Search

Matrix embedding (ME) code is a commonly used steganography technique, which uses linear block codes to improve embedding efficiency. However, its main disadvantage is the inability to perform maximum likelihood decoding due to the high complexity of decoding large ME codes. As such, it is difficult to improve the embedding efficiency. The proposed q-ary embedding code can provide excellent embedding efficiency and is suitable for various embedding rates (large and small payloads). This article discusses that by using perforation technology, a convolutional code with a high embedding rate can be easily converted into a convolutional code with a low embedding rate. By keeping the embedding rate of the (2, 1) convolutional code unchanged, convolutional codes with different embedding rates can be designed through puncturing.

Background Lignocellulolytic enzymes are essential for agricultural waste disposal and production of renewable bioenergy. Many commercialized cellulase mixtures have been developed, mostly from saprophytic or endophytic fungal species. The cost of complete cellulose digestion is considerable because a wide range of cellulolytic enzymes is needed. However, most fungi can only produce limited range of highly bioactive cellulolytic enzymes. We aimed to investigate a simple yet specific method for discovering unique enzymes so that fungal species producing a diverse group of cellulolytic enzymes can be identified. Results The culture medium of an endophytic fungus, Daldinia caldariorum D263, contained a complete set of cellulolytic enzymes capable of effectively digesting cellulose residues into glucose. By taking advantage of the unique product inhibition property of β-glucosidases, we have established an improved zymography method that can easily distinguish β-glucosidase and exoglucanase activity. Our zymography method revealed that D263 can secrete a wide range of highly bioactive cellulases. Analyzing the assembled genome of D263, we found over 100 potential genes for cellulolytic enzymes that are distinct from those of the commercially used fungal species Trichoderma reesei and Aspergillus niger. We further identified several of these cellulolytic enzymes by mass spectrometry. Conclusions The genome of Daldinia caldariorum D263 has been sequenced and annotated taking advantage of a simple yet specific zymography method followed by mass spectrometry analysis, and it appears to encode and secrete a wide range of bioactive cellulolytic enzymes. The genome and cellulolytic enzyme secretion of this unique endophytic fungus should be of value for identifying active cellulolytic enzymes that can facilitate conversion of agricultural wastes to fermentable sugars for the industrial production of biofuels.

Additional file 2: Figure S1. D263 does not supplement the activity of CTec3. Figure S2. No D263 LPMO activity visualized on zymography.

Additional file 1: Table S1. Optimal growth conditions for the ascomycetes tested.

Goods distribution management is an extremely important link for logistics units.Especially for enterprises or units that have a large number of distribution needs, effective and immediate control of the cargo trajectory is a very difficult problem.At present,in order to strengthen delivery performance. More manpower and equipment must be invested to digest a large amount of goods.Although there is enough manpower in the warehouse to complete most of the inventory, distribution.But after leaving the warehouse, often only one or two people are left to be responsible for remote multi-point distribution.Barcode labels are the mainstream system used by Logistics industry.Although it can improve part of the efficiency, it can only replace part of the human.In fact, it is impossible to control all logistics status in time and accurately. In the end, we still need to rely on manpower and work experience to reduce the error rate.This paper combines the recording and management functions of RFID, GPS, WiFi module and database server.Grasp the important information such as the corresponding time, location and cargo list (time, place, object) in the process of goods distribution, and after comparing with the itinerary arrangement, achieve the effect of distribution itinerary management and real-time automatic inspection.

In recent years, the development and research of GAN[1] is nothing more than a change in the number or structure of the generated network. The method of discriminate network is only to map different regional features to different discriminators and integrate them. As we all know, the quality of generator can affect the effectiveness of the entire network directly, but I think the function of the discriminator is the important pillar to support the entire network. So the author proposed a face-generation network named Jigsaw Generative Adversarial Network, which uses a single generator network with a discriminator as a layer. Each layer creates different parts to enhance the authenticity of each part, and then the face is composed in a jigsaw way, and is matched with the style module of Style GAN[2] to achieve more highly build quality. The proposed system can select the desired style for data set generation. For example, you can select the adult male style to generate a data set of all adult men and use this data set for research, or use the extracted style modules to apply to other generation networks and control the direction of the generated graph of the generated network.

