Search

In the area of medical imaging, automation of medical image classification or recognition is an active field of research. Over the past decade, due to the popularity and usability of artificial neural networks, it is becoming the norm to achieve this automation by deep neural networks. In toxicology based research, zebrafish has become a key model organism in phenotypical imaging and drug discovery. Detection of complex patterns and phenotypes in zebrafish embryo during preclinical or clinical trials is a standard part of the drug discovery cycle. Currently this classification task of phenotypes is mostly experts based. In this work, we propose a fine-tuned convolution neural network (CNN) based model for automated classification of different phenotypical changes observed due to the toxic substance in the zebrafish embryo. We demonstrated the ability of CNN model as well as a fine-tuned CNN based model to classify different deformation in an embryo with high accuracy. Such automated medical imaging model can be used extensively by experts in the area of toxicology and drug discovery.

This paper presents a binary coded evolutionary computational method inspired from the evolution in plant genetics. It introduces the concept of artificial DNA which is an abstract idea inspired from inheritance of characteristics in plant genetics through transmitting dominant and recessive genes and Epimutaiton. It involves a rehabilitation process which similar to plant biology provides further evolving mechanism against environmental mutation for being better and better. Test of the effectiveness, consistency, and efficiency of the proposed optimizer have been demonstrated through a variety of complex benchmark test functions. Simulation results and associated analysis of the proposed optimizer in comparison to Self-learning particle swarm optimization (SLPSO), Shuffled Frog Leap Algorithm (SFLA), Multi-species hybrid Genetic Algorithm (MSGA), Gravitational search algorithm (GSA), Group Search Optimization (GSO), Cuckoo Search (CS), Probabilistic Bee Algorithm (PBA), and Hybrid Differential PSO (HDSO) approve its applicability in solving complex problems. In this paper, we have shown effective results on thirty variables benchmark test problems of different classes.

In the context of efficient generation expansion planning (GEP) and transmission expansion planning (TEP), value assessment method (VAM) is the critical topic to discuss. Presently, two well-known VAMs, min-cut max-flow (MCMF) and load curtailment strategy (LCS), are used for GEP and TEP. MCMF does not follow electrical laws and is unable to calculate congestion cost (CC) and re-dispatch cost (RDC). LCS calculates both, but in iterative way, thus takes a long time to provide solution. In the constrained network, multiple quantities like demand/energy not served (D/ENS) and generation not served (GNS), wheeling loss (WL), CC and RDC are existing together and thus have to be calculated together to encounter the loss in all aspects. Existing methods show limitations in this regard and do not calculate all above described quantities simultaneously. Thus, in this paper, a non-iterative VAM (NVAM) is presented based on electrical laws, which calculates value of the present and the planned systems by incorporating all system quantities of D/ENS, GNS, WL, CC and RDC together. Due to non-iterative batch approach, it is quite faster compared to the above-mentioned traditional VAMs, i.e., MCMF and LCS. Furthermore, comparative results on IEEE-5 bus and IEEE-24 bus power systems show its higher efficiency. The MATLAB code of the introduced NVAM is provided in “Appendix” for further development by the researchers.

The perceptual adaptation of the image (PAI) is introduced by inspiration from Chevreul–Mach Bands (CMB) visual phenomenon. By boosting the CMB assisting illusory effect on boundaries of the regions, PAI adapts the image to the perception of the human visual system and thereof increases the quality of the image. PAI is proposed for application to standard images or the output of any image processing technique. For the implementation of the PAI on the image, an algorithm of morphological filters (MFs) is presented, which geometrically adds the model of CMB effect. Numerical evaluation by improvement ratios of four no-reference image quality assessment (NR-IQA) indexes approves PAI performance where it can be noticeably observed in visual comparisons. Furthermore, PAI is applied as a postprocessing block for classical morphological filtering, weighted morphological filtering, and median morphological filtering in cancelation of salt and pepper, Gaussian, and speckle noise from MRI images, where the above specified NR-IQA indexes validate it. PAI effect on image enhancement is benchmarked upon morphological image sharpening and high-boost filtering.

