Honeybees are one of the most important pollinating species in agriculture. Every three out of four crops have honeybee as their sole pollinator. Since 2006 there has been a drastic decrease in the bee population which is attributed to Colony Collapse Disorder(CCD). The bee colonies fail/ die without giving any traditional health symptoms which otherwise could help in alerting the Beekeepers in advance about their situation. Electronic Beehive Monitoring System has various sensors embedded in it to extract video, audio and temperature data that could provide critical information on colony behavior and health without invasive beehive inspections. Previously, significant patterns and information have been extracted by processing the video/image data, but no work has been done using audio data. This research inaugurates and takes the first step towards the use of audio data in the Electronic Beehive Monitoring System (BeePi) by enabling a path towards the automatic classification of audio samples in different classes and categories within it. The experimental results give an initial support to the claim that monitoring of bee buzzing signals from the hive is feasible, it can be a good indicator to estimate hive health and can help to differentiate normal behavior against any deviation for honeybees.

This thesis is concerned with the development of novel methods of classifying data that is not inherently clustered. The performance of these novel algorithms in finding classifications in this data will be compared with that of existing artificial intelligence methods.

No description available.

Design problems in engineering are typically complex, and are therefore decomposed into a hierarchy of smaller, simpler design problems by the design management. It is often the case in a hierarchical design problem that an upstream design team’s achievable performance space becomes the design space for a downstream design team. A Bayesian network classifier is proposed in this research to map and classify a design team’s attainable performance space. The classifier will allow for enhanced collaboration between design teams, letting an upstream design team efficiently identify and share their attainable performance space with a downstream design team. The goal is that design teams can work concurrently, rather than sequentially, thereby reducing lead time and design costs. In converging to a design solution, intelligently narrowing the design space allows for resources to be focused in the most beneficial regions. However, the process of narrowing the design space is non-trivial, as each design team must make performance trade-offs that may unknowingly affect other design teams. The performance space mapping provided by the Bayesian network classifier allows designers to better understand the consequences of narrowing the design space. This knowledge allows design decisions to be made at the system-level, and be propagated down to the subsystem-level, leading to higher quality designs. The proposed methods of mapping the performance space are then applied to a hierarchical, multi-level metamaterial design problem. The design problem explores the possibility of designing and fabricating composite materials that have desirable macro-scale mechanical properties as a result of embedded micro-scale inclusions. The designed metamaterial is found to have stiffness and loss properties that surpass those of conventional composite materials. / text

Processing decision information is a vital part of Computer Science fields in which pattern recognition problems arise. Decision information can be generalized as alternative decisions (or classes), attributes and attribute values, which are the basis for classification. Different classification approaches exist, such as decision trees, decision tables and Naïve Bayesian classifiers, which capture and manipulate decision information in order to construct a specific decision model (or classifier). These approaches are often tightly coupled to learning strategies, special data structures and the special characteristics of the decision information captured, etc. The approaches are also connected to the way of how certain problems are addressed, e.g., memory consumption, low accuracy, etc. This situation causes problems for a simple choice, comparison, combination and manipulation of different decision models learned over the same or different samples of decision information. The choice and comparison of decision models are not merely the choice of a model with a higher prediction accuracy and a comparison of prediction accuracies, respectively. We also need to take into account that a decision model, when used in a certain application, often has an impact on the application's performance. Often, the combination and manipulation of different decision models are implementation- or application-specific, thus, lacking the generality that leads to the construction of decision models with combined or modified decision information. They also become difficult to transfer from one application domain to another. In order to unify different approaches, we define Decision Algebra, a theoretical framework that presents decision models as higher order decision functions that abstract from their implementation details. Decision Algebra defines the operations necessary to decide, combine, approximate, and manipulate decision functions along with operation signatures and general algebraic laws. Due to its algebraic completeness (i.e., a complete algebraic semantics of operations and its implementation efficiency), defining and developing decision models is simple as such instances require implementing just one core operation based on which other operations can be derived. Another advantage of Decision Algebra is composability: it allows for combination of decision models constructed using different approaches. The accuracy and learning convergence properties of the combined model can be proven regardless of the actual approach. In addition, the applications that process decision information can be defined using Decision Algebra regardless of the different classification approaches. For example, we use Decision Algebra in a context-aware composition domain, where we showed that context-aware applications improve performance when using Decision Algebra. In addition, we suggest an approach to integrate this context-aware component into legacy applications.

