Framing Early Alert of Struggling Students as an Anomaly Detection Problem: An Exploration

Abstract Reed–Xiaoli detector (RXD) is recognized as the benchmark algorithm for image anomaly detection; however, it presents known limitations, namely the dependence over the image following a multivariate Gaussian model, the estimation and inversion of a high-dimensional covariance matrix, and the inability to effectively include spatial awareness in its evaluation. In this work, a novel graph-based solution to the image anomaly detection problem is proposed; leveraging the graph Fourier transform, we are able to overcome some of RXD’s limitations while reducing computational cost at the same time. Tests over both hyperspectral and medical images, using both synthetic and real anomalies, prove the proposed technique is able to obtain significant gains over performance by other algorithms in the state of the art.

Download Full-text

Detecting potential reference list manipulation within a citation network

10.21203/rs.3.rs-812039/v1 ◽

2021 ◽

Author(s):

Jonathan Wren ◽

Constantin Georgescu

Keyword(s):

Anomaly Detection ◽

Peer Review ◽

Gini Index ◽

Review Process ◽

Peer Review Process ◽

Citation Network ◽

Reference List ◽

Detection Problem ◽

Zipf's Law ◽

Academic Influence

Abstract Although citations are used as a quantifiable, objective metric of academic influence, references could be added to a paper to inflate the perceived influence of a body of research. This reference list manipulation (RLM) could take place during the peer-review process, or prior to it. Surveys have estimated how many people may have been affected by coercive RLM at one time or another, but it is not known how many authors engage in RLM, nor to what degree. By examining a subset of active, highly published authors (n = 20,803) in PubMed, we find the frequency of non-self citations (NSC) to one author coming from one paper approximates Zipf’s law, permitting the task to be approached statistically. Framed as an anomaly detection problem, higher confidence is gained the more outlier status is correlated across dimensions relative to non-outliers. We find the NSC Gini Index correlates highly with anomalous patterns across multiple RLM-related distributions. Between 81 (FDR < 0.05) and 231 (FDR < 0.10) authors are outliers on the curve, suggestive of chronic, repeated RLM. Approximately 16% of all authors may have engaged in RLM to some degree. Authors who use 18% or more of their references for self-citation are significantly more likely to have NSC Gini distortions, suggesting a potential willingness to coerce others to cite them.

Download Full-text

Towards Bio-Inspired Anomaly Detection Using the Cursory Dendritic Cell Algorithm

Algorithms ◽

10.3390/a15010001 ◽

2021 ◽

Vol 15 (1) ◽

pp. 1

Author(s):

Carlos Pinto ◽

Rui Pinto ◽

Gil Gonçalves

Keyword(s):

Dendritic Cell ◽

Anomaly Detection ◽

Production Systems ◽

Detection System ◽

Artificial Immune Systems ◽

Object Oriented ◽

Research Area ◽

Detection Problem ◽

Network Intrusion ◽

Dendritic Cell Algorithm

The autonomous and adaptable identification of anomalies in industrial contexts, particularly in the physical processes of Cyber-Physical Production Systems (CPPS), requires using critical technologies to identify failures correctly. Most of the existing solutions in the anomaly detection research area do not consider such systems’ dynamics. Due to the complexity and multidimensionality of CPPS, a scalable, adaptable, and rapid anomaly detection system is needed, considering the new design specifications of Industry 4.0 solutions. Immune-based models, such as the Dendritic Cell Algorithm (DCA), may provide a rich source of inspiration for detecting anomalies, since the anomaly detection problem in CPPS greatly resembles the functionality of the biological dendritic cells in defending the human body from hazardous pathogens. This paper tackles DCA limitations that may compromise its usage in anomaly detection applications, such as the manual characterization of safe and danger signals, data analysis not suitable for online classification, and the lack of an object-oriented implementation of the algorithm. The proposed approach, the Cursory Dendritic Cell Algorithm (CDCA), is a novel variation of the DCA, developed to be flexible and monitor physical industrial processes continually while detecting anomalies in an online fashion. This work’s contribution is threefold. First, it provides a comprehensive review of Artificial Immune Systems (AIS), focusing on AIS applied to the anomaly detection problem. Then, a new object-oriented architecture for the DCA implementation is described, enabling the modularity and abstraction of the algorithm stages into different classes (modules). Finally, the CDCA for the anomaly detection problem is proposed. The CDCA was successfully validated in two industrial-oriented dataset benchmarks for physical anomaly and network intrusion detection, the Skoltech Anomaly Benchmark (SKAB) and M2M using OPC UA. When compared to other algorithms, the proposed approach exhibits promising classification results. It was placed fourth on the SKAB scoreboard and presented a competitive performance with the incremental Dendritic Cell Algorithm (iDCA).