An image quality index plays an increasingly vital role in image processing applications for dynamic monitoring and quality adjustment, optimization and parameter setting of the imaging systems, and finally benchmarking the image processing techniques. All the above goals highly require a sustainable quantitative measure of image quality. This manuscript analytically reviews the popular reference-based metrics of image quality which have been employed for the evaluation of image enhancement techniques. The efficiency and sustainability of eleven indexes are evaluated and compared in the assessment of image enhancement after the cancellation of speckle, salt and pepper, and Gaussian noises from MRI images separately by a linear filter and three varieties of morphological filters. The results indicate more clarity and sustainability of similarity-based indexes. The direction of designing a universal similarity-based index based on information content of the image is suggested as a future research direction.

Image representation through local descriptors is a research hotspot in computer vision. In this letter, we propose a novel local image descriptor based on intensity permutation and zone division. The oFAST detector is first employed to detect keypoints with orientations, and then steered patterns are applied to sample rotation-invariant points within the local keypoint patch. In the step of local patch description, intensity permutation and zone division are implemented to construct our descriptor, with the advantages of inherent robustness and invariance to monotonic brightness changes. Our proposed algorithm performed well in the experiments on benchmark dataset for descriptor evaluation.

All mobile carriers these days have provided 3G and 4G services to their customers. The evolution of cellular networks from 3G to 4G has improved several performance metrics of the data communications. The focus of this paper is to evaluate two of the most important performance metrics: throughput and delay. We consider the cellular network as an integrate infrastructure that includes mobile and fixed nodes. Based on this model we calculate and analyze the throughput and delay. Our results illustrate that the throughput is increased while the delay is decreased in 4G data network compared to the previous 3G architecture. In addition, we evaluate how the delay affects the security of the network.

The importance of wireless cellular communication in our daily lives has grown considerably in the last decade. The smartphones are widely used nowadays, besides voice communication; the authors routinely use them to access the internet, conduct monetary transactions, send text messages and query a lot of useful information regarding the location of specific places of interest. The use of smartphones in their day-to-day communication raises many unresolved security and privacy issues. In this paper they identify relevant security attacks in Wireless Cellular Network. The authors conduct experiments in four different platforms such as Iphone, Android, Windows and Blackberry. The packets captured through Wireshark for approximately 24 minutes, giving them a lot of information regarding security and privacy issues involving the users. A lot of useful apps installed and used by the end-users have serious issues in terms of privacy and the information exposed. Which is the better platform comparing all four and what exactly do they expose from the user’s information? What are the threats and countermeasures that the users should be aware of? The aim of the authors’ paper is to give answers to the above questions based on the data captured by conducting real-life scenarios.

Morphological filters (MFs) are composed of two basic operators: dilation and erosion, inspired by natural geometrical dilation and erosion. MFs locally modify geometrical features of the signal/image using a probe resembling a segment of a function/image that is called structuring element. This chapter analytically explains MFs and their inspirational features from natural geometry. The basic theory of MFs in the binary domain is illustrated, and at the sequence, it has been shown how it is extended to the domain of multivalued functions. Each morphological operator is clarified by intuitive geometrical interpretations. Creative natural inspired analogies are deployed to give a clear intuition to readers about the process of each of them. In this regard, binary and grayscale morphological operators and their properties are well defined and depicted via many examples.

Heartbeat classification is a crucial step for arrhythmia diagnosis during electrocardiographic (ECG) analysis. The new scenario of wireless body sensor network- (WBSN-) enabled ECG monitoring puts forward a higher-level demand for this traditional ECG analysis task. Previously reported methods mainly addressed this requirement with the applications of a shallow structured classifier and expert-designed features. In this study, modified frequency slice wavelet transform (MFSWT) was firstly employed to produce the time-frequency image for heartbeat signal. Then the deep learning (DL) method was performed for the heartbeat classification. Here, we proposed a novel model incorporating automatic feature abstraction and a deep neural network (DNN) classifier. Features were automatically abstracted by the stacked denoising auto-encoder (SDA) from the transferred time-frequency image. DNN classifier was constructed by an encoder layer of SDA and a softmax layer. In addition, a deterministic patient-specific heartbeat classifier was achieved by fine-tuning on heartbeat samples, which included a small subset of individual samples. The performance of the proposed model was evaluated on the MIT-BIH arrhythmia database. Results showed that an overall accuracy of 97.5% was achieved using the proposed model, confirming that the proposed DNN model is a powerful tool for heartbeat pattern recognition.

