Kernel Null Space Methods for Novelty Detection

Condition monitoring is an indispensable element related to the operation of rotating machinery. In this article, the monitoring system for the parallel gearbox was proposed. The novelty detection approach is used to develop the condition assessment support system, which requires data collection for a healthy structure. The measured signals were processed to extract quantitative indicators sensitive to the type of damage occurring in this type of structure. The indicator’s values were used for the development of four different novelty detection algorithms. Presented novelty detection models operate on three principles: feature space distance, probability distribution, and input reconstruction. One of the distance-based models is adaptive, adjusting to new data flowing in the form of a stream. The authors test the developed algorithms on experimental and simulation data with a similar distribution, using the training set consisting mainly of samples generated by the simulator. Presented in the article results demonstrate the effectiveness of the trained models on both data sets.

Estradiol or diarylpropionitrile administration to wild type, but not estrogen receptor beta knockout, mice enhances performance in the object recognition and object placement tasks

This paper investigates the influence of the signal to noise ratio (SNR) and the type of a noise on the performance of two adaptive novelty detection methods. The evaluated methods are Learning Entropy (LE) and Error and Learning Based Novelty Detection (ELBND). The methods are compared in empirical way in classification framework. A classification based only on the error of the adaptive model was used as a reference. The research in this field is important, because a noise is present in every measured data and can drastically influence the result of tasks like the novelty detection. Moreover, various types of noise can influence the novelty detection in different ways, therefore the optimal method of adaptive novelty detection can be hard to choose. This assumption is supported by experimental results in this study.

Young pigs exhibit differential exploratory behavior during novelty preference tasks in response to age, sex, and delay

Appearance of microcalcifications in mammograms is one of the early signs of breast cancer. In this work, one-class support vector machines (SVM), a novelty detection method, is utilized for detection of the mammogram samples containing microcalcifications. These samples are small regions of the mammograms with the size of 25x25 pixels. Each of the samples are represented by 25 features that are already proven to be accurate identifiers of the microcalcifications. Since the obtained classification performance of one-class SVM with all these 25 features is very low (accuracy = 0.5575, sensitivity = 0.2107, specificity = 0.9042), number of these features is reduced by using principal component analysis (PCA). Training a classifier only with the PCA features achieves an improved performance (accuracy = 0.9464, sensitivity = 1.0000, specificity = 0.8927) where the number of false negative samples is reduced from 206 to 0.

Positive modulation of alpha-amino-3-hydroxy-5-methyl-4-isoxazolepropionic acid (AMPA) receptors reverses sub-chronic PCP-induced deficits in the novel object recognition task in rats

One-class CNNs have shown promise in novelty detection. However, very less work has been done on extending them to multiclass classification. The proposed approach is a viable effort in this direction. It uses one-class CNNs i.e., it trains one CNN per class, for multiclass classification. An ensemble of such one-class CNNs is used for multiclass classification. The benefits of the approach are generally better recognition accuracy while taking almost even half or two-thirds of the training time of a conventional multi-class deep network. The proposed approach has been applied successfully to face recognition and object recognition tasks. For face recognition, a 1000 frame RGB video, featuring many faces together, has been used for benchmarking of the proposed approach. Its database is available on request via e-mail. For object recognition, the Caltech-101 Image Database and 17Flowers Dataset have also been used. The experimental results support the claims made.

The detection of new information in a document stream is an important component of many potential applications. In this paper, a new novelty detection approach based on the identification of sentence level patterns is proposed. Given a user's information need, some patterns in sentences such as combinations of query words, named entities and phrases, may contain more important and relevant information than single words. Therefore, the proposed novelty detection approach focuses on the identification of previously unseen query-related patterns in sentences. Specifically, a query is preprocessed and represented with patterns that include both query words and required answer types. These patterns are used to retrieve sentences, which are then determined to be novel if it is likely that a new answer is present. An analysis of patterns in sentences was performed with data from the TREC 2002 novelty track and experiments on novelty detection were carried out on data from the TREC 2003 and 2004 novelty tracks. The experimental results show that the proposed pattern-based approach significantly outperforms all three baselines in terms of precision at top ranks.

