An automatic voice pleasantness classification system based on prosodic and acoustic patterns of voice preference

In the last few years the number of systems and devices that use voice based interaction has grown significantly. For a continued use of these systems the interface must be reliable and pleasant in order to provide an optimal user experience. However there are currently very few studies that try to evaluate how good is a voice when the application is a speech based interface. In this paper we present a new automatic voice pleasantness classification system based on prosodic and acoustic patterns of voice preference. Our study is based on a multi-language database composed by female voices. In the objective performance evaluation the system achieved a 7.3% error rate.

Impact of carbon/nitrogen feeding strategy on polyhydroxyalkanoates production using mixed microbial cultures

Polyhydroxyalkanoates (PHA) production using mixed microbial cultures (MMC) requires a multi-stage process involving the microbial selection of PHA-storing microorganisms, typically operated in sequencing batch reactors (SBR), and an accumulation reactor. Since low-cost renewable feedstocks used as process feedstock are often nitrogen-deficient, nutrient supply in the selection stage is required to allow for microbial growth. In this context, the possibility to uncouple nitrogen supply from carbon feeding within the SBR cycle has been investigated in this study. Moreover, three different COD:N ratios (100:3.79, 100:3.03 and 100:2.43) were tested in three different runs which also allowed the study of COD:N ratio on the SBR performance. For each run, a synthetic mixture of acetic and propionic acids at an overall organic load rate of 8.5 gCOD L-1 d-1 was used as carbon feedstock, whereas ammonium sulfate was the nitrogen source in a lab-scale sequence batch reactor (SBR) with 1 L of working volume. Besides, a sludge retention time (SRT) of 1 d was used as well as a 6 h cycle length. The uncoupled feeding strategy significantly enhanced the selective pressure towards PHA-storing microorganisms, resulting in a two-fold increase in the PHA production (up to about 1.3 gCOD L-1). A high storage response was observed for the two runs with the COD:N ratios (gCOD:gN) of 100:3.79 and 100:3.03, whereas the lowest investigated nitrogen load resulted in very poor performance in terms of polymer production. In fact, strong nitrogen limitation caused fungi to grow and a very poor storage ability by microorganisms that thrived in those conditions. The COD:N ratio also affected the polymer composition, indeed the produced poly(3-hydroxybutyrate-co-3-hydroxyvalerate) (PHBV) showed a variable HV content (1-20 %, w/w) among the three runs, lessening as the COD:N increased. This clearly suggests the possibility to use the COD:N ratio as a tool for tuning polymer properties regardless the composition of the feedstock.

Genetic algorithm for shipping route estimation with long-range tracking data : automatic reconstruction of shipping routes based on the historical ship positions for maritime safety applications

Ship tracking systems allow Maritime Organizations that are concerned with the Safety at Sea to obtain information on the current location and route of merchant vessels. Thanks to Space technology in recent years the geographical coverage of the ship tracking platforms has increased significantly, from radar based near-shore traffic monitoring towards a worldwide picture of the maritime traffic situation. The long-range tracking systems currently in operations allow the storage of ship position data over many years: a valuable source of knowledge about the shipping routes between different ocean regions. The outcome of this Master project is a software prototype for the estimation of the most operated shipping route between any two geographical locations. The analysis is based on the historical ship positions acquired with long-range tracking systems. The proposed approach makes use of a Genetic Algorithm applied on a training set of relevant ship positions extracted from the long-term storage tracking database of the European Maritime Safety Agency (EMSA). The analysis of some representative shipping routes is presented and the quality of the results and their operational applications are assessed by a Maritime Safety expert.

Automatic top-down processing explains common left occipito-temporal responses to visual words and objects.

Previous studies have demonstrated that a region in the left ventral occipito-temporal (LvOT) cortex is highly selective to the visual forms of written words and objects relative to closely matched visual stimuli. Here, we investigated why LvOT activation is not higher for reading than picture naming even though written words and pictures of objects have grossly different visual forms. To compare neuronal responses for words and pictures within the same LvOT area, we used functional magnetic resonance imaging adaptation and instructed participants to name target stimuli that followed briefly presented masked primes that were either presented in the same stimulus type as the target (word-word, picture-picture) or a different stimulus type (picture-word, word-picture). We found that activation throughout posterior and anterior parts of LvOT was reduced when the prime had the same name/response as the target irrespective of whether the prime-target relationship was within or between stimulus type. As posterior LvOT is a visual form processing area, and there was no visual form similarity between different stimulus types, we suggest that our results indicate automatic top-down influences from pictures to words and words to pictures. This novel perspective motivates further investigation of the functional properties of this intriguing region.

Automatic measurement of key ski jumping phases and temporal events with a wearable system.

