A sparse representation based fast detection method for surface defect detection of bottle caps

A practical machine-vision-based system is developed for fast detection of defects occurring on the surface of bottle caps. This system can be used to extract the circular region as the region of interests (ROI) from the surface of a bottle cap, and then use the circular region projection histogram (CRPH) as the matching features. We establish two dictionaries for the template and possible defect, respectively. Due to the requirements of high-speed production as well as detecting quality, a fast algorithm based on a sparse representation is proposed to speed up the searching. In the sparse representation, non-zero elements in the sparse factors indicate the defect's size and position. Experimental results in industrial trials show that the proposed method outperforms the orientation code method (OCM) and is able to produce promising results for detecting defects on the surface of bottle caps.

Towards groundwater security in coastal East Africa: initiating a regional research network and integrated hydrogeologic, climatic & socio-economic observatories in coastal aquifers of the Comoros Islands, Kenya and Tanzania

African coastal regions are expected to experience the highest rates of population growth in coming decades. Fresh groundwater resources in the coastal zone of East Africa (EA) are highly vulnerable to seawater intrusion. Increasing water demand is leading to unsustainable and ill-planned well drilling and abstraction. Wells supplying domestic, industrial and agricultural needs are or have become, in many areas, too saline for use. Climate change, including weather changes and sea level rise, is expected to exacerbate this problem. The multiplicity of physical, demographic and socio-economic driving factors makes this a very challenging issue for management. At present the state and probable evolution of coastal aquifers in EA are not well documented. The UPGro project 'Towards groundwater security in coastal East Africa' brings together teams from Kenya, Tanzania, Comoros Islands and Europe to address this knowledge gap. An integrative multidisciplinary approach, combining the expertise of hydrogeologists, hydrologists and social scientists, is investigating selected sites along the coastal zone in each country. Hydrogeologic observatories have been established in different geologic and climatic settings representative of the coastal EA region, where focussed research will identify the current status of groundwater and identify future threats based on projected demographic and climate change scenarios. Researchers are also engaging with end users as well as local community and stakeholder groups in each area in order to understanding the issues most affecting the communities and searching sustainable strategies for addressing these.

PRECYSE: Cyber-attack Detection and Response for Industrial Control Systems

In this short paper, we present an integrated approach to detecting and mitigating cyber-attacks to modern interconnected industrial control systems. One of the primary goals of this approach is that it is cost effective, and thus whenever possible it builds on open-source security technologies and open standards, which are complemented with novel security solutions that address the specific challenges of securing critical infrastructures.

Substance misuse in life and death in a 2-year cohort of suicides

Background: Although substance misuse is a key risk factor in suicide, relatively little is known about the relationship between lifetime misuse and misuse at the time of suicide.

Aims: To examine the relationship between substance misuse and subsequent suicide.

Method: Linkage of coroners' reports to primary care records for 403 suicides occurring over 2 years.

Results: With alcohol misuse, 67% of the cohort had previously sought help for alcohol problems and 39% were intoxicated at the time of suicide. Regarding misuse of other substances, 54% of the cohort was tested. Almost one in four (38%) tested positive, defined as an excess of drugs over the prescribed therapeutic dosage and/or detection of illicit substances. Those tested were more likely to be young and have a history of drug misuse.

Conclusions: A deeper understanding of the relationship between substance misuse and suicide could contribute to prevention initiatives. Furthermore, standardised toxicology screening processes would avoid diminishing the importance of psychosocial factors involved in suicide as a 'cause of death'.

Predictive Maintenance for Improved Sustainability - An Ion Beam Etch Endpoint Detection System Use Case

In modern semiconductor manufacturing facilities maintenance strategies are increasingly shifting from traditional preventive maintenance (PM) based approaches to more efficient and sustainable predictive maintenance (PdM) approaches. This paper describes the development of such an online PdM module for the endpoint detection system of an ion beam etch tool in semiconductor manufacturing. The developed system uses optical emission spectroscopy (OES) data from the endpoint detection system to estimate the RUL of lenses, a key detector component that degrades over time. Simulation studies for historical data for the use case demonstrate the effectiveness of the proposed PdM solution and the potential for improved sustainability that it affords.

