Neural networks have frequently been found to give accurate solutions to hard classification problems. However neural networks do not make explained classifications because the class boundaries are implicitly defined by the network weights, and these weights do not lend themselves to simple analysis. Explanation is desirable because it gives problem insight both to the designer and to the user of the classifier. Many methods have been suggested for explaining the classification given by a neural network, but they all suffer from one or more of the following disadvantages: a lack of equivalence between the network and the explanation; the absence of a probability framework required to express the uncertainty present in the data; a restriction to problems with binary or coarsely discretised features; reliance on axis-aligned rules, which are intrinsically poor at describing the boundaries generated by neural networks. The structure of the solution presented in this thesis rests on the following steps: Train a standard neural network to estimate the class conditional probabilities. Bayes’ rule then defines the optimal class boundaries. Obtain an explicit representation of these class boundaries using a piece-wise linearisation technique. Note that the class boundaries are otherwise only implicitly defined by the network weights. Obtain a safe but possibly partial description of this explicit representation using rules based upon the city-block distance to a prototype pattern. The methods required to achieve the last two represent novel work which seeks to explain the answers given by a proven neural network solution to the classification problem.

This research focused on the off-line cursive script recognition application. The problem is very large and difficult and there is much room for improvement in every aspect of the problem. Many different aspects of this problem were explored in pursuit of solutions to create a more practical and usable off-line cursive script recognizer than is currently available.

This dissertation addresses the general problem of recognition of acoustic signals which may be derived from speech, sonar, or acoustic phenomena. The specific problem of recognizing speech is the main focus of this research. The intention is to design a recognition system for a definite number of discrete words. For this purpose specifically, eight isolated words from the T1MIT database are selected. Four medium length words "greasy," "dark," "wash," and "water" are used. In addition, four short words are considered "she," "had," "in," and "all." The recognition system addresses the following issues: filtering or preprocessing, training, and decision-making. The preprocessing phase uses linear predictive coding of order 12. Following the filtering process, a vector quantization method is used to further reduce the input data and generate a finite inductive sequence of symbols representative of each input signal. The sequences generated by the vector quantization process of the same word are factored, and a single ruling or reference template is generated and stored in a codebook. This system introduces a new modeling technique which relies heavily on the basic concept that all finite sequences are finitely inductive. This technique is used in the training stage. In order to accommodate the variabilities in speech, the training is performed casualty, and a large number of training speakers is used from eight different dialect regions. Hence, a speaker independent recognition system is realized. The matching process compares the incoming speech with each of the templates stored, and a closeness ration is computed. A ratio table is generated anH the matching word that corresponds to the smallest ratio (i.e. indicating that the ruling has removed most of the symbols) is selected. Promising results were obtained for isolated words, and the recognition rates ranged between 50% and 100%.

This thesis has aimed to explore an application of Multibiometrics to secured wireless communications. The medium of study for this purpose included Wi-Fi, 3G, and WiMAX, over which simulations and experimental studies were carried out to assess the performance. In specific, restriction of access to authorized users only is provided by a technique referred to hereafter as multibiometric cryptosystem. In brief, the system is built upon a complete challenge/response methodology in order to obtain a high level of security on the basis of user identification by fingerprint and further confirmation by verification of the user through text-dependent speaker recognition. First is the enrolment phase by which the database of watermarked fingerprints with memorable texts along with the voice features, based on the same texts, is created by sending them to the server through wireless channel. Later is the verification stage at which claimed users, ones who claim are genuine, are verified against the database, and it consists of five steps. Initially faced by the identification level, one is asked to first present one’s fingerprint and a memorable word, former is watermarked into latter, in order for system to authenticate the fingerprint and verify the validity of it by retrieving the challenge for accepted user. The following three steps then involve speaker recognition including the user responding to the challenge by text-dependent voice, server authenticating the response, and finally server accepting/rejecting the user. In order to implement fingerprint watermarking, i.e. incorporating the memorable word as a watermark message into the fingerprint image, an algorithm of five steps has been developed. The first three novel steps having to do with the fingerprint image enhancement (CLAHE with 'Clip Limit', standard deviation analysis and sliding neighborhood) have been followed with further two steps for embedding, and extracting the watermark into the enhanced fingerprint image utilising Discrete Wavelet Transform (DWT). In the speaker recognition stage, the limitations of this technique in wireless communication have been addressed by sending voice feature (cepstral coefficients) instead of raw sample. This scheme is to reap the advantages of reducing the transmission time and dependency of the data on communication channel, together with no loss of packet. Finally, the obtained results have verified the claims.

