An imbalanced dataset is a dataset that has a majority class which is a class has far more example distributions than other classes. It is difficult to deal with unbalanced datasets in classification problems, and many classification algorithms do not perform well in unbalanced datasets. In this paper, we present our logistic regression analysis with Python on imbalanced datasets and determine different thresholds for classification according to the data proportion of imbalanced datasets.

The security threats to mobile application are growing explosively. Mobile app flaws and security defects could open doors for hackers to easily attack mobile apps. Secure software development must be addressed earlier in the development lifecycle rather than fixing the security holes after attacking. Early elimination of possible security vulnerability will secure our software, and mitigate the security risk threats by potential malicious attacking. However, many software developer professionals lack the necessary security knowledge and skills at the development stagef. In this paper we explore the Android common IPC vulnerability and present our developed IPC flaw detectors with open source FindSecurityBugs plugin in Android Studio IDE.

Software-defined networks (SDN) proposed a new conception of network architecture, which facilitates the innovation of network rapidly. The main components are OpenFlow-capable switches and controller, with those components, control plane is decoupled from data plane and network administrators have programmable central control of network traffic via a controller. Although this new concept of networks infrastructure leads to the progress in networking, it encounters security challenges existing in traditional network and it also introduces new security issues specific to SDN. This paper explores major possible security threats and attacks in SDN switch and proposes new approach to dynamically detect and monitor malicious behaviors on flow message passing and defend such attacks to militate the security threats to switch flow table the channel between switch and controller.

The security threats to mobile application are growing explosively. Mobile app flaws and security defects could open doors for hackers to easily attack mobile apps. Secure software development must be addressed earlier in the development lifecycle rather than fixing the security holes after attacking. Early eliminating against possible security vulnerability will help us increase the security of our software, and militate the consequence of damages of data loss caused by potential malicious attacking. However, many software developer professionals lack the necessary security knowledge and skills at the development stage and Secure Mobile Software Development (SMSD) is not yet well represented in current computing curriculum. In this paper we present a static security analysis approach with open source FindSecurityBugs plugin for Android Studio IDE. We categorized the common mobile vulnerability for developers based on OWASP mobile security recommendations and developed detectors to meet the SMSD needs in industry and education.

A decision tree is an important classification technique in data mining classification. Decision trees have proved to be valuable tools for the classification, description, and generalization of data. J48 is a decision tree algorithm which is used to create classification model. J48 is an open source Java implementation of the C4.5 algorithm in the Weka data mining tool. In this paper, we present the method of improving accuracy for decision tree mining with data preprocessing. We applied the supervised filter discretization on J48 algorithm to construct a decision tree. We compared the results with the J48 without discretization. The results obtained from experiments show that accuracy of J48 after discretization is better than J48 before discretization.

As mobile computing is becoming more and more popular, the security threats to mobile applications are simultaneously increasing explosively. Most malicious activities hack the user's private information, such as contact and location information, hijack the user's transactions and communications, and exploit the confidential enterprise data stored in mobile databases or in cache on mobile devices. Database security is one of the most important security areas to be addressed. Many schools are integrating database security topics into database and cybersecurity education. This paper addresses the needs for pedagogical learning materials for database security education and the challenges of building database security capacity through effective, engaging, and investigative learning approaches, through transferrable and integratable mobile-based learning modules with hands-on companion labs based on the OWASP recommendations, such as input validation, data encryption, data sharing, auditing, and others. The primary goal of this learning approach is to create a motivating learning environment that encourages and engages all students in database security concepts and practices learning. The preliminary feedback from students was positive. Students gained hands-on real world learning experiences on Mobile Database Security (MDS) with Android mobile devices, which also greatly promoted students' self-efficacy and confidence in their mobile security learning.

This poster addresses the needs of pedagogical learning materials for Secure Mobile Software Development(SMSD) education and challenges of building SMSD capacity. In this poster, we present an innovative authentic learning approach for SMSD through real-world-scenario case studies. The primary goal of this learning approach is to create an engaging and motivating learning environment that encourages students in learning emerging security concepts and practices such as mobile software developments. It provides students with hands-on laboratory practices on real-world mobile app developments and security. Each module consists of a series of progressive sub-labs: a pre-lab, lab activities, and a student add-on post-lab. The preliminary feedback from students is positive. Students have gained hands-on real world experiences on mobile security with Android mobile devices, which also greatly promoted students' self-efficacy and confidences in their mobile security learning.

Replica placement (RP) is an important technology in content delivery systems to achieve efficient and effective content delivery. Peer-assisted content delivery network (PCDN) has been proposed for simultaneously obtaining the scalability advantage of peer-to-peer networks and the reliability and manageability advantages of content delivery networks. However, the benefits of peer assistance can be severely affected by the self-interested or malicious behaviors of peers. In this research, we utilize mechanism design theory to design robust algorithms for RP in PCDN with the coexistence of altruistic, self-interested, and malicious seeders. Our preliminary results show that RP algorithms that consider peer contributions have better performance in PCDN, in addition, our mechanism incentivizes the contribution of self-interested seeders and further improves the performance of RP in PCDN. We also quantify the impact of malicious behavior on the performance of the mechanism and extend the mechanism to tolerate malicious behaviors.