The image perception by human brain through the eyes is not exactly what the eyes receive. In order to have an enhanced view of the received image and more clarity in detail, the brain naturally modifies the color tones in adjacent neighborhoods of colors. A very famous example of this human sight natural modification to the view is the famous Chevreul–Mach bands. In this phenomenon, every bar is filled with one solid level of gray, but human brain perceives narrow bands at the edges with increased contrast which does not reflect the physical reality of solid gray bars. This human visual system action in illusion, highlighting the edges, is inspired here in visual illusory image enhancement (VIIE). An algorithm for the newly introduced VIIE by deploying morphological filters is presented as morphological VIIE (MVIIE). It deploys morphological filters for boosting the same effect on the image edges and aiding human sight by increasing the contrast of the sight. MVIIE algorithm is explained in this chapter. Significant image enhancement, by MVIEE, is approved through the experiments in terms of image quality metrics and visual perception.

The decision tree-based classification is a popular approach for pattern recognition and data mining. Most decision tree induction methods assume training data being present at one central location. Given the growth in distributed databases at geographically dispersed locations, the methods for decision tree induction in distributed settings are gaining importance. This paper extends two well-known decision tree methods for centralized data to distributed data settings. The first method is an extension of CHAID algorithm and generates single feature based multi-way split decision trees. The second method is based on Fisher's linear discriminant (FLO) function and generates multifeature binary trees. Both methods aim to generate compact trees and are able to handle multiple classes. The suggested extensions for distributed environment are compared to their centralized counterparts and also to each other. Theoretical analysis and experimental tests demonstrate the effectiveness of the extensions. In addition, the side-by-side comparison highlights the advantages and deficiencies of these methods under different settings of the distribution environments.

The decision tree-based classification is a popular approach for pattern recognition and data mining. Most decision tree induction methods assume training data being present at one central location. Given the growth in distributed databases at geographically dispersed locations, the methods for decision tree induction in distributed settings are gaining importance. This paper describes one such method that generates compact trees using multifeature splits in place of single feature split decision trees generated by most existing methods for distributed data. Our method is based on Fisher's linear discriminant function, and is capable of dealing with multiple classes in the data. For homogeneously distributed data, the decision trees produced by our method are identical to decision trees generated using Fisher's linear discriminant function with centrally stored data. For heterogeneously distributed data, a certain approximation is involved with a small change in performance with respect to the tree generated with centrally stored data. Experimental results for several well-known datasets are presented and compared with decision trees generated using Fisher's linear discriminant function with centrally stored data.

Blind Components Processing (BCP), a novel approach in processing of data (signal, image, etc.) components, is introduced as well some applications to information communications technology (ICT) are proposed. The newly introduced BCP is with capability of deployment orientation in a wider range of applications. The fundamental of BCP is based on Blind Source Separation (BSS), a methodology which searches for unknown sources of mixtures without a prior knowledge of either the sources or the mixing process. Most of the natural, biomedical as well as industrial observed signals are mixtures of different components while the components and the way they mixed are unknown. If we decompose the signal into its components by BSS, then we can process the components separately without interfering the other components signal/data. Such internal access to signal components leads to extraction of plenty of information as well more efficient processing compared to normal signal processing wherein all the structure of the signal is gone under processing and modification. This manuscript besides the introducing BCP, proposes a practical applications of BCP with technical merit for harmonic noise cancellation as well stock pricing model.

With rapid advances in technology and connectivity, the capability to capture data from multiple sources has given rise to multiview learning wherein each object has multiple representations and a learned model, whether supervised or unsupervised, needs to integrate these different representations. Multiview learning has shown to yield better predictive and clustering models, it also is able to provide a better insight into relationships between different views for making better decisions. In this paper, we consider the problem of multiview clustering and present a soft-hard clustering approach. In our approach, all object views are first independently mapped into a unit hypercube via soft clustering. The mapped views are next integrated via a hard clustering approach to yield the final results. Both soft and hard clustering stages utilize k-means or its variant c-means, which makes our method suitable for large-scale data problems. Furthermore, additional parallelization of the view mapping stage in parallel is possible, thus making the method more attractive for large-scale data applications. The performance of the method using three benchmark data sets is demonstrated and a comparison with other published results shows our method mostly yields a slightly better performance.

