Search

The integrated security SIS ECU 911 will oversee monitoring emergency situations, video surveillance, and alarm monitoring reported through 911 services throughout the Ecuadorian territory. This research addresses space and time pattern detection at SIS ECU 911 (Imbabura-Ecuador) using mining data techniques to support decision-making processes in addition to operating costs. In 2018–2019, 47.4% of placed calls were ill-intentioned generating significant unnecessary operating costs. The study was conducted in four phases (i) caller location and call data gathering (ii) Creation of a Geo-database and hotspots (iii) Making of data clocks (iv) Prediction model applying a Geo-graphical Weighted Regression (GWR). Hotspots determined that the largest number of ill-intentioned came from Ibarra and Otavalo cities. Data clocks showed a temporary pattern in the months of July and August as they are the most critical months. The GWR model identified that the rate for this type of phone call partially corresponds to a spatial predominant pattern that originated in the rural areas of Ibarra and Pimampiro. Therefore, all ill-intentioned calls respond to certain temporary spatial patterns that help us understand this problem aiming to pose mitigating alternatives.

Encryption-type ransomware has risen in prominence lately as the go-to malware for threat actors aiming to compromise Android devices. In this paper, we present a ransomware detection technique based on behaviours observed in the system calls performed by the malware. We identify and present some common high-level system call behavioural patterns targeted at encryption-type ransomware and evaluate these patterns. We further present our repeatable and extensible methodology for extracting the system call log and patterns.

This project proposes a NooJ algorithm with the task to find and categorize various slurs, insults and ultimately, hate speech in Croatian. The results also provide a more detailed insight into inappropriate language in Croatian. We strongly emphasize the ethical considerations of (mis)identifying hate speech and as a result, an unethical and undeserved censorship of inappropriate, but free speech. Thus, we tried to make a clear distinction between insults and hate speech. The test corpus consists of written online comments and remarks posted on five Croatian Facebook news pages during one week period. Given the differences between the standard Croatian grammar and syntax, and what is actually being used in informal on-line communication, the false negatives present the biggest difficulty since some variations (substandard usages of cases, spelling errors, colloquialisms) are impossible to predict, and therefore, extremely hard to implement into the algorithm.

Sense takes many guises in Nabokov’s work, whether this be “common,” “moral,” “bodily,” or “aesthetic.” The idea of “cerebral” sense and (non)sense, however, are also integral features, especially when considering Nabokov’s wordplay. Looking predominantly at excerpts from Despair and Invitation to a Beheading, Rodgers argues that the apparent nonsense presented to us is offset by both visceral sense (in the form of pattern detection) and cerebral sense (in the form of cognitive challenge). This interplay between the visceral and cerebral senses, it is argued, engenders aesthetic sense, with the universal desire to puzzle-solve situated at the heart of our reading experience. The essay suggests that specific interpretative impasses in Nabokov’s work can be traversed by acknowledging the help provided from the corporeal senses of sight and sound.

Endoscopic measurement of ulcerative colitis (UC) severity is important since endoscopic disease severity may better predict future outcomes in UC than symptoms. However, it is difficult to evaluate the endoscopic severity of UC objectively because of the non-uniform nature of endoscopic features associated with UC, and large variations in their patterns. In this paper, we propose a method to classify UC severity in colonoscopy videos by detecting the vascular (vein) patterns which are defined specifically in this paper as the amounts of blood vessels in the video frames. To detect these vascular patterns, we use Convolutional Neural Network (CNN) and image preprocessing methods. The experiments show that the proposed method for classifying UC severity by detecting these vascular patterns increases classification effectiveness significantly.

This paper deals with the problem of pattern detection in telemetry data, in particular, the approach of automatic machine state detection based on the vibration signal proposed. The approach based on the analysis of the signal via clustering. The paper provides basic information about telemetry data analysis, vibration data analysis, and machine condition monitoring. Also, an overview of cluster analysis methods provided. The proposed approach based on clustering of objects represented with feature set extracted from vibration signals. Given the explanation of the technique and illustrative example of the application of the proposed approach applied to vibration data provided by SmartEdge Agile device for industrial electric motor considered.

