Data Mining Practical Machine Learning Tools and Techniques

https://bura.brunel.ac.uk/bitstream/2438/14221/1/FullText.pdf

A survey of deep neural network architectures and their applications

Deep learning in agriculture: A survey

Deep learning is at the heart of the current rise of artificial intelligence. In the field of computer vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas, deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has recently led to a large influx of contributions in this direction. This paper presents the first comprehensive survey on adversarial attacks on deep learning in computer vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

The purpose of this study is to examine existing deep learning techniques for addressing class imbalanced data. Effective classification with imbalanced data is an important area of research, as high class imbalance is naturally inherent in many real-world applications, e.g., fraud detection and cancer detection. Moreover, highly imbalanced data poses added difficulty, as most learners will exhibit bias towards the majority class, and in extreme cases, may ignore the minority class altogether. Class imbalance has been studied thoroughly over the last two decades using traditional machine learning models, i.e. non-deep learning. Despite recent advances in deep learning, along with its increasing popularity, very little empirical work in the area of deep learning with class imbalance exists. Having achieved record-breaking performance results in several complex domains, investigating the use of deep neural networks for problems containing high levels of class imbalance is of great interest. Available studies regarding class imbalance and deep learning are surveyed in order to better understand the efficacy of deep learning when applied to class imbalanced data. This survey discusses the implementation details and experimental results for each study, and offers additional insight into their strengths and weaknesses. Several areas of focus include: data complexity, architectures tested, performance interpretation, ease of use, big data application, and generalization to other domains. We have found that research in this area is very limited, that most existing work focuses on computer vision tasks with convolutional neural networks, and that the effects of big data are rarely considered. Several traditional methods for class imbalance, e.g. data sampling and cost-sensitive learning, prove to be applicable in deep learning, while more advanced methods that exploit neural network feature learning abilities show promising results. The survey concludes with a discussion that highlights various gaps in deep learning from class imbalanced data for the purpose of guiding future research.

/pdf/survey-on-deep-learning-with-class-imbalance-439xfmfr76.pdf

Survey on deep learning with class imbalance

Big Data Analytics and Deep Learning are two high-focus of data science. Big Data has become important as many organizations both public and private have been collecting massive amounts of domain-specific information, which can contain useful information about problems such as national intelligence, cyber security, fraud detection, marketing, and medical informatics. Companies such as Google and Microsoft are analyzing large volumes of data for business analysis and decisions, impacting existing and future technology. Deep Learning algorithms extract high-level, complex abstractions as data representations through a hierarchical learning process. Complex abstractions are learnt at a given level based on relatively simpler abstractions formulated in the preceding level in the hierarchy. A key benefit of Deep Learning is