This paper proposes a new active learning approach, confidence-based active learning, for training a wide range of classifiers. This approach is based on identifying and annotating uncertain samples. The uncertainty value of each sample is measured by its conditional error. The approach takes advantage of current classifiers' probability preserving and ordering properties. It calibrates the output scores of classifiers to conditional error. Thus, it can estimate the uncertainty value for each input sample according to its output score from a classifier and select only samples with uncertainty value above a user-defined threshold. Even though we cannot guarantee the optimality of the proposed approach, we find it to provide good performance. Compared with existing methods, this approach is robust without additional computational effort. A new active learning method for support vector machines (SVMs) is implemented following this approach. A dynamic bin width allocation method is proposed to accurately estimate sample conditional error and this method adapts to the underlying probabilities. The effectiveness of the proposed approach is demonstrated using synthetic and real data sets and its performance is compared with the widely used least certain active learning method.

Multi-label classification has received more attention recently in the fields of data mining and machine learning. Though many approaches have been proposed, the critical issue of how to combine single labels to form a multi-label remains challenging. In this work, we propose a novel multi-label classification approach that each label is represented by two exclusive events: the label is selected or not selected. Then a weighted graph is used to represent all the events and their correlations. The multi-label learning is transformed into finding a constrained minimum cut of the weighted graph. In the experiments, we compare the proposed approach with the state-of-the-art multi-label classifier ML-KNN, and the results show that the new approach is efficient in terms of all the popular metrics used to evaluate multi-label classification performance.

Traffic sign recognition (TSR) is an essential research issue in the design of driving support system and smart vehicles. In this paper, we propose a permutation-based image feature to describe traffic signs, which has an inherent advantage of illumination invariance and fast implementation. Our proposed feature LIPID (local image permutation interval descriptor) employs interval division and zone number assignment on order permutation of pixel intensities, and takes the zone numbers as the descriptor. A comprehensive performance evaluation on German Traffic Sign Recognition Benchmark (GTSRB) dataset is carried out, which reveals the great performance of our proposed method. Experiment results exhibit that our feature outperforms some state-of-the-art descriptors, showing a potential prospect in TSR applications.

In this paper, we address the problem of classification of continuous general audio data (GAD) for content-based retrieval, and describe a scheme that is able to classify audio segments into seven categories consisting of silence, single speaker speech, music, environmental noise, multiple speakers' speech, simultaneous speech and music, and speech and noise. We studied a total of 143 classification features for their discrimination capability. Our study shows that cepstral-based features such as the Mel-frequency cepstral coefficients (MFCC) and linear prediction coefficients (LPC) provide better classification accuracy compared to temporal and spectral features. To minimize the classification errors near the boundaries of audio segments of different type in general audio data, a segmentation–pooling scheme is also proposed in this work. This scheme yields classification results that are consistent with human perception. Our classification system provides over 90% accuracy at a processing speed dozens of times faster than the playing rate.

The problem of face detection in images – locating image areas corresponding to human faces – has received a considerable amount of attention in recent years due to numerous possible applications. In this paper, we describe a face detection system for an image annotation task that requires detection of faces at multiple scales against a complex background. The proposed system is a top-down system; it uses the presence of skin tone pixels coupled with shape and face-specific features to locate faces in images. The main distinguishing feature of the proposed system is its use of an iterative region partitioning procedure to generate candidate face regions. To date, the performance of the system has been tested with over 200 test images of varying complexity with promising results.

This paper presents a scheme for image retrieval that lets a user retrieve images either by exploring summary views of the image collection at diAerent levels or by similarity retrieval using query images. The proposed scheme is based on image clustering through a hierarchy of self-organizing feature maps. While the suggested scheme can work with any kind of low-level feature representation of images, our implementation and description of the system is centered on the use of image color information. Experimental results using a database of 2100 images are presented to show the eAcacy of the suggested scheme. ” 1999 Published by Elsevier Science B.V. All rights reserved.

Digital video is becoming widely available in compressed form, such as a motion JPEG or MPEG coded bitstream. In applications such as video browsing or picture-in-picture, or in transcoding for a lower bit rate, there is a need to downscale the video prior to its transmission. In such instances, the conventional approach to generating a downscaled video bitstream at the video server would be to first decompress the video, perform the downscaling operation in the pixel domain, and then recompress it as, say, an MPEG, bitstream for efficient delivery. This process is computationally expensive due to the motion-estimation process needed during the recompression phase. We propose an alternative compressed domain-based approach that computes motion vectors for the downscaled (N/2xN/2) video sequence directly from the original motion vectors for the N/spl times/N video sequence. We further discover that the scheme produces better results by weighting the original motion vectors adaptively. The proposed approach can lead to significant computational savings compared to the conventional spatial (pixel) domain approach. The proposed approach is useful for video severs that provide quality of service in real time for heterogeneous clients.