Pum-Riang is a type of Thai silk with many patterns. Only experts can identify these patterns on sight. In order to help the general public who are interested in Pum-Riang silk, we propose an automatic Pum-Riang pattern detection using texture analysis. The process is divided into the feature extraction step, feature extraction step, and classifier training step. For each step, we compare various methods and parameters when applicable. The best model is evaluated on a separate test set. It achieves the perfect accuracy of 1.0, indicating that all test samples are correctly classified.

We consider the problem of pattern detection in large scale railway timetables. This problem arises in rolling stock optimization planning in order to identify invariant sections of the timetable for which a cyclic rotation plan is adequate. We propose a dual reduction technique which leads to an decomposition and enumeration method. Computational results for real world instances demonstrate that the method is able to produce optimal solutions as fast as standard MIP solvers.

Advances in Soft Computing have increased the probabilities of implementing mechanisms that are able to predict human behaviour. One of the fields that benefits more from the particular improvements are Digital Forensics. Criminal activity involving smartphones shows interesting behavioural variations that led the authors to create a technique that analyzes smartphone users’ activity and recognizes potentially suspicious patterns according to predefined expert knowledge in actual use case scenarios by the use of fuzzy systems with different configurations.

Pattern Detection (PD) plays an important role in several image processing applications such as feature tracking, object recognition, stereo matching and remote sensing. PD involves two critical aspects: similarity measurement and search strategy. The simplest available PD method finds the best possible coincidence between the images through an exhaustive computation of the Normalized cross-correlation (NCC) values (similarity measurement) for all elements of the source image (search strategy).

Holistically detecting interstitial lung disease (ILD) patterns from CT images is challenging yet clinically important. Unfortunately, most existing solutions rely on manually provided regions of interest, limiting their clinical usefulness. In addition, no work has yet focused on predicting more than one ILD from the same CT slice, despite the frequency of such occurrences. To address these limitations, we propose two variations of multi-label deep convolutional neural networks (CNNs). The first uses a deep CNN to detect the presence of multiple ILDs using a regression-based loss function. Our second variant further improves performance, using spatially invariant Fisher Vector encoding of the CNN feature activations. We test our algorithms on a dataset of 533 patients using five-fold cross-validation, achieving high area-under-curve (AUC) scores of 0.982, 0.972, 0.893 and 0.993 for Ground Glass, Reticular, Honeycomb and Emphysema, respectively. As such, our work represents an important step forward in providing clinically effective ILD detection.

The mobility pattern of vessel is one of the key metrics on ocean MDTN network. Because of the high cost, little experiment has focused on research of vessel mobility pattern for the moment. In this paper, we study the traces of thousands of vessels. Firstly, after studying the traces of vessels, we observe that the vessel’s traces is confined by invisible boundary. Second, through defining the distance between traces, we design MR-Similarity algorithm to find the mobility pattern of vessels. Finally, we realize our algorithm on cluster and evaluate the performance and accuracy. Our results can provide the guidelines on design of data routing protocols on ocean MDTN.

The growing number of different models and approaches for Geographic Information Systems (GIS) brings high complexity when we want to develop new approaches and compare a new GIS algorithm. In order to test and compare different processing models and approaches, in a simple way, we identified the need of defining uniform testing methods, able to compare processing algorithms in terms of performance and accuracy regarding: large imaging processing, algorithms for GIS pattern-detection.

Online Social network services, a web-based information sharing service which is utilized for public relationship and advertising promotion by brands and organizations. Since online social network is always altering, how to influence as much members as possible in community at appropriate moment will be a thoughtful problem. And strategy of article publishing decision will be important to every kind of online social network community operator.