Download Full-text

Vision Transformer-Based Tailing Detection in Videos

Applied Sciences ◽

10.3390/app112411591 ◽

2021 ◽

Vol 11 (24) ◽

pp. 11591

Author(s):

Jaewoo Lee ◽

Sungjun Lee ◽

Wonki Cho ◽

Zahid Ali Siddiqui ◽

Unsang Park

Keyword(s):

Time Series ◽

Anomaly Detection ◽

Spatial Information ◽

Detection Problem ◽

Walking Pattern ◽

Series Of Experiments ◽

Time Series Images ◽

Small Dataset ◽

Better Than ◽

Do So

Tailing is defined as an event where a suspicious person follows someone closely. We define the problem of tailing detection from videos as an anomaly detection problem, where the goal is to find abnormalities in the walking pattern of the pedestrians (victim and follower). We, therefore, propose a modified Time-Series Vision Transformer (TSViT), a method for anomaly detection in video, specifically for tailing detection with a small dataset. We introduce an effective way to train TSViT with a small dataset by regularizing the prediction model. To do so, we first encode the spatial information of the pedestrians into 2D patterns and then pass them as tokens to the TSViT. Through a series of experiments, we show that the tailing detection on a small dataset using TSViT outperforms popular CNN-based architectures, as the CNN architectures tend to overfit with a small dataset of time-series images. We also show that when using time-series images, the performance of CNN-based architecture gradually drops, as the network depth is increased, to increase its capacity. On the other hand, a decreasing number of heads in Vision Transformer architecture shows good performance on time-series images, and the performance is further increased as the input resolution of the images is increased. Experimental results demonstrate that the TSViT performs better than the handcrafted rule-based method and CNN-based method for tailing detection. TSViT can be used in many applications for video anomaly detection, even with a small dataset.

Download Full-text

INTRUSION DETECTION FOR DISCRETE SEQUENCES

International Journal of Communication Networks and Security ◽

10.47893/ijcns.2013.1066 ◽

2013 ◽

pp. 43-45

Author(s):

MRS. M. VIJAYALAKSHMI ◽

MR. K . JANARDHAN

Keyword(s):

Time Series ◽

Anomaly Detection ◽

Problem Formulation ◽

Detection Problem ◽

Basic Technique ◽

Global Understanding ◽

Discrete Sequences ◽

Problem Formulations ◽

Online Anomaly Detection ◽

Disconnected Domains

Global understanding of the sequence anomaly detection problem and how techniques proposed for different domains relate to each other. Our specific contributions are as follows: We identify three distinct formulations of the anomaly detection problem, and review techniques from many disparate and disconnected domains that address each of these formulations. Within each problem formulation, we group techniques into categories based on the nature of the underlying algorithm. For each category, we provide a basic anomaly detection technique, and show how the existing techniques are variants of the basic technique. This approach shows how different techniques within a category are related or different from each other. Our categorization reveals new variants and combinations that have not been investigated before for anomaly detection. We also provide a discussion of relative strengths and weaknesses of different techniques. We show how techniques developed for one problem formulation can be adapted to solve a different formulation; thereby providing several novel adaptations to solve the different problem formulations. We highlight the applicability of the techniques that handle discrete sequences to other related areas such as online anomaly detection and time series anomaly detection.

Download Full-text

Anomaly Detection in Hyperspectral Imagery Based on Spectral Gradient and LLE

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.121-126.720 ◽

2011 ◽

Vol 121-126 ◽

pp. 720-724

Author(s):

Liang Liang Wang ◽

Zhi Yong Li ◽

Ji Xiang Sun

Keyword(s):

Anomaly Detection ◽

Euclidean Distance ◽

Hyperspectral Imagery ◽

Detection Algorithm ◽

Hyperspectral Data ◽

Experimental Results ◽

Feature Analysis ◽

Detection Problem ◽

Local Linear Embedding ◽

Linear Embedding

The local linear embedding algorithm(LLE) is applied into the anomaly detection algorithm on the basis of the feature analysis of the hyperspectral data. Then, to deal with the problem of declining capacity of identifying the neighborhood caused by the Euclidean distance, an improved LLE algorithm is developed. The improved LLE algorithm selects neighborhood pixels according to the spectral gradient, thus making the anomaly detection more robust to the changes of light and terrain. Experimental results prove the feasibility of using LLE algorithm to solve the anomaly detection problem, and the effectiveness of the algorithm in improving the detection performance.

Download Full-text

Big data & early alert (anomaly) detection in Paiton coal fired power plant

10.1063/5.0000809 ◽

2020 ◽

Author(s):

Akbar Rachmad Virgiawan ◽

Adhi Eko Apriyanto ◽

Henry Pariaman

Keyword(s):

Big Data ◽

Power Plant ◽

Anomaly Detection ◽

Early Alert

Download Full-text

The Detection Method of Fire Abnormal Based on Directional Drilling in Complex Conditions of Mine

E3S Web of Conferences ◽

10.1051/e3sconf/20183801007 ◽

2018 ◽

Vol 38 ◽

pp. 01007

Author(s):

Duan Huijun ◽

Hao Shijun ◽

Feng Jie

Keyword(s):

Anomaly Detection ◽

Detection Method ◽

Technical Support ◽

Fire Prevention ◽

Directional Drilling ◽

Detection Problem ◽

Abnormal Detection ◽

Drilling Technology ◽

Measurement While Drilling ◽

Open Branch

In the light of more and more urgent hidden fire abnormal detection problem in complex conditions of mine, a method which is used directional drilling technology is put forward. The method can avoid the obstacles in mine, and complete the fire abnormal detection. This paper based on analyzing the trajectory control of directional drilling, measurement while drilling and the characteristic of open branch process, the project of the directional drilling is formulated combination with a complex condition mine, and the detection of fire abnormal is implemented. This method can provide technical support for fire prevention, which also can provide a new way for fire anomaly detection in the similar mine.

Download Full-text