Search

Foot ulcers and amputations are common conditions in people with diabetes and can considerably impact quality of life, necessitate a lengthy hospital stay and increase mortality. Preventative foot care and examination can prevent or delay ulceration, and individuals may seek information from publicly available social media resources such as YouTube. Therefore, the purpose of this study is to evaluate the educational quality and reliability of publicly available YouTube videos on diabetes foot examinations.A YouTube search for "diabetic foot examination" was conducted, and the first 100 relevant English videos focused on examining the diabetic foot were included for evaluation. The Journal of the American Medical Association (JAMA) standards were used to measure video reliability. The Global Quality Score (GQS) and the Diabetes UK Annual Foot Check (DUK-C) checklist were used to assess video educational quality. Differences in JAMA, GQS, and DUK-C ratings were analysed after videos were sorted by topic and source.The mean number of views per video was 101,311.9 ± 348,383.6, and the mean video power index was 41.6 ± 170.0. The most common upload source was from physicians (28%) and, the most popular material category was diabetes foot examination (58 videos). In terms of video reliability, 36% of videos scored 0. According to the GQS standards, only 5% of the videos are of excellent quality, while 34% are of poor quality, with 24 videos scoring between 0 and 1 on the DUK-C scale.While foot care examination videos have a substantial audience, the majority are considered low in quality and reliability. Videos on comprehensive diabetic foot examination should be accessed on reputable sources that guarantee standardisations of video quality and take into account the simplification of information transmission in order to reach lay audiences.

Medical image security relies upon the arrival of improved techniques for enhancing the confusion as well as diffusion processes in the pixel level manipulations. Non-linear circuits constructed with hardware components can be employed for hardware–software co-design in medical image encryption. The proposed approach has adopted Chua diode circuit for the generation of 256 × 256 random synthetic image with the entropy of 7.9972. This synthetic image has been utilised to scramble the DICOM image for the second level of diffusion as the cellular automata provides the first level of scrambling and diffusion. The average correlation coefficients of encrypted pixels are 0.00204, −0.00298 and −0.00054 in three directions. The encrypted pixels pass the NIST SP 800-22 test suite and offer resistance to statistical, differential and chosen plain text attacks.

This paper presents the design of an adaptive input–output feedback linearizing dorsal fin control system for the yaw plane control of low-speed bio-robotic autonomous underwater vehicles (BAUVs). The control forces are generated by cambering two dorsal fins mounted in the vertical plane on either side of the vehicle. The BAUV model includes nonlinear hydrodynamics, and it is assumed that its hydrodynamic coefficients as well as the physical parameters are not known. For the purpose of design, a linear combination of the yaw angle tracking error and its derivative and integral is chosen as the controlled output variable. An adaptive input–output feedback linearizing control law is derived for the trajectory control of the yaw angle. Unlike indirect adaptive control, here the controller gains are directly tuned. The stability of the zero dynamics is examined. Simulation results are presented for tracking exponential and sinusoidal yaw angle trajectories and for turning maneuvers, and it is shown that the adaptive control system accomplishes precise yaw angle control of the BAUV using dorsal fins in spite of the nonlinearity and large uncertainties in the system parameters.

In this paper, adaptive control of low speed bio-robotic autonomous underwater vehicles (BAUVs) in the dive plane using dorsal fins is considered. It is assumed that the model parameters are completely unknown and only the depth of the vehicle is measured for feedback. Two dorsal fins are mounted in the horizontal plane on either side of the BAUV. The normal force produced by the fins, when cambered, is used for the maneuvering. The BAUV model considered here is non-minimum phase. An indirect adaptive control system is designed for the depth control using the dorsal fins. The control system consists of a gradient based identifier for online parameter estimation, an observer for state estimation, and an optimal controller. Simulation results are presented which show that the adaptive control system accomplishes precise depth control of the BAUV using dorsal fins in spite of large uncertainties in the system parameters.

This paper treats the question of control of a biorobotic autonomous undersea vehicle (BAUV) in the yaw plane using a biomimetic mechanism resembling the pectoral fins of fish. These fins are assumed to undergo a combined sway-yaw motion and the bias angle is treated as a control input, which is varied in time to accomplish the maneuver in the yaw-plane. The forces and moments produced by the flapping foil are parametrized using computational fluid dynamics. A finite-difference-based, Cartesian grid immersed boundary solver is used to simulate flow past the flapping foils. The periodic forces and moments are expanded as a Fourier series and a discrete-time model of the BAUV is developed for the purpose of control. An optimal control system for the set point control of the yaw angle and an inverse control law for the tracking of time-varying yaw angle trajectories are designed. Simulation results show that in the closed-loop system, the yaw angle follows commanded sinusoidal trajectories and the segments of the intersample yaw trajectory remain close to the discrete-time reference trajectory. It is also found that the fins suitably located near the center of mass of the vehicle provide better maneuverability.

