ISR: indoor shop recognition via user-friendly and efficient fingerprinting on smartphones

Indoor shop recognition can not only help mobile users to quickly recognize a shop to know about the information of interest without needing to enter the shop, but also assist in achieving more accurate user localization in a shopping mall. However, the existing Wi-Fi fingerprint-based approaches or image-based approaches cannot accomplish this goal well due to a huge cost of constructing large-scale fingerprint database and poor accuracy. In order to address these issues, we proposed a user-friendly and efficient fingerprinting method to collect various valuable sensory data with smartphones, which can not only reduce the randomness of fingerprints and the negative impact of pedestrians in image matching, but also be used to derive the user-to-shop distance based on the perspective projection model for assisting in determining an accurate fingerprint searching scope. We also proposed an efficient fingerprint searching and matching method to improve the recognition accuracy. We implemented a prototype system and collected fingerprint datasets in a shopping mall. Extensive experiments demonstrate that our solution achieves promising results in realistic scenarios.     

Efficient dynamic time warping for 3D handwriting recognition using gyroscope equipped smartphones

Handwriting character recognition from three-dimensional (3D) accelerometer data has emerged as a popular technique for natural human computer interaction. In this paper, we propose a 3D gyroscope-based handwriting recognition system that uses stepwise lower-bounded dynamic time warping, instead of conventional 3D accelerometer data. The results of experiments conducted indicate that our proposed method is more effective and efficient than conventional methods for user-independent recognition of the 26 lowercase letters in the English alphabet.     

Energy efficient indoor tracking on smartphones

Continuously identifying a user’s location context provides new opportunities to understand daily life and human behavior. Indoor location systems have been mainly based on WiFi infrastructures which consume a great deal of energy mostly due to keeping the user’s WiFi device connected to the infrastructure and network communication, limiting the overall time when a user can be tracked. Particularly such tracking systems on battery-limited mobile devices must be energy-efficient to limit the impact on the experience of using a phone. Recently, there have been a lot of studies of energy-efficient positioning systems, but these have focused on outdoor positioning technologies. In this paper, we propose a novel indoor tracking framework that intelligently determines the location sampling rate and the frequency of network communication, to optimize the accuracy of the location data while being energy-efficient at the same time. This framework leverages an accelerometer, widely available on everyday smartphones, to reduce the duty cycle and the network communication frequency when a tracked user is moving slowly or not at all. Our framework can work for 14 h without charging, supporting applications that require this location information without affecting user experience.     

An efficient posture recognition method using fuzzy logic

Computer-human interaction plays an important role in virtual reality. Glove-based input devices have many desirable features which make direct interactions between the user and the virtual world possible. However, due to the complexity of the human hand, recognising hand functions precisely and efficiently is not an easy task. Existing algorithms are either imprecise or computationally expensive, making them impractical to integrate with VR applications, which are usually very CPU intensive.In the problem of posture and gesture recognition, both the sample patterns stored in the database and the ones to be recognised may be imprecise. This kind of imprecise knowledge can be best dealt with using fuzzy logic. A fast and simple posture recognition method using fuzzy logic is presented in this paper. Our model consists of three components: the posture database, the classifier and the identifier. The classifier roughly classifies the sample postures before they are put into the posture database. The identifier compares an input posture with the records in the identified class and finds the right match efficiently. Fuzzy logic is applied in both the classification and identification processes to cope with imprecise data. The main goal of this method is to recognise hand functions in an accurate and efficient manner. The accuracy, efficiency and the noise tolerance of the model have been examined through a number of experiments.     

Slider vibration reduction using slider surface texture

Surface texture with a height of 4.5 nm was fabricated on two types of pico-sliders using argon plasma etching. The nominal flying height of the sliders was 5 and 7 nm, respectively. Laser Doppler vibrometry (LDV) was used to investigate the dynamics of the textured and untextured sliders during steady-state flying and during contact start/stop (CSS). During steady-state flying, the texture was found to significantly reduce both rigid body slider vibration modes and air-bearing modes. During CSS, the amplitude of both out-of-plane and in-plane vibrations was found to be reduced as a consequence of the texture on the slider surfaces.     

Small-vocabulary speech recognition using surface electromyography

We present results of electromyographic (EMG) speech recognition on a small vocabulary of 15 English words. EMG speech recognition holds promise for mitigating the effects of high acoustic noise on speech intelligibility in communication systems, including those used by first responders (a focus of this work). We collected 150 examples per word of single-channel EMG data from a male subject, speaking normally while wearing a firefighter’s self-contained breathing apparatus. The signal processing consisted of an activity detector, a feature extractor, and a neural network classifier. Testing produced an overall average correct classification rate on the 15 words of 74% with a 95% confidence interval of (71%, 77%). Once trained, the subject used a classifier as part of a real-time system to communicate to a cellular phone and to control a robotic device. These tasks were performed under an ambient noise level of approximately 95 decibels. We also describe ongoing work on phoneme-level EMG speech recognition.     