We propose a new method, based on inertial sensors, to automatically measure at high frequency the durations of the main phases of ski jumping (i.e. take-off release, take-off, and early flight). The kinematics of the ski jumping movement were recorded by four inertial sensors, attached to the thigh and shank of junior athletes, for 40 jumps performed during indoor conditions and 36 jumps in field conditions. An algorithm was designed to detect temporal events from the recorded signals and to estimate the duration of each phase. These durations were evaluated against a reference camera-based motion capture system and by trainers conducting video observations. The precision for the take-off release and take-off durations (indoor < 39 ms, outdoor = 27 ms) can be considered technically valid for performance assessment. The errors for early flight duration (indoor = 22 ms, outdoor = 119 ms) were comparable to the trainers' variability and should be interpreted with caution. No significant changes in the error were noted between indoor and outdoor conditions, and individual jumping technique did not influence the error of take-off release and take-off. Therefore, the proposed system can provide valuable information for performance evaluation of ski jumpers during training sessions.

Automatic Mallampati Classification Using Active Appearance Models

Difficult tracheal intubation assessment is an important research topic in anesthesia as failed intubations are important causes of mortality in anesthetic practice. The modified Mallampati score is widely used, alone or in conjunction with other criteria, to predict the difficulty of intubation. This work presents an automatic method to assess the modified Mallampati score from an image of a patient with the mouth wide open. For this purpose we propose an active appearance models (AAM) based method and use linear support vector machines (SVM) to select a subset of relevant features obtained using the AAM. This feature selection step proves to be essential as it improves drastically the performance of classification, which is obtained using SVM with RBF kernel and majority voting. We test our method on images of 100 patients undergoing elective surgery and achieve 97.9% accuracy in the leave-one-out crossvalidation test and provide a key element to an automatic difficult intubation assessment system.

Analysis of the feeding behaviour of the mosquito Culex pipiens L. (Diptera: Culicidae) in relation to West Nile virus

The goal ofthis literature review is to inform the reader on several aspects of West Nile Virus (WNV) transmission by its mosquito vector, Culex pipiens and to elucidate how Cx. pipiens and WNV are intertwined. The first few sections of the literature review describe the life cycle and blood feeding behaviours ofmosquitoes so that baseline data ofmosquito biology are established. In addition to explaining how and why a mosquito blood feeds, the section on "Blood Meal Analysis" describes the different methods for determining the vertebrate source of mosquito blood meals and a brief history of these testing methods. Since this thesis looks at the feeding behaviour of Cx. pipiens, it is important to know how to determine what they are feeding upon. Discussion on other mosquito-borne diseases related to WNV gives a broader perspective to the thesis, and examines other diseases that have occurred in Ontario in the past. This is followed by background information on WNV and theories on how this virus came to North America and how it relates to Cx. pipiens. The final sections discuss Cx. pipiens and give background information to how this species of mosquito exists and behaves within North America.

An investigation of sugar feeding by black flies (Diptera: Simuliidae)

Although much research has been conducted on blood-meal acquisition in adult female black flies (Diptera: Simuliidae), the same cannot be said for sugarmeals. Both sexes feed on sugar which provides energy for flight and it has been commonly held that nectar is the major carbohydrate source. This thesis addresses the question of whether a non-floral carbohydrate source, specifically homopteran honeydew, is ingested by male and female black flies. Black flies reared in the laboratory have been observed to readily ingest freshly excreted and older (dry) honeydew when presented with honeydew coated tamarack branches. Field work was conducted in Algonquin Park, Ontario in the spring and summer of 1993. Three separate studies were designed to test whether homopteran honeydew is an important carbohydrate source for black flies and whether flies from different habitats utilize different sugar sources. The sugars melezitose and / or stachyose are known to occur in a variety of homopteran honeydews and therefore were used as indicators of honeydew feeding by black flies. In the first study, black flies were collected with insect nets from a stand of Larix larcina heavily infested with honeydew - producing homopterans (Adelges lariciatus). Six black fly species were captured: Simulium venustum, S. rostra tum, S. vittatum, Stegopterna mutata, S. aureum and S. quebecense. Samples of honeydew and individual black flies were tested using thin layer chromatography (T. L. C.) with fructose, glucose, sucrose, turanose, melezitose, raffinose and stachyose as standards. All sugars except turanose and melezitose were found in the adelgid honeydew samples. Since the sugar melezitose was absent from ~ honeydew samples, stachyose was used to indicate that black flies were feeding from this particular honeydew source. Of the 201 black flies tested, 194 contained sugars which occurred in 16 combinations. Stachyose combinations excluding melezitose, present in 45.9 % of flies, were used to indicate that black flies had been feeding on the adelgid honeydew. In the second study, black flies were collected in the morning and evening on 8 collection dates, using a vehicle mounted insect net. The crops and midguts of 10 male and 10 female Simulium venustum were dissected on each sample date. In total the gut contents of 320 individual flies were analysed by T. L. C. The sugars identified from these flies were present in the following proportions: fructose (100.0%), glucose (100.0%), sucrose/turanose (50.4%), melezitose (30.3%), raffinose (18.8%) and stachyose (8.7%). These sugars occurred in fourteen different combinations. It is argued that the presence of melezitose and / or stachyose indicates that black flies had fed on homopteran honeydew. Significantly more female flies (40.0%) than male flies (27.5%) had fed on honeydew. In the third study, adult black flies were sampled by sweep netting vegetation in four habitats in the morning and evening on 8 collection dates. The habitats are as follows: (1) Davies Bog, (2) Abandoned Air Field (dominated by blueberries, Vaccinium spp.), (3) Deciduous Habitat and (4) Coniferous Habitat. Sugars in the crops and midguts of female flies were tested by T. L. C. and, for S. venustum, it was found that significantly fewer flies (18.8%) from the Air Field contained honeydew than from the other three sites (Davies Bog, 34.4%; Deciduous Habitat, 36.2%; Coniferous Habitat, 25.0%). Of the 1287 black flies tested individually by T. L. C. 441 (34.3%) contained melezitose and / or stachyose sugars indicating that this proportion of the population were feeding from Homopteran honeydew. It is therefore clear that floral (nectar) sugars are not the only source of carbohydrates available to black flies.