While a correlation between suffering from psychosis and an increased risk of engaging in aggressive behaviours has been established, many factors have been explored which may contribute to increasing this risk. Patients with a diagnosis of psychosis have been shown to have significant difficulties in facial affect recognition (FAR) and some authors have proposed that this may contribute to increasing the risk of displaying aggressive or violent behaviours. A systematic review of the current evidence regarding the links between facial affect recognition and aggression was conducted. Results were varied with some studies providing evidence of a link between emotion recognition difficulties and aggression, while others were unable to establish such an association. Results should be interpreted with some caution as the quality of included studies was poor due to small sample sizes, insufficient power and limited reporting of results. Adequately powered, randomised controlled studies using appropriate blinding procedures and validated measures are therefore required. There is a substantial evidence base demonstrating difficulties in emotional perception in patients with psychosis, with evidence suggesting a relationship with reduced social functioning, increased aggression and more severe symptoms of psychosis. In this review we aim to review this field to assess if there is a causal link between facial affect recognition difficulties and psychosis. The Bradford Hill criteria for establishing a causal relationship from observational data were used to generate key hypotheses, which were then tested against existing evidence. Where a published meta-analysis was not already available, new meta-analyses were conducted. A large effect of FAR difficulties in those with a diagnosis of psychosis, with a small to moderate correlation between FAR problems and symptoms of psychosis was found. Evidence was provided for the existence of FAR problems in those at clinical high risk of psychosis, while remediation of psychosis symptoms did not appear to impact FAR difficulties. There appears to be good evidence of the existence of facial affect recognition difficulties in the causation of psychosis, though larger, longitudinal studies are required to provide further evidence of this.

Many items encoded into episodic memory are highly similar – seeing a stranger’s car may result in a memory representation which overlaps in many features with the memory of your friend’s car. To avoid falsely recognising the novel but similar car, it is important for the representations to be distinguished in memory. Even in healthy young adults failures of this mnemonic discrimination lead relatively often to false recognition, and such errors become substantially more frequent in older age. Whether an item’s representation is discriminated from similar memory representations depends critically on how it is encoded. However, the precise encoding mechanisms involved remain poorly understood. Establishing the determinants of successful mnemonic discrimination is essential for future research into strategies or interventions to prevent recognition errors, particularly in the context of age-related decline. A fuller understanding of age-related decline in mnemonic discrimination can also inform basic models of memory. This thesis evaluated the contribution of encoding processes to mnemonic discrimination both in young adults and in ageing, within the framework of two prominent accounts of recognition memory, the pattern separation account (Wilson et al., 2006) and Fuzzy Trace Theory (FTT; Brainerd & Reyna, 2002). Firstly, a functional magnetic resonance imaging study in young adults found evidence for differences in regions engaged at encoding of images according to the accuracy of later mnemonic discrimination, consistent with both pattern separation and FTT. Evidence of functional overlap between regions showing activity consistent with pattern separation, and activity associated with later accurate recognition was consistent with a role of cortical pattern separation in successful encoding, but there was no direct evidence that cortical pattern separation contributed to mnemonic discrimination. This first evidence of cortical pattern separation in humans was supported by findings that in the majority of pattern separation regions, response functions to stimuli varied in their similarity to previous items were consistent with predictions of computational models. Regional variation in the dimension(s) of similarity (conceptual/perceptual) driving pattern separation was indicative of variation in the type of mnemonic interference minimised by cortical pattern separation. Further evidence of encoding contributions to mnemonic discrimination was provided by an event-related potential study in young and older adults. Older adults showed less distinct waveforms than young adults at encoding of items whose similar lures were later correctly rejected compared to those falsely recognised, supporting the proposal that age-related encoding impairments contribute to the decline in mnemonic discrimination. Finally, a set of behavioural studies found that older adults’ mnemonic discrimination deficit is increased by conceptual similarity, supporting previous findings and consistent with FTT’s account of greater emphasis by older adults on gist processing. However, older adults required greater reduction in perceptual or conceptual similarity in order to successfully reject lures, as uniquely predicted by the pattern separation account. Together, the findings support the notion that encoding processes contribute directly to mnemonic discrimination and its age-related decline. An integrated view of the pattern separation account and FTT is discussed and developed in relation to the current findings.

