Ghyslain Gagnon

Robust multiple-instance learning ensembles using random subspace instance selection

Many real-world pattern recognition problems can be modeled using multiple-instance learning (MIL), where instances are grouped into bags, and each bag is assigned a label. State-of-the-art MIL methods provide a high level of performance when strong assumptions are made regarding the underlying data distributions, and the proportion of positive to negative instances in positive bags. In this paper, a new method called Random Subspace Instance Selection (RSIS) is proposed for the robust design of MIL ensembles without any prior assumptions on the data structure and the proportion of instances in bags. First, instance selection probabilities are computed based on training data clustered in random subspaces. A pool of classifiers is then generated using the training subsets created with these selection probabilities. By using RSIS, MIL ensembles are more robust to many data distributions and noise, and are not adversely affected by the proportion of positive instances in positive bags because training instances are repeatedly selected in a probabilistic manner. Moreover, RSIS also allows the identification of positive instances on an individual basis, as required in many practical applications. Results obtained with several real-world and synthetic databases show the robustness of MIL ensembles designed with the proposed RSIS method over a range of witness rates, noisy features and data distributions compared to reference methods in the literature. HighlightsA new method, Random Subspace Instance Selection, is proposed to design MIL ensembles.The method yields ensembles that are robust to variations of witness rate, data distributions and noise.The method yields state-of-the-art results on several benchmark data sets.

Adaptive Air-to-Ground Secure Communication System Based on ADS-B and Wide-Area Multilateration

A novel air-to-ground (ATG) communication system, which is based on adaptive modulation and beamforming enabled by automatic dependent surveillance-broadcast (ADS-B) and multilateration techniques, is presented in this paper. From an aircraft geolocation perspective, the proposed multilateration technique uses the time-difference-of-arrival (TDOA), angle-of-arrival (AOA), and frequency-difference-of-arrival (FDOA) features within the ADS-B signal to implement the hybrid geolocation mechanism. Moreover, this hybrid mechanism aims for the optimal selection of multilateration sensors to provide a precise aircraft geolocation estimate by minimizing the geometric dilution-of-precision (GDOP) metric and imparts significant resilience to the current ADS-B-based geolocation framework to withstand any form of attack involving aircraft impersonation and ADS-B message infringement. From an ATG communication perspective, the ground base stations can use this hybrid aircraft geolocation estimate to dynamically adapt their modulation parameters and transmission beampattern in an effort to provide a high-data-rate secure ATG communication link. Additionally, we develop a hardware prototype that is highly accurate in estimating AOA data and facilitating TDOA and FDOA extraction associated with the received ADS-B signal. This hardware setup for the ADS-B-based ATG system is analytically established and validated with commercially available universal software-defined radio peripheral units. This hardware setup displays 1.5° AOA estimation accuracy, whereas the simulated geolocation accuracy is approximately 30 m over 100 nautical miles for a typical aircraft trajectory. The adaptive modulation and beamforming approach assisted by the proposed GDOP-minimization-based multilateration strategy achieves significant enhancement in throughput and reduction in packet error rate.

SPREAD SPECTRUM COMMUNICATION SYSTEM WITH SEQUENCE SYNCHRONIZATION UNIT USING CHAOTIC SYMBOLIC DYNAMICS MODULATION

In this paper, we propose a new asynchronous multiuser communication system based on spread spectrum and chaotic symbolic dynamics modulation. By combining spread spectrum and chaotic modulation, the proposed system provides increased security by reducing the probability of detection while allowing multiuser transmissions. The sequence synchronization of chaos communication system is studied. A time acquisition technique based on serial search is proposed to achieve synchronization. An analysis is carried out to determine the probability of detection, the probability of false alarm and the bit error rate of the system. Simulation results show that the proposed system can achieve sequence synchronization under low signal-to-noise ratios, and also confirm our analytically computed expressions.

Continuous Compensation of Binary-Weighted DAC Nonlinearities in Bandpass Delta-Sigma Modulators

We present a novel calibration technique to compensate for DAC element mismatches in bandpass multibit delta-sigma (DeltaSigma) modulators. The proposed technique is purely digital and requires only a minor modification to the modulator loop. It is compatible with binary weighted element DACs and the storage requirements for the calibrated coefficients increases only linearly with the number of quantizer bits. The calibration is performed without breaking the loop, which allows continuous tracking of environmental drifts. Simulation results show a peak signal to noise and distortion ratio (SNDR) of 68 dB after calibration for a DAC with plusmn1% mismatches, a sinusoid input signal near 1/4 of the sampling frequency and an oversampling ratio of only 10. Those results represent a 26 dB improvement over the non-calibrated case while being within 2 dB of an ideal-DAC case.