Determining species of individual trees is important for forest management. In this thesis we investigate if it is possible to discriminate between Norway spruce, Scots pine and deciduous trees from airborne laser scanning data by using unique probability density functions estimated for each specie. We estimate the probability density functions in three different ways: by fitting a beta distribution, histogram density estimation and kernel density estimation. All these methods classifies single laser returns (and not segments of laser returns). The resulting classification is compared with a reference method based on features extracted from airborne laser scanning data.We measure how well a method performs by using the overall accuracy, that is the proportion of correctly predicted trees. The highest overall accuracy obtained by the methods we developed in this thesis is obtained by using histogram-density estimation where an overall accuracy of 83.4 percent is achieved. This result can be compared with the best result from the reference method that produced an overall accuracy of 84.1 percent. The fact that we achieve a high level of correctly classified trees indicates that it is possible to use these types of methods for identification of tree species. / Att kunna artbestämma enskilda träd är viktigt inom skogsbruket. I denna uppsats undersöker vi om det är möjligt att skilja mellan gran, tall och lövträd med data från en flygburen laserskanner genom att skatta en unik täthetsfunktion för varje trädslag. Täthetsfunktionerna skattas på tre olika sätt: genom att anpassa en beta-fördelning, skatta täthetsfunktionen med histogram samt skatta täthetsfunktionen med en kernel täthetsskattning. Alla dessa metoder klassificerar varje enskild laserretur (och inte segment av laserreturer). Resultaten från vår klassificering jämförs sedan med en referensmetod som bygger på särdrag från laserskanner data. Vi mäter hur väl metoderna presterar genom att jämföra den totala precisionen, vilket är andelen korrektklassificerade träd. Den högsta totala precisionen för de framtagna metoderna i denna uppsats erhölls med metoden som bygger på täthetsskattning med histogram. Precisionen för denna metod var 83,4 procent rättklassicerade träd. Detta kan jämföras med en rättklassificering på 84,1 procent vilket är det bästa resultatet för referensmetoderna. Att vi erhåller en så pass hög grad av rättklassificerade träd tyder på att de metoder som vi använder oss av är användbara för trädslagsklassificering.

Currently technologies such as EEG, EMG and EOG recordings are the established methods used in the analysis of sleep. But if these methods are to be employed to study sleep in rodents, extensive surgery and recovery is involved which can be both time consuming and costly. This thesis presents and analyzes a cost effective, non-invasive, high throughput system for detecting the sleep and wake patterns in mice using a piezoelectric sensor. This sensor was placed at the bottom of the mice cages to monitor the movements of the mice. The thesis work included the development of the instrumentation and signal acquisition system for recording the signals critical to sleep and wake classification. Classification of the mouse sleep and wake states were studied for a linear classifier and a Neural Network classifier based on 23 features extracted from the Power Spectrum (PS), Generalized Spectrum (GS), and Autocorrelation (AC) functions of short data intervals. The testing of the classifiers was done on two data sets collected from two mice, with each data set having around 5 hours of data. A scoring of the sleep and wake states was also done via human observation to aid in the training of the classifiers. The performances of these two classifiers were analyzed by looking at the misclassification error of a set of test features when run through a classifier trained by a set of training features. The best performing features were selected by first testing each of the 23 features individually in a linear classifier and ranking them according to their misclassification rate. A test was then done on the 10 best individually performing features where they were grouped in all possible combinations of 5 features to determine the feature combinations leading to the lowest error rates in a multi feature classifier. From this test 5 features were eventually chosen to do the classification. It was found that the features related to the signal energy and the spectral peaks in the 3Hz range gave the lowest errors. Error rates as low as 4% and 9% were achieved from a 5-feature linear classifier for the two data sets. The error rates from a 5-feature Neural Network classifier were found to be 6% and 12% respectively for these two data sets.

För att köpa boken skicka en beställning till exp@ling.su.se/ To order the book send an e-mail to exp@ling.su.se

In this paper we describe a technique of classifier combination used in a human identification system. The system integrates all available features from multi-modal sources within a Bayesian framework. The framework allows representinga class of popular classifier combination rules and methods within a single formalism. It relies on a “per-class” measure of confidence derived from performance of each classifier on training data that is shown to improve performance on a synthetic data set. The method is especially relevant in autonomous surveillance setting where varying time scales and missing features are a common occurrence. We show an application of this technique to the real-world surveillance database of video and audio recordings of people collected over several weeks in the office setting.

Scientific research on free will was started by Libet et al. (1982). They detected that thereadiness potential (RP) proceeded urges with up to 350ms. One interpretation of the RP wasthat it represented motor planning. The research progress of antecedent brain activity inrelation to conscious urges is investigated by looking at contemporary studies. How differentassumptions and definitions of the free will concept influences interpretation of these studiesis also discussed. The evidence is in favor that the RP is not representing motor planning.Antecedent activity has been detected with numerous technologies, most notably fMRIclassifiers which have been used to predict decisions in advance. Scrutiny of these resultsreveals that the experimental setups are dependent on time-locking trials which may construethe results. It is shown that predictions based on probabilistic antecedents can be interpretedin numerous ways. The review shows that free will positions differ from each other onseveral factors, such as whether free will is either-or or exists on a spectrum. Some notablepositions are not dependent on antecedent activity at all. The notion of control is one of thepivotal factors deciding if a subject experience free will, not if they are the causer per se.Future discussion will be improved by systematizing the differences between the free willpositions and communicating them clearly. Convergent evidence points at the explanatorymodel of free will being a cognitive feeling – A feeling which reports ownership over actionsbut does not cause them.