Monitoring systems have been extensively applied in daily life as a result of technological advancements. Foreground detection is an important technique to refine monitoring systems. Dynamic backgrounds in the environment form a rather challenging issue in foreground detection. For example, fluttering leaves, wavelets on water, flashes on monitor screens, shadow changes are all likely to lead to erroneous analysis in foreground detection. This study proposes a foreground detection algorithm, called texture-based codebook method, which using a codebook model in combination with texture features. The codebook model used to construct a background model can effectively compress data to achieve optimal processing speeds, whereas the local binary pattern is adopted to identify texture features because of its powerful capacity for texture description and fast computation. Subsequently, texture-based connected component labeling is applied to the results from the codebook model to increase accuracy and reduce error rates. In addition, to adapt to the environment, a short-term information model has been added for better background model updates. Gradient-based time difference is also incorporated to cope with global light changes. The experiment outcome shows that the algorithm proposed is capable of real-time processing and also has good adaptability. It is able to achieve decent recognition rates when tested in different environments.

The development of science and technology causes fundamental changes in the field of people's eating from traditional queuing to order and then waiting for meals to reservation, online ordering, and electronic service. The main direction of development is satisfying customer's demand faster and correctly. This study comprehensively compares the advantages and disadvantages of three models, and issues the fourth model. It uses an image recognition system, and excludes the effect of image rotation and luminance. It completes the ordering process as long as server uses the camera to take the photo. This way greatly reduces the time spending, the error occurring, the money costing, and takes effect in the small restaurants.

Three-dimensional (3D) medical image segmentation is used to segment the target (a lesion or an organ) in 3D medical images. Through this process, 3D target information is obtained; hence, this technology is an important auxiliary tool for medical diagnosis. Although some methods have proved to be successful for two-dimensional (2D) image segmentation, their direct use in the 3D case has been unsatisfactory. To obtain more precise tumor segmentation results from 3D MR images, in this paper, we propose a method known as the 3D shape-weighted level set method (3D-SLSM). The proposed method first converts the LSM, which is superior with respect to 2D image segmentation, into a 3D algorithm that is suitable for overall calculations in 3D image models, and which improves the efficiency and accuracy of calculations. A 3D shape-weighted value is then added for each 3D-SLSM iterative process according to the changes in volume. Besides increasing the convergence rate and eliminating background noise, this shape-weighted value also brings the segmented contour closer to the actual tumor margins. To perform a quantitative analysis of 3D-SLSM and to examine its feasibility in clinical applications, we have divided our experiments into computer-simulated sequence images and actual breast MRI cases. Subsequently, we simultaneously compared various existing 3D segmentation methods. The experimental results demonstrated that 3D-SLSM exhibited precise segmentation results for both types of experimental images. In addition, 3D-SLSM showed better results for quantitative data compared with existing 3D segmentation methods.

Medical image segmentation is an important aided technique for medical diagnosis. In the past, some researchers have proved effectiveness on two-dimensional (2D) image segmentation; but the achievements of three-dimensional (3D) image segmentation are still unsatisfactory and challenging. This paper presents a 3D Modified Active Contour Method (3D-MACM) that is aimed at breast tumor segmentation in 3D magnetic resonance images (MRI). It acquires an accurate 3D tumor segmented model in order to provide physicians with 3D function such as position, volume, shape characteristics, distribution, etc. In the development process of proposed method, the traditional 2D technique must first evolve into 3D technique and then modify the smoothing method to facilitate the overall operation of the stacked MRIs, so it is called 3D modified ACM. To assess the accuracy of 3D-MACM, we have conducted experiments on breast MRI and simulated cases and have compared with the traditional active contour method and level set method. The results show that not only is the method developed in this paper more accurate than traditional methods, it also has an accuracy greater than 99% and a false alarm rate less than 0.8%, according to the standard model.