Multiple instance learning: A survey of problem characteristics and applications

Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag. This formulation is gaining interest because it naturally fits various problems and allows to leverage weakly labeled data. Consequently, it has been used in diverse application fields such as computer vision and document classification. However, learning from bags raises important challenges that are unique to MIL. This paper provides a comprehensive survey of the characteristics which define and differentiate the types of MIL problems. Until now, these problem characteristics have not been formally identified and described. As a result, the variations in performance of MIL algorithms from one data set to another are difficult to explain. In this paper, MIL problem characteristics are grouped into four broad categories: the composition of the bags, the types of data distribution, the ambiguity of instance labels, and the task to be performed. Methods specialized to address each category are reviewed. Then, the extent to which these characteristics manifest themselves in key MIL application areas are described. Finally, experiments are conducted to compare the performance of 16 state-of-the-art MIL methods on selected problem characteristics. This paper provides insight on how the problem characteristics affect MIL algorithms, recommendations for future benchmarking and promising avenues for research. Code is available on-line at https://github.com/macarbonneau/MILSurvey.

RSSI-based indoor tracking using the extended Kalman filter and circularly polarized antennas

A tracking scenario comprising a mobile emitter node moving through an indoor environment covered by multiple anchor receivers is investigated in this work. A localization method based on received signal strength indicators (RSSI) and making use of the extended Kalman filter (EKF) and circularly polarized (CP) antennas is proposed. The EKF implements the position-velocity (PV) model, which assumes that the target is moving at a near-constant velocity during any given short time interval Δt. The measurement vector is composed of velocities in addition to RSSI values, which allow to deal with the error term between measurements and the propagation model directly. CP antennas are used on both the anchor nodes and the mobile node. These antennas are known to reduce the effects of multipath, especially those caused by single reflections. As a result, the RSSI values received in line of sight are more accurate and stable than those received from linearly polarized antennas. We tested our approach by tracking the movement of a robot following a predefined trajectory. The maximum location estimation error (LEE) is found to be 0.52 m. In addition, velocity changes are easily tracked during the target movement, which demonstrates the effectiveness of the proposed approach.

A wireless sensor network for residential electrical energy consumption measurement

A wireless sensor network for residential electrical energy consumption measurements is presented. The system integrates wireless sensors to measure the energy consumption of individual electrical circuits in a breaker panel. Each sensor is battery-powered and transmits its data using the 802.15.4 wireless protocol to a communication hub which forwards the aggregated data to a server via Ethernet or Wi-Fi. The sensors use Hall-effect current sensors, a microcontroller, two button-cell batteries and a wireless transmitter. The sensors accuracy is better than 0.8 A on a range of 0-30 A.

Feature Learning from Spectrograms for Assessment of Personality Traits

Several methods have recently been proposed to analyze speech and automatically infer the personality of the speaker. These methods often rely on prosodic and other hand crafted speech processing features extracted with off-the-shelf toolboxes. To achieve high accuracy, numerous features are typically extracted using complex and highly parameterized algorithms. In this paper, a new method based on feature learning and spectrogram analysis is proposed to simplify the feature extraction process while maintaining a high level of accuracy. The proposed method learns a dictionary of discriminant features from patches extracted in the spectrogram representations of training speech segments. Each speech segment is then encoded using the dictionary, and the resulting feature set is used to perform classification of personality traits. Experiments indicate that the proposed method achieves state-of-the-art results with an important reduction in complexity when compared to the most recent reference methods. The number of features, and difficulties linked to the feature extraction process are greatly reduced as only one type of descriptors is used, for which the 7 parameters can be tuned automatically. In contrast, the simplest reference method uses 4 types of descriptors to which 6 functionals are applied, resulting in over 20 parameters to be tuned.

WSN-UAV Monitoring System with Collaborative Beamforming and ADS-B Based Multilateration

This paper presents wireless sensor network unmanned aerial vehicle (WSN-UAV) system for military remote monitoring and surveillance. Large scale WSN is deployed in a battlefield or wide hostile region to collect information of interest and send it to a UAV. Collaborative beamforming (CB) is used to achieve the ground-to-air transmissions. An automatic dependent surveillance-broadcast (ADS-B) based multilateration is used to obtain the UAV location and tracking information. It is found that a minimum distance between the UAV and the WSN is required for proper operation of the CB due to the precision of the multilateration and the movement of the UAV.

Witness identification in multiple instance learning using random subspaces

Multiple instance learning (MIL) is a form of weakly-supervised learning where instances are organized in bags. A label is provided for bags, but not for instances. MIL literature typically focuses on the classification of bags seen as one object, or as a combination of their instances. In both cases, performance is generally measured using labels assigned to entire bags. In this paper, the MIL problem is formulated as a knowledge discovery task for which algorithms seek to discover the witnesses (i.e. identifying positive instances), using the weak supervision provided by bag labels. Some MIL methods are suitable for instance classification, but perform poorly in application where the witness rate is low, or when the positive class distribution is multimodal. A new method that clusters data projected in random subspaces is proposed to perform witness identification in these adverse settings. The proposed method is assessed on MIL data sets from three application domains, and compared to 7 reference MIL algorithms for the witness identification task. The proposed algorithm constantly ranks among the best methods in all experiments, while all other methods perform unevenly across data sets.