No description available.

Streamed data classification problems (SDCPs) require classifiers with the ability to learn and to adjust to the underlying relationships in data streams, in real-time. This requirement poses a challenge to classifiers, because the learning task is no longer just to find the optimal decision boundaries, but also to track changes in the decision boundaries as new training data is received. The challenge is due to concept drift, i.e. the changing of decision boundaries over time. Changes include disappearing, appearing, or shifting decision boundaries. This thesis proposes an online learning approach for feed forward neural networks (FFNNs) that meets the requirements of SDCPs. The approach uses regularisation to optimise the architecture via the weights, and quantum particle swarm optimisation (QPSO) to dynamically adjust the weights. The learning approach is applied to a FFNN, which uses rectified linear activation functions, to form a novel SDCP classifier. The classifier is empirically investigated on several SDCPs. Both weight decay (WD) and weight elimination (WE) are investigated as regularisers. Empirical results show that using QPSO with no regularisation, causes the classifier to completely saturate. However, using QPSO with regularisation enables the classifier to dynamically adapt both its implicit architecture and weights as decision boundaries change. Furthermore, the results favour WE over WD as a regulariser for QPSO. / Dissertation (MSc)--University of Pretoria, 2020. / National Research Foundation (NRF) / Computer Science / MSc / Unrestricted

The problems of achieving high detection rate with low false alarm rate for human detection and tracking in video sequence, performance scalability, and improving response time are addressed in this thesis. The underlying causes are the effect of scene complexity, human-to-human interactions, scale changes, and scene background-human interactions. A two-stage processing solution, namely, human detection, and human tracking with two novel pattern classifiers is presented. Scale independent human detection is achieved by processing in the wavelet domain using square wavelet features. These features used to characterise human silhouettes at different scales are similar to rectangular features used in [Viola 2001]. At the detection stage two detectors are combined to improve detection rate. The first detector is based on shape-outline of humans extracted from the scene using a reduced complexity outline extraction algorithm. A Shape mismatch measure is used to differentiate between the human and the background class. The second detector uses rectangular features as primitives for silhouette description in the wavelet domain. The marginal distribution of features collocated at a particular position on a candidate human (a patch of the image) is used to describe statistically the silhouette. Two similarity measures are computed between a candidate human and the model histograms of human and non human classes. The similarity measure is used to discriminate between the human and the non human class. At the tracking stage, a tracker based on joint probabilistic data association filter (JPDAF) for data association, and motion correspondence is presented. Track clustering is used to reduce hypothesis enumeration complexity. Towards improving response time with increase in frame dimension, scene complexity, and number of channels; a scalable algorithmic architecture and operating accuracy prediction technique is presented. A scheduling strategy for improving the response time and throughput by parallel processing is also presented.

This thesis focuses on simulating, detecting, localizing and classifying the power quality disturbances using advanced signal processing techniques and neural networks. Primarily discrete wavelet and Fourier transforms are used for feature extraction, and classification is achieved by using neural network algorithms. The proposed feature vector consists of a combination of features computed using multi resolution analysis and discrete Fourier transform. The proposed feature vectors exploit the benefits of having both time and frequency domain information simultaneously. Two different classification algorithms based on Feed forward neural network and adaptive resonance theory neural networks are proposed for classification. This thesis demonstrates that the proposed methodology achieves a good computational and error classification efficiency rate.

Title: Artificial Neural Networks and Their Usage For Knowledge Extraction Author: RNDr. Zuzana Petříčková Department: Department of Theoretical Computer Science and Mathema- tical Logic Supervisor: doc. RNDr. Iveta Mrázová, CSc., Department of Theoretical Computer Science and Mathematical Logic Abstract: The model of multi/layered feed/forward neural networks is well known for its ability to generalize well and to find complex non/linear dependencies in the data. On the other hand, it tends to create complex internal structures, especially for large data sets. Efficient solutions to demanding tasks currently dealt with require fast training, adequate generalization and a transparent and simple network structure. In this thesis, we propose a general framework for training of BP/networks. It is based on the fast and robust scaled conjugate gradient technique. This classical training algorithm is enhanced with analytical or approximative sensitivity inhibition during training and enforcement of a transparent in- ternal knowledge representation. Redundant hidden and input neurons are pruned based on internal representation and sensitivity analysis. The performance of the developed framework has been tested on various types of data with promising results. The framework provides a fast training algorithm,...