Portfolio optimization generally involves maximizing the expected return of a portfolio while minimizing its risk. However, when considering these 2 conflicting objectives in decision-making contexts, an efficient approach is required to evaluate the solution in the set of efficient frontiers/Pareto optimal solutions. Selecting and managing an investment portfolio are critical for investors. This study proposes an integrated method for portfolio optimization that involves decisions on stock screening, stock selection, and capital allocation. The initial step involves examining the financial data of investment targets. The portfolio is then selected according to the firms’ relative efficiency by using a data envelopment analysis (DEA) model. To determine the allocation of capital to each stock in the constructed portfolio, a multi-objective decision-making (MODM) model is developed. The integrated DEA-MODM approach is applied to Taiwan’s financial market and compared with several benchmarking mutual funds for empirical testing. This comparative study shows that the proposed approach outperforms the Taiwan Excel 50 ETF and 3 other benchmarking mutual funds in numerous quarters of the testing period regarding return rates and Sharpe ratios. Therefore, the proposed integrated DEA-MODM approach can be useful to both investors and researchers.

This paper presents to apply Automatic Speech Recognition (ASR) algorithm to the meal service robot so that the user can be easier to order the meal and increase interaction between the robot and human. The Mel-frequency Cepstral coefficients (MFCC) is used to scratch the feature parameters, and Hidden Markov Model (HMM) is applied as the recognition speech model via Spce3200. It is based on the embedded HMM for speech recognition and thus reducing the size and power in a less computational time. There are 25 sets of Chinese speech data are trained and tested using a sentence and multi sentences under different environments. The highest recognition rate in a sentence has confirmed up to 95%, and multi-sentences can reach 85%. Accordingly, the practical results have indicated its relevant reliability.

As technology developed, the surveillance system has been widely used in our daily lives. Monitoring systems, background filtering is a very important technology. Even so, in that respect are different dynamics in the surrounding ground for background filtering is a challenging problem, for example: leaves of the shaking, water fluctuations, the display flashes, the light changes to easily filter out background on error analysis. We indicate a coding book model combining the background removing algorithm of texture and background model using a coded book to benefit is the ability to effectively compress information to achieve the best focal ratio. Built using local binary pattern, texture because the local binary pattern, texture description quite well, but is computationally quite fast. And so, based along the texture of the connected object model results should be commingled with the code book can effectively raise the accuracy and scale down the error rate. In addition, in order to adjust to the current environment, added a short term information model to improve the background model update. And global change, grounded on the gradient Time difference method to work it. Experimental results indicate that our proposed algorithm for real time processing and better adaptability, tested in a different environment, and can get good credit rate.

The main objective of this study was to develop a new technique for MR Image segmentation that not only addresses the shortcomings of existing segmentation methods, but also preserves the advantages they offer, thus leading to high accuracy while segmenting the designated target from the MR image. The proposed method consists of two parts, first part is to enhance the contrast between the target and the background, and second part is to segment the target from images. In order to obtain accurate quantitative analysis and to confirm that the proposed method delivers excellent results for real MR images, experimental data were assigned into two groups: computer simulation and actual Breast MRIs. Finally, we compare the experimental results with those of several existing renowned image segmentation algorithms to confirm the advantages and contributions of the proposed method.

This article presents a new multispectral signature detection approach to magnetic resonance (MR) image classification. It is called the gray system theory (GST) method. In recent years, although GST has been used in various fields, applying the GST to medical images is very rare. The theoretical basis of GST is the gray hazy set; the main element is composed of an uncertain or abstract set and through a series of algorithms, the gray messages or phenomena are transformed into white ones. The concept of the theory is based on the information coverage, which establishes a new regular set based on source data and then the set is mapped to a 2D space. A series of experiments are conducted and compared to the commonly used fuzzy C-means (FCM) method, extension theory, and perceptron for performance evaluation. The results show that the GST method is a promising and effective spectral technique for MR image classification.