Research on effective and efficient mobile threat analysis becomes an emerging and important topic in cybersecurity research area. Static analysis and dynamic analysis constitute two of the most popular types of techniques for security analysis and evaluation; nevertheless, each of them has its strengths and weaknesses. To leverage the benefits of both approaches, we propose a hybrid approach that integrates the static and dynamic analysis for detecting security threats in mobile applications. The key of this approach is the unification of data states and software execution on critical test paths. The approach consists of two phases. In the first phase, a pilot static analysis is conducted to identify potential critical attack paths based on Android APIs and existing attack patterns. In the second phase, a dynamic analysis follows the identified critical paths to execute the program in a limited and focused manner. Attacks shall be detected by checking the conformance of the detected paths with existing attack patterns. The method will report the types of detected attack scenarios based on types of sensitive data that may be compromised, such as web browser cookie.

Biometric authentication, a key component for many secure protocols and applications, is a process of authenticating a user by matching her biometric data against a biometric database stored at a server managed by an entity. If there is a match, the user can log into her account or obtain the services provided by the entity. Privacy-preserving biometric authentication (PPBA) considers a situation where the biometric data are kept private during the authentication process. That is the user's biometric data record is never disclosed to the entity, and the data stored in the entity's biometric database are never disclosed to the user. Due to the reduction in operational costs and high computing power, it is beneficial for an entity to outsource not only its data but also computations such as biometric authentication process to a cloud. However, due to well-documented security risks faced by a cloud, sensitive data like biometrics should be encrypted first and then outsourced to the cloud. When the biometric data are encrypted and cannot be decrypted by the cloud, the existing PPBA protocols are not applicable. Therefore, in this paper, we propose a two-party PPBA protocol when the biometric data in consideration are fully encrypted and outsourced to a cloud. In the proposed protocol, the security of the biometric data is completely protected since the encrypted biometric data are never decrypted during the authentication process. In addition, we formally analyze the security of the proposed protocol and provide extensive empirical results to show its runtime complexity.

To enhance the Information Assurance and Security in computer science (CS) education and to prepare students for the challenges of security issues, this paper presents our ongoing work on developing mobile-based hands-on security learning modules that will be integrated into existing courses in CS curriculum.

In the medical community, the demand for detecting texture abnormalities related to pathological Protein Conformation Diseases (PCD) has been increasing for years. In this paper, we use the value (V) channel of an HSV (Hue, Saturation, Value) image, which provides a measurable Detection Region of the V Channel (DRVC) for isolating muscular Intranuclear Inclusions (INIs) indicative of Oculopharyngeal Muscular Dystrophy (OPMD), one variety of PCD. Derived from the Cumulative Distribution Function (CDF) computation over DRVC (CDF-DRVC), the robust cumulative histogram presents the INIs-texture-carrying intensity data as non-decreasing distributions, leading to an accurate estimation of intensities in the texture feature extraction. Beyond the proposed CDF-DRVC methodology, we introduce a methodology of feature synthesis to enhance the quality of feature representations. The experiments are conducted on irregular microscopic images (where variations in size and shape occur) in the binary classes of healthy and sick cases related to OPMD. The proposed framework achieves a higher accuracy rate for the detection as compared to other methods, and exhibits a detection strategy for other types of PCD in medical applications.

This work-in-progress paper presents an approach to authentic learning of mobile security through real-world-scenario case studies. Five sets of case studies are being developed to cover the state-of-the-art of mobile security knowledge and practices. Some of the developed case studies are being implemented in related courses and the preliminary feedback is positive.

Computer networking/security courses are essential parts of college computer science curriculum, and hands-on networking/security experience is well recognized as an effective approach to help students understand better about the network concepts, the layered architecture of network protocols, and network security. A new affordable and easily-adoptable approach to networking/security labs is desirable to enhance network teaching and learning. In this paper, we present our mobile device-based hands-on labware for computer network/security learning, which is guided by authentic learning principles to immerse students in a real world relevant learning environment. The developed labware has been used in various networking and security related courses, and students claim that they can learn more with the hands-on authentic learning experience.

As smart mobile devices grow increasingly in popularity, so do the incentives for attackers. Recent surveys on mobile security describe the rapidly increasing number and sophistication of mobile attacks. Newer sources of risks are being introduced or explored in the mobile computing paradigm where traditional security threats are also evolving. The prevalence of mobile devices and the rapid growth of mobile threats have resulted in a shortage of mobile security personnel. Educational activities are needed to promote mobile security education and to meet the emerging industry and education needs. This paper presents our initial effort on exploring a learning approach to mobile security, which aims at taking advantages of the benefits of mobile devices and the best practices in learning information security, promoting students' interests, and improving students' self-efficacy. An Android security labware is designed to implement the environment and materials for the learning approach. We integrated the pilot modules of the labware into two security courses in two semesters. The majority of the students provided positive feedback and enjoyed the Android security practices.

Digital mobile devices, such as smart phones, have become an essential part of daily lives for the young generation, especially college students. The rapid growth of wireless and mobile technologies results in a huge demand on qualified professionals in this area. More and more schools started teaching wireless and mobile networking, but how to provide students with hands-on practice experience is still a challenge. The networking capabilities of smart mobile devices make it a perfect instructional tool for networking related course teaching. In this study, we have designed and developed a labware with Android smart phones that focuses on teaching and learning of fundamental data communications and networking concepts by making use of the mobile nature of smart phones and mobile devices. The goal of this labware is to provide students with hands-on experience with mobile devices to better understand networking concepts such as different layers of TCP/IP protocol, Bluetooth, Wi-Fi, and a wide range of networking methodologies/implementations in a easy-adoptable, affordable, and effective way.