The kinematics of a free-floating space robot (FFSR) is more complex than that of a fixed-base robot, and hence its motion planning is more difficult. In this paper, the kinematics of the FFSR is introduced firstly. Then the null space approach is used to reparameterize the path: the direction and magnitude are decoupled and no direction error is introduced. And the Newton iterative method is adopted to find the optimal magnitude of the joint velocity. A plannar FFSR with a 2 DOFs manipulator is selected to test the algorithm and simulation results illustrate that the path following is realized prisely. Finally, deficiencies of the method and prospecsts for the future are summarized.

Central histamine H3 receptors are a family of presynaptic auto and heteroreceptors. Blockade of the presynaptic H3 receptors activates the downstream pathway(s) involved in the processes of learning and memory, making it a potential therapeutic option for ameliorating cognitive dysfunction. Samelisant (SUVN-G3031) is a potent and selective inverse agonist at the H3 receptors. The aim of this research is to study the effects of Samelisant in diverse animal models of cognitive functions. The effects of Samelisant on cognitive functions were studied using social recognition, object recognition and Morris water maze tasks. Neurochemical and electrophysiological effects of Samelisant were monitored using microdialysis and electroencephalography techniques. Samelisant showed procognitive effects in diverse animal models of cognition at doses ranging from 0.3 to 3 mg/kg, per os (p.o.) (social recognition and object recognition task). Samelisant significantly increased the brain acetylcholine levels in the cortex at doses of 10 and 20 mg/kg, p.o. In the Morris water maze task, combined administration of suboptimal doses of Samelisant and donepezil resulted in procognitive effects significantly larger than the either treatment. Similarly, Samelisant significantly potentiated the effects of donepezil on pharmacodynamic biomarkers of cognition i.e. acetylcholine levels in brain and neuronal theta oscillations. Samelisant may have potential utility in the treatment of cognitive deficits associated with hypocholinergic state.

Domain adaptation from RGB-D to RGB images

Memantine ameliorates the impairment of hippocampal long-term potentiation in olfactory bulbectomized mice.

Spaced initial stimulus familiarization enhances novelty preference in Long-Evans rats

Assessing rodent hippocampal involvement in the novel object recognition task. A review

Before a future with household robots is really feasible, those robots need to be easily adaptable to novel environments and users, be able to apply previously acquired knowledge, and able to learn from perceiving and interacting with the world and users around them. This thesis proposes a cognitive architecture and a set of underlining methods for automatic knowledge acquisition that will bring household robots one step closer to reality. The thesis was inspired by the cognitive development of babies and subsequently treats the topics: Knowledge representation, Sensory motor integration, Knowledge acquisition & learning and Real world applications. We derived ways to describe and efficiently combine visual information, despite cluttered environments and changing illumination. We propose a method to combine different key-point extractors and to select only a small subset based on their information entropy. Since object appearances can vary in colour, texture and 2D/3D shape, we extract feature vectors from multiple viewpoints of the object and calculate the dominant features, which leads to a more robust object recognition process. This also automatically calculates the most efficient way to store the representative features of unknown objects. This method is similar to the information storage process in humans; an important characteristic of human learning is the pruning of information in the working memory to the most relevant information to be stored in long term memory. In order to detect and segment objects without any prior knowledge on their appearance or their background, we designed a visual-attention module that is able to find the salient parts of an image and clusters them into objects ranked by their saliency. Once these objects are localized, the system must act upon them to efficiently learn their properties. This is achieved by simultaneous exploration and manipulation of the selected - most salient - unknown object. However, such a cognitive system cannot be realized without a robot body, and therefore we designed a simple and affordable robot. Another cognitive ability that a future household robot certainly must have is knowledge accumulation from previous experiences. Consequently, we designed a cognitive architecture that allows a robot that has no pre- insight in the world and its objects to incrementally acquire all its expertise from interaction with the environment. We proposed models of working and long term memory as well as algorithms for novelty detection. Finally, we treat two realized applications for external parties, based on our algorithms: Bin-picking by an industrial robot and action detection in ceiling mounted cameras in elderly homes.