This paper presents a computer-assisted diagnostic system for mass detection and classification, which performs mass detection on regions of interest followed by the benign-malignant classification on detected masses. In order for mass detection to be effective, a sequence of preprocessing steps are designed to enhance the intensity of a region of interest, remove the noise effects and locate suspicious masses using five texture features generated from the spatial gray level difference matrix (SGLDM) and fractal dimension. Finally, a probabilistic neural network (PNN) coupled with entropic thresholding techniques is developed for mass extraction. Since the shapes of masses are crucial in classification between benignancy and malignancy, four shape features are further generated and joined with the five features previously used in mass detection to be implemented in another PNN for mass classification. To evaluate our designed system a data set collected in the Taichung Veteran General Hospital, Taiwan, R.O.C. was used for performance evaluation. The results are encouraging and have shown promise of our system.

While the image was sewed in cloth with thread or was made a physical model by 3D printer, the colors of the thread or the material of the 3D printer was limit, to simplify the manufacture processing. Although the conventional image clustering algorithm can segment the image into seldom clusters and give each cluster a specific color that decrease most colors and preserver the main feature. However the contour will be cluster in many clusters induce by the color gradient of the contour. This paper proposed a clustering algorithm based on involved spatial distance to assign the contour a consistent color. The experimental shown that the proposed algorithm had cluster quality more than 90%, the maximum improvement was 57% that com-pared with the conventional clustering algorithm.

We proposed a three-dimensional (3D) model reconstruction system for breast tumors, which will serve as a diagnostic reference for physicians and also address the shortcomings of the traditional breast needle localization method or other methods reported in previous studies. The proposed system uses multispectral breast magnetic resonance images as input and detects the contour of the tumor in different sections using a developed active contour method-multispectral gradient vector flow snake (MGVFS) method. Thus, the system constructs a 3D model of only the breast tumor and excludes other tissues. To confirm the results obtained with the MGVFS method, we conducted experiments to evaluate its accuracy in contour detection, and compared the results with traditional contour methods. Our results demonstrate that the MGVFS method has the highest accuracy with a correction rate as high as 99.79%.

Most image enlargement techniques suffer the problem of zigzagged edges and jagged images following enlargement. Humans are sensitive to the edges of objects; if the edges in the image are sharp, the visual is considered to be high quality. To solve this problem, this paper presents a new and effective method for image enlargement and enhancement based on adaptive inverse hyperbolic tangent (AIHT) algorithm. Conventional image enlargement and enhancement methods enlarge the image using interpolation, and subsequently enhance the image without considering image features. However, this study presents the method based on Adaptive Inverse Hyperbolic Tangent algorithm to enhance images according to image features before enlarging the image. Experimental results indicate that the proposed algorithm is capable of adaptively enhancing the image and extruding object details, thereby improving enlargements by smoothing the edge of the objects in the image.

Various motor imagery processes produce distinct electroencephalography (EEG). In this study, C3 and C4 electrode were distributed on the scalp surface of a participant to record the event-related potential (left and right hand movement) produced during testing. The event-related synchronization (ERS) and event-related desynchronization (ERD) were analyzed, and energy values of the EEG produced during the event period were calculated and used as event features. Finally, a fuzzy C-means (FCM) classifier was used to classify eigenvalues, grouping the features of left and right hand movement in EEG signals.

Orthogonal subspace projection (OSP) approach has shown success in hyperspectral image classification. Recently, the feasibility of applying OSP to multispectral image classification was also demonstrated via SPOT (Satellite Pour 1’Observation de la Terra) and Landsat (Land Satellite) images. Since an MR (magnetic resonance) image sequence is also acquired by multiple spectral channels (bands), this paper presents a new application of OSP in MR image classification. The idea is to model an MR image pixel in the sequence as a linear mixture of substances (such as white matter, gray matter, cerebral spinal fluid) of interest from which each of these substances can be classified by a specific subspace projection operator followed by a desired matched filter. The experimental results show that OSP provides a promising alternative to existing MR image classification techniques.

An analysis system for the single-trial electroencephalogram (EEG) recognition is presented. In combination with wavelet and amplitude modulation (AM), the gray-based competitive Hopfield clustering network (GCHCN) is applied to the clustering of left-finger lifting and resting. The fractal features in multiscale are extracted from the discrete wavelet transform (DWT) data by using fractal dimension. GCHCN is used for the recognition of features. GCHCN is an unsupervised clustering approach for the biomedical signals. Compared with popular supervised linear discriminant analysis (LDA) classifier and multilayer perceptron (MLP) classifier, GCHCN achieves promising results in lifting recognition.

