169,972 research outputs found
Hierarchal decomposition for unusual fish trajectory detection
No full textFish behavior analysis is presented using an unusual trajectory detection method. The proposed method is based on a hierarchy which is formed using the similarity of clustered and labeled data applying hierarchal data decomposition. The fish trajectories from unconstrained underwater videos are classified as normal and unusual where normal trajectories represents common behaviors of fish and unusual trajectories represent rare behaviors. A new trajectory is classified using the constructed hierarchy where different heuristics are applicable. The main contribution of the proposed method is presenting a novel supervised approach to unusual behavior detection (where many methods in this field are unsupervised) which demonstrates significantly improved results
A fuzzy k-NN approach for cancer diagnosis with microarray gene expression data
No full textRecent advances in DNA microarray technology have made it possible to measure the expression level of several thousand of genes simultaneously. The gene expression profiles obtained from microarray techniques have provided the opportunity of early diagnosis of cancer with the use of supervised learning algorithms. As a simple, effective and nonparametric classification method, k-Nearest Neighbor (k-NN) algorithm has recently been applied for the problem of cancer diagnosis and categorization. An obvious problem of traditional k-NN algorithm is that, when the density of training data is uneven, the precision of classification may reduce due to the consideration of first k nearest neighbors but not the differences of distances. A recent solution for this problem is adopting the theory of fuzzy sets and constructing a new membership function based on the similarities. This study has been conducted to demonstrate in what degree the fuzzification of k-NN algorithm can improve the prediction accuracy of cancer classification based on gene expression data. According to the results of the experiments over a six distinct benchmarking dataset spanning 27 diagnostic categories, it reveals that the fuzzy k-NN algorithm promotes the accuracy of cancer classification to a certain degree. Results also encourage the use of this fuzzification technique on similar problems in computational biology
Fusion of thermal- and visible-band video for abandoned object detection
No full textTimely detection of packages that are left unattended in public spaces is a security concern, and rapid detection is important for prevention of potential threats. Because constant surveillance of such places is challenging and labor intensive, automated abandoned-object-detection systems aiding operators have started to be widely used. In many studies, stationary objects, such as people sitting on a bench, are also detected as suspicious objects due to abandoned items being defined as items newly added to the scene and remained stationary for a predefined time. Therefore, any stationary object results in an alarm causing a high number of false alarms. These false alarms could be prevented by classifying suspicious items as living and nonliving objects. In this study, a system for abandoned object detection that aids operators surveilling indoor environments such as airports, railway or metro stations, is proposed. By analysis of information from a thermal-and visible-band camera, people and the objects left behind can be detected and discriminated as living and nonliving, reducing the false-alarm rate. Experiments demonstrate that using data obtained from a thermal camera in addition to a visible-band camera also increases the true detection rate of abandoned objects. (C) 2011 SPIE and IS&T. [DOI: 10.1117/1.3602204
A multimodal approach for individual tracking of people and their belongings
No full textIn this study, a fully automatic surveillance system for indoor environments which is capable of tracking multiple objects using both visible and thermal band images is proposed. These two modalities are fused to track people and the objects they carry separately using their heat signatures and the owners of the belongings are determined. Fusion of complementary information from different modalities (for example, thermal images are not affected by shadows and there is no thermal reflection or halo effect in visible images) is shown to result in better object detection performance. We use adaptive background modeling and local intensity operation for object detection and the mean-shift tracking algorithm for fully automatic tracking. Trackers are refreshed to resolve potential problems which may occur due to the changes in object's size, shape and to handle occlusion-split and to detect newly emerging objects as well as objects that leave the scene. The proposed scheme is applied to the abandoned object detection problem and the results are compared with the state of art methods. The results show that the proposed method facilitate individual tracking of objects for various applications, and provide lower false alarm rates compared to the state of art methods when applied to the abandoned object detection problem
Detection of Abnormal Fish Trajectories Using a Clustering Based Hierarchical Classifier
No full textWe address the analysis of fish trajectories in unconstrained underwater videos environmental changes which can be observed from the abnormal behaviour of fish. The fish trajectories are separated into normal and abnormal classes which indicate the common behaviour of fish and the behaviours that are rare/ unusual respectively. The proposed solution is based on a novel type of hierarchical classifier which builds the tree using clustered and labelled data based on similarity of data while using different feature sets at different levels of hierarchy. The paper presents a new method for fish trajectory analysis which has better performance compared to state-of-the-art techniques while the results are significant considering the challenges of underwater environments, low video quality, erratic movement of fish and highly imbalanced trajectory data that we used. Moreover, the proposed method is also powerful enough to classify highly imbalanced real-world datasets
Fish Behavior Analysis