Most people are able to recognise familiar tunes even when played in a different key. It is assumed that this depends on a general capacity for relative pitch perception; the ability to recognise the pattern of inter-note intervals that characterises the tune. However, when healthy adults are required to detect rare deviant melodic patterns in a sequence of randomly transposed standard patterns they perform close to chance. Musically experienced participants perform better than naive participants, but even they find the task difficult, despite the fact that musical education includes training in interval recognition.

Tire tread prints, being common type of evidence at crime scene, contain useful information for the investigator. To determine the brand or manufacturer of a tire related to the tread, database of tire treads is required. It can be built using thousands of tire photographs available in many existing web shops. To build such a database tire photographs must be downloaded and processed automatically.

Chemical-based coordination models have proven useful to engineer self-organising and self-adaptive systems. Formal assessment of emergent global behaviours in self-organising systems is still an issue, most of the time emergent properties are being analysed through extensive simulations. This paper aims at integrating logic programs into a chemical-based coordination model in order to engineer self-organising systems as well as assess their emergent properties. Our model is generic and accommodates various logics. By tuning the internal logic language we can tackle and solve coordination problems in a rigorous way, without renouncing to important engineering properties such as compactness, modularity and reusability of code. This paper discusses our logic-based coordination model and shows how to engineer and verify a simple pattern detection example and a gradient-chemotaxis example.

As one of the important methods on prediction, data mining plays a significant role specifically in the field of abnormal prediction to ensure security. Based on the remote sensing data of the sun-synchronous polar orbit EOS-AQUA satellite of USA, this paper proposes an abnormal pattern detection method with sequential pattern mining and matching. First of all, based on the selected observation area, abnormal sequential patterns are mined and frequent abnormal sequential patterns are formed. Then, seismic sequential pattern is generated, and the matching algorithm of earthquake is established. Finally, the accuracy rate and the false positive rate of prediction are worked out. All experiments are conducted with the remote sensing satellite from 2005 to 2014, and the experimental results are interesting. According to the carbon monoxide content, the accuracy rate is 65 % while the false positive rate is 15 % by using the data of 30 days before earthquake for prediction.

Finding all frequent itemsets (patterns) in a given database is a challenging process that in general consumes time and space. Time is measured in terms of the number of database scans required to produce all frequent itemsets. Space is consumed by the number of potential frequent itemsets which will end up classified as not frequent. To overcome both limitations, namely space and time, we propose a novel approach for generating all possible frequent itemsets by introducing a new representation of items into groups of four items and within each group, items are assigned one of four prime numbers, namely 2, 3, 5, and 7. The reported results demonstrate the applicability and effectiveness of the proposed approach. Our approach satisfies scalability in terms of number of transactions and number of items.

Auto Modulating Pattern Detection Algorithm (AMP) is a novel data processing technique to detect adverse hazards for various monitoring applications. This ongoing experimental study seeks to expand the one-dimensional “point-sensing” AMP to the two-dimensional “plane-sensing” case. AMP will be validated as an effective spatiotemporal technique for detecting leakage in fluid distribution pipeline networks.

The study of cell morphology and cell mobility variation when cells are grown on top of patterned substrates is becoming a very important factor in tissue regeneration.

The last decade has witnessed tremendous growths of Internet of Things(IoT). Numerous condition monitoring systems(CMS) are widely applied to monitor equipments simultaneously. With the help of CMS, a large variety of monitor data from a large number of equipments can be collected in a very short time. However, it is a non-trivial task to take full advantage of such large amounts of monitor data in the context of anomaly detection. In this paper, we propose an approach called Latent Correlation based Anomaly Detection(LCAD) that can quickly detect potential anomalies from a large amount of monitor data, which posits that abnormal ones are a small portion in a mass of similar individuals. Instead of focusing on each single monitor data series, we identify the abnormal pattern by modeling the latent correlation among multiple correlative monitor data series using the Latent Correlation Probabilistic Model(LCPM), a probabilistic distribution model which can help to detect anomalies depending on their relations with LCPM. In order to validate our approach, we conduct experiments on the real-world datasets and the experimental results show that when facing a large amount of correlative monitor data series LCAD has a better performance as compared to the previous anomaly detection approaches.