Conventional processing of JPEG or MPEG compressed image or video data involves first decompressing the data and applying the desired processing function, and then the processed data are recompressed for the purposes of transmission or storage. We propose an alternate processing pipeline which involves direct manipulation of the JPEG or MPEG compressed domain representation to achieve the desired spatial domain processing. For direct manipulation in the compressed domain, we develop a discrete cosine transform (DCT)-domain convolution theorem which besides exploiting the sparseness of the DCT-domain representation also exploits the orthogonality and symmetry in the DCT-domain representation. These properties lead to efficient compressed domain-based processing methods unlike their spatial domain counterparts, where such properties are not available. This theorem can be used in a variety of image and video editing functions when the image and video data are available only as a JPEG or MPEG bitstream. We illustrate the use of the DCT-domain convolution theorem in a typical video editing application such as video bluescreen editing.

The decision tree classifiers represent a nonparametric classification methodology that is equally popular in pattern recognition and machine learning. Such classifiers are also popular in neural networks under the label of neural trees. This paper presents a new approach for designing these classifiers. Instead of following the common top-down approach to generate a decision tree, a structure-driven approach for induction of decision trees, SDIDT, is proposed. In this approach, a tree structure of fixed size with empty internal nodes, i.e. nodes without any splitting function, and labeled terminal nodes is first assumed. Using a collection of training vectors of known classification, a neural learning scheme combining backpropagation and soft competitive learning is then used to simultaneously determine the splits for each decision tree node. The advantage of the SDIDT approach is that it generates compact trees that have multifeature splits at each internal node which are determined on global rather than local basis; consequently it produces decision trees yielding better classification and interpretation of the underlying relationships in the data. Several well-known examples of data sets of different complexities and characteristics are used to demonstrate the strengths of the SDIDT method.

Off-line cursive script recognition has got increasing attention during the last three decades since it is of interest in several areas such as banking and postal service. An off-line cursive handwritten word recognition system is described in this paper and is used for legal amount interpretation in personal checks. The proposed recognition system uses a set of geometric and topologic features to characterize each word. By considering the spatial distribution of these features in a word image, the proposed system maps each word into two strings of finite symbols. A local associative indexing scheme is then used on these strings to organize a vocabulary. When presented with an unknown word, the system uses the same indexing scheme to retrieve a set of candidate words likely to match the input word. A verification process is then carried out to find the best match among the candidate set. The performance of the proposed system has been tested with a legal amount image database from real bankchecks. The results obtained indicate that the proposed system is able to recognize legal amounts with great accuracy.

The organization of video information for video databases requires segmentation of a video into its constituent shots and their subsequent characterization in terms of content and camera work. In this paper, we look at these two steps using compressed video data directly. For shot detection, we suggest a scheme consisting of comparing intensity, row, and column histograms of successive I frames of MPEG video using the chi-square test. For characterization of segmented shots, we address the problem of classifying shot motion into different categories using a set of features derived from motion vectors of P and B frames of MPEG video. The central component of the proposed shot motion characterization scheme is a decision tree classifier built through a process of supervised learning. Experimental results using a variety of videos are presented to demonstrate the effectiveness of performing shot detection and characterization directly on compressed video.

Image representation through local descriptors is the basis of numerous computer vision applications. In the past decade, many local image descriptors such as SIFT and SURF have been proposed, yet algorithms requiring low memory and computation complexity are still preferred. Binary descriptors such as BRIEF have been suggested to satisfy this demand, showing a comparable performance but much faster computation speed. In this paper, we propose a novel local image descriptor, LIPID, which employs intensity permutation and interval division to yield an effective performance in terms of speed and recognition. Our method is inspired by LUCID, proposed by Ziegler and Christiansen [8]. An extensive evaluation on the well-known benchmark datasets reveals the robustness and effectiveness of LIPID as well as its capability to handle illumination changes and texture images.

It is common to view multiple-layer feedforward neural networks as black boxes since the knowledge embedded in the connection weights of these networks is generally considered incomprehensible. This paper proposes a solution to this deficiency of neural networks by suggesting a mapping procedure for converting the weights of a neuron into a symbolic representation and demonstrating its use towards understanding the internal representation and the input-output mapping learned by a feedforward neural network. Several examples are presented to illustrate the proposed symbolic mapping of neurons.

