Computer-aided Diagnosis (CAD) systems have become a significant assistance tool, that are used to help identify abnormal/normal regions of interest in mammograms faster and more effectively than human readers. In this work, we propose a new approach for breast cancer identification of all type of lesions in digital mammograms by combining low-and high-level mammogram descriptors in a compact form. The proposed method consists of two major stages: Initially, a feature extraction process that utilizes two dimensional discrete transforms based on ART, Shapelets and textural representations based on Gabor filter banks, is used to extract low-level visual descriptors. To further improve our method's performance, the semantic information of each mammogram given by radiologists is encoded in a 16-bit length word high-level feature vector. All features are stored in a quaternion and fused using the L2 norm prior to their presentation to the classification module. For the classification task, each ROS is recognized using two different classification models, Ada Boost and Random Forest. The proposed method is evaluated on regions taken from the DDSM database. The results show that Ada Boost outperforms Random Forest in terms of accuracy (99.2%$(\pm 0.527)$against 93.78%$(\pm 1.659))$, precision, recall and F-measure. Both classifiers achieve a mean accuracy of 33% and 38% higher than using only visual descriptors, showing that semantic information can indeed improve the diagnosis when it is combined with standard visual features.

Cyber-Physical Systems constitute one of the core concepts in Industry 4.0 aiming at realizing production systems that combine the efforts from human workers, robots and intelligent entities. This is particularly true in Human-Robot Collaboration manufacturing where a tight peer-to-peer interaction between humans and (intelligent) autonomous robots is necessary. Such production systems need a holistic integration along different levels of abstraction and coordination for deploying effective and safe control solutions. We propose the use of novel Artificial Intelligence technologies to enhance flexibility and adaptability of these collaborative systems. Our aim is to advance the classical human-aware paradigm that considers the worker as an anonymous acting entity, in favour of a user-aware paradigm, that considers a worker as profiled user characterized with a number of specific features influencing the “shape” of the collaboration.

Mammography is still the most effective procedure for early diagnosis of breast cancer. Computer-aided Diagnosis (CAD) systems can be very helpful in this direction and an assistance tool for radiologists to recognize abnormal and normal regions of interest in digital mammograms faster than traditional screening program. In this paper, we propose a new method for breast cancer recognition of all types of lesions in digital mammograms using multimodal features in a quaternionic representation. The proposed method consists of two steps: First, a feature extraction module utilizes two dimensional discrete transforms based on ART, Shapelets and Gabor filters to extract low-level visual descriptors of ROS. In addition, semantic mammogram information provided by radiologists, is encoded into a 16-bit length word used as high-level feature vector. All multimodal features are fused in a compact quaternionic representation prior to their presentation to the classification module in the second step. For the classification task, ROSs are diagnosed using trained Support-Vector-Machines (SVMs). The proposed method is evaluated on regions taken from the DDSM database. The proposed feature set achieves a mean accuracy of 87.22% (±2.678) and AUC = 0.98, that is 34% higher than using only visual descriptors, proving the significant information that semantic descriptors contain.

In this paper, a novel methodology for estimating the shape of human biconcave Red Blood Cells (RBCs), using color scattering images, is presented. The information retrieval process includes, image normalization, features extraction using both Histogram of Oriented Gradients (HoG) and region covariance features (RCoV); and features dimensionality reduction using the Independent Component Analysis (ICA). The points of interest (PoIs) are detected using the Harriscorner detector in order to extract the image features. A scheme using adjustable algorithms, i.e. support vectors machine (SVM) is adopted in order to fuse the multimodal features. A Radial Basis Function Neural Network (RBF-NN) estimates the RBC geometrical properties. The proposed method is evaluated in both regression and identification tasks by processing images of a simulated device used to acquire scattering phenomena of moving RBCs. The evaluation database includes 23625 scattering images, obtained by means of the Boundary Element Method. The regression and identification accuracy of the actual RBC shape is estimated using three feature sets in the presence of additive white Gaussian noise from 60 to 10 dB SNR, giving a mean error rate less than 1 percent of the actual RBC shape, and more than 99 percent mean identification rate in a set of valid RBCs size.