To address the need for innovative mobile security learning materials and for promoting mobile security education, this paper presents our work-in-progress effort on developing a real-world relevant security labware to provide students with mobile threat analysis and protection experience. A preliminary evaluation has been conducted on the pilot labs and positive feedback has been received.

Data replication is an important technique for improving the accessibility, availability, and reliability of distributed data storage systems. Secret sharing or erasure coding based data fragmentation techniques can be integrated into these systems to improve the system security and survivability. In this paper, a two-tier distributed system is modeled to provide secure data object replication using the integration of data replication and fragmentation approaches. We study the secure replica placement problem in the system with the presence of rational but selfish data owners. Multiple agents place replicas of data objects in the system in order to maximize their own profits while satisfying their security requirements. Algorithmic mechanism design theory is applied to design a direct revelation mechanism to motivate the truth telling of data owners and to approximate the local optimal replica placement. Comparative experiments have been conducted to evaluate the performance of the mechanism.

Tracking a moving target of interest at a high resolution with a dynamically designated network camera while ensuring complete-coverage of the area under surveillance of a video camera network can be a challenging task. Game theory can be applied to the situation, treating individual cameras as players and area coverage as utility. Camera collaboration is needed when one camera handoff the job of tracking a moving target of interest to another. By taking into account coverage shared by two cameras as secondary utility and giving precedence to border-covering camera directions, we can improve the performance of collaborative tracking, reducing complete-coverage failures as well as their associated uncovered blocks between handoffs. The cost of camera adjustment involved in a handoff can also be reduced this way.

Innovative learning methodologies and tools are needed to foster students' interest in programming, improve the effectiveness of programming teaching, and retain the students in computing programs. We present a Collaborative Interactive Cyber learning Platform for Anywhere Anytime Java Programming Learning, an open-source cyber learning platform for Computer Science programming education, to support anywhere anytime personalized and collaborative programming learning. A preliminary evaluation of the proposed cyber learning platform and learning methods has been conducted and the students' responses have been very positive.

Cloud computing has tremendous potential to meet the current needs of cyber-education. This paper presents a work-in-progress work to promote personalized and collaborative learning in computer science introductory programming courses through the design and development of a live and interactive cloud learning environment.

This paper proposes to build reusable live programming learning objects for improving introductory computer programming learning. The learning objects employ an innovative learning model, called Interactive Learning Model, to provide visualized and interactive programming learning in a perception and practice integrated, cloud-based, learning platform. A prototype learning environment has been implemented and deployed in Google Cloud to test and evaluate the learning outcomes of proposed learning objects and learning model.

This paper describes a fully automated computer vision system for detection and classification of the seven basic facial expressions using Multi-Class Support Vector Machine (SVM). Facial expressions are communicated by subtle changes in one or more discrete features such as tightening of the lips, raising the eyebrows, opening and closing of eyes or certain combination of them, which can be identified through monitoring the changes in muscle movements (Action Units), located around the regions of mouth, eyes and eyebrows. For classifying facial expressions, an analytic representation of face with 15 feature points has been used that provides visual observation of the discrete features responsible for the seven basic facial expressions. Feature points from the region of mouth are detected by segmenting the lip contour applying a variational formulation of the level set method. A multidetector approach of facial feature point detection is utilized for identifying the feature-points from the regions of eyes, eyebrows and nose. Feature vectors composed of 15 features are then obtained with respect to the average representation of neutral face and are used to train a Multiclass SVM classifier. The proposed method has been tested over two different facial expression image databases and the average successful recognition rates of 92.04% and 86.33% have been achieved.

In this paper, we study leader election in the presence of selfish nodes for intrusion detection in mobile ad hoc networks (MANETs). To balance the resource consumption among all nodes and prolong the lifetime of an MANET, nodes with the most remaining resources should be elected as the leaders. However, there are two main obstacles in achieving this goal. First, without incentives for serving others, a node might behave selfishly by lying about its remaining resources and avoiding being elected. Second, electing an optimal collection of leaders to minimize the overall resource consumption may incur a prohibitive performance overhead, if such an election requires flooding the network. To address the issue of selfish nodes, we present a solution based on mechanism design theory. More specifically, the solution provides nodes with incentives in the form of reputations to encourage nodes in honestly participating in the election process. The amount of incentives is based on the Vickrey, Clarke, and Groves (VCG) model to ensure truth-telling to be the dominant strategy for any node. To address the optimal election issue, we propose a series of local election algorithms that can lead to globally optimal election results with a low cost. We address these issues in two possible application settings, namely, Cluster-Dependent Leader Election (CDLE) and Cluster-Independent Leader Election (CILE). The former assumes given clusters of nodes, whereas the latter does not require any preclustering. Finally, we justify the effectiveness of the proposed schemes through extensive experiments.

We process the unideal iris images that are acquired in an unconstrained situation and are affected severely by gaze deviations, eyelid and eyelash occlusions, non uniform intensities, motion blurs, reflections, etc. The proposed unideal iris recognition algorithm has two novelties as compared to the previous works; firstly, we propose to deploy a region-based active contour model to segment an unideal iris image with intensity inhomogeneity; Secondly, an iterative algorithm, called the Modified Contribution- Selection Algorithm (MCSA), is used in the context of coalitional game theory to select a subset of informative features without compromising the recognition rate. The verification performance of the proposed scheme is validated using the UBIRIS Version 1, the ICE 2005, and the WVU Unideal datasets.