Many applications in image science require similarity retrieval of an image from a large collection of images. In such cases, image indexing becomes important for efficient organization and retrieval of images. This paper addresses this issue in the context of a database of handwritten signature images and describes a system for similarity retrieval and identification of handwritten signature images. The proposed system uses a set of geometric and topologic features to map a signature image into two strings of finite symbols. A local associative indexing scheme is then used on the strings to organize and search the signature image database. The advantage of the local associative indexing is that it is tolerant of missing features and allows queries even with partial signatures. The performance of the system has been tested with an image database of 120 signatures. The results obtained indicate that the proposed system is able to identify signatures with great accuracy even when a part of a signature is missing.

Tree classifiers represent a popular non-parametric classification methodology that has been successfully used in many pattern recognition and learning tasks. However, "is feature-value/spl ges/thrsh" type of tests used in tree classifiers are often found sensitive to noise and minor variations in the data. This has led to the use of soft thresholding in decision trees. Following the decision tree to feedforward neural network mapping of the entropy net, three neural implementation schemes for tree classifiers, that allow soft thresholding, are presented in this paper. Results of several experiments using well-known data sets are described to compare the performance of the proposed implementations with respect to decision trees with hard thresholding. >

Electronic medical records provide us with an enormous amount of data with vast potential. If properly analyzed, medical data can be converted to knowledge that improves treatment, uncovers unexpected associations, and supports the personal experience of doctors and nurses, allowing them to make more informed decisions. Medical data is often generated by monitoring across a period of time, whether new data arrives quickly or slowly, consistently or sporadically, but many data mining methods are not designed to consider the temporal aspect of a data set. Besides the extra dimension of time, medical processes often involve interaction between many attributes at once, complicating the discovery of relevant patterns and associations. Specialized methods to interpret medical data can improve the quality of knowledge extracted from it. Tensors are appropriate data structures to represent our data in a multi-dimensional format, taking into account the relationship between many dimensions at once. We can further segment our data into discrete temporal chunks, creating a sequence of tensors. By applying dynamic tensor analysis to our tensor sequence, we can reveal patterns and associations within our data set and capture their change over time. This information can be developed into medical knowledge that can be used to support future treatment.

The importance of wireless cellular communication in our daily lives has grown considerably in the last decade. Besides using cell phones for voice communication, we routinely use them to access the internet, conduct monetary transactions, send text messages and query a lot of useful information regarding the location of specific places of interest. The use of mobile devices in our day-to-day communication raises many unresolved security issues. In this paper we identify the possible attacks on the wireless cellular network architecture and propose some appropriate countermeasures. Several attacks can be prevented in order to preserve security in wireless cellular communication.

The extraction of a meaningful relationship between a robot and its environment from sensed data is a key component of all intelligent robot task. In many instances, the relationship between the sensed data and the desired output from the robot is so highly complex that it becomes very difficult to specify algorithms for extracting the desired relationships. In such situations, the use of a nonalgorithmic approach through the procedural learning exhibited by the feedforward multiple-layer neural networks appears very attractive. Motivated by this, we present in this paper the details of applying such networks to the task of robot localization. The robot localization scheme presented here uses an ultrasonic ring sensor to capture the environment and is meant for indoor applications. Experimental results simulated and real sensor data are presented to show the usefulness of the proposed scheme.

A new multistage Hough transform approach to the problem of ellipse detection in images is presented. The proposed approach is based on the polar and pole definition of conics and its advantage lies in avoiding the propagation of parameter estimation error over the successive stages of the Hough transform. The proposed method is capable of detecting partially visible ellipses, overlapping ellipses, and groups of concentric ellipses. A set of experimental results is presented to demonstrate these capabilities of the suggested approach.

A data fusion model consisting of several levels of parallel decision fusions is considered. Global optimization of such a model is discussed to obtain the fusion rules for overall optimal performance. The reliability analysis of the proposed model is carried out to establish its superiority over the existing parallel and serial fusion models. >

An evolutionary solution for optimal forecasting the movement of a patient is proposed in this paper. As the great changes of society and environment in modern life, high living pressure results in more and more mental disorders. The safety issue regarding the mental illness patients has risen. According to the statistics of patient safety repost system from the Ministry of the interior in Taiwan, the accidents happened in all the patients have over 85% from the schizophrenias during their treatment period. It indicates the potential dangerous of the psychotics while they are in the treatment period. Therefore, to prevent the accidents will need to focus on the understanding of patient movement in order to issue the warning before the accident happened. It is a practical problem in health care. Moving object prediction addresses the problem of locating a moving object correctly. Therefore, how to effectively forecast or predict the location of moving objects can lead to valuable design for real world applications regarding the issues of moving objects. To address the solution for forecasting problem, we applied evolutionary algorithm (EA) as the target algorithm. The algorithm has powerful techniques to helping stochastic search on the fittest solutions for the problems. Hence, the objective of this paper is to devise the methods that apply EA to solve the practical problems. A case study is a good means to broaden the understanding of the methods how EA can solve problems. Moreover, a case analysis to apply the model for the accident prevention of inpatients is presented to identify the potential of solving the practical problem.

