We present methods to predict and validate home and work places of anonymized users using their mobile network data. Knowledge of home and work place of a user is essential in order to find his (and overall population) mobility profiles. There are many methods that predict home and work places using GPS data. But unlike GPS data, mobile network data using GSM do not provide the exact location of a phone event. We use a novel criterion that combines an extracted feature from mobile data (i.e., Inactivity - no phone event for a given period of time) with open source data about location category % (i.e., Streetdirectory.com) to predict home location. Results show that the new criterion gives better prediction accuracy than inactivity alone. We predict work place using the idea that one goes to her work place on most of the weekdays but rarely on weekends. We validate our methods by comparing against the ground truth obtained from open source data. Validation results show that our proposed methods are about 25% more accurate than existing methods both for home and work place predictions.

This paper presents an integrated framework to enable using standard non-sequential machine learning tools for accurate multi-modal activity recognition. We develop a novel framework that contains simple pre- and post-classification strategies to improve the overall performance. We achieve this through class-imbalance correction on the learning data using structure preserving oversampling (SPO), leveraging the sequential nature of sensory data using smoothing of the predicted label sequence and classifier fusion, respectively. Through evaluation on recent publicly available activity datasets comprising of a large amount of multi-dimensional sensory data, we demonstrate that our proposed strategies are effective in improving classification performance over common techniques such as One Nearest Neighbor (1NN) and Support Vector Machines (SVM). Our framework also shows better performance over sequential probabilistic models, such as Conditional Random Field (CRF) and Hidden Markov Model (HMM) and when these models are used as meta-learners.

This poster presents an integrated framework to enable using standard non-sequential machine learning tools for accurate multi-modal activity recognition. Our framework contains simple pre- and post-classification strategies such as class-imbalance correction on the learning data using structure preserving oversampling, leveraging the sequential nature of sensory data using smoothing of the predicted label sequence and classifier fusion, respectively, for improved performance. Through evaluation on recent publicly-available OPPORTUNITY activity datasets comprising of a large amount of multi-dimensional, continuous-valued sensory data, we show that our proposed strategies are effective in improving the performance over common techniques such as One Nearest Neighbor (1NN) and Support Vector Machines (SVM). Our framework also shows better performance over sequential probabilistic models, such as Conditional Random Field (CRF) and Hidden Markov Models (HMM) and when these models are used as meta-learners.

The deployment of a sensor node to manage a group of sensors and collate their readings for system health monitoring is gaining popularity within the manufacturing industry. Such a sensor node is able to perform real-time configurations of the individual sensors that are attached to it. Sensors are capable of acquiring data at different sampling frequencies based on the sensing requirements. The different sampling rates affect power consumption, sensor lifespan, and the resultant network bandwidth usage due to the data transfer incurred. These settings also have an immediate impact on the accuracy of the diagnostics and prognostics models that are employed for system health monitoring. In this paper, we propose a novel adaptive classification system architecture for system health monitoring that is well suited to accommodate and take advantage of the variable sampling rate of sensors. As such, our proposed system is able to yield a more effective health monitoring system by reducing the power consumption of the sensors, extending the sensors' lifespan, as well as reducing the resultant network traffic and data logging requirements. We also propose an ensemble based learning method to integrate multiple existing classifiers with different feature representations, which can achieve significantly better, stable results compared with the individual state-of-the-art techniques, especially in the scenario when we have very limited training data. This result is extremely important in many real-world applications because it is often impractical, if not impossible, to hand-label large amounts of training data.

In many real-world applications of the time series classification problem, not only could the negative training instances be missing, the number of positive instances available for learning may also be rather limited. This has motivated the development of new classification algorithms that can learn from a small set P of labeled seed positive instances augmented with a set U of unlabeled instances (i.e. PU learning algorithms). However, existing PU learning algorithms for time series classification have less than satisfactory performance as they are unable to identify the class boundary between positive and negative instances accurately. In this paper, we propose a novel PU learning algorithm LCLC (Learning from Common Local Clusters) for time series classification. LCLC is designed to effectively identify the ground truths' positive and negative boundaries, resulting in more accurate classifiers than those constructed using existing methods. We have applied LCLC to classify time series data from different application domains; the experimental results demonstrate that LCLC out-performs existing methods significantly.

Audio podcasting has been widely used by many online sites such as newspapers, web portals, journal, etc., to deliver audio content to users through download or subscription. Within 1 to 30 minutes long of one podcast story, it is often that multiple audio advertisements (ads) are inserted into and repeated, with each of a length of 5 to 30 seconds, at different locations. Based on knowledge of typical structures of podcast contents, this paper proposes a novel efficient advertisement discovery approach to identify and locate unknown ads from a large collection of audio podcasting. Two techniques: candidate region segmentation and sampling technique are employed to speed up the search. The approach has been tested over a variety of podcast contents collected from MIT Technology Review, Scientific American, and Singapore Podcast websites. Experimental results show that the proposed approach achieves detection rate of 97.5% with a significant computation saving as compared to existing state-of-the art methods.