Robust localization of inner/outer boundary from an iris image plays an important role in iris recognition. However, the conventional iris/pupil localization methods using the region-based segmentation or the gradient-based boundary finding are often hampered by non-linear deformations, pupil dilations, head rotations, motion blurs, reflections, non-uniform intensities, low image contrast, camera angles and diffusions, and presence of eyelids and eyelashes. The novelty of this research effort is that we apply a parallel game-theoretic decision making procedure by using the modified Chakra borty and Duncan's algorithm, which integrates the region-based segmentation and gradient-based boundary finding methods and fuses the complementary strengths of each of these individual methods. This integrated scheme forms a unified approach, which is robust to noise and poor localization.

D-S evidence theory is a method broadly applied in fusion for decision-making. However, this theory has some shortcomings in the formula of evidence combination with the exception that evidence of fully conflict can not be combined, then the probability validity is difficult to determine and sometimes the composed evidence is different from people's subjective judgments or some other issues. These confine the application of evidence to some extent. Some of them have the dubious credibility which affects the fusion result when Multi evidence are combined together. In order to expand the application of the formula of this theory and enhance the reliability of the fusion results, a new combination formula is introduced in this paper, which is also compared with other formulas in other literatures and finally the improved reliability of this combination formula is verified. At last, through data-mining of the decision-making information on a number of isolated points, a new method using combined evidence to make decisions is described. It's proven from the experimental results that the new combination method not only works well and effectively in the evidence of a high level of conflict but also is applicable to fusion for decision-making.

Most existing iris recognition algorithms focus on the processing and recognition of the ideal iris images that are acquired in a controlled environment. In this paper, we process the nonideal iris images that are captured in an unconstrained situation and are affected severely by gaze deviation, eyelids and eyelashes occlusions, nonuniform intensity, motion blur, reflections, etc. The proposed iris recognition algorithm has three novelties as compared to the previous works; firstly, we deploy a region-based active contour model to segment a nonideal iris image with intensity inhomogeneity; secondly, genetic algorithms (GAs) are deployed to select the subset of informative texture features without compromising the recognition accuracy; Thirdly, to speed up the matching process and to control the misclassification error, we apply a combined approach called the adaptive asymmetrical support vector machines (AASVMs). The verification and identification performance of the proposed scheme is validated on three challenging iris image datasets, namely, the ICE 2005, the WVU Nonideal, and the UBIRIS Version 1.

A mechanism involving evolutionary genetic programming (GP) and the expectation maximization algorithm (EM) is proposed to generate feature functions, based on the primitive features, for an image pattern recognition system on the diagnosis of the disease OPMD. Experiments show that the propose algorithm achieves an average performance of 90.20% recognition rate on diagnosis, while reducing the number of feature dimensions from 11 primitive features to the space of a single generated feature.

A mechanism involving evolutionary genetic programming (GP) and the expectation maximization algorithm (EM) is proposed to generate feature functions automatically, based on the primitive features, for an image pattern recognition system on the diagnosis of the disease OPMD. Prior to the feature function generation, we introduce a novel technique of the primitive texture feature extraction, which deals with non-uniform images, from the histogram region of interest by thresholds (HROIT). Compared with the performance achieved by support vector machine (SVM) using the whole primitive texture features, the GP-EM methodology, as a whole, achieves a better performance of 90.20% recognition rate on diagnosis, while projecting the hyperspace of the primitive features onto the space of a single generated feature.

This paper presents an aspect-oriented calculus for security called λ_SAOP. It is based on the λ_calculus and contains pointcuts that are relevant to security hardening of applications. The main contribution of the paper is a semantics for λ_SAOP advice weaving in the presence of these pointcuts. We instrument the effect-based type inference system to inject advices into expressions during static typing. The proposed semantics for advice weaving is in the spirit of AspectJ, a prominent aspect-oriented programming language, where advices are injected before, after or around the join points that match their respective pointcuts. For this purpose, we accommodate the effect-based inference algorithm to take matching and weaving processes into consideration. In addition, we establish the required soundness and preservation proofs.

This paper presents an integrated decision support system for an automated melanoma recognition of dermoscopic images based on multiple expert fusion. In this context, the ultimate aim is to support decision making by predicting image categories (e.g., melanoma, benign and dysplastic nevi) by combining outputs from different classifiers. A fast and automatic segmentation method to detect the lesion from the background healthy skin is proposed and lesion-specific local color and texture-related features are extracted. For the classification, combining experts which are classifiers with different structures, are examined as alternative solution instead of an individual classifier. In this approach, probabilistic outputs of the experts are combined based on the combination rules that are derived by following Bayespsila theorem. The category label with the highest confidence score is considered to be the class of a test image. Experimental results on a collection of 358 dermoscopic images demonstrate the effectiveness of the proposed expert fusion-based approach.

Automated line detection is a classical image processing topic with many applications such as road detection in remote images and vessel detection in medical images. Many traditional line detectors, such as Gabor filter, the second order derivative of Gaussian and Radon transform will response not only to lines but also to edges, e.g. they will give high responses to the edges of bright lines or blobs when only dark lines are required. To reduce false detections when extracting only dark (or bright) lines, in this paper we propose a line detector by using the first derivative of Gaussian. It can detect dark lines without much false detection on blobs or bright lines. Meanwhile, the proposed method can estimate line width simultaneously. Experiments on various images are performed to test the proposed algorithm.