Quality of service (QoS) is becoming an attractive feature for high-performance networks and parallel machines because, in those environments, there are different traffic types, each one having its own requirements. In that sense, deadline-based algorithms can provide powerful QoS provision. However, the cost associated with keeping ordered lists of packets makes these algorithms impractical for high-performance networks. In this paper, we explore how to efficiently adapt the Earliest Deadline First family of algorithms to high-speed network environments. The results show excellent performance using just two virtual channels, FIFO queues, and a cost feasible with today's technology.

In this paper we present the design and performance evaluation of a network emulation cluster built with commodity PCs and network switches. Each emulated node runs inside its own virtual machine and is complete with a kernel and device drivers and the virtual machine monitor ensures isolation between the emulated nodes, fair access to the resources of the underlying physical node, and high performance. The load of traffic conditioning (emulating packet delays, losses and other characteristics of widearea network links) is shared between all physical nodes by conditioning only the traffic originated by the emulated nodes they host. The above organization results in an emulation testbed that is low cost and scalable while providing strict resource isolation between emulated nodes and high emulation fidelity by allowing the emulation of kernels and other system level software. In this paper we present the main considerations behind the design of our testbed and through detailed performance evaluation we demonstrate that our approach can result in a scalable emulation system with high performance.

Multicasting enables efficient usage of network resources in applications that require group communication. In addition to the well known multicast applications, new communication technologies that can benefit from multicast keep emerging. A recent example are the various types of virtual private network (VPN) applications that carry customer traffic over public networks creating the illusion of a private network for each customer. Still, due to the difficulty of aggregating multicast destination addresses, multicasting suffers from the forwarding state scalability problems. In this work we investigate how the problem of multicast state scalability re-emerges in the VPN setting and how it can be effectively addressed there using the MPLS label based forwarding paradigm.

Virtual private networks (VPNs) are a popular method for connecting enterprises over a public network infrastructure. Using an IP-based backbone has the potential to significantly reduce the capital expenditure of the service providers and allow them to offer a variety of legacy and new services using a common infrastructure. Recently, a variety of methods have been proposed that enable implementation of VPN services over IP-based backbone networks. Scalability is one of the basic requirements in all the IP-based VPN architectures. In this paper, we focus on cases where the provider must support explicit routing of customer's traffic, and thus have to implement some form of constrained path computation in its backbone network. Routing protocols that support constrained path computation have been known to cause high volumes of routing protocol control traffic. This overhead can seriously affect the operation of the backbone routers and limit the scalability of the VPN architecture. We propose a mechanism that significantly reduces the overhead from routing protocol messages in the core of the network by exchanging resource availability information only between the edge routers. We show that with relatively straightforward changes to the protocols used in the backbone, it is possible to achieve considerable savings in the amount of the routing protocol control overhead without compromising routing performance.

Flooding is a fundamental operation used extensively in communication protocols. Flooding introduces two types of overhead: (a) additional network traffic from the flooded packets, and (b) additional processing at the control processor of a network node that has to receive all the flooded packets, perform duplicate detection and process them. In contrast to packet forwarding resources, control processor resources are usually limited resulting flooding having a major impact on the load of the control processor. In this work we will investigate if is possible to take advantage of the higher performance forwarding plane of a network node to implement flooding and duplicate flooded packet detection. This will allow us to significantly reduce some of the cost associated with flooding. We will show how flooding can be implemented in the multi-protocol label switching (MPLS) forwarding plane and we will discuss potential uses of forwarding plane flooding in traffic engineering and virtual private network applications.

In this paper, we share our experience in designing and building a content-based switch which we call L5. In addition to the layer 2-3-4 information available in the packet, a content-based switch uses application level information to route traffic in the network. Making routing decisions based on information contained in the payload is not a new idea. In fact application level proxies which are functionally equivalent to a content-based switch, have been around for years. Our contribution is in combining the functionalities of an application level proxy with the data handling capabilities of a switch into a single system. In this paper, we describe the architecture of the L5 system along with the details of how application level information can be efficiently processed in the switch hardware. We cover two specific application examples that we believe are ideal candidates for content-based switching: one is routing HTTP sessions based on uniform resource locators (URL) and the other is session-aware dispatching of secure socket layer (SSL) connections.