Laboratizing the border: The production, translation and anticipation of security technologies

This paper critically interrogates how borders are produced by scientists, engineers and security experts in advance of the actual deployment of technical devices they develop. This paper explores the prior stages of translation and decision-making as a socio-technical device is conceived and developed. Drawing on in-depth interviews, observations and ethnographic research of the EU-funded Handhold project (consisting of nine teams in five countries), it explores how assumptions about the way security technologies will and should perform at the border shape the way that scientists, engineers, and security experts develop a portable, integrated device to detect CBRNE threats at borders. In disaggregating the moments of sovereign decision making across multiple sites and times, this paper questions the supposed linearity of how science comes out of and feeds back into the world of border security. An interrogation of competing assumptions and understandings of security threats and needs, of competing logics of innovation and pragmatism, of the demands of differentiated temporalities in detection and interrogation, and of the presumed capacities, behaviours, and needs of phantasmic competitors and end-users reveals a complex, circulating and co-constitutive process of device development that laboratises the border itself. We trace how sovereign decisions are enacted as assemblages in the antecedent register of device development itself through the everyday decisions of researchers in the laboratory, and the material components of the Handhold device itself.

Building pH Sensors into Paper-based Small-molecular Logic Sys-tems for Very Simple Detection of Edges of Objects

Genetically-engineered bacteria and reactive DNA networks detect edges of objects, as done in our retinas and as also found within computer vision. We now demonstrate that simple molecular logic systems (a combination of a pH sensor, a photo acid generator and a pH buffer spread on paper) without any organization can achieve this relatively complex computational goal with good-fidelity. This causes a jump in the complexity achievable by molecular logic-based computation and extends its applicability. The molecular species involved in light dose-driven 'off-on-off' fluorescence is diverted in the ‘on’ state by proton diffusion from irradiated to unirradiated regions where it escapes a strong quencher, thus visualizing the edge of a mask.

Region-based Mixture of Gaussians Modelling for Foreground Detection in Dynamic Scenes

One of the most widely used techniques in computer vision for foreground detection is to model each background pixel as a Mixture of Gaussians (MoG). While this is effective for a static camera with a fixed or a slowly varying background, it fails to handle any fast, dynamic movement in the background. In this paper, we propose a generalised framework, called region-based MoG (RMoG), that takes into consideration neighbouring pixels while generating the model of the observed scene. The model equations are derived from Expectation Maximisation theory for batch mode, and stochastic approximation is used for online mode updates. We evaluate our region-based approach against ten sequences containing dynamic backgrounds, and show that the region-based approach provides a performance improvement over the traditional single pixel MoG. For feature and region sizes that are equal, the effect of increasing the learning rate is to reduce both true and false positives. Comparison with four state-of-the art approaches shows that RMoG outperforms the others in reducing false positives whilst still maintaining reasonable foreground definition. Lastly, using the ChangeDetection (CDNet 2014) benchmark, we evaluated RMoG against numerous surveillance scenes and found it to amongst the leading performers for dynamic background scenes, whilst providing comparable performance for other commonly occurring surveillance scenes.

A Game-Theoretic Approach for Threats Detection and Intervention in Surveillance

Threat prevention with limited security resources is a challenging problem. An optimal strategy is to eectively predict attackers' targets (or goals) based on current available information, and use such predictions to prevent (or disrupt) their planned attacks. In this paper, we propose a game-theoretic framework to address this challenge which encompasses the following three elements. First, we design a method to analyze an attacker's types in order to determine the most plausible type of an attacker. Second, we propose an approach to predict possible targets of an attack and the course of actions that the attackers may take even when the attackers' types are ambiguous. Third, a game-theoretic based strategy is developed to determine the best protection actions for defenders (security resources).

N-gram density based malware detection

N-gram analysis is an approach that investigates the structure of a program using bytes, characters or text strings. This research uses dynamic analysis to investigate malware detection using a classification approach based on N-gram analysis. The motivation for this research is to find a subset of Ngram features that makes a robust indicator of malware. The experiments within this paper represent programs as N-gram density histograms, gained through dynamic analysis. A Support Vector Machine (SVM) is used as the program classifier to determine the ability of N-grams to correctly determine the presence of malicious software. The preliminary findings show that an N-gram size N=3 and N=4 present the best avenues for further analysis.

Dimensions of Suicide Research: Substance misuse in life and death in a 2-year cohort of suicides

Background
While substance misuse is a key risk factor in suicide relatively little is known about the relationship between lifetime misuse and misuse in suicide.