No full textIn this chapter, we address fish behavior analysis in unconstrained underwater videos. Assessing this is based on unusual fish trajectory detection which tries to detect rare fish behaviors, which can help marine biologists to detect new behaviors and to detect environmental changes observed from the unusual trajectories of fish. Fish trajectories are classified as normal and unusual which are the common behaviors of fish and the behaviors that are rare respectively. We investigated three different classification methods to detect unusual fish trajectories. The first method is a filtering method to eliminate normal trajectories, the second method is based on labeled and clustered data and the third method constructs a hierarchy using clustered and labeled data based on data similarity. The first two methods can be seen as preliminary works while the results of them are significant considering the challenges of underwater environments and highly imbalanced trajectory data that we used. In this chapter, we briefly summarize these two methods and mainly focus on the third method (hierarchial decomposition) which presented improved results and performed better than the state of art methods
Toward Modeling Commensal Interactions in Human Dyads
No full textWe postulate the need for the creation of computational methods to model interactions specific to commensal settings. They would be used to analyze and quantify interactions during shared meals, and to design new devices for commensality. To illustrate the concept, we present algorithms for measuring: 1) food intake ratio and synchronization, and 2) smile ratio and synchronization in pairs of eaters. They process images of two commensals captured simultaneously to extract information specific to their nonverbal behaviors and subsequently apply the Event Synchronization algorithm to compute their degree of synchronization. Next, we test the proposed methods on videos of 12 dyads sharing meals. Our findings suggest that the self-reported strength of the relationship is positively correlated with the degree of food intake synchronization and inversely correlated with the quantity of smiles. We conclude by discussing potential applications for developing artificial companions to support solo eaters
Classifying imbalanced data sets using similarity based hierarchical decomposition
No full textAbstract Classification of data is difficult if the data is imbalanced and classes are overlapping. In recent years, more research has started to focus on classification of imbalanced data since real world data is often skewed. Traditional methods are more successful with classifying the class that has the most samples (majority class) compared to the other classes (minority classes). For the classification of imbalanced data sets, different methods are available, although each has some advantages and shortcomings. In this study, we propose a new hierarchical decomposition method for imbalanced data sets which is different from previously proposed solutions to the class imbalance problem. Additionally, it does not require any data pre-processing step as many other solutions need. The new method is based on clustering and outlier detection. The hierarchy is constructed using the similarity of labeled data subsets at each level of the hierarchy with different levels being built by different data and feature subsets. Clustering is used to partition the data while outlier detection is utilized to detect minority class samples. The comparison of the proposed method with state of art the methods using 20 public imbalanced data sets and 181 synthetic data sets showed that the proposed method׳s classification performance is better than the state of art methods. It is especially successful if the minority class is sparser than the majority class. It has accurate performance even when classes have sub-varieties and minority and majority classes are overlapping. Moreover, its performance is also good when the class imbalance ratio is low, i.e. classes are more imbalanced
Detection of abandoned objects using thermal and visible band tracking Görünür ve termal bant taki̇bi̇ kullanilarak terk edi̇lmi̇ş nesne tespi̇ti̇
No full textBu çalışmada, insanlar ve taşıdıkları nesnelerin ayrı takibini temel alan bir terk edilmiş nesne tespiti yöntemi sunulmaktadır. İnsanların ve taşıdıkları nesnelerin ayrı takibini sağlayabilmek için görünür bant verisine ek olarak termal bant veri kullanılmış ve bu nesneler iyileştirilmiş, uyarlamalı ortalama kayma takibi ile takip edilmişlerdir. Termal ve görünür bant verilerin tümleştirilmesi ve sıcaklık bilgisinden yararlanılarak nesneler; insan ve taşınan nesne şeklinde sınıflandırılır, bu nesnelerin gezingeleri bulunur, taşınan nesnelerin sahipleri belirlenir ve terk edilmiş şüpheli nesneler tespit edilerek alarm verilir. Ortalama kayma takibine ek olarak, uyarlanabilir arka plan modellemesi ve yerel yeğinlik operasyonu kullanılmış ve tamamen otomatik bir takip sistemi oluşturulmuştur. Sonuçlara göre; önerilen yöntem dayanıklı, düşük yanlış alarm oranı ile diğer yöntemlerle karşılaştırılabilir ve gözetleme operatörlerine yardımcı olmak amacıyla halka açık iç alan uygulamalarında kullanılabilir bir yöntemdir
Setting the stage for the machine intelligence era in marine science
No full textMachine learning, a subfield of artificial intelligence, offers various methods that can be applied in marine science. It supports data-driven learning, which can result in automated decision making of de novo data. It has significant advantages compared with manual analyses that are labour intensive and require considerable time. Machine learning approaches have great potential to improve the quality and extent of marine research by identifying latent patterns and hidden trends, particularly in large datasets that are intractable using other approaches. New sensor technology supports collection of large amounts of data from the marine environment. The rapidly developing machine learning subfield known as deep learning-which applies algorithms (artificial neural networks) inspired by the structure and function of the brain-is able to solve very complex problems by processing big datasets in a short time, sometimes achieving better performance than human experts. Given the opportunities that machine learning can provide, its integration into marine science and marine resource management is inevitable. The purpose of this themed set of articles is to provide as wide a selection as possible of case studies that demonstrate the applications, utility, and promise of machine learning in marine science. We also provide a forward-look by envisioning a marine science of the future into which machine learning has been fully incorporated
- …
