Search

Water is a basic and primary resource which is required for sustenance of life on the Earth. The importance of water quality is increasing with the ascending water pollution owing to industrialization and depletion of fresh water sources. The countries having low control on reducing water pollution are likely to retain poor public health. Additionally, the methods being used in most developing countries are not effective and are based more on human intervention than on technological and automated solutions. Typically, most of the water samples and related data are monitored and tested in laboratories, which eventually consumes time and effort at the expense of producing fewer reliable results. In view of the above, there is an imperative need to devise a proper and systematic system to regularly monitor and manage the quality of water resources to arrest the related issues. Towards such ends, Internet of Things (IoT) is a great alternative to such traditional approaches which are complex and ineffective and it allows taking remote measurements in real-time with minimal human involvement. The proposed system consists of various water quality measuring nodes encompassing various sensors including dissolved oxygen, turbidity, pH level, water temperature, and total dissolved solids. These sensors nodes deployed at various sites of the study area transmit data to the server for processing and analysis using GSM modules. The data collected over months is used for water quality classification using water quality indices and for bacterial prediction by employing machine learning algorithms. For data visualization, a Web portal is developed which consists of a dashboard of Web services to display the heat maps and other related info-graphics. The real-time water quality data is collected using IoT nodes and the historic data is acquired from the Rawal Lake Filtration Plant. Several machine learning algorithms including neural networks (NN), convolutional neural networks (CNN), ridge regression (RR), support vector machines (SVM), decision tree regression (DTR), Bayesian regression (BR), and an ensemble of all models are trained for fecal coliform bacterial prediction, where SVM and Bayesian regression models have shown the optimal performance with mean squared error (MSE) of 0.35575 and 0.39566 respectively. The proposed system provides an alternative and more convenient solution for bacterial prediction, which otherwise is done manually in labs and is an expensive and time-consuming approach. In addition to this, it offers several other advantages including remote monitoring, ease of scalability, real-time status of water quality, and a portable hardware. [ABSTRACT FROM AUTHOR]

Understanding the semantics of objects and scenes using multi-modal RGB-D sensors serves many robotics applications. Key challenges for accurate RGB-D image recognition are the scarcity of training data, variations due to viewpoint changes and the heterogeneous nature of the data. We address these problems and propose a generic deep learning framework based on a pre-trained convolutional neural network, as a feature extractor for both the colour and depth channels. We propose a rich multi-scale feature representation, referred to as convolutional hypercube pyramid (HP-CNN), that is able to encode discriminative information from the convolutional tensors at different levels of detail. We also present a technique to fuse the proposed HP-CNN with the activations of fully connected neurons based on an extreme learning machine classifier in a late fusion scheme which leads to a highly discriminative and compact representation. To further improve performance, we devise HP-CNN-T which is a view-invariant descriptor extracted from a multi-view 3D object pose (M3DOP) model. M3DOP is learned from over 140,000 RGB-D images that are synthetically generated by rendering CAD models from different viewpoints. Extensive evaluations on four RGB-D object and scene recognition datasets demonstrate that our HP-CNN and HP-CNN-T consistently outperforms state-of-the-art methods for several recognition tasks by a significant margin. [ABSTRACT FROM AUTHOR]

Efficient and accurate representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification. Existing methods either make prior assumptions about the data structure, or perform heavy computations to learn structure from the data itself. In this paper, we propose an efficient image set representation that does not make any prior assumptions about the structure of the underlying data. We learn the nonlinear structure of image sets with deep extreme learning machines that are very efficient and generalize well even on a limited number of training samples. Extensive experiments on a broad range of public datasets for image set classification show that the proposed algorithm consistently outperforms state-of-the-art image set classification methods both in terms of speed and accuracy. [ABSTRACT FROM AUTHOR]

Recognizing semantic category of objects and scenes captured using vision-based sensors is a challenging yet essential capability for mobile robots and UAVs to perform high-level tasks such as long-term autonomous navigation. However, extracting discriminative features from multi-modal inputs, such as RGB-D images, in a unified manner is non-trivial given the heterogeneous nature of the modalities. We propose a deep network which seeks to construct a joint and shared multi-modal representation through bilinearly combining the convolutional neural network (CNN) streams of the RGB and depth channels. This technique motivates bilateral transfer learning between the modalities by taking the outer product of each feature extractor output. Furthermore, we devise a technique for multi-scale feature abstraction using deeply supervised branches which are connected to all convolutional layers of the multi-stream CNN. We show that end-to-end learning of the network is feasible even with a limited amount of training data and the trained network generalizes across different datasets and applications. Experimental evaluations on benchmark RGB-D object and scene categorization datasets show that the proposed technique consistently outperforms state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