Inspired by the philosophy of ancient Chinese Taoism, Xu's Bayesian ying-yang (BYY) learning technique performs clustering by harmonizing the training data (yang) with the solution (ying). In our previous work, the BYY learning technique was applied to a fuzzy cerebellar model articulation controller (FCMAC) to find the optimal fuzzy sets; however, this is not suitable for time series data analysis. To address this problem, we propose an incremental BYY learning technique in this paper, with the idea of sliding window and rule structure dynamic algorithms. Three contributions are made as a result of this research. First, an online expectation-maximization algorithm incorporated with the sliding window is proposed for the fuzzification phase. Second, the memory requirement is greatly reduced since the entire data set no longer needs to be obtained during the prediction process. Third, the rule structure dynamic algorithm with dynamically initializing, recruiting, and pruning rules relieves the "curse of dimensionality" problem that is inherent in the FCMAC. Because of these features, the experimental results of the benchmark data sets of currency exchange rates and Mackey-Glass show that the proposed model is more suitable for real-time streaming data analysis.

Since the collapse or failure of a bank could trigger an adverse financial repercussion and generate negative impacts, it is desirable to have an early warning system (EWS) that identifies potential bank failures or high-risk banks through the traits of financial distress. This research is aimed to construct a novel GA-FCMAC-BYY model as an alternative to analyze bank solvency. The proposed model attempts to advance our previous work which uses fuzzy cerebellar model arithmetic controller-Bayesian Ying-Yang (FCMAC-BYY) network. Inspired by the ancient Chinese Ying Yang philosophy, FCMAC-BYY obtains optimal solution by achieving harmony between inputs and fuzzy clusters sets. However, it optimizes the fuzzy sets in the individual dimensions, resulting in the lost of relative binding data and global optimization may not be achieved. Genetic algorithm (GA) is introduced here to look into the issue. GA operates on a population of potential solutions based on the principle of survival of the fittest to produce better approximations to a solution. Populations of candidate solutions are evaluated using fitness functions to determine the best solution. Thereafter, chromosomes would be evolved to produces new genes in the search of the optimal solution. The performance of the proposed GA-FCMAC-BYY model as a bank failure classification and early warning system is very encouraging.

This paper analyses stock market price prediction based on a hierarchical cerebellar model arithmetic controller (HCMAC) neural network. Applications using stock market price prediction tools are required to be adaptive to new incoming data as well as have fast learning capabilities. Current popular neural networks are based on the Multi Layer Perceptron (MLP) structure which has low memory consumption and has a fast processing speed however the performance of the MLP deteriorates as the network expands. An HCMAC structure uses a direct memory mapping technique which would perform consistently fast independent of size of network. The drawback is a huge amount of memory is required to perform direct mapping. This can be reduced by using self-organizing techniques to optimize the clusters during each training cycle. The accuracy of the output can be controlled based on the values set in the cyclic self-organizing module. The cyclic self-organizing HCMAC (CSOHCMAC) combines both the HCMAC and cyclic self-organizing modules to create a neural network model that would be robust and fast as well as flexible to adapt to changes

This paper proposes an evolving fuzzy associative memory neural network model based on the fuzzy CMAC (FCMAC). FCMAC is an auto-associate memory feed forward neural network with attractive properties of fast learning and simple computation. Evolving techniques aim at building adaptive intelligent systems that evolve both their structure and parameters through incremental online learning. During fuzzification phase, the proposed ESOFCMAC uses raw numerical values of a training data set without any preprocessing and obtains dynamic partition-base clusters with no prior knowledge of the number of clusters. The performance of ESOFCMAC is illustrated on several benchmark data sets and compared with traditional models.

As an associative memory neural network model, the cerebellar model articulation controller (CMAC) has attractive properties of fast learning and simple computation, but its rigid structure makes it difficult to approximate certain functions. This research attempts to construct a novel neural fuzzy CMAC, in which Bayesian Ying-Yang (BYY) learning is introduced to determine the optimal fuzzy sets, and a truth-value restriction inference scheme is subsequently employed to derive the truth values of the rule weights of implication rules. The BYY is motivated from the famous Chinese ancient Ying-Yang philosophy: everything in the universe can be viewed as a product of a constant conflict between opposites-Ying and Yang, a perfect status is reached when Ying and Yang achieve harmony. The proposed fuzzy CMAC (FCMAC)-BYY enjoys the following advantages. First, it has a higher generalization ability because the fuzzy rule sets are systematically optimized by BYY; second, it reduces the memory requirement of the network by a significant degree as compared to the original CMAC; and third, it provides an intuitive fuzzy logic reasoning and has clear semantic meanings. The experimental results on some benchmark datasets show that the proposed FCMAC-BYY outperforms the existing representative techniques in the research literature.