Aim
To examine the relationship between a history of substance misuse and misuse at the time of a suicide.

Method
Linkage of Coroner reports of 403 suicides occurring over two years with associated primary care records. History of substance misuse was defined as alcohol misuse and/or prescription or illicit drug misuse, for which medical help was sought.

Results
With alcohol misuse: 65% of the cohort had previously sought help and 42% were intoxicated at the suicide (with 30% of these seeing their GP in the previous year). With misuse of other substances: 54% of the cohort were tested for blood toxicology (37% of these tested positive) - with positive toxicology defined as an excess of prescription drugs over the therapeutic minima and/or detection of illicit substances. Those tested were more likely to be young and have a history of drug abuse.

Conclusion
Understanding the links between substance misuse and the use of substances in conjunction with the act of suicide is discussed in light of the study results and current pathology and coroner practices.

Android Malware Detection: an Eigenspace Analysis Approach

The battle to mitigate Android malware has become more critical with the emergence of new strains incorporating increasingly sophisticated evasion techniques, in turn necessitating more advanced detection capabilities. Hence, in this paper we propose and evaluate a machine learning based approach based on eigenspace analysis for Android malware detection using features derived from static analysis characterization of Android applications. Empirical evaluation with a dataset of real malware and benign samples show that detection rate of over 96% with a very low false positive rate is achievable using the proposed method.

Contextual Intrusion Alerts for SCADA Networks

The complexity of modern SCADA networks and their associated cyber-attacks requires an expressive but flexible manner for representing both domain knowledge and collected intrusion alerts with the ability to integrate them for enhanced analytical capabilities and better understanding of attacks. This paper proposes an ontology-based approach for contextualized intrusion alerts in SCADA networks. In this approach, three security ontologies were developed to represent and store information on intrusion alerts, Modbus communications, and Modbus attack descriptions. This information is correlated into enriched intrusion alerts using simple ontology logic rules written in Semantic Query-Enhanced Web Rules (SQWRL). The contextualized alerts give analysts the means to better understand evolving attacks and to uncover the semantic relationships between sequences of individual attack events. The proposed system is illustrated by two use case scenarios.

Kernelized structural classification for 3D dogs body parts detection

Despite pattern recognition methods for human behavioral analysis has flourished in the last decade, animal behavioral analysis has been almost neglected. Those few approaches are mostly focused on preserving livestock economic value while attention on the welfare of companion animals, like dogs, is now emerging as a social need. In this work, following the analogy with human behavior recognition, we propose a system for recognizing body parts of dogs kept in pens. We decide to adopt both 2D and 3D features in order to obtain a rich description of the dog model. Images are acquired using the Microsoft Kinect to capture the depth map images of the dog. Upon depth maps a Structural Support Vector Machine (SSVM) is employed to identify the body parts using both 3D features and 2D images. The proposal relies on a kernelized discriminative structural classificator specifically tailored for dogs independently from the size and breed. The classification is performed in an online fashion using the LaRank optimization technique to obtaining real time performances. Promising results have emerged during the experimental evaluation carried out at a dog shelter, managed by IZSAM, in Teramo, Italy.

Patterns and predictors of help-seeking contacts with health services and general practitioner detection of suicidality prior to suicide: a cohort analysis of suicides occurring over a two-year period

Background: Contact with primary care and psychiatric services prior to suicide may be considerable, presenting
opportunities for intervention. However, there is scant knowledge on the frequency, nature and determinants of
contact.
Method: Retrospective cohort study-an analysis of deaths recorded as suicide by the Northern Ireland Coroner’s
Office linked with data from General Practice patient records over a 2 year period
Results: Eighty-seven per cent of suicides were in contact with General Practice services in the 12 months before
suicide. The frequency of contact with services was considerable, particularly among patients with a common
mental disorder or substance misuse problems. A diagnosis of psychiatric problems was absent in 40 % of suicides.
Excluding suicide attempts, the main predictors of a noted general practitioner concern for patient suicidality are
male gender, frequency of consultations, diagnosis of mental illness and substance misuse.
Conclusions: Despite widespread and frequent contact, a substantial proportion of suicidal people were
undiagnosed and untreated for mental health problems. General Practitioner alertness to suicidality may be too
narrowly focused.