A Survey on Deep Learning for Human Activity Recognition

Human activity recognition is a key to a lot of applications such as healthcare and smart home. In this study, we provide a comprehensive survey on recent advances and challenges in human activity recognition (HAR) with deep learning. Although there are many surveys on HAR, they focused mainly on the taxonomy of HAR and reviewed the state-of-the-art HAR systems implemented with conventional machine learning methods. Recently, several works have also been done on reviewing studies that use deep models for HAR, whereas these works cover few deep models and their variants. There is still a need for a comprehensive and in-depth survey on HAR with recently developed deep learning methods.

Adversarial Perturbation Defense on Deep Neural Networks

Deep neural networks (DNNs) have been verified to be easily attacked by well-designed adversarial perturbations. Image objects with small perturbations that are imperceptible to human eyes can induce DNN-based image class classifiers towards making erroneous predictions with high probability. Adversarial perturbations can also fool real-world machine learning systems and transfer between different architectures and datasets. Recently, defense methods against adversarial perturbations have become a hot topic and attracted much attention. A large number of works have been put forward to defend against adversarial perturbations, enhancing DNN robustness against potential attacks, or interpreting the origin of adversarial perturbations. In this article, we provide a comprehensive survey on classical and state-of-the-art defense methods by illuminating their main concepts, in-depth algorithms, and fundamental hypotheses regarding the origin of adversarial perturbations. In addition, we further discuss potential directions of this domain for future researchers.

A Survey of Deep Active Learning

Active learning (AL) attempts to maximize a model’s performance gain while annotating the fewest samples possible. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize a massive number of parameters if the model is to learn how to extract high-quality features. In recent years, due to the rapid development of internet technology, we have entered an era of information abundance characterized by massive amounts of available data. As a result, DL has attracted significant attention from researchers and has been rapidly developed. Compared with DL, however, researchers have a relatively low interest in AL. This is mainly because before the rise of DL, traditional machine learning requires relatively few labeled samples, meaning that early AL is rarely according the value it deserves. Although DL has made breakthroughs in various fields, most of this success is due to a large number of publicly available annotated datasets. However, the acquisition of a large number of high-quality annotated datasets consumes a lot of manpower, making it unfeasible in fields that require high levels of expertise (such as speech recognition, information extraction, medical images, etc.). Therefore, AL is gradually coming to receive the attention it is due. It is therefore natural to investigate whether AL can be used to reduce the cost of sample annotation while retaining the powerful learning capabilities of DL. As a result of such investigations, deep active learning (DeepAL) has emerged. Although research on this topic is quite abundant, there has not yet been a comprehensive survey of DeepAL-related works; accordingly, this article aims to fill this gap. We provide a formal classification method for the existing work, along with a comprehensive and systematic overview. In addition, we also analyze and summarize the development of DeepAL from an application perspective. Finally, we discuss the confusion and problems associated with DeepAL and provide some possible development directions.

Computing Blindfolded on Data Homomorphically Encrypted under Multiple Keys: A Survey

With capability of performing computations on encrypted data without needing the secret key, homomorphic encryption (HE) is a promising cryptographic technique that makes outsourced computations secure and privacy-preserving. A decade after Gentry’s breakthrough discovery of how we might support arbitrary computations on encrypted data, many studies followed and improved various aspects of HE, such as faster bootstrapping and ciphertext packing. However, the topic of how to support secure computations on ciphertexts encrypted under multiple keys does not receive enough attention. This capability is crucial in many application scenarios where data owners want to engage in joint computations and are preferred to protect their sensitive data under their own secret keys. Enabling this capability is a non-trivial task. In this article, we present a comprehensive survey of the state-of-the-art multi-key techniques and schemes that target different systems and threat models. In particular, we review recent constructions based on Threshold Homomorphic Encryption (ThHE) and Multi-Key Homomorphic Encryption (MKHE). We analyze these cryptographic techniques and schemes based on a new secure outsourced computation model and examine their complexities. We share lessons learned and draw observations for designing better schemes with reduced overheads.

A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation

Image representation is an important topic in computer vision and pattern recognition. It plays a fundamental role in a range of applications toward understanding visual contents. Moment-based image representation has been reported to be effective in satisfying the core conditions of semantic description due to its beneficial mathematical properties, especially geometric invariance and independence. This article presents a comprehensive survey of the orthogonal moments for image representation, covering recent advances in fast/accurate calculation, robustness/invariance optimization, definition extension, and application. We also create a software package for a variety of widely used orthogonal moments and evaluate such methods in a same base. The presented theory analysis, software implementation, and evaluation results can support the community, particularly in developing novel techniques and promoting real-world applications.