It was reported that between 44,000 and 98,000 deaths occur annually as a consequence of medical errors within American hospitals alone [1] and the US National Association of Boards of Pharmacy reports that as many as 7,000 deaths occur in the US each year because of incorrect prescriptions [2] Therefore, a great desire to improve access to new healthcare methods, and the challenge of delivering healthcare becomes significant nowadays.

A model based two-dimensional object recognition system capable of performing under occlusion and geometric transformation is described in this paper. The system is based on the concept of associative search using overlapping local features. During the training phase, the local features are hashed to set up the associations between the features and models. In the recognition phase, the same hashing procedure is used to retrieve associations that participate in a voting process to determine the identity of the shape. Two associative retrieval techniques for discrete and continuous features, respectively, are described in the paper. The performance of the system is studied using a test set of 1,000 shapes that are corrupted versions of 100 models in the shape database. It is shown that the incorporation of a verification phase to confirm the retrieved associations can provide zero error performance with a small reject rate.

This paper describes Data Modeling for unstructured data of Diffusion Tensor Imaging (DTI). Data Modeling is an essential first step for data preparation in any data management and data mining procedure. Conventional Entity- Relational (E-R) data modeling is lossy, irreproducible, and time-consuming especially when dealing with unstructured image data associated with complex systems like the human brain. We propose a methodological framework for more objective E-R data modeling with unlimited query support by eliminating the structured content-dependent metadata associated with the unstructured data. The proposed method is applied to DTI data and a minimum system is implemented accordingly. Eventually supported with navigation, data fusion, and feature extraction modules, the proposed system provides a content-based support environment (C-BASE). Such an environment facilitates an unlimited query support with a reproducible and efficient database schema. Switching between different modalities of data, while confining the feature extractors within the object(s) of interest, we supply anatomically specific query results. The price of such a scheme is relatively large storage and in some cases high computational cost. The data modeling and its mathematical framework, behind the scene of query executions and the user interface of the system are presented in this paper.

Software Project Management (SPM) is one of the primary factors to software success or failure. Software projects often fail because the mangers do not know true project status. Software project planning can be one of the most critical activities in the SPM process. Without a realistic and objective software project plan, the software development process cannot be managed in an effective way. This paper presents a metric-based multi-agent system, Software Project Planning Associate (SPPA), to assist managers in understanding and visualizing SPM process defined in a software project plan. SPPA consists of Intelligent Agents developed in the Java programming language and JESS (Java Expert System Shell) to assist a software project manager in objectively initializing a software project plan, refining/improving a plan, organizing, staffing, scheduling, measuring, visualizing, controlling, tracking, predicting, and data collecting. The resources, tasks, schedules, and milestones of the software project are described in a generic metric-based software project plan. As software development process evolves, metrics are unobtrusively gathered and compliance to the plan is reported by intelligent agents. Software process effectiveness predictions are made and recommendations are dynamically reported by multi intelligent agents suggesting the software development that should be executed to best comply with the software project plan.

This paper formulates the automated tagging of media as a multilabel classification problem. An induction method for creating a multilabel decision tree is presented, then applied to the problem of identifying emotions associated with music clips. The results are compared to two other multilabel classification approaches (CLUS and RAKEL), and the proposed approach is shown to produce better results using a variety of performance measures.

The decision tree-based classification is a popular approach for pattern recognition and data mining. Most decision tree induction methods assume training data being present at one central location. Given the growth in distributed databases at geographically dispersed locations, the methods for decision tree induction in distributed settings are gaining importance. This paper describes one distributed learning algorithm which extends the original(centralized) CHAID algorithm to its distributed version. This distributed algorithm generates exactly the same results as its centralized counterpart. For completeness, a distributed quantization method is proposed so that continuous data can be processed by our algorithm. Experimental results for several well known data sets are presented and compared with decision trees generated using CHAID with centrally stored data.

