'Introducing Dendritic Cells as a Novel Immune-Inspired Algorithm for Anomaly Detection'

Abstract. Dendritic cells are antigen presenting cells that provide a vital link between the innate and adaptive immune system. Research into this family of cells has revealed that they perform the role of coordinating T-cell based immune responses, both reactive and for generating tolerance. We have derived an algorithm based on the functionality of these cells, and have used the signals and differentiation pathways to build a control mechanism for an artificial immune system. We present our algorithmic details in addition to some preliminary results, where the algorithm was applied for the purpose of anomaly detection. We hope that this algorithm will eventually become the key component within a large, distributed immune system, based on sound immunological concepts.

Low-Volatility Anomaly in Helsinki Stock Exchange

International research shows that low-volatility stocks have beaten high-volatility stocks in terms of returns for decades on multiple markets. This abbreviation from traditional risk-return framework is known as low-volatility anomaly. This study focuses on explaining the anomaly and finding how strongly it appears in NASDAQ OMX Helsinki stock exchange. Data consists of all listed companies starting from 2001 and ending close to 2015. Methodology follows closely Baker and Haugen (2012) by sorting companies into deciles according to 3-month volatility and then calculating monthly returns for these different volatility groups. Annualized return for the lowest volatility decile is 8.85 %, while highest volatility decile destroys wealth at rate of -19.96 % per annum. Results are parallel also in quintiles that represent larger amount of companies and thus dilute outliers. Observation period captures financial crisis of 2007-2008 and European debt crisis, which embodies as low main index annual return of 1 %, but at the same time proves the success of low-volatility strategy. Low-volatility anomaly is driven by multiple reasons such as leverage constrained trading and managerial incentives which both prompt to invest in risky assets, but behavioral matters also have major weight in maintaining the anomaly.

Magnetic Theory and Applications in the Naples Bay (Southern Tyrrhenian Sea, Italy): Magnetic Anomaly Fields and Relationships with Morpho-Structural Lineaments

Magnetic theory and application to a complex volcanic area located in Southern Italy are here discussed showing the example of the Gulf of Naples, located at Southern Italy Tyrrhenian margin. A magnetic anomaly map of the Gulf of Naples has been constructed aimed at highlighting new knowledge on geophysics and volcanology of this area of the Eastern Tyrrhenian margin, characterized by a complex geophysical setting, strongly depending on sea bottom topography. The theoretical aspects of marine magnetometry and multibeam bathymetry have been discussed. Magnetic data processing included the correction of the data for the diurnal variation, the correction of the data for the offset and the leveling of the data as a function of the correction at the cross-points of the navigation lines. Multibeam and single-beam bathymetric data processing has been considered. Magnetic anomaly fields in the Naples Bay have been discussed through a detailed geological interpretation and correlated with main morpho-structural features recognized through morphobathymetric interpretation. Details of magnetic anomalies have been selected, represented and correlated with significant seismic profiles, recorded on the same navigation lines of magnetometry. They include the continental shelf offshore the Somma-Vesuvius volcanic complex, the outer shelf of the Gulf of Pozzuoli offshore the Phlegrean Fields volcanic complex, the relict volcanic banks of Pentapalummo, Nisida and Miseno, the Gaia volcanic bank on the Naples slope, the western slope of the Dohrn canyon, the Magnaghi canyon’s head and the magnetic anomalies among the Ischia and Procida islands.

Information Fusion for Anomaly Detection with the Dendritic Cell Algorithm

Dendritic cells are antigen presenting cells that provide a vital link between the innate and adaptive immune system, providing the initial detection of pathogenic invaders. Research into this family of cells has revealed that they perform information fusion which directs immune responses. We have derived a Dendritic Cell Algorithm based on the functionality of these cells, by modelling the biological signals and differentiation pathways to build a control mechanism for an artificial immune system. We present algorithmic details in addition to experimental results, when the algorithm was applied to anomaly detection for the detection of port scans. The results show the Dendritic Cell Algorithm is successful at detecting port scans.

Introducting Dendritic Cells as a Novel Immune-Inspired Algorithm for Anomaly Detection

Dendritic cells are antigen presenting cells that provide a vital link between the innate and adaptive immune system. Research into this family of cells has revealed that they perform the role of coordinating T-cell based immune responses, both reactive and for generating tolerance. We have derived an algorithm based on the functionality of these cells, and have used the signals and differentiation pathways to build a control mechanism for an artificial immune system. We present our algorithmic details in addition to some preliminary results, where the algorithm was applied for the purpose of anomaly detection. We hope that this algorithm will eventually become the key component within a large, distributed immune system, based on sound imnological concepts.

An Immune Inspired Approach to Anomaly Detection

The immune system provides a rich metaphor for computer security: anomaly detection that works in nature should work for machines. However, early artificial immune system approaches for computer security had only limited success. Arguably, this was due to these artificial systems being based on too simplistic a view of the immune system. We present here a second generation artificial immune system for process anomaly detection. It improves on earlier systems by having different artificial cell types that process information. Following detailed information about how to build such second generation systems, we find that communication between cells types is key to performance. Through realistic testing and validation we show that second generation artificial immune systems are capable of anomaly detection beyond generic system policies. The paper concludes with a discussion and outline of the next steps in this exciting area of computer security.