We propose a Bayesian approach to learn discriminative dictionaries for sparse representation of data. The proposed approach infers probability distributions over the atoms of a discriminative dictionary using a finite approximation of Beta Process. It also computes sets of Bernoulli distributions that associate class labels to the learned dictionary atoms. This association signifies the selection probabilities of the dictionary atoms in the expansion of class-specific data. Furthermore, the non-parametric character of the proposed approach allows it to infer the correct size of the dictionary. We exploit the aforementioned Bernoulli distributions in separately learning a linear classifier. The classifier uses the same hierarchical Bayesian model as the dictionary, which we present along the analytical inference solution for Gibbs sampling. For classification, a test instance is first sparsely encoded over the learned dictionary and the codes are fed to the classifier. We performed experiments for face and action recognition; and object and scene-category classification using five public datasets and compared the results with state-of-the-art discriminative sparse representation approaches. Experiments show that the proposed Bayesian approach consistently outperforms the existing approaches. [ABSTRACT FROM AUTHOR]

Underwater video and digital still cameras are rapidly being adopted by marine scientists and managers as a tool for non-destructively quantifying and measuring the relative abundance, cover and size of marine fauna and flora. Imagery recorded of fish can be time consuming and costly to process and analyze manually. For this reason, there is great interest in automatic classification, counting, and measurement of fish. Unconstrained underwater scenes are highly variable due to changes in light intensity, changes in fish orientation due to movement, a variety of background habitats which sometimes also move, and most importantly similarity in shape and patterns among fish of different species. This poses a great challenge for image/video processing techniques to accurately differentiate between classes or species of fish to perform automatic classification. We present a machine learning approach, which is suitable for solving this challenge. We demonstrate the use of a convolution neural network model in a hierarchical feature combination setup to learn species-dependent visual features of fish that are unique, yet abstract and robust against environmental and intra-and inter-species variability. This approach avoids the need for explicitly extracting features from raw images of the fish using several fragmented image processing techniques. As a result, we achieve a single and generic trained architecture with favorable performance even for sample images of fish species that have not been used in training. Using the LifeCLEF14 and LifeCLEF15 benchmark fish datasets, we have demonstrated results with a correct classification rate of more than 90%. [ABSTRACT FROM AUTHOR]

Choosing a suitable classifier for a given dataset is an important part of developing a pattern recognition system. Since a large variety of classification algorithms are proposed in literature, non-experts do not know which method should be used in order to obtain good classification results on their data. Meta-learning tries to address this problem by recommending promising classifiers based on meta-features computed from a given dataset. In this paper, we empirically evaluate five different categories of state-of-the-art meta-features for their suitability in predicting classification accuracies of several widely used classifiers (including Support Vector Machines, Neural Networks, Random Forests, Decision Trees, and Logistic Regression). Based on the evaluation results, we have developed the first open source meta-learning system that is capable of accurately predicting accuracies of target classifiers. The user provides a dataset as input and gets an automatically created high-performance ready-to-use pattern recognition system in a few simple steps. A user study of the system with non-experts showed that the users were able to develop more accurate pattern recognition systems in significantly less development time when using our system as compared to using a state-of-the-art data mining software. [ABSTRACT FROM AUTHOR]

The performance of most of the classification algorithms on a particular dataset is highly dependent on the learning parameters used for training them. Different approaches like grid search or genetic algorithms are frequently employed to find suitable parameter values for a given dataset. Grid search has the advantage of finding more accurate solutions in general at the cost of higher computation time. Genetic algorithms, on the other hand, are able to find good solutions in less time, but the accuracy of these solutions is usually lower than those of grid search. This paper uses ideas from meta-learning and case-based reasoning to provide good starting points to the genetic algorithm. The presented approach reaches the accuracy of grid search at a significantly lower computational cost. We performed extensive experiments for optimizing learning parameters of the Support Vector Machine (SVM) and the Random Forest classifiers on over 100 datasets from UCI and StatLib repositories. For the SVM classifier, grid search achieved an average accuracy of 81 % and took six hours for training, whereas the standard genetic algorithm obtained 74 % accuracy in close to one hour of training. Our method was able to achieve an average accuracy of 81 % in only about 45 minutes. Similar results were achieved for the Random Forest classifier. Besides a standard genetic algorithm, we also compared the presented method with three state-of-the-art optimization algorithms: Generating Set Search, Dividing Rectangles, and the Covariance Matrix Adaptation Evolution Strategy. Experimental results show that our method achieved the highest average accuracy for both classifiers. Our approach can be particularly useful when training classifiers on large datasets where grid search is not feasible. [ABSTRACT FROM AUTHOR]

Abstract: Benchmarking pattern recognition, machine learning and data mining methods commonly relies on real-world data sets. However, there are some disadvantages in using real-world data. On one hand collecting real-world data can become difficult or impossible for various reasons, on the other hand real-world variables are hard to control, even in the problem domain; in the feature domain, where most statistical learning methods operate, exercising control is even more difficult and hence rarely attempted. This is at odds with the scientific experimentation guidelines mandating the use of as directly controllable and as directly observable variables as possible. Because of this, synthetic data possesses certain advantages over real-world data sets. In this paper we propose a method that produces synthetic data with guaranteed global and class-specific statistical properties. This method is based on overlapping class densities placed on the corners of a regular k-simplex. This generator can be used for algorithm testing and fair performance evaluation of statistical learning methods. Because of the strong properties of this generator researchers can reproduce each others experiments by knowing the parameters used, instead of transmitting large data sets. [Copyright &y& Elsevier]