Occlusion and poor feature point detection are two of the main difficulties in the use of multiple frames for establishing correspondence of feature points. A formulation of the correspondence problem as an optimization problem is used to handle these difficulties. Modifications to an existing iterative optimization procedure for solving the formulation of the correspondence problem are discussed. Experimental results are presented to show the merits of the formulation. >

How the mapping of decision trees into a multilayer neural network structure can be exploited for the systematic design of a class of layered neural networks, called entropy nets (which have far fewer connections), is shown. Several important issues such as the automatic tree generation, incorporation of the incremental learning, and the generalization of knowledge acquired during the tree design phase are discussed. A two-step methodology for designing entropy networks is presented. The methodology specifies the number of neurons needed in each layer, along with the desired output, thereby leading to a faster progressive training procedure that allows each layer to be trained separately. Two examples are presented to show the success of neural network design through decision-tree mapping. >

CASMIL aims to develop a cost-effective and efficient approach to monitor and predict deformation during surgery, allowing accurate, and real-time intra-operative information to be provided reliably to the surgeon.CASMIL is a comprehensive Image-guided Neurosurgery System with extensive novel features. It is an integration of various modules including rigid and non-rigid body co-registration (image-image, image-atlas, and image-patient), automated 3D segmentation, brain shift predictor, knowledge based query tools, intelligent planning, and augmented reality. One of the vital and unique modules is the Intelligent Planning module, which displays the best surgical corridor on the computer screen based on tumor location, captured surgeon knowledge, and predicted brain shift using patient specific Finite Element Model. Also, it has multi-level parallel computing to provide near real-time interaction with iMRI (Intra-operative MRI). In addition, it has been securely web-enabled and optimized for remote web and PDA access.A version of this system is being used and tested using real patient data and is expected to be in use in the operating room at the Detroit Medical Center in the first half of 2006.CASMIL is currently under development and is targeted for minimally invasive surgeries. With minimal changes to the design, it can be easily extended and made available for other surgical procedures.

This paper describes a method for detecting and locating objects in images. The presented approach relies on finding general landmark candidates (glc) in an image. A glc is a closed region that can be either an object landmark (ol) or a non-object landmark (nol). The entire ol's are then grouped into object clusters (oc's). Given a set of training images, the method builds a database of ol and nol regions and oc's. When a query image is presented, we detect all of the ol's and group them into oc candidates. These cluster candidates are then classified using the oc's from the training database. This method can be used to detect and locate objects from images in many different unconstrained environments, such as detecting vehicles, speed signs, etc... The method is tested on two different cases and is shown to yield a high success rate.

Protein expression analysis has traditionally relied upon visual evaluation of immunohistochemical reaction by a pathologist, who analyzes the grade of staining intensity and estimates the percentage of cells stained in the area of interest. This method is effective in experienced hands but has potential limitations in its reproducibility due to subjectivity between and within operators. These limitations are particularly pronounced in gray areas where a distinction of weak from moderate protein expression can be clinically significant. Some research also suggests that sub localization of the protein expression into different components such as nuclei versus cytoplasm may be of great importance. This distinction can be particularly difficult to quantify using manual methods. In this paper, we formulate the problem of quantitative protein expression analysis as an active learning classification problem, where a very small set of pre-sampled user data is used for understanding expert evaluation. The expert coveted confidence is mapped to derive an uncertainty region to select the supplemental learning data. This is done by posing a structured query to the unknown data set. The newly identified samples are then augmented to the training set for incremental learning. The strength of our algorithm is measured in its ability to learn with minimum user interaction. Chroma analysis results of a Tissue Micro-array (TMA) images are presented to demonstrate the user interaction and learning ability. The chroma analysis results are then processed to obtain quantitative results.

This paper discusses the use of a combination of support vector machine and decision tree learning for recognizing four emotions in speech, which are neutral, angry, lombard, and loud. The base features selected were pitch, derivative of pitch, energy, speaking rate, formants, band-widths, and Mel frequency cepstral coefficients. Three methods of combining learned support vector machine and decision tree classifiers were proposed, namely, minimum misclassification, maximum accuracy, and dominant class. Using the Speech Under Simulated and Actual Stress database, the average accuracy from the minimum misclassification, maximum accuracy, and dominant class methods were 72.4%, 70.8%, 71.3% respectively as opposed to 63.9% and 67.4% which were obtained by using support vector machine and decision tree learning alone.