The objective of this study is to establish that subjective evaluation of fatty as well as normal ultrasound human liver images based on echotexture (spatial pattern of echoes) and echogenicity by visual inspection can be corroborated by Haralick's statistical texture analysis. Seventy-six ultrasound scan images of human normal livers and twenty-four ultrasound images of fatty livers as identified by the radiologist on the basis of echotexture and echogenecity, have been collected from hospital for this study. An unsupervised neural network learning technique, namely, Self Organising Map (SOM) has been employed to generate profile plots. Using Student's t like statistic for each feature as a measure of distinction between normal and fatty livers, two most appropriate features, namely, maximum probability (Maxp) and uniformity (Uni) are selected from this profile plots. These two features are found to form clusters with little overlap for normal and fatty livers. Thus statistical texture analysis of the ultrasound human images using "Maxp" and "Uni" presented the best results for corroborating the classification as made the radiologist by visual inspection. This work may be a humble beginning to model the radiologists' perceptual findings that may emerge in future as a new tool with respect to 'ultrasonic biopsy'.

Attacks on Computer Networks are one of the major threats on using Internet these days. Intrusion Detection Systems (IDS) are one of the security tools available to detect possible intrusions in a Network or in a Host. Research showed that application of machine learning techniques in intrusion detection could achieve high detection rate as well as low false positive rate. This paper discusses some commonly used machine learning techniques in Intrusion Detection System and also reviews some of the existing machine learning IDS proposed by authors at different times.

The security of resources in a corporate network is always important to the organization. For this reason, different techniques, such as firewall and intrusion detection systems, are important. Years of long research have resulted in the contribution of different advancements in these techniques. Artificial intelligence, machine learning techniques, soft computing techniques, and bio-inspired techniques have been efficient in detecting advanced network attacks. However, very often, different new attacks are most successful in breaching these detection techniques. This very reason has been a motivation for us to explore the biological aspects and its defense mechanisms for designing a secure network model. After much study, we have identified that plants have a very well-established and evolved detection and a response mechanism to pathogens. In this paper, we have proposed and implemented a network attack detection and a response model inspired by plants. It is a three-layered model in analogy to the three-layer defense mechanism of plants to pathogens. We have further tested the proposed model to different network attacks and have compared the results to the open-source intrusion detection system, Snort. The experimental results also establish that the model is competent to detect and trigger an automated response whenever required. INDEX TERMS Bio-inspired computing, intrusion detection system, fuzzy logic, network attacks.

The motivation of this paper is to introduce Henstock–Orlicz space with non-absolute integrable functions. We prove that [Formula: see text] is dense in the Henstock–Orlicz space, which is not dense in the classical Orlicz space.

Machine learning is successful in many applications including securing a network from unseen attack. The application of learning algorithm for detecting anomaly in a network has been fundamental since few years. With increasing use of machine learning techniques, it has become important to study to what extent it is good to be dependent on them. Altogether a different discipline called 'adversarial learning' have come up as a separate dimension of study. The work in this paper is to test the robustness of online machine learning based IDS to carefully crafted packets by the attacker called poison packets. The objective is to observe how a remote attacker can deviate the normal behavior of machine learning based classifier in the IDS by injecting the network with carefully crafted packets externally, that may seem normal by the classification algorithm and the instance made part of its future training set. This behavior eventually can lead to a poisoned learning by the classification algorithm in the long run, resulting in misclassification of true attack instances. This work explores one such approach with SOM and SVM as the online learning-based classification algorithms.