We propose genetic algorithms to improve the feature subset selection by combining the valuable outcomes from multiple feature selection methods. This paper also motivates the use of asymmetrical SVM, which focuses on two important issues. The first issue is the sample ratio bias, and the second issue is that the different types of misclassification error may have different costs, which lead to different misclassification losses. The asymmetrical SVM also influences the trade-off between the cases of false accept and false reject. In order to overcome the problem induced by the traditional SVM due to its slower performance issue in the test phase caused by the number of support vectors, we also implement an adaptive algorithm to select the feature vector (FV) from the support vector solutions.

In this paper, we study the election of multiple leaders for intrusion detection in the presence of selfish nodes in mobile ad hoc networks (MANETs). To balance the resource consumption and prolong the lifetime of all nodes, each cluster should elect a node with the most remaining resources as its leader. However, without incentives for serving others, a node may behave selfishly by lying about its remaining resource and avoiding being elected. We present a solution based on mechanism design theory. More specifically, we design a scheme for electing cluster leaders that have the following two advantages: First, the collection of elected leaders is the optimal in the sense that the overall resource consumption will be balanced among all nodes in the network overtime. Second, the scheme provides the leaders with incentives in the form of reputation so that nodes are encouraged to honestly participate in the election process. The design of such incentives is based on the Vickrey, Clarke, and Groves (VCG) model by which truth-telling is the dominant strategy for each node. Simulation results show that our scheme can effectively prolong the overall lifetime of IDS in MANET and balance the resource consumptions among all the nodes.

A traditional host-based intrusion detection system (HIDS) has to continuously monitor thousands of objects on the host, regardless of whether or not there are any attacks and in what scenarios these attacks have been occurred. This leads to a huge consumption of system resources. In this paper, we put forward an approach that dynamically adjusts the objects a HIDS monitors according to the expected attack scenario. To achieve this goal, we formulate a repeated non-cooperative game between an attacker and a HIDS. The solution leads the HIDS to find the optimal number of objects that should be monitored and the corresponding monitored time. We study the case of multiple-step attack to gain more insight of the solution for this game model. Therefore, our model considers the tradeoff between the detection accuracy and the resource consumption. Analysis and simulation results prove that our approach can effectively decrease the resource consumption of the HIDS taking into consideration the detection accuracy.

One popular solution for reducing the resource consumption of intrusion detection system (IDS) in MANET is to elect a head-cluster (leader) to provide intrusion detection service to other nodes in the same cluster. However, such a moderate mode is only suitable when the probability of attack is low. Once the probability of attack is high, victim nodes should launch their own IDSs to detect and thwart intrusions. Such a robust mode is, however, costly with respect to energy and leads nodes to die faster. Clearly, to reduce the resource consumption of IDSs and yet keep its effectiveness, a critical issue is: when should we shift from moderate to robust mode? In this paper, we formalize this issue as a nonzero-sum noncooperative game theoretical model that takes into consideration the tradeoff between security and IDS resource consumption. The game solution will guide the leader-IDS to find the right moment for notifying the victim node to launch its IDS once the security risk is high enough. To achieve this goal, the Bayesian game theory is used to analyze the interaction between the leader-IDS and intruder with incomplete information about the intruder. By solving such a game, we are able to find the threshold value for notifying the victim node to launch its IDS once the probability of attack exceeds that value. Simulation results show that our scheme can effectively reduce the IDS resource consumption without sacrificing security.

We propose a robust and imperceptible spectral watermarking method for high rate embedding of a watermark into 3D polygonal meshes. Our approach consists of four main steps: (1) the mesh is partitioned into smaller sub-meshes, and then the watermark embedding and extraction algorithms are applied to each sub-mesh, (2) the mesh Laplacian spectral compression is applied to the sub-meshes, (3) the watermark data is distributed over the spectral coefficients of the compressed sub-meshes, (4) the modified spectral coefficients with some other basis functions are used to obtain uncompressed watermarked 3D mesh. The main attractive features of this approach are simplicity, flexibility in data embedding capacity, and fast implementation. Extensive experimental results show the improved performance of the proposed method, and also its robustness against the most common attacks including the geometric transformations, adaptive random noise, mesh smoothing, mesh cropping, and combinations of these attacks.

This paper presents an implicitly-typed functional, aspect-oriented programming language: lambda_AOP. The main contribution of the paper is a semantics for lambda_AOP advice weaving. The weaving is type-based and implemented statically. We extend the Hindley-Milner type inference system to inject applicable advices into lambda expressions during typing. The proposed semantics for advice weaving is close to the spirit of Aspect J, the most popular AOP language, where advices are injected before, after, or around points that match their respective pointcuts. For this purpose, the sequence construct of the extended lambda-calculus is used.

In this paper, we apply the multi-objective genetic algorithm (MOGA) and asymmetrical support vector machine to improve the performance of an iris recognition system. We utilize the collarette region instead of using the complete information of iris region for recognition purpose. The deterministic feature sequence extracted from the iris images using the 2-D Gabor wavelets is applied to train the support vector machine (SVM). We use the MOGA to optimize the features and also to increase the overall recognition accuracy based on the matching performance of the tuned SVM. The traditional SVM is modified to an asymmetrical SVM to treat the cases of the False Accept and the False Reject differently and also to handle the unbalanced data of a specific class with respect to the other classes. The proposed technique is computationally effective with recognition rates of 97.70% and 95.60% on the ICE (Iris Challenge Evaluation) and the WVU (West Virginia University) iris datasets respectively.