Feeding rates, parental investment, and brood reduction in Caspian terns (Sterna caspia)

Fresh egg-weights and feeding rates to chicks were related to chick survival as one means of quantifying apportionment of parental investment wi thin broods of Caspian Terns (SterDI casRla) at a colony in Georgian Bay. Lake Huron, during 1978 and 1979. Ftrst-laid eggs from 2-egg clutches were Significantly heavier and usually hatched one to three days earlier than second-laid eggs in both years of the study. In both years, first-hatched chicks were larger and generally better fed than second-hatched siblings. The disparity between feedIng rates of first- and second-hatched ehicks was greater in 1979. Brood feeding I rates correlated positively with the percentage of food fed to the least-fed sibUng through the period of B-chick ages zero to 10 days in 1978. I suggest that after this age period, parental control over whlcb cbick was fed diminished. In 1978, 10 of 16 secondhatched chicks were fed more than their older siblings during their first 5 days. 'lb.is is interpreted as a parental response to reduce the competitive advantage of the larger first-hatched chicks. Most chick losses were apparently caused by starvation or preda. tion. In 1979, seeorvl-hatched chick disappearance (due to predation) was -related to low feeding rates, whereas first-hatched chick disappearance was related to low fresh egg-weights.. First-hatched chicks survived better than second-hatched chicks both years, and more pairs fledged two chicks in 1978. Maximum estimated feeding rates at the nest and fledging ages suggested that food was more avatlable in 1978 than in 1979. In 1979, second eggs apparently functioned as "insurance" eggs. When the first-laid egg falled to hatch, or the first-hatched chick died, the second-hatched chick was often successfully fledged. When first-hatched chicks survived, the second-hatched chick usually starved or was preyed upon, reducing the brood to one chick. Parental investment patterns favored first-hatched chicks. Brood reduction, when employed, discouraged total nest failure, however, under appropriate conditions, brood reduction was avoided and full broods (or two chicks) were fledged.

The effect of feeding regime on larval black fly (Diptera: simuliidae) primary head fan ray number

Identification of larval simuliids has always been difficult due to the morphological similarity many species bear to one another. For this reason all characters available have been drawn upon to aid in species identification, including head fan ray number. Even in light of an increasing body of anecdotal reports that head fan ray number is not fixed, it has continued to be used to aid species identification. In the current experiment simuliid larvae were reared under controlled laboratory conditions to last instar in one of three feeding regimes. Out of nine trials, the results of six showed a significant inverse relationship between feeding regime and head fan ray number. In addition to the laboratory experiments, larvae were also collected from the field over the course of the spring and summer, 1994. From these samples significant interspecific and intraspecific variations in head fan ray number were found both spatially and temporally within Algonquin Park. From these data it is concluded that head fan ray number for the species analysed is a developmentally plastic character, which varies in response to food availability. Furthermore, given the extreme variations in head fan ray number found in some species, I recommend that head fan ray number not be used as an aid to identification unless it can be shown to be a fixed character for the species in question.