Mobile context inference using two-layered Bayesian networks for smartphones

Recently, mobile context inference becomes an important issue. Bayesian probabilistic model is one of the most popular probabilistic approaches for context inference. It efficiently represents and exploits the conditional independence of propositions. However, there are some limitations for probabilistic context inference in mobile devices. Mobile devices relatively lacks of sufficient memory. In this paper, we present a novel method for efficient Bayesian inference on a mobile phone. In order to overcome the constraints of the mobile environment, the method uses two-layered Bayesian networks with tree structure. In contrast to the conventional techniques, this method attempts to use probabilistic models with fixed tree structures and intermediate nodes. It can reduce the inference time by eliminating junction tree creation. To evaluate the performance of this method, an experiment is conducted with data collected over a month. The result shows the efficiency and effectiveness of the proposed method.     

A framework for efficient FE vibration software

A new hybrid stress finite plate vibration capability, providing high accuracy for coarse-meshes is presented with a view to enhancing the behavioural characteristics of the standard hybrid FEM. The software meets demands of the real-life user for reliable and cost-objective identification of a wide range of vibration modes. The FE matrices are constructed through the expedient of introducing a system of algorithms which provides an efficient and easily implemented capability that can be translated into any of the existing high level computing languages, viz. FORTRAN.The computational scheme enables the development of a large number of increasingly sophisticated elements from a single element module as easily as possible by providing it with a library of datasets. All the previously recognised advantages of the hybrid FEM are retained, whilst an exact analytical integrator returns the requisite information for the elemental matrices, and thereby obviates an aliasing problem that has plagued the cost-objectiveness of the conventional hybrid stress implementations. Extensive numerical tests manifest the numerical potentials of the present hybrid FE computational strategy.     

Exertion interfaces for computer videogames using smartphones as input controllers

As mobile phones become smarter and include a wider and more powerful array of sensory components, the opportunity to leverage those capabilities in contexts other than telephony grows. We have in particular identified those sensory capabilities as key components for modern user interfaces that can detect movement, actions and intentions to enrich human-computer interaction in a natural way. In this work, we present research around using smartphones as input controllers in the context of exertion videogames. We propose a conceptual framework that identifies the core elements of such interfaces, regardless of the underlying technological platforms, and provides a design pattern for their integration into existing videogames without having to change the game’s source code. We present a proof of concept implementation for the framework, with two smartphone input controllers, which using a soft button and accelerometer data, interface to a target-shooting exertion game played while exercising on a stationary bicycle. We present findings from a user experience evaluation.     

Mesh optimization for surface approximation using an efficient coarse-to-fine evolutionary algorithm

The investigated mesh optimization problem C(N,n) for surface approximation, which is NP-hard, is to minimize the global error between a digital surface and its approximating mesh surface by efficiently locating a limited number n of grid points which are a subset of the original N sample points. This paper proposes an efficient coarse-to-fine evolutionary algorithm (CTFEA) with a novel orthogonal array crossover (OAX) for solving the mesh optimization problem. OAX adaptively divides the meshes of parents into a number of parts using a tuning parameter for applying a coarse-to-fine technique. Meshes of children are formed from an intelligent combination of the good parts from their parents rather than the conventional random combination. The better one of two parts in two parents is chosen by evaluating the contribution of the individual parts to the fitness function based on orthogonal experimental design. The coarse-to-fine technique of CTFEA can advantageously solve large mesh optimization problems. Furthermore, CTFEA using an additional inheritance technique can further efficiently locate the grid points in the mesh surface. It is shown empirically that CTFEA outperforms the existing evolutionary algorithm in terms of both approximation quality and convergence speed, especially in solving large mesh optimization problems.     

An efficient algorithm for 3D hand gesture recognition using combined neural classifiers

Gestures are the dynamic movements of hands within a certain time interval, which are of practical importance in many areas, such as human–computer interaction, computer vision, and computer graphics. The human hand gesture can provide a free and natural alternative to today’s cumbersome interface devices so as to improve the efficiency and effectiveness of human–computer interaction. This paper presents a neural-based combined classifier for 3D gesture recognition. The combined classifier is based on varying the parameters related to both the design and training of neural network classifier. The boosting algorithm is used to make perturbation of the training set employing the Multi-Layer Perceptron as base classifier. The final decision of the ensemble of classifiers is based on the majority voting rule. Experiments performed on 3D gesture database show the robustness of the proposed technique.     