This paper describes a fully automated method of classifying facial expressions using support vector machines (SVM). Facial expressions are communicated by subtle changes in one or more discrete features such as tightening the lips, raising the eyebrows, opening and closing of the eyes or certain combination of them, which can be identified through monitoring the changes in muscles movement located near about the regions of mouth, eyes and eyebrows. In this work, we have applied an analytic face model using eleven feature points that represent and identify the principle muscle actions as well as provide measurements of the discrete features responsible for each of the six basic human emotions. A multi-detector approach of facial feature point localization has been utilized for identifying these points of interest from the contours of facial components such as eyes, eyebrows and mouth. Feature vectors composed of eleven features are then obtained by calculating the degree of displacement of these eleven feature points from a non-changeable rigid point. Finally, the obtained feature sets are used to train a SVM classifier so that it can classify facial expressions when given to it in the form of a feature set. The method has been tested on two different publicly available facial expression databases and on average, 89.44% and 84.86% of successful recognition rates have been achieved.

A content-based image retrieval (CBIR) framework for diverse collection of medical images of different imaging modalities, anatomic regions with different orientations and biological systems is proposed. Organization of images in such a database (DB) is well defined with predefined semantic categories; hence, it can be useful for category-specific searching. The proposed framework consists of machine learning methods for image prefiltering, similarity matching using statistical distance measures, and a relevance feedback (RF) scheme. To narrow down the semantic gap and increase the retrieval efficiency, we investigate both supervised and unsupervised learning techniques to associate low-level global image features (e.g., color, texture, and edge) in the projected PCA-based eigenspace with their high-level semantic and visual categories. Specially, we explore the use of a probabilistic multiclass support vector machine (SVM) and fuzzy c-mean (FCM) clustering for categorization and prefiltering of images to reduce the search space. A category-specific statistical similarity matching is proposed in a finer level on the prefiltered images. To incorporate a better perception subjectivity, an RF mechanism is also added to update the query parameters dynamically and adjust the proposed matching functions. Experiments are based on a ground-truth DB consisting of 5000 diverse medical images of 20 predefined categories. Analysis of results based on cross-validation (CV) accuracy and precision-recall for image categorization and retrieval is reported. It demonstrates the improvement, effectiveness, and efficiency achieved by the proposed framework.

This paper presents a content-based image retrieval system for dermatoscopic images as a diagnostic aid to the dermatologists for skin cancer recognition. In this context, the ultimate aim is to support decision making by locating, retrieving and displaying relevant past cases along with diagnostic reports. However, most challenging aspect in this domain is to extract local lesion specific image features and define the relevance between query and database images for retrieval. A fast and automatic segmentation method to detect the lesion from background healthy skin is proposed. This method first transforms a color image into an intensity image by utilizing domain specific image properties and NBS color distance in HVC color space. Lesion mask is detected by fusing individually segmented images based on iterative thresholding. Lesion specific local color and texture features are extracted and represented in the form of mean and variance-covariance of color channels and in a reduced PCA sub-space. Finally, for effective image retrieval, a similarity matching function is defined based on the fusion of a Bhattacharyya and Euclidean distance metric. The performance of the retrieval system is evaluated using average precision on a collection of 358 images, which demonstrates effectiveness of the proposed approach

This paper presents a fusion-based similarity matching framework for content-based image retrieval on a combination of global, semi-global and local region specific features at different levels of abstraction. In this framework, an image is represented by global color and edge histogram descriptors, semi-global color and texture descriptors from grid based overlapping sub-images and local color features from a clustering-based segmented regions. As a result, image similarities are obtained through a weighted combination of overall similarity fusing global, semi-global and local region-based image level similarities. This fusing approach decreases the impact of inaccurate segmentation and increases retrieval effectiveness as constituent features are of a complementary nature. The experimental results on a general-purpose image database indicate that the aggregation or fusion-based technique provides an effective and flexible tool for similarity calculation based on a combination of descriptors from different levels of image representation

In this paper, we consider the problem of detecting intrusions initiated by cooperative malicious nodes in infrastructure-based networks. We achieve this objective by sampling a subset of the transmitted packets, between each intruder and the victim, over selected links or router interfaces. Here, the total sampling rate on all links must not exceed the sampling budget constraint. We build a game theoretic framework to model distributed network intrusions through multiple malicious nodes and a common victim node. To the best of our knowledge, there has not been any study for the case where the attack is distributed over cooperative intruders using game theory. Non-cooperative game theory is used to formally express the problem, where the two players are: (1) the intruders and (2) the intrusion detection system. Our game theoretic framework will guide the intruders to know their attack strategy and the IDS to have an optimal sampling strategy in order to detect these intrusion packets.

