Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining Practical Machine Learning Tools and Techniques

Matrix Factorization Techniques for Recommender Systems

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters’ influence on performance to provide insights about their optimisation.

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

This book, written by two major figures in adaptive control, provides a wealth of material for researchers, practitioners, and students. While some researchers in adaptive control may note the absence of a particular topic, the book‘s scope represents a high-gain instrument. It can be used by designers of control systems to enhance their work through the information on many new theoretical developments, and can be used by mathematical control theory specialists to adapt their research to practical needs. The book is strongly recommended to anyone interested in adaptive control.

Adaptive Control

A variety of real-life mobile sensing applications are becoming available, especially in the life-logging, fitness tracking and health monitoring domains. These applications use mobile sensors embedded in smart phones to recognize human activities in order to get a better understanding of human behavior. While progress has been made, human activity recognition remains a challenging task. This is partly due to the broad range of human activities as well as the rich variation in how a given activity can be performed. Using features that clearly separate between activities is crucial. In this paper, we propose an approach to automatically extract discriminative features for activity recognition. Specifically, we develop a method based on Convolutional Neural Networks (CNN), which can capture local dependency and scale invariance of a signal as it has been shown in speech recognition and image recognition domains. In addition, a modified weight sharing technique, called partial weight sharing, is proposed and applied to accelerometer signals to get further improvements. The experimental results on three public datasets, Skoda (assembly line activities), Opportunity (activities in kitchen), Actitracker (jogging, walking, etc.), indicate that our novel CNN-based approach is practical and achieves higher accuracy than existing state-of-the-art methods.

/pdf/convolutional-neural-networks-for-human-activity-recognition-4s49imeg87.pdf

Convolutional Neural Networks for human activity recognition using mobile sensors

This paper presents a novel niching algorithm, probabilistic crowding. Like its predecessor deterministic crowding, probabilistic crowding is fast, simple, and requires no parameters beyond that of the classical GA. In probabilistic crowding, subpopulations are maintained reliably, and we analyze and predict how this maintenance takes place. 

This paper also identifies probabilistic crowding as a member of a family of algorithms, which we call integrated tournament algorithms. Integrated tournament algorithms also include deterministic crowding, restricted tournament selection, elitist recombination, parallel recombinative simulated annealing, the Metropolis algorithm, and simulated annealing.

/pdf/probabilistic-crowding-deterministic-crowding-with-1t5y7mz879.pdf

Probabilistic Crowding: Deterministic Crowding with Probabilistic Replacement

Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant sensor modalities, etc.). Besides, it is difficult to interpret the recurrent networks to gain insight into the models' behavior. To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention. These two mechanisms adaptively focus on important signals and sensor modalities. To further improve the understandability and mean Fl score, we add continuity constraints, considering that continuous sensor signals are more robust than discrete ones. We evaluate the approaches on three datasets and obtain state-of-the-art results. Furthermore, qualitative analysis shows that the attention learned by the models agree well with human intuition.

Understanding and improving recurrent networks for human activity recognition by continuous attention

We present FootprintID, an indoor pedestrian identification system that utilizes footstep-induced structural vibration to infer pedestrian identities for enabling various smart building applications. Previous studies have explored other sensing methods, including vision-, RF-, mobile-, and acoustic-based methods. They often require specific sensing conditions, including line-of-sight, high sensor density, and carrying wearable devices. Vibration-based methods, on the other hand, provide easy-to-install sparse sensing and utilize gait to distinguish different individuals. However, the challenge for these methods is that the signals are sensitive to the gait variations caused by different walking speeds and the floor variations caused by structural heterogeneity. We present FootprintID, a vibration-based approach that achieves robust pedestrian identification. The system uses vibration sensors to detect footstep-induced vibrations. It then selects vibration signals and classifiers to accommodate sensing variations, taking step location and frequency into account. We utilize the physical insight on how individual step signal changes with walking speeds and introduce an iterative transductive learning algorithm (ITSVM) to achieve robust classification with limited labeled training data. When trained only on the average walking speed and tested on different walking speeds, FootprintID achieves up to 96% accuracy and a 3X improvement in extreme speeds compared to the Support Vector Machine. Furthermore, it achieves up to 90% accuracy (1.5X improvement) in uncontrolled experiments.

/pdf/footprintid-indoor-pedestrian-identification-through-ambient-3kghy25uat.pdf

FootprintID: Indoor Pedestrian Identification through Ambient Structural Vibration Sensing

A method and apparatus are provided for dynamically reassigning agents among call types in a call distribution system having a plurality of agents assigned to a plurality of call types. The method includes the steps of detecting a deficiency in agent responsibility assigned to a call type of the plurality of call types based upon a measured service parameter and corresponding target service parameter and determining an agent allocation among the plurality of call types best suited to correct the deficiency.

Ole J. Mengshoel

Papers

Convolutional Neural Networks for human activity recognition using mobile sensors

Probabilistic Crowding: Deterministic Crowding with Probabilistic Replacement

Understanding and improving recurrent networks for human activity recognition by continuous attention

FootprintID: Indoor Pedestrian Identification through Ambient Structural Vibration Sensing

Contact center autopilot algorithms