Dempster-Shafer for Anomaly Detection

In this paper, we implement an anomaly detection system using the Dempster-Shafer method. Using two standard benchmark problems we show that by combining multiple signals it is possible to achieve better results than by using a single signal. We further show that by applying this approach to a real-world email dataset the algorithm works for email worm detection. Dempster-Shafer can be a promising method for anomaly detection problems with multiple features (data sources), and two or more classes.

Dendritic Cells for Real-Time Anomaly Detection

Dendritic Cells (DCs) are innate immune system cells which have the power to activate or suppress the immune system. The behaviour of human DCs is abstracted to form an algorithm suitable for anomaly detection. We test this algorithm on the real-time problem of port scan detection. Our results show a significant difference in artificial DC behaviour for an outgoing portscan when compared to behaviour for normal processes.

Dendritic Cells for Anomaly Detection

Artificial immune systems, more specifically the negative selection algorithm, have previously been applied to intrusion detection. The aim of this research is to develop an intrusion detection system based on a novel concept in immunology, the Danger Theory. Dendritic Cells (DCs) are antigen presenting cells and key to the activation of the human immune system. DCs perform the vital role of combining signals from the host tissue and correlate these signals with proteins known as antigens. In algorithmic terms, individual DCs perform multi-sensor data fusion based on time-windows. The whole population of DCs asynchronously correlates the fused signals with a secondary data stream. The behaviour of human DCs is abstracted to form the DC Algorithm (DCA), which is implemented using an immune inspired framework, libtissue. This system is used to detect context switching for a basic machine learning dataset and to detect outgoing portscans in real-time. Experimental results show a significant difference between an outgoing portscan and normal traffic.

'Introducing Dendritic Cells as a Novel Immune-Inspired Algorithm for Anomaly Detection'

Abstract. Dendritic cells are antigen presenting cells that provide a vital link between the innate and adaptive immune system. Research into this family of cells has revealed that they perform the role of coordinating T-cell based immune responses, both reactive and for generating tolerance. We have derived an algorithm based on the functionality of these cells, and have used the signals and differentiation pathways to build a control mechanism for an artificial immune system. We present our algorithmic details in addition to some preliminary results, where the algorithm was applied for the purpose of anomaly detection. We hope that this algorithm will eventually become the key component within a large, distributed immune system, based on sound immunological concepts.

Anomaly diagnosis in ceramic claddings by thermography - A review

With the increasing importance given to building rehabilitation comes the need to create simple, fast and non-destructive testing methods (NDT) to identify problems and for anomaly diagnosis. Ceramic tiles are one of the most typical kinds of exterior wall cladding in several countries; the earliest known examples are Egyptian dating from 4000 BC. This type of building facade coating, though being quite often used in due to its aesthetic and architectural characteristics, is one of the most complex that can be applied given the several parts from which it is composed; hence, it is also one of the most difficult to correctly diagnose with expeditious methods. The detachment of ceramic wall tiles is probably the most common and difficult to identify anomaly associated with this kind of cladding and it is also definitely the one that can compromise security the most. Thus, it is necessary to study a process of inspection more efficient and economic than the currently used which often consist in semi-destructive methods (the most common is the pull off test), that can only be used in a small part of the building at a time, allowing some assumptions of what can the rest of the cladding be like. Infrared thermography (IRT) is a NDT with a wide variety of applications in building inspection that is becoming commonly used to identify anomalies related with thermal variations in the inspected surfaces. Few authors have studied the application of IRT in anomalies associated with ceramic claddings claiming that the presence of air or water beneath the superficial layer will influence the heat transfer in a way that can be detected in both a qualitative and a quantitative way by the thermal camera, providing information about the state of the wall in a much broad area per trial than other methods commonly used nowadays. This article intends to present a review of the state of art of this NDT and its potentiality in becoming a more efficient way to diagnose anomalies in ceramic wall claddings.

On the effect of Arabian Sea and Indian Ocean sea surface temperature anomaly on the monsoon rainfall of south-east of Iran

