The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Smartphones nowadays are used not only for communication but also for many emerging applications, such as m-commerce. And, biometric methods can provide promising applications to secure mobile devices. In this paper, we propose a novel authentication mechanism using the information collected from the accelerometer sensor and touchscreen of the smartphone. We design an authentication mechanism that...
Deep learning has recently exhibited good performance in many applications. The convolution neural network is an often-used architecture for deep learning and has been widely used in computer vision and audio recognition, and outperformed other related handcraft designed feature in recent years. These techniques compared to other artificial intelligence algorithms and handcraft features need extremely...
In order to realize the copyright protection of audio information and improve the security of the watermarking algorithm, a secure robust audio watermarking algorithm via quantization of the random correlation coefficients in lifting wavelet transform domain and QR decomposition is proposed Firstly, lifting wavelet transform is performed on the audio data, the approximate components are mapped into...
This paper proposes a novel feature fusion method for the protein subcellular multiple-site localization prediction. Several types of features are employed in this novel protein coding method. The first one is the composition of amino acids. The second is pseudo amino acid composition, which mainly extract the location information of each amino acid residues in protein sequence. Lastly, the information...
Facial shape cloning (FSC) is a task aiming to simulate the plastic surgery result of reshaping a user's face to bear analogy to a model's facial appearance. Facial cosmetic reproducing (FMR) is another task intending to emulate the transfer of the cosmetic effects on a model face to the user's face. This paper presents a method which can perform both the FSC and the FMR. This proposed method features...
With the worldwide popular of the stereoscopic film "Avatar", stereoscopic video has become the focus of the industry, and also greatly promoted the development of stereoscopic video shooting technology. On the market nowadays, the stereoscopic video shooting cradle head gets horizontal mostly through the manual setting of the independent knobs and the legs of the tripod by observing the...
Digital Image Elasto Tomography (DIET) is noninvasive approach for detection and screening test of breast cancer at an early stage. In DIET mechanical vibrations are applied on the surface of breast after applying fiducial markers and images are taken to capture surface motion using five digital cameras. Applying Scale Invariant Feature Transform (SIFT) on the unmarked surface of the breast to produce...
A detection method for cheating behavior in examination room based on artificial bee colony algorithm is presented. The problem of moving objects detection is transformed into the difference function of color value between foreground and background. Artificial bee colony algorithm is applied for optimizing the objective function. The background component is separated from the sequence images by value...
In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent Fully Connected Neuro-Fuzzy Inference System (F-CONFIS). The F-CONFIS is a new type of neural network that differs from traditional neural networks, which there are the dependent and repeated weights. For these special properties, its learning algorithm should be different from that of the conventional neural networks. Therefore,...
In a remote smart collaboration application, sharing seamless and consistent information between a local site and interacting remote participants is essential. Often visual seams are created when inconsistent visual information is shared due to heterogeneous projector-camera systems (ProCams). One known issue is flickering noise occurred from re-capturing projected scenes with the camera of ProCams...
In view of the data sparseness problem existed in the traditional collaborative filtering recommendation algorithm, this paper proposes a hybrid collaborative filtering recommender framework integrated FCM clustering and Slope One algorithm and FSUBCF algorithm. Firstly this algorithm use the Slope One algorithm based on FCM cluster to predict item ratings that users have not rated in matrix, and...
In this paper, we present an efficient algorithm for solving optimization problems, which is based on gravitational search algorithm (GSA). In the proposed technique, called Two-Step method, the best solution of position will be considered and calculated with another agents, and the fitness of extended agents are compared with agents in original gravitation field, which can reinforce the exploration...
In this paper, to integrate android systems, intelligent computing and web service on an intelligent mobile web service computing systems for bioinformatics is proposed. That is, users can send parameters to control the intelligent computing system under Matlab/C#/Java and query from clientside to server-side in the proposed bioinformatics systems with their android phone. Besides, the proposed system...
The problem of recovering low-rank matrix from only a subset of observed entries is known as the matrix completion problem. Many problems arising in compressive sensing, image processing, machine learning, can be usefully cast as this problem. In this paper, we propose an extended linearized augmented Lagrangian method of multipliers for the problem, and prove its global convergence. We show that...
Reasonable timing design for traffic light can induce and maintain the transportation systems in good order. How to allocate the time are the keys. In the paper, the theory of time-varying universe is used to describe the circle time, and corresponding fuzzy sets on the universe are also discussed to modeling the situation of traffic flow, then the parallel traffic management and control methods which...
According to the shadows and shading constraints in the Lambert illumination model, the paper proposes a method to detect image forgery. This method describes a multitude of constraints in shading and shadows based on the direction of the light source, by analyzing the intersection of the wedges to verify the images. The linear programming problem is employed to confine the direction and angle in...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.