No description available.

Indiana University-Purdue University Indianapolis (IUPUI) / The compressed air system is widely used throughout the industry. Air compressors are one of the most costly systems to operate in industrial plants in terms of energy consumption. Therefore, it becomes one of the primary targets when it comes to electrical energy and load management practices. Load forecasting is the first step in developing energy management systems both on the supply and user side. A comprehensive literature review has been conducted, and there was a need to study if predicting compressed air system’s load is a possibility. System’s load profile will be valuable to the industry practitioners as well as related software providers in developing better practice and tools for load management and look-ahead scheduling programs. Feed forward neural networks (FFNN) and long short-term memory (LSTM) techniques have been used to perform 15 minutes ahead prediction. Three cases of different sizes and control methods have been studied. The results proved the possibility of the forecast. In this study two control methods have been developed by using the prediction. The first control method is designed for variable speed driven air compressors. The goal was to decrease the maximum electrical load for the air compressor by using the system's full operational capabilities and the air receiver tank. This goal has been achieved by optimizing the system operation and developing a practical control method. The results can be used to decrease the maximum electrical load consumed by the system as well as assuring the sufficient air for the users during the peak compressed air demand by users. This method can also prevent backup or secondary systems from running during the peak compressed air demand which can result in more energy and demand savings. Load management plays a pivotal role and developing maximum load reduction methods by users can result in more sustainability as well as the cost reduction for developing sustainable energy production sources. The last part of this research is concentrated on reducing the energy consumed by load/unload controlled air compressors. Two novel control methods have been introduced. One method uses the prediction as input, and the other one doesn't require prediction. Both of them resulted in energy consumption reduction by increasing the off period with the same compressed air output or in other words without sacrificing the required compressed air needed for production. / 2019-12-05

Information Filtering and Recommender Systems have been used and has been implemented in various ways from various entities since the dawn of the Internet, and state-of-the-art approaches rely on Machine Learning and Deep Learning in order to create accurate and personalized recommendations for users in a given context. These models require big amounts of data with a variety of features such as time, location and user data in order to find correlations and patterns that other classical models such as matrix factorization and collaborative filtering cannot. This thesis researches, implements and compares a variety of models with the primary focus of Machine Learning and Deep Learning for the task of music recommendation and do so successfully by representing the task of recommendation as a multi-class extreme classification task with 100 000 distinct labels. By comparing fourteen different experiments, all implemented models successfully learn features such as time, location, user features and previous listening history in order to create context-aware personalized music predictions, and solves the cold start problem by using user demographic information, where the best model being capable of capturing the intended label in its top 100 list of recommended items for more than 1/3 of the unseen data in an offine evaluation, when evaluating on randomly selected examples from the unseen following week. / Informationsfiltrering och rekommendationssystem har använts och implementeratspå flera olika sätt från olika enheter sedan gryningen avInternet, och moderna tillvägagångssätt beror påMaskininlärrning samtDjupinlärningför att kunna skapa precisa och personliga rekommendationerför användare i en given kontext. Dessa modeller kräver data i storamängder med en varians av kännetecken såsom tid, plats och användardataför att kunna hitta korrelationer samt mönster som klassiska modellersåsom matris faktorisering samt samverkande filtrering inte kan. Dettaexamensarbete forskar, implementerar och jämför en mängd av modellermed fokus påMaskininlärning samt Djupinlärning för musikrekommendationoch gör det med succé genom att representera rekommendationsproblemetsom ett extremt multi-klass klassifikationsproblem med 100000 unika klasser att välja utav. Genom att jämföra fjorton olika experiment,så lär alla modeller sig kännetäcken såsomtid, plats, användarkänneteckenoch lyssningshistorik för att kunna skapa kontextberoendepersonaliserade musikprediktioner, och löser kallstartsproblemet genomanvändning av användares demografiska kännetäcken, där den bästa modellenklarar av att fånga målklassen i sin rekommendationslista medlängd 100 för mer än 1/3 av det osedda datat under en offline evaluering,när slumpmässigt valda exempel från den osedda kommande veckanevalueras.