We discuss an implementation of QoS routing extensions to the open shortest path first (OSPF) routing protocol and evaluate its performance over a wide range of operating conditions. Our evaluations are aimed at assessing the cost and feasibility of QoS routing in IP networks. The results provide insight into the respective weights of the two major components of QoS routing costs, processing cost and protocol overhead and establish strong empirical evidence that the cost of QoS routing is well within the limits of modern technology and can be justified by the performance improvements.

The last couple of years has seen a growing momentum towards using the Internet for conducting business. One of the key enablers for business applications is the ability to setup secure channels across the Internet. The Secure Sockets Layer (SSL) protocol provides this capability and it is the most widely used transport layer security protocol. In this paper we investigate the performance of SSL both from a latency as well as a throughput point of view. Since SSL is primarily used to secure Web transactions, we use the SPECWeb96 benchmark suitably modified for use with the SSL protocol. We benchmark two of the more popular Web servers that are in use today and find that they are a couple of orders of magnitude slower when it comes to serving secure Web pages. We investigate the reason for this deficiency by instrumenting the SSL protocol stack with a detailed profiling of the protocol processing components. Based on our findings we suggest two modifications to the protocol that reduce the latency as well as increase the throughput at the server.

Quality of service (QoS) routing algorithms have become the focus of research due to their potential for increasing the utilization of an integrated services packet network (ISPN) serving requests with QoS requirements. While heuristics for determining paths for such requests have been formulated for a variety of QoS models, little attention has been given to the overall processing complexity of the QoS routing protocol. Although on-demand path computation is very attractive due to its simplicity, many believe that its processing cost will be prohibitive in environments with high request rates. We study alternatives to on-demand path computation that can reduce this processing overhead. In addition to the well known solution of path pre-computation we introduce and study path caching, an incremental modification of on-demand path computation. The simulation results show that caching is an effective alternative to path pre-computation and that both path caching and pre-computation can achieve significant processing cost savings without severely compromising the routing performance.

Quality of service (QoS) routing algorithms have become the focus of recent research due to their potential for increasing the utilization of an integrated services packet network (ISPN) that handles requests with QoS requirements. While heuristics for determining paths for such requests have been formulated for a variety of QoS models, little attention has been given to the overall processing complexity of the QoS routing architecture. Although on demand path computation is very attractive due to its simplicity, many believe that its processing cost will be prohibitive in environments with high request rates. In this work, we first characterize the processing cost of QoS routing algorithms that use the constrained widest-shortest path heuristic to compute QoS paths in a link state based routing environment. By simulating a variety of realistic traffic conditions we investigate the effectiveness of path pre-computation in reducing the amount of routing protocol computation. We mainly want to determine how much reduction in routing processing cost is possible before the routing performance becomes unacceptably low. Our results show that path pre-computation can significantly reduce the processing cost of on-demand path computation but with a proportional routing performance loss.

Recent studies provide evidence that Quality of Service (QoS) routing can provide increased network utilization compared to routing that is not sensitive to QoS requirements of traffic. However, there are still strong concerns about the increased cost of QoS routing, both in terms of more complex and frequent computations and increased routing protocol overhead. The main goals of this paper are to study these two cost components, and propose solutions that achieve good routing performance with reduced processing cost. First, we identify the parameters that determine the protocol traffic overhead, namely (a) policy for triggering updates, (b) sensitivity of this policy, and (c) clamp down timers that limit the rate of updates. Using simulation, we study the relative significance of these factors and investigate the relationship between routing performance and the amount of update traffic. In addition, we explore a range of design options to reduce the processing cost of QoS routing algorithms, and study their effect on routing performance. Based on the conclusions of these studies, we develop extensions to the basic QoS routing, that can achieve good routing performance with limited update generation rates. The paper also addresses the impact on the results of a number of secondary factors such as topology, high level admission control, and characteristics of network traffic.