This paper presents an image retrieval framework with scalable image representation and inverted file-based indexing by incorporating automatically generated visual keywords. A codebook of visual keywords is implemented adopting a self-organizing map (SOM)-based vector quantization on the feature space of segmented image regions. The codebook is utilized to represent images by calculating the keyword statistics in the individual images as well as in the collection as a whole. To reduce the dimensionality of the sparse feature vector, latent semantic indexing technique is applied and a similarity matching function is proposed by exploiting the correlation between visual keywords. A query expansion strategy is also proposed in the inverted index based on the topology preserving structure of the SOM. Experimental results over a collection of 5000 general photographic images demonstrate the efficiency and effectiveness of the proposed approach compared to the low-level histogram-based approaches

We propose an improved iris recognition method for person identification using an iris segmentation approach based on chain code and zigzag collarette area with support vector machine (SVM). The zigzag collarette area is selected as a personal identification pattern which captures only the most important areas of iris complex pattern and better recognition accuracy is achieved. The idea to use the zigzag collarette area is that it is insensitive to the pupil dilation and usually not affected by eyelids or eyelashes. The deterministic feature sequence is extracted from iris images using Gabor wavelet technique and used to train SVM as iris classifiers. The traditional SVM is modified as asymmetrical SVM to treat False Accept and False Reject differently to satisfy several security requirements. The parameters of SVM are tuned to improve overall system performance. Our experimental results also indicate that the performance of SVM as a classifier is far better than the performance of backpropagation neural network (BPNN), K-nearest neighbor (KNN), Hamming and Mahalanobis distance. The proposed innovative technique is computationally effective as well as reliable in term of recognition rate of 99.56%.

This paper presents a new approach to automated retinal vessel segmentation based on multiscale analysis and adaptive thresholding. The accurate identification of the appearance of blood vessels in ocular fundus plays an important role in medical diagnosis of many diseases. In contrast to the existing methods for computer aided diagnosis which are either window-based or tracking based, we propose a novel scheme which combines multiscale analysis and adaptive thresholding to help eye care specialists to screen larger populations for vessel abnormalities under various conditions such as vessel size and local contrast. Our method includes a multiscale analytical scheme based on Gabor filters and scale multiplication, and adaptive thresholding. The experimental results demonstrate the feasibility and effectiveness of the proposed algorithms which are good for detecting large and small vessels concurrently with robustness to denoise and enhance the responses at low contrast.

The development of microarray technology has supplied a large volume of data to many fields. This data has thousands of features and is also very noisy. So it is very difficult to represent and understand its complex relationships directly. In this paper we propose a method, called case-based reasoning classifier( CBR) that improves the performance considerably when applied to cancer classification from gene expression data. We also used the Mahalanobis classifier which accurately classifies the gene expression data. In our analysis, a benchmark dataset such as Leukemia cancer dataset, have been used. Experimental results indicate that the above classifier produces a better recognition rate on the benchmark dataset.

Current holistic appearance based face recognition methods require a high dimensional feature space to attain fruitful performance. In this paper, we have proposed a relatively low feature dimensional, template-matching scheme to cope with the transformed appearance-based face recognition problem. We use aggregated Gabor filter responses to represent face images. We investigated the effect of "duplicate" images (images from different sessions) and the effect of facial expressions. Our results indicate that the proposed method is more robust in recognizing "duplicate" images with variations in facial expression than the principal component analysis method.

By using the fusion of contextual, visual and non-visual features, a model based on Dempster-Shafer (D-S) evidence theory is proposed to obtain a reliable driver's fatigue recognition. Firstly, an overall model structure is set up with respect to the selected features and key symptoms of driver's fatigue. Secondly, a set of heuristic knowledge rules are used to determine the basic probability assignment; and a modified evidence combination is adopted to combine multiple pieces of evidence including consistent and conflicting ones. Thirdly, decision policy based on the basic probability assignment is applied to fatigue recognition. At last, an example is given to illustrate the proposed fatigue recognition model.

We introduce the notion of a k-time license for digital content and a method for ensuring its security via a k-time encryption scheme. A k-times license is an agreement that legally allows the purchaser to use the licensed material at most k times. The digital content is only accessible through a provided application that decrypts and re-encrypts the content according to our k-time encryption scheme. The application must use secret keys during this process, a vulnerability since the application resides on the user's PC or electronic device. To help heighten the level of security of our system, we also introduce the idea of hiding secret keys in the heuristic solutions of NP-hard problems and then further extend the security with some other well known methods.

In this paper we propose an architecture for secure access of computers inside an organization from a remote location. We use biometrics features and a one-time password mechanism on top of secure socket layer (SSL) for authentication. We also provide three layers of security levels for network communication, and also a mechanism for secure file accesses based on the security privileges assigned to various users is proposed. The files to be accessed from the server are categorized depending on their access privileges and encrypted using a key assigned to each category.

We present an indexing method for volumetric images using the Principal Component Analysis. The scatter plot of the first two components is used to develop a signature of the image set. Using this signature we can compare and recognize various images effectively. We have implemented the proposed method on a number of biomedical images.

This paper presents a hierarchical stereo matching strategy using the discrete wavelet transform (DWT). Both area- and feature-based methods are combined into a single process by taking advantage of the discrete wavelet decomposition. Image components extracted from the approximation, horizontal, and vertical channels of the decomposition are combined to do the matching at each level. The disparity at a coarse level is then propagated to the finer levels. Since the detail channel of the decomposition is discarded, the noise is automatically reduced. Experiments using various kinds of image pairs show that the method is accurate, fast, and highly robust to noise.

This paper presents a new approach to similar shape retrieval by coarse-to-fine curve matching and data mining techniques. The proposed method extends the concepts of conventional data warehouse and image database for effective image indexing. An image data warehouse schema is developed to integrate multiple shape features for hierarchical shape representation, dynamic similarity measures and fast query processing. A guided search scheme is introduced, that combines the methods of invariant moments, 2D polygonal arc matching and B-spline curve matching, to search for the best similar shape in a hierarchical fashion. The proposed method is applied to the tropical cyclone pattern recognition by utilizing the active contour model (snake) to extend the traditional Dvorak technique for tropical cyclone intensity analysis and forecasting from satellite imagery.