Receiver operating characteristics (ROC) has been widely used as a performance evaluation tool to measure effectiveness of medical modalities. It is derived from a standard detection theory with false alarm and detection power interpreted as false positive (FP) and true positive (TP) respectively in terms of medical diagnosis. The ROC curve is plotted based on TP versus FP via hard decisions. This paper presents a three dimensional (3D) ROC analysis which extends the traditional two-dimensional (2D) ROC analysis by including a threshold parameter in a third dimension resulting from soft decisions, (SD). As a result, a 3D ROC curve can be plotted based on three parameters, TP, FP and SD. By virtue of such a 3D ROC curve three two-dimensional (2D) ROC curves can be derived, one of which is the traditional 2D ROC curve of TP versus FP with SD reduced to hard decision. In order to illustrate its utility in medical diagnosis, its application to magnetic resonance (MR) image classification is demonstrated.

Epileptiform activities can be detected by scanning the electroencephalogram (EEG) signals of an epileptic patient. Since EEG provides multi-channel signals, it is an opportunity to employ multi-spectrum signal processing techniques for improving the accuracy of signal separation or feature extraction. Although multi-channel signals provide stronger characteristics than a single signal for feature extraction, taking all of the EEG signals into consideration may interfere with the accuracy of epileptiform discharge detection because a part of the signals that do not contain the epileptic activity will be treated as noise. In this paper, we developed a new signature analysis scheme, grouped-channel restricted band analysis (GRBA), for interictal epileptiform discharges (IED) detection from EEG signals. Unlike most traditional epileptic activity detection techniques that inaccurately take single or all EEG signals into consideration, GRBA simultaneously considers three important characteristics of epileptiform discharge waves, i.e. multispectral, finite spread, and specific duration, to detect epileptiform discharges efficiently. A series of experiments were conducted to compare GRBA with traditional feature-classifier methods and the non-grouped approach to evaluate this novel approach by the correct detection rate (Rc) and receiver operating characteristic (ROC) curves. The experimental results showed that our new signature analysis scheme, GRBA, had a superior quality. Moreover, we observed that the area under ROC curves and the Rc for GRBA were as high as 0.9479 and 94.1%, respectively.

Presently, radiologists used to rely on contrast-injection to acquire the contrast-enhanced breast magnetic resonance imaging (MRI), in order to improve the accuracy of breast cancer screening. Instead of contrast-injection, this paper proposed a spectral signature detection technology, constrained energy minimization (CEM), which could successfully classify breast MRIs into four major tissues (fatty tissue, glandular tissue, tumor and muscle) and show the classified results in high contrast images. After compared with a specific subspace projection operator called orthogonal subspace projection (OSP), the commonly used C-means (CM) algorithm and real contrast-injected breast MRIs, the results show that the high contrast images generated by CEM have superior quality.

In this paper, three groups of characteristics related to mass texture are adopted, namely, SGLD (spatial gray level dependence), TS (texture spectrum) and TFCM (texture feature coding method) to describe the characteristics of masses and normal textures on digitized mammograms. Next, under the testing by classifiers, three feature selection methods - SBS (sequential backward selection), SFS (sequential forward selection) and SFSM (sequential floating search method) are used to find out suboptimal subset from 19 features in order to improve the performance of mass detection. Finally, two classifiers PNN (probabilistic neural network) and SVM (support vector machine) are applied and their performances are compared

Detection of masses is much more difficult than that of microcalcifications (MCCs) because breast masses are part of tissues that may not be detected effectively by the techniques developed for detection of MCCs. In this chapter, we present a texture feature coding method (TFCM) to extract features that could characterize special properties of masses. It extracts gradient variations of gray level co-occurrence matrix as texture features. As a result, the TFCM is more sensitive to changes in texture. Three neural network architectures, backpropagation neural network, probabilistic neural network, and radial basis function neural network are used for mass detection with inputs provided by TFCM-extracted features. The experimental results show that our TFCM-based neural network approaches can achieve a detection rate of approximately 87% with a 10% false alarm rate.