcijos turėtų geriau tikti prognozavimui. / In this thesis a novel technique is used to construct sparse generalized Gaussian Kernel regression model- so called neural network. Kernel which maximize Renyi entropy is used too. Experimental results obtained using these models are promising.

Raman spectroscopy has been successfully employed in the classification of breast pathologies involving basis spectra for chemical constituents of breast tissue and resulted in high sensitivity (94%) and specificity (96%) (Haka et al, 2005). Motivated by recent developments in nonparametric regression, in this work, we adapt stacking, boosting, and dynamic ensemble learning into a nonparametric regression framework with application to Raman spectroscopy analysis for breast cancer diagnosis. In Chapter 2, we apply compound estimation (Charnigo and Srinivasan, 2011) in Raman spectra analysis to classify normal, benign, and malignant breast tissue. We explore both the spectra profiles and their derivatives to differentiate different types of breast tissue. In Chapters 3-5 of this dissertation, we develop a novel paradigm for incorporating ensemble learning classification methodology into a nonparametric regression framework. Specifically, in Chapter 3 we set up modified stacking framework and combine different classifiers together to make better predictions in nonparametric regression settings. In Chapter 4 we develop a method by incorporating a modified AdaBoost algorithm in nonparametric regression settings to improve classification accuracy. In Chapter 5 we propose a dynamic ensemble integration based on multiple meta-learning strategies for nonparametric regression based classification. In Chapter 6, we revisit the Raman spectroscopy data in Chapter 2, and make improvements based on the developments of the methods from Chapter 3 to Chapter 4. Finally we summarize the major findings and contributions of this work as well as identify opportunities for future research and their public health implications.

Chemical exposure in humans rarely consists of a single chemical. The everyday exposure is characterized by thousands of chemicals mainly present at low levels. Despite that fact, risk assessment of chemicals is carried out on a chemical-by-chemical basis although there is a consensus that this view is too simplistic. This thesis aims to validate a statistical method to study the impact of mixtures of contaminants and to use that method to investigate the associations between circulating levels of a large number of environmental contaminants and atherosclerosis and the metabolic syndrome in an elderly population. Contaminants measured in the circulation represented various classes, such as persistent organic pollutants, plastic-associated chemicals and metals. There was little co-variation among the contaminants and only two clusters of PCBs could be discerned. Gradient boosted CARTs were used to assess additive and multiplicative associations between atherosclerosis, as measured by the intima-media thickness (IMT) and the echogenicity of the intima-media complex (IM-GSM), and prevalent metabolic syndrome. Systolic blood pressure was the most important predictor of IMT while the influence of the contaminants was marginal. Three phthalate metabolites; MMP, MEHP and MIBP were strongly related to IM-GSM. A synergistic interaction was found for MMP and MIBP, and a small antagonistic interaction was found for MIBP and MEHP. Associations between the contaminants and prevalent metabolic syndrome were modest, but three pesticides; p,p’-DDE, hexachlorbenzene and trans-nonachlor along with PCBs 118 and 209 and mercury were the strongest predictors of prevalent metabolic syndrome. This thesis concludes that many contaminants need to be measured to get a clear picture of the exposure. Boosted CARTs are useful for uncovering interactions. Multiplicative and/or additive effects of certain contaminant mixtures were found for atherosclerosis or the metabolic syndrome.

We consider the problem of detecting a large number of different classes of objects in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, at multiple locations and scales. This can be slow and can require a lot of training data, since each classifier requires the computation of many different image features. In particular, for independently trained detectors, the (run-time) computational complexity, and the (training-time) sample complexity, scales linearly with the number of classes to be detected. It seems unlikely that such an approach will scale up to allow recognition of hundreds or thousands of objects.We present a multi-class boosting procedure (joint boosting) that reduces the computational and sample complexity, by finding common features that can be shared across the classes (and/or views). The detectors for each class are trained jointly, rather than independently. For a given performance level, the total number of features required, and therefore the computational cost, is observed to scale approximately logarithmically with the number of classes. The features selected jointly are closer to edges and generic features typical of many natural structures instead of finding specific object parts. Those generic features generalize better and reduce considerably the computational cost of an algorithm for multi-class object detection.

We seek to both detect and segment objects in images. To exploit both local image data as well as contextual information, we introduce Boosted Random Fields (BRFs), which uses Boosting to learn the graph structure and local evidence of a conditional random field (CRF). The graph structure is learned by assembling graph fragments in an additive model. The connections between individual pixels are not very informative, but by using dense graphs, we can pool information from large regions of the image; dense models also support efficient inference. We show how contextual information from other objects can improve detection performance, both in terms of accuracy and speed, by using a computational cascade. We apply our system to detect stuff and things in office and street scenes.

Object recognition systems relying on local descriptors are increasingly used because of their perceived robustness with respect to occlusions and to global geometrical deformations. Descriptors of this type -- based on a set of oriented Gaussian derivative filters -- are used in our recognition system. In this paper, we explore a multi-view 3D object recognition system that does not use explicit geometrical information. The basic idea is to find discriminant features to describe an object across different views. A boosting procedure is used to select features out of a large feature pool of local features collected from the positive training examples. We describe experiments on face images with excellent recognition rate.