Southeast region of the country has hot and dry weather which causes to happen heavy rainfall in short time period of warm seasons and to occur river flooding. These precipitations are influenced by monsoon system of India ocean. In these thesis, It was tried to evaluate the relation between thermal anomaly of sea surface in India ocean and Arab sea which effects on southeast monsoon precipitations of Iran, For evaluation of this happening in southeast, data were collected from 7 synoptic observation stations of Bandar Abbas, Minab, Kerman , Bam, Chabahar, Iranshahr, Zahedan and 17 rain gauge stations during June to September of each year from 1980 to 2010. Rainy days were determine and then some information about synoptic circulation models, maps of average pressure of sea surface, geopotential height of 700hP surface, geopotential height of 500hP surface, temperature of 850 hPa surface, humidity of 700 hPa surface, vertical velocity of 700 hPa surface, vertical velocity of 500 hP and humidity of 2 meters height for 6 systems were extracted from NCEP/NCAR website for evaluation. By evaluation of these systems it was determined that the monsoon low pressure system tab brings needed humidity of these precipitations to this region from India ocean and Arab sea with a vast circulation. It is seen that warm air pool locates on Iran and cold air pool locates on west of India at 800 hPa surface. In a rainy day this warm air transfers to high latitudes and influences the temperature trough of southeast cold air pool of the country. In the middle surfaces of 700 and 500 hPa, the connection between low height system above India and low height system above the higher latitudes causes the low height system above India to be strength and developed. By evaluation of humidity at 2 meters height and 700 hPa surface we observe that humidity Increases in the southeast region. With penetrating of the low height system of India above the 700 and 500 hPa surfaces of southeast of Iran, the value of negative omega (Rising vertical velocity) is increased. In the second pace, it was shown the evaluation of how the correlation between sea surface temperature anomaly in India Ocean and Arab sea influences southeast monsoon precipitation of Iran. For this purpose the data of water surface temperature anomaly of Arab sea and India ocean, the data of precipitation anomaly of 7 synoptic stations , mentioned above, and correlation coefficient among the data of precipitation anomaly and water surface temperature anomaly of Arab Sea, east and west of India ocean were calculated. In conclusion it was shown that the maximum correlation coefficient of precipitation anomaly had belonged to India Ocean in June and no meaningful correlation was resulted in July among precipitation anomaly and sea surface temperature anomaly for three regions, which were evaluated.

On the trace anomaly of a Weyl fermion

La seguente tesi si sviluppa in tre parti: un'introduzione alle simmetrie conformi e di scala, una parte centrale dedicata alle anomalie quantistiche ed una terza parte dedicata all'anomalia di traccia per fermioni. Nella seconda parte in particolare si introduce il metodo di calcolo alla Fujikawa e si discute la scelta di regolatori adeguati ed un metodo per ottenerli, si applicano poi questi metodi ai campi, scalare e vettoriale, per l'anomalia di traccia in spazio curvo. Nell'ultimo capitolo si calcolano le anomalie di traccia per un fermione di Dirac e per uno di Weyl; la motivazione per calcolare queste anomalie nasce dal fatto che recenti articoli hanno suggerito che possa emergere un termine immaginario proporzionale alle densità di Pontryagin nell'anomalia di Weyl. Noi non abbiamo trovato questo termine e il risultato è che l'anomalia di traccia risulta essere metà di quella per il caso di Dirac.

Real-time anomaly detection of gamma-ray bursts for the Cherenkov Telescope Array using deep learning

The Cherenkov Telescope Array (CTA) will be the next-generation ground-based observatory to study the universe in the very-high-energy domain. The observatory will rely on a Science Alert Generation (SAG) system to analyze the real-time data from the telescopes and generate science alerts. The SAG system will play a crucial role in the search and follow-up of transients from external alerts, enabling multi-wavelength and multi-messenger collaborations. It will maximize the potential for the detection of the rarest phenomena, such as gamma-ray bursts (GRBs), which are the science case for this study. This study presents an anomaly detection method based on deep learning for detecting gamma-ray burst events in real-time. The performance of the proposed method is evaluated and compared against the Li&Ma standard technique in two use cases of serendipitous discoveries and follow-up observations, using short exposure times. The method shows promising results in detecting GRBs and is flexible enough to allow real-time search for transient events on multiple time scales. The method does not assume background nor source models and doe not require a minimum number of photon counts to perform analysis, making it well-suited for real-time analysis. Future improvements involve further tests, relaxing some of the assumptions made in this study as well as post-trials correction of the detection significance. Moreover, the ability to detect other transient classes in different scenarios must be investigated for completeness. The system can be integrated within the SAG system of CTA and deployed on the onsite computing clusters. This would provide valuable insights into the method's performance in a real-world setting and be another valuable tool for discovering new transient events in real-time. Overall, this study makes a significant contribution to the field of astrophysics by demonstrating the effectiveness of deep learning-based anomaly detection techniques for real-time source detection in gamma-ray astronomy.

Query Library Development and Anomaly Detection on Flight Data

During the last semester of the Master’s Degree in Artificial Intelligence, I carried out my internship working for TXT e-Solution on the ADMITTED project. This paper describes the work done in those months. The thesis will be divided into two parts representing the two different tasks I was assigned during the course of my experience. The First part will be about the introduction of the project and the work done on the admittedly library, maintaining the code base and writing the test suits. The work carried out is more connected to the Software engineer role, developing features, fixing bugs and testing. The second part will describe the experiments done on the Anomaly detection task using a Deep Learning technique called Autoencoder, this task is on the other hand more connected to the data science role. The two tasks were not done simultaneously but were dealt with one after the other, which is why I preferred to divide them into two separate parts of this paper.