We present a wavelet-based, high performance, hierarchical scheme for image matching which includes (1) dynamic detection of interesting points as feature points at different levels of subband images via the wavelet transform, (2) adaptive thresholding selection based on compactness measures of fuzzy sets in image feature space, and (3) a guided searching strategy for the best matching from coarse level to fine level. In contrast to the traditional parallel approaches which rely on specialized parallel machines, we explored the potential of distributed systems for parallelism. The proposed image matching algorithms were implemented on a network of workstation clusters using parallel virtual machine (PVM). The results show that our wavelet-based hierarchical image matching scheme is efficient and effective for object recognition.

The Dempster's rule of combination is a widely used technique to integrate evidence collected from different sources. In this paper, it is shown that the values of certain functions defined on a family of belief structures decrease (by scale factors depending on the degree of conflict) when the belief structures are combined according to the Dempster's rule. Similar results also hold when an arbitrary belief structure is prioritized while computing the combination. Furthermore, the length of the belief-plausibility interval is decreased during a nonhierarchical aggregation of belief structures. Several types of inheritance networks are also proposed each of which allows considerable flexibility in the choice of prioritization.

This paper presents a gray-scale skeletonization algorithm based on the gray weighted distance transformation (GWDT). The proposed algorithm is conceptually simple and could be used to process nonuniformly distributed gray-scale images. The algorithm can detect the hollows on the gray-scale image, a feature that is often ignored in other skeletonization algorithms, and improves the quality of the skeleton.

Parallax displacement is used to determine a relative 3D conic projective structure. This value is invariant between any number of views in time if the conic is not moving with respect to the plane of the homography. It can be used to determine conic correspondence between three simultaneous views. The corresponding conics may then be used to determine the epipolar geometry. This method of determining conic correspondence works with unknown and even changing epipolar geometry. The relative 3D conic projective structure may be used to segment groups of conics which have consistent motion.

This paper describes an approach to high performance image matching, which includes parallel feature detection and hierarchical image matching. To improve the performance of the traditional image matching algorithms, we adopted interesting points as feature points to reduce the redundant edge points and proposed a parallel guided image matching scheme by using Hausdorff distance. A series of experiments have been conducted and the results indicate the effectiveness of the proposed approach in terms of speed-up and matching accuracy.

A new feature-based method for the correspondence problem is proposed. The used feature is the boundary of a parameter-dependent connected component ((/spl epsiv/,/spl delta/)-component, Wang and Bhattacharya, 1996) of an image. We prove that under certain conditions, there is a one-to-one relationship between the sets of the boundary points in a pair of stereo images. This correspondence may be identified through epipolar geometry. Furthermore, since such connected components may represent some meaningful objects (Wang and Bhattacharya, 1996) in images, we may obtain the corresponding objects directly, instead of only the corresponding points or lines as in some other methods which need the process of feature grouping to conduct further analysis. Also, a hierarchy of the connected components provides us with a coarse-to-fine matching method to recover the surface corresponding to a connected component.

We propose a new sequential width-independent thinning algorithm for binary images. The algorithm uses a 4-neighbor distance transformation, and is designed to preserve the topological properties and shape of the object to be thinned. Comparison of the run time with a standard algorithm is given.

We define a distance measure between 3D polygonal arcs of equal length, and show that the minimum value of this distance measure is the smallest eigenvalue of a certain matrix. Using this, we develop a mismatch measure and a matching algorithm for 3D polygonal arcs of unequal lengths.

This paper presents mutual invariants of families of coplanar conics. These invariants are compared with the use for invariants of two conics and a case is presented where the proposed invariants have a greater discriminating power than the previously used invariants. The use of invariants is extended to any number of coplanar conics. A lambda-matrix is associated with each family of coplanar conics. The use of lambda-matrices is extended from the single-variable polynomial to multivariable polynomials. The Segre characteristic and other invariants of the lambda-matrix are used as invariants of the family of conics.

We show that the minimum value of a distance measure between 3-D polygonal arcs of equal length is the smallest eigenvalue of a certain matrix. Using this we develop a mismatch measure and a matching algorithm for 3-D polygonal arcs of unequal lengths.

A new definition of the connected components of gray images which depends on two parameters /spl epsiv/ and /spl delta/ is introduced. The definition takes into account both the gray values of the pixels and the differences of the gray values of the neighboring pixels. An algorithm to partition an image into its (/spl epsiv/,/spl delta/)-components and several experimental results are given. A practical advantage of the definition is that a segmentation of an image can be done by finding its (/spl epsiv/,/spl delta/)-components for some appropriate values of /spl epsiv/, /spl delta/. Also, we may study an image globally through the interrelationships of the (/spl epsiv/,/spl delta/)-components rather than that of the pixels. Thus our theory provides a possible method of transition from low level computer vision to an intermediate level vision.

We develop an iterated histogram modification algorithm for enhancing gray images. The modified image has very few gray levels corresponding to the spikes found. A process of sharpening the peaks on the histogram of an image is considered using an iterative process where large bins increase at the expense of nearby smaller bins.>

A multidimensional approach is introduced to the representation of uncertain information in conjunction with the Dempster-Schafer theory. A multidimensional array, called a transition array, is defined, which stores the joint probabilities of the occurrences of a set of variables taking values in different sets. Using this array, it is shown how to compute the information regarding the probability of occurrences of the variables as certain matrix products.>