Automatic Structure Generation using Genetic Programming and Fractal Geometry

Three dimensional model design is a well-known and studied field, with numerous real-world applications. However, the manual construction of these models can often be time-consuming to the average user, despite the advantages o ffered through computational advances. This thesis presents an approach to the design of 3D structures using evolutionary computation and L-systems, which involves the automated production of such designs using a strict set of fitness functions. These functions focus on the geometric properties of the models produced, as well as their quantifiable aesthetic value - a topic which has not been widely investigated with respect to 3D models. New extensions to existing aesthetic measures are discussed and implemented in the presented system in order to produce designs which are visually pleasing. The system itself facilitates the construction of models requiring minimal user initialization and no user-based feedback throughout the evolutionary cycle. The genetic programming evolved models are shown to satisfy multiple criteria, conveying a relationship between their assigned aesthetic value and their perceived aesthetic value. Exploration into the applicability and e ffectiveness of a multi-objective approach to the problem is also presented, with a focus on both performance and visual results. Although subjective, these results o er insight into future applications and study in the fi eld of computational aesthetics and automated structure design.

Automatic evolution of conceptual building architectures

This thesis describes research in which genetic programming is used to automatically evolve shape grammars that construct three dimensional models of possible external building architectures. A completely automated fitness function is used, which evaluates the three dimensional building models according to different geometric properties such as surface normals, height, building footprint, and more. In order to evaluate the buildings on the different criteria, a multi-objective fitness function is used. The results obtained from the automated system were successful in satisfying the multiple objective criteria as well as creating interesting and unique designs that a human-aided system might not discover. In this study of evolutionary design, the architectures created are not meant to be fully functional and structurally sound blueprints for constructing a building, but are meant to be inspirational ideas for possible architectural designs. The evolved models are applicable for today's architectural industries as well as in the video game and movie industries. Many new avenues for future work have also been discovered and highlighted.

Automatic Inference of Graph Models for Complex Networks with Genetic Programming

Complex networks can arise naturally and spontaneously from all things that act as a part of a larger system. From the patterns of socialization between people to the way biological systems organize themselves, complex networks are ubiquitous, but are currently poorly understood. A number of algorithms, designed by humans, have been proposed to describe the organizational behaviour of real-world networks. Consequently, breakthroughs in genetics, medicine, epidemiology, neuroscience, telecommunications and the social sciences have recently resulted. The algorithms, called graph models, represent significant human effort. Deriving accurate graph models is non-trivial, time-intensive, challenging and may only yield useful results for very specific phenomena. An automated approach can greatly reduce the human effort required and if effective, provide a valuable tool for understanding the large decentralized systems of interrelated things around us. To the best of the author's knowledge this thesis proposes the first method for the automatic inference of graph models for complex networks with varied properties, with and without community structure. Furthermore, to the best of the author's knowledge it is the first application of genetic programming for the automatic inference of graph models. The system and methodology was tested against benchmark data, and was shown to be capable of reproducing close approximations to well-known algorithms designed by humans. Furthermore, when used to infer a model for real biological data the resulting model was more representative than models currently used in the literature.

Real-Time Automatic Object Classification and Tracking using Genetic Programming and NVIDIA R CUDA TM

Genetic Programming (GP) is a widely used methodology for solving various computational problems. GP's problem solving ability is usually hindered by its long execution times. In this thesis, GP is applied toward real-time computer vision. In particular, object classification and tracking using a parallel GP system is discussed. First, a study of suitable GP languages for object classification is presented. Two main GP approaches for visual pattern classification, namely the block-classifiers and the pixel-classifiers, were studied. Results showed that the pixel-classifiers generally performed better. Using these results, a suitable language was selected for the real-time implementation. Synthetic video data was used in the experiments. The goal of the experiments was to evolve a unique classifier for each texture pattern that existed in the video. The experiments revealed that the system was capable of correctly tracking the textures in the video. The performance of the system was on-par with real-time requirements.

Network Similarity Measures and Automatic Construction of Graph Models using Genetic Programming

A complex network is an abstract representation of an intricate system of interrelated elements where the patterns of connection hold significant meaning. One particular complex network is a social network whereby the vertices represent people and edges denote their daily interactions. Understanding social network dynamics can be vital to the mitigation of disease spread as these networks model the interactions, and thus avenues of spread, between individuals. To better understand complex networks, algorithms which generate graphs exhibiting observed properties of real-world networks, known as graph models, are often constructed. While various efforts to aid with the construction of graph models have been proposed using statistical and probabilistic methods, genetic programming (GP) has only recently been considered. However, determining that a graph model of a complex network accurately describes the target network(s) is not a trivial task as the graph models are often stochastic in nature and the notion of similarity is dependent upon the expected behavior of the network. This thesis examines a number of well-known network properties to determine which measures best allowed networks generated by different graph models, and thus the models themselves, to be distinguished. A proposed meta-analysis procedure was used to demonstrate how these network measures interact when used together as classifiers to determine network, and thus model, (dis)similarity. The analytical results form the basis of the fitness evaluation for a GP system used to automatically construct graph models for complex networks. The GP-based automatic inference system was used to reproduce existing, well-known graph models as well as a real-world network. Results indicated that the automatically inferred models exemplified functional similarity when compared to their respective target networks. This approach also showed promise when used to infer a model for a mammalian brain network.