May 16 2018 cs.CL
The recent developments in the field of biomedicine have made large volumes of biomedical literature available to the medical practitioners. Due to the large size and lack of efficient searching strategies, medical practitioners struggle to obtain necessary information available in the biomedical literature. Moreover, the most sophisticated search engines of age are not intelligent enough to interpret the clinicians' questions. These facts reflect the urgent need of an information retrieval system that accepts the queries from medical practitioners' in natural language and returns the answers quickly and efficiently. In this paper, we present an implementation of a machine intelligence based CLINIcal Question Answering system (CLINIQA) to answer medical practitioner's questions. The system was rigorously evaluated on different text mining algorithms and the best components for the system were selected. The system makes use of Unified Medical Language System for semantic analysis of both questions and medical documents. In addition, the system employs supervised machine learning algorithms for classification of the documents, identifying the focus of the question and answer selection. Effective domain-specific heuristics are designed for answer ranking. The performance evaluation on hundred clinical questions shows the effectiveness of our approach.
Nov 08 2017 cs.RO
Bed-making is a universal home task that can be challenging for senior citizens due to reaching motions. Automating bed-making has multiple technical challenges such as perception in an unstructured environments, deformable object manipulation, obstacle avoidance and sequential decision making. We explore how DART, an LfD algorithm for learning robust policies, can be applied to automating bed making without fiducial markers with a Toyota Human Support Robot (HSR). By gathering human demonstrations for grasping the sheet and failure detection, we can learn deep neural network policies that leverage pre-trained YOLO features to automate the task. Experiments with a 1/2 scale twin bed and distractors placed on the bed, suggest policies learned on 50 demonstrations with DART achieve 96% sheet coverage, which is over 200% better than a corner detector baseline using contour detection.
Aug 20 2012 cs.CR
The significance of the DDoS problem and the increased occurrence, sophistication and strength of attacks has led to the dawn of numerous prevention mechanisms. Each proposed prevention mechanism has some unique advantages and disadvantages over the others. In this paper, we present a classification of available mechanisms that are proposed in literature on preventing Internet services from possible DDoS attacks and discuss the strengths and weaknesses of each mechanism. This provides better understanding of the problem and enables a security administrator to effectively equip his arsenal with proper prevention mechanisms for fighting against DDoS threat.
Apr 26 2012 cs.CR
In this paper, an analytical model for DDoS attacks detection is proposed, in which propagation of abrupt traffic changes inside public domain is monitored to detect a wide range of DDoS attacks. Although, various statistical measures can be used to construct profile of the traffic normally seen in the network to identify anomalies whenever traffic goes out of profile, we have selected volume and flow measure. Consideration of varying tolerance factors make proposed detection system scalable to the varying network conditions and attack loads in real time. NS-2 network simulator on Linux platform is used as simulation testbed. Simulation results show that our proposed solution gives a drastic improvement in terms of detection rate and false positive rate. However, the mammoth volume generated by DDoS attacks pose the biggest challenge in terms of memory and computational overheads as far as monitoring and analysis of traffic at single point connecting victim is concerned. To address this problem, a distributed cooperative technique is proposed that distributes memory and computational overheads to all edge routers for detecting a wide range of DDoS attacks at early stage.
Apr 26 2012 cs.CR
Denial of service (DoS) attacks and more particularly the distributed ones (DDoS) are one of the latest threat and pose a grave danger to users, organizations and infrastructures of the Internet. Several schemes have been proposed on how to detect some of these attacks, but they suffer from a range of problems, some of them being impractical and others not being effective against these attacks. This paper reports the design principles and evaluation results of our proposed framework that autonomously detects and accurately characterizes a wide range of flooding DDoS attacks in ISP network. Attacks are detected by the constant monitoring of propagation of abrupt traffic changes inside ISP network. For this, a newly designed flow-volume based approach (FVBA) is used to construct profile of the traffic normally seen in the network, and identify anomalies whenever traffic goes out of profile. Consideration of varying tolerance factors make proposed detection system scalable to the varying network conditions and attack loads in real time. Six-sigma method is used to identify threshold values accurately for malicious flows characterization. FVBA has been extensively evaluated in a controlled test-bed environment. Detection thresholds and efficiency is justified using receiver operating characteristics (ROC) curve. For validation, KDD 99, a publicly available benchmark dataset is used. The results show that our proposed system gives a drastic improvement in terms of detection and false alarm rate.
Mar 13 2012 cs.CR
Disruption from service caused by DDoS attacks is an immense threat to Internet today. These attacks can disrupt the availability of Internet services completely, by eating either computational or communication resources through sheer volume of packets sent from distributed locations in a coordinated manner or graceful degradation of network performance by sending attack traffic at low rate. In this paper, we describe a novel framework that deals with the detection of variety of DDoS attacks by monitoring propagation of abrupt traffic changes inside ISP Domain and then characterizes flows that carry attack traffic. Two statistical metrics namely, Volume and Flow are used as parameters to detect DDoS attacks. Effectiveness of an anomaly based detection and characterization system highly depends on accuracy of threshold value settings. Inaccurate threshold values cause a large number of false positives and negatives. Therefore, in our scheme, Six-Sigma and varying tolerance factor methods are used to identify threshold values accurately and dynamically for various statistical metrics. NS-2 network simulator on Linux platform is used as simulation testbed to validate effectiveness of proposed approach. Different attack scenarios are implemented by varying total number of zombie machines and at different attack strengths. The comparison with volume-based approach clearly indicates the supremacy of our proposed system.
Mar 13 2012 cs.CR
Anomaly-based DDoS detection systems construct profile of the traffic normally seen in the network, and identify anomalies whenever traffic deviate from normal profile beyond a threshold. This extend of deviation is normally not utilised. This paper reports the evaluation results of proposed approach that utilises this extend of deviation from detection threshold to estimate strength of DDoS attack using various regression models. A relationship is established between number of zombies and observed deviation in sample entropy. Various statistical performance measures, such as coefficient of determination (R2), coefficient of correlation (CC), sum of square error (SSE), mean square error (MSE), root mean square error (RMSE), normalised mean square error (NMSE), Nash-Sutcliffe efficiency index (\eta) and mean absolute error (MAE) are used to measure the performance of various regression models. Internet type topologies used for simulation are generated using transit-stub model of GT-ITM topology generator. NS-2 network simulator on Linux platform is used as simulation test bed for launching DDoS attacks with varied attack strength. A comparative study is performed using different regression models for estimating strength of DDoS attack. The simulation results are promising as we are able to estimate strength of DDoS attack efficiently with very less error rate using various regression models.
Apr 22 2010 cs.SE
A UML based metamodel for Bunge-Wand-Weber (BWW) ontology is presented. BWW ontology is a generic framework for analysis and conceptualization of real world objects. It includes categories that can be applied to analyze and classify objects found in an information system. In the context of BWW ontology, the metamodel is a representation of the ontological categories and relationships among them. An objective behind developing an object-oriented metamodel has been to model BWW ontology in terms of widely used notions in software development. The main contributions of this paper are a classification for ontological categories, a description template, and representations through UML and typed based models.