Contextual advertising on web pages has become very popular recently and it poses its own set of unique text mining challenges. Often advertisers wish to either target (or avoid) some specific content on web pages which may appear only in a small part of the page. Learning for these targeting tasks is difficult since most training pages are multi-topic and need expensive human labeling at the sub-document level for accurate training. In this paper we investigate ways to learn for sub-document classification when only page level labels are available - these labels only indicate if the relevant content exists in the given page or not. We propose the application of multiple-instance learning to this task to improve the effectiveness of traditional methods. We apply sub-document classification to two different problems in contextual advertising. One is "sensitive content detection" where the advertiser wants to avoid content relating to war, violence, pornography, etc. even if they occur only in a small part of a page. The second problem involves opinion mining from review sites - the advertiser wants to detect and avoid negative opinion about their product when positive, negative and neutral sentiments co-exist on a page. In both these scenarios we present experimental results to show that our proposed system is able to get good block level labeling for free and improve the performance of traditional learning methods.

Speaker verification can be treated as a statistical hypothesis testing problem. The most commonly used approach is the likelihood ratio test (LRT), which can be shown to be optimal using the Neymann-Pearson lemma. However, in most practical situations the Neymann-Pearson lemma does not apply. In this paper, we present a more robust approach that makes use of a hybrid generative-discriminative framework for text-dependent speaker verification. Our algorithm makes use of a generative models to learn the characteristics of a speaker and then discriminative models to discriminate between a speaker and an impostor. One of the advantages of the proposed algorithm is that it does not require us to retrain the generative model. The proposed model, on an average, yields 36.41% relative improvement in EER over a LRT.

The Viterbi algorithm is an efficient and optimal method for decoding linear-chain Markov Models. However, the entire input sequence must be observed before the labels for any time step can be generated, and therefore Viterbi cannot be directly applied to online/interactive/streaming scenarios without incurring significant (possibly unbounded) latency. A widely used approach is to break the input stream into fixed-size windows, and apply Viterbi to each window. Larger windows lead to higher accuracy, but result in higher latency.We propose several alternative algorithms to the fixed-sized window decoding approach. These approaches compute a certainty measure on predicted labels that allows us to trade off latency for expected accuracy dynamically, without having to choose a fixed window size up front. Not surprisingly, this more principled approach gives us a substantial improvement over choosing a fixed window. We show the effectiveness of the approach for the task of spotting semi-structured information in large documents. When compared to full Viterbi, the approach suffers a 0.1 percent error degradation with a average latency of 2.6 time steps (versus the potentially infinite latency of Viterbi). When compared to fixed windows Viterbi, we achieve a 40x reduction in error and 6x reduction in latency.

In recent work, conditional Markov chain models (CMM) have been used to extract information from semi-structured text (one example is the Conditional Random Field [10]). Applications range from finding the author and title in research papers to finding the phone number and street address in a web page. The CMM framework combines a priori knowledge encoded as features with a set of labeled training data to learn an efficient extraction process. We will show that similar problems can be solved more effectively by learning a discriminative context free grammar from training data. The grammar has several distinct advantages: long range, even global, constraints can be used to disambiguate entity labels; training data is used more efficiently; and a set of new more powerful features can be introduced. The grammar based approach also results in semantic information (encoded in the form of a parse tree) which could be used for IR applications like question answering. The specific problem we consider is of extracting personal contact, or address, information from unstructured sources such as documents and emails. While linear-chain CMMs perform reasonably well on this task, we show that a statistical parsing approach results in a 50% reduction in error rate. This system also has the advantage of being interactive, similar to the system described in [9]. In cases where there are multiple errors, a single user correction can be propagated to correct multiple errors automatically. Using a discriminatively trained grammar, 93.71% of all tokens are labeled correctly (compared to 88.43% for a CMM) and 72.87% of records have all tokens labeled correctly (compared to 45.29% for the CMM).

Grammars are a powerful technique for modeling and extracting the structure of documents. One large challenge, however, is computational complexity. The computational cost of grammatical parsing is related to both the complexity of the input and the ambiguity of the grammar. For programming languages, where the terminals appear in a linear sequence and the grammar is unambiguous, parsing is O(N). For natural languages, which are linear yet have an ambiguous grammar, parsing is O(N/sup 3/). For documents, where the terminals are arranged in two dimensions and the grammar is ambiguous, parsing time can be exponential in the number of terminals. In this paper we introduce (and unify) several types of geometrical data structures which can be used to significantly accelerate parsing time. Each data structure embodies a different geometrical constraint on the set of possible valid parses. These data structures are very general, in that they can be used by any type of grammatical model, and a wide variety of document understanding tasks, to limit the set of hypotheses examined and tested. Assuming a clean design for the parsing software, the same parsing framework can be tested with various geometric constraints to determine the most effective combination.