A Comprehensive Survey on Interoperability for IIoT: Taxonomy, Standards, and Future Directions

In the era of Industry 4.0, the Internet-of-Things (IoT) performs the driving position analogous to the initial industrial metamorphosis. IoT affords the potential to couple machine-to-machine intercommunication and real-time information-gathering within the industry domain. Hence, the enactment of IoT in the industry magnifies effective optimization, authority, and data-driven judgment. However, this field undergoes several interoperable issues, including large numbers of heterogeneous IoT gadgets, tools, software, sensing, and processing components, joining through the Internet, despite the deficiency of communication protocols and standards. Recently, various interoperable protocols, platforms, standards, and technologies are enhanced and altered according to the specifications of the applicability in industrial applications. However, there are no recent survey papers that primarily examine various interoperability issues that Industrial IoT (IIoT) faces. In this review, we investigate the conventional and recent developments of relevant state-of-the-art IIoT technologies, frameworks, and solutions for facilitating interoperability between different IIoT components. We also discuss several interoperable IIoT standards, protocols, and models for digitizing the industrial revolution. Finally, we conclude this survey with an inherent discussion of open challenges and directions for future research.

A Survey on String Constraint Solving

String constraint solving refers to solving combinatorial problems involving constraints over string variables. String solving approaches have become popular over the past few years given the massive use of strings in different application domains like formal analysis, automated testing, database query processing, and cybersecurity. This article reports a comprehensive survey on string constraint solving by exploring the large number of approaches that have been proposed over the past few decades to solve string constraints.

Evolutionary Large-Scale Multi-Objective Optimization: A Survey

Multi-objective evolutionary algorithms (MOEAs) have shown promising performance in solving various optimization problems, but their performance may deteriorate drastically when tackling problems containing a large number of decision variables. In recent years, much effort been devoted to addressing the challenges brought by large-scale multi-objective optimization problems. This article presents a comprehensive survey of stat-of-the-art MOEAs for solving large-scale multi-objective optimization problems. We start with a categorization of these MOEAs into decision variable grouping based, decision space reduction based, and novel search strategy based MOEAs, discussing their strengths and weaknesses. Then, we review the benchmark problems for performance assessment and a few important and emerging applications of MOEAs for large-scale multi-objective optimization. Last, we discuss some remaining challenges and future research directions of evolutionary large-scale multi-objective optimization.

Data-driven Crowd Modeling Techniques: A Survey

Data-driven crowd modeling has now become a popular and effective approach for generating realistic crowd simulation and has been applied to a range of applications, such as anomaly detection and game design. In the past decades, a number of data-driven crowd modeling techniques have been proposed, providing many options for people to generate virtual crowd simulation. This article provides a comprehensive survey of these state-of-the-art data-driven modeling techniques. We first describe the commonly used datasets for crowd modeling. Then, we categorize and discuss the state-of-the-art data-driven crowd modeling methods. After that, data-driven crowd model validation techniques are discussed. Finally, six promising future research topics of data-driven crowd modeling are discussed.

A Comprehensive Survey of Attacks without Physical Access Targeting Hardware Vulnerabilities in IoT/IIoT Devices, and Their Detection Mechanisms

With the advances in the field of the Internet of Things (IoT) and Industrial IoT (IIoT), these devices are increasingly used in daily life or industry. To reduce costs related to the time required to develop these devices, security features are usually not considered. This situation creates a major security concern. Many solutions have been proposed to protect IoT/IIoT against various attacks, most of which are based on attacks involving physical access. However, a new class of attacks has emerged targeting hardware vulnerabilities in the micro-architecture that do not require physical access. We present attacks based on micro-architectural hardware vulnerabilities and the side effects they produce in the system. In addition, we present security mechanisms that can be implemented to address some of these attacks. Most of the security mechanisms target a small set of attack vectors or a single specific attack vector. As many attack vectors exist, solutions must be found to protect against a wide variety of threats. This survey aims to inform designers about the side effects related to attacks and detection mechanisms that have been described in the literature. For this purpose, we present two tables listing and classifying the side effects and detection mechanisms based on the given criteria.