Cloud-based efficient scheme for handwritten digit recognition

Multimedia Tools and Applications - Handwritten character recognition has been acknowledged and achieved more prominent attention in pattern recognition research community due to enormous...     

Second-order motion descriptors for efficient action recognition

Pattern Analysis and Applications - Human action recognition from realistic video data constitutes a challenging and relevant research area. Leading the state of the art we can find those methods...     

Extended Spectral Regression for efficient scene recognition

This paper proposes a novel method based on Spectral Regression (SR) for efficient scene recognition. First, a new SR approach, called Extended Spectral Regression (ESR), is proposed to perform manifold learning on a huge number of data samples. Then, an efficient Bag-of-Words (BOW) based method is developed which employs ESR to encapsulate local visual features with their semantic, spatial, scale, and orientation information for scene recognition. In many applications, such as image classification and multimedia analysis, there are a huge number of low-level feature samples in a training set. It prohibits direct application of SR to perform manifold learning on such dataset. In ESR, we first group the samples into tiny clusters, and then devise an approach to reduce the size of the similarity matrix for graph learning. In this way, the subspace learning on graph Laplacian for a vast dataset is computationally feasible on a personal computer. In the ESR-based scene recognition, we first propose an enhanced low-level feature representation which combines the scale, orientation, spatial position, and local appearance of a local feature. Then, ESR is applied to embed enhanced low-level image features. The ESR-based feature embedding not only generates a low dimension feature representation but also integrates various aspects of low-level features into the compact representation. The bag-of-words is then generated from the embedded features for image classification. The comparative experiments on open benchmark datasets for scene recognition demonstrate that the proposed method outperforms baseline approaches. It is suitable for real-time applications on mobile platforms, e.g. tablets and smart phones.     

An efficient 3D face recognition approach using local geometrical signatures

This paper presents a computationally efficient 3D face recognition system based on a novel facial signature called Angular Radial Signature (ARS) which is extracted from the semi-rigid region of the face. Kernel Principal Component Analysis (KPCA) is then used to extract the mid-level features from the extracted ARSs to improve the discriminative power. The mid-level features are then concatenated into a single feature vector and fed into a Support Vector Machine (SVM) to perform face recognition. The proposed approach addresses the expression variation problem by using facial scans with various expressions of different individuals for training. We conducted a number of experiments on the Face Recognition Grand Challenge (FRGC v2.0) and the 3D track of Shape Retrieval Contest (SHREC 2008) datasets, and a superior recognition performance has been achieved. Our experimental results show that the proposed system achieves very high Verification Rates (VRs) of 97.8% and 88.5% at a 0.1% False Acceptance Rate (FAR) for the “neutral vs. nonneutral” experiments on the FRGC v2.0 and the SHREC 2008 datasets respectively, and 96.7% for the ROC III experiment of the FRGC v2.0 dataset. Our experiments also demonstrate the computational efficiency of the proposed approach.     

Love wave immunosensor for antibody recognition using an innovative semicarbazide surface functionalization

A new novel and easy functionalization route of a Love wave acoustic sensor based on the α-oxo-semicarbazone bond is described. The interest is firstly to observe in real-time the immobilization of the peptide on the semicarbazide surface of the transducer and secondly to monitor the specific binding of antibodies. Site-specific immobilization of antigenic-peptides as well as binding of murine monoclonal antibodies has been shown by gravimetric measurements. A tetramethylrhodamine-labeled goat antibody directed against murine antibodies was used to further characterize the biomolecular interactions by fluorescence microscopy and surface analysis (by AFM). Our data show that the gravimetric monitoring developed from the prepared Love wave immunosensor is a promising alternative route to characterize chemical and biomolecular events.     

Locally linear discriminant embedding: An efficient method for face recognition

In this paper an efficient feature extraction method named as locally linear discriminant embedding (LLDE) is proposed for face recognition. It is well known that a point can be linearly reconstructed by its neighbors and the reconstruction weights are under the sum-to-one constraint in the classical locally linear embedding (LLE). So the constrained weights obey an important symmetry: for any particular data point, they are invariant to rotations, rescalings and translations. The latter two are introduced to the proposed method to strengthen the classification ability of the original LLE. The data with different class labels are translated by the corresponding vectors and those belonging to the same class are translated by the same vector. In order to cluster the data with the same label closer, they are also rescaled to some extent. So after translation and rescaling, the discriminability of the data will be improved significantly. The proposed method is compared with some related feature extraction methods such as maximum margin criterion (MMC), as well as other supervised manifold learning-based approaches, for example ensemble unified LLE and linear discriminant analysis (En-ULLELDA), locally linear discriminant analysis (LLDA). Experimental results on Yale and CMU PIE face databases convince us that the proposed method provides a better representation of the class information and obtains much higher recognition accuracies.