abstract: In recent years, conventional convolutional neural network (CNN) has achieved outstanding performance in image and speech processing applications. Unfortunately, the pooling operation in CNN ignores important spatial information which is an important attribute in many applications. The recently proposed capsule network retains spatial information and improves the capabilities of traditional CNN. It uses capsules to describe features in multiple dimensions and dynamic routing to increase the statistical stability of the network. In this work, we first use capsule network for overlapping digit recognition problem. We evaluate the performance of the network with respect to recognition accuracy, convergence and training time per epoch. We show that capsule network achieves higher accuracy when training set size is small. When training set size is larger, capsule network and conventional CNN have comparable recognition accuracy. The training time per epoch for capsule network is longer than conventional CNN because of the dynamic routing algorithm. An analysis of the GPU timing shows that adjusting the capsule structure can help decrease the time complexity of the dynamic routing algorithm significantly. Next, we design a capsule network for speech recognition, specifically, overlapping word recognition. We use both capsule network and conventional CNN to recognize 2 overlapping words in speech files created from 5 word classes. We show that capsule network achieves a considerably higher recognition accuracy (96.92%) compared to conventional CNN (85.19%). Our results show that capsule network recognizes overlapping word by recognizing each individual word in the speech. We also verify the scalability of capsule network by increasing the number of word classes from 5 to 10. Capsule network still shows a high recognition accuracy of 95.42% in case of 10 words while the accuracy of conventional CNN decreases sharply to 73.18%. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2018

Doctor of Philosophy(PhD) / Communication is a fundamental process that allows animals to effectively transfer information between groups or individuals. Recognition plays an essential role in permitting animals to distinguish individuals based upon both communicatory and non-communicatory signals allowing animals to direct suitable behaviours towards them. Several modes of recognition exist and in colonial breeding animals which congregate in large numbers, acoustic signalling is thought to be the most effective as it suffers less from environmental degradation. Otariid seals (fur seals and sea lions) are generally colonial breeding species which congregate at high densities on offshore islands. In contrast to the other Arctocephaline species, the Australian fur seal, Arctocephalus pusillus doriferus, along with its conspecific, the Cape fur seal, A. p. pusillus, display many of the behavioural traits of sea lions. This may have important consequences in terms of its social structure and evolution. The acoustic communication of Australian fur seals was studied on Kanowna Island, Bass Strait, Australia. Analysing the acoustic structure of vocalisations and their use facilitates our understanding of the social function of calls in animal communication. The vocal repertoires of males, females, pups and yearlings were characterised and their behavioural context examined. Call structural variations in males were evident with changes in behavioural context, indicating parallel changes in the emotive state of sender. For a call to be used in vocal recognition it must display stereotypy within callers and variation between them. In Australian fur seal females and pups, individuals were found to have unique calls. Mutual mother-pup recognition has been suggested for otariids and this study supports the potential for this process to occur through the use of vocalisations. Call structural changes in pup vocalisations were also investigated over the progression of the year, from birth to weaning. Vocalisations produced by pups increased in duration, lowered in both the number of parts per call and the harmonic band containing the maximum frequency as they became older, suggesting calls are changing constantly as pups grow toward maturity. It has been suggested through descriptive reports, that the bark call produced by males is important to vocal recognition. The present study quantified this through the analysis of vocalisations produced by male Australian fur seals. Results support descriptive evidence suggesting that male barks can be used to discriminate callers. Traditional playback studies further confirmed that territorial male Australian fur seals respond significantly more to the calls of strangers than to those of neighbours, supporting male vocal recognition. This study modified call features of the bark to determine the importance to vocal recognition. The results indicate that the whole frequency spectrum was important to recognition. There was also an increase in response from males when they heard more bark units, indicating the importance of repetition by a caller. Recognition occurred when males heard between 25-75% of each bark unit, indicating that the whole duration of each bark unit is not necessary for recognition to occur. This may have particular advantages for communication in acoustically complex breeding environments, where parts of calls may be degraded by the environment. The present study examined the life history characteristics of otariids to determine the factors likely to influence and shape its vocal behaviour. Preliminary results indicate that female density, body size and the breeding environment all influence the vocal behaviour of otariids, while duration of lactation and the degree of polygyny do not appear to be influential. Understanding these interactions may help elucidate how vocal recognition and communication have evolved in different pinniped species.

Stastical pattern recognition is the most successful approach to automatic speech and speaker recognition (ASASR). Of all the statistical pattern recognition techniques, the hidden Markov model (HMM) is the most important. The Gaussian mixture model (GMM) and vector quantisation (VQ) are also effective techniques, especially for speaker recognition and in conjunction with HMMs. for speech recognition. However, the performance of these techniques degrades rapidly in the context of insufficient training data and in the presence of noise or distortion. Fuzzy approaches with their adjustable parameters can reduce such degradation. Fuzzy set theory is one of the most, successful approaches in pattern recognition, where, based on the idea of a fuzzy membership function, fuzzy C'-means (FCM) clustering and noise clustering (NC) are the most, important techniques. To establish fuzzy approaches to ASASR, the following basic problems are solved. First, a time-dependent fuzzy membership function is defined for the HMM. Second, a general distance is proposed to obtain a relationship between modelling and clustering techniques. Third, fuzzy entropy (FE) clustering is proposed to relate fuzzy models to statistical models. Finally, fuzzy membership functions are proposed as discriminant functions in decison making. The following models are proposed: 1) the FE-HMM. NC-FE-HMM. FE-GMM. NC-FEGMM. FE-VQ and NC-FE-VQ in the FE approach. 2) the FCM-HMM. NC-FCM-HMM. FCM-GMM and NC-FCM-GMM in the FCM approach, and 3) the hard HMM and GMM as the special models of both FE and FCM approaches. Finally, a fuzzy approach to speaker verification and a further extension using possibility theory are also proposed. The evaluation experiments performed on the TI46, ANDOSL and YOHO corpora showbetter results for all of the proposed techniques in comparison with the non-fuzzy baseline techniques.

This thesis proposes a methodology for the design of man-machine interfaces by combining top-down and bottom-up processes in vision. From a computational perspective, we propose that the scientific-cognitive question of combining top-down and bottom-up knowledge is similar to the engineering question of labeling a training set in a supervised learning problem. We investigate these questions in the realm of facial analysis. We propose the use of a linear morphable model (LMM) for representing top-down structure and use it to model various facial variations such as mouth shapes and expression, the pose of faces and visual speech (visemes). We apply a supervised learning method based on support vector machine (SVM) regression for estimating the parameters of LMMs directly from pixel-based representations of faces. We combine these methods for designing new, more self-contained systems for recognizing facial expressions, estimating facial pose and for recognizing visemes.