https://scholarlypublications.universiteitleiden.nl/access/item%3A2943283/view

Deep learning for visual understanding

Human activity recognition systems are developed as part of a framework to enable continuous monitoring of human behaviours in the area of ambient assisted living, sports injury detection, elderly care, rehabilitation, and entertainment and surveillance in smart home environments. The extraction of relevant features is the most challenging part of the mobile and wearable sensor-based human activity recognition pipeline. Feature extraction influences the algorithm performance and reduces computation time and complexity. However, current human activity recognition relies on handcrafted features that are incapable of handling complex activities especially with the current influx of multimodal and high dimensional sensor data. With the emergence of deep learning and increased computation powers, deep learning and artificial intelligence methods are being adopted for automatic feature learning in diverse areas like health, image classification, and recently, for feature extraction and classification of simple and complex human activity recognition in mobile and wearable sensors. Furthermore, the fusion of mobile or wearable sensors and deep learning methods for feature learning provide diversity, offers higher generalisation, and tackles challenging issues in human activity recognition. The focus of this review is to provide in-depth summaries of deep learning methods for mobile and wearable sensor-based human activity recognition. The review presents the methods, uniqueness, advantages and their limitations. We not only categorise the studies into generative, discriminative and hybrid methods but also highlight their important advantages. Furthermore, the review presents classification and evaluation procedures and discusses publicly available datasets for mobile sensor human activity recognition. Finally, we outline and explain some challenges to open research problems that require further research and improvements.

Deep learning algorithms for human activity recognition using mobile and wearable sensor networks: State of the art and research challenges

Machine learning on big data

Anomaly detection is an important problem that has been well-studied within diverse research areas and application domains. The aim of this survey is two-fold, firstly we present a structured and comprehensive overview of research methods in deep learning-based anomaly detection. Furthermore, we review the adoption of these methods for anomaly across various application domains and assess their effectiveness. We have grouped state-of-the-art research techniques into different categories based on the underlying assumptions and approach adopted. Within each category we outline the basic anomaly detection technique, along with its variants and present key assumptions, to differentiate between normal and anomalous behavior. For each category, we present we also present the advantages and limitations and discuss the computational complexity of the techniques in real application domains. Finally, we outline open issues in research and challenges faced while adopting these techniques.

Deep Learning for Anomaly Detection: A Survey.

Classical autoencoders are neural networks that can learn efficient low-dimensional representations of data in higher-dimensional space. The task of an autoencoder is, given an input x, to map x to a lower dimensional point y such that x can likely be recovered from y. The structure of the underlying autoencoder network can be chosen to represent the data on a smaller dimension, effectively compressing the input. Inspired by this idea, we introduce the model of a quantum autoencoder to perform similar tasks on quantum data. The quantum autoencoder is trained to compress a particular data set of quantum states, where a classical compression algorithm cannot be employed. The parameters of the quantum autoencoder are trained using classical optimization algorithms. We show an example of a simple programmable circuit that can be trained as an efficient autoencoder. We apply our model in the context of quantum simulation to compress ground states of the Hubbard model and molecular Hamiltonians.

https://iopscience.iop.org/article/10.1088/2058-9565/aa8072/pdf

Quantum autoencoders for efficient compression of quantum data

Autoencoder for words

This work uses the L-system to construct a tree structure for the text sequence and derives its complexity. It serves as a measure of structural complexity of the text. It is applied to anomaly detection in data transmission.

Syntactic sensitive complexity for symbol-free sequence

This work uses L-system to model the text sequence. The sequence complexity is obtained by calculating the complexity of its modeling system. It can sense certain quasi-regular structures and serves as a measure of regularity of the sequence. The outliers and statistics of the complexity values can be applied to the anomaly detection of symbol sequences.

Syntactic Sensitive Complexity for Symbol-Free Sequence

Instead of training a single code vector for a word by using Elman network [1], this work presents a method to train multi-code for the polysemous word where each code represents a different meaning of the word. These multiple codes can accommodate different meanings of a word and facilitate the operation of word-sense disambiguation in semantic space.

Autoencoder for polysemous word

Hand-printed character recognition is an important application in our life. A method called the feature-to-feature adhesion method is developed to achieve the task. There are two geometrical relations constructed in an earlier method. This work rewrites geometrical relations and con- structs them into the Hopfield model to improve the matching result. We also provided some new applications which can be solved by our improved method.

Daw-Ran Liou

Papers

Autoencoder for words

Syntactic sensitive complexity for symbol-free sequence

Syntactic Sensitive Complexity for Symbol-Free Sequence

Autoencoder for polysemous word

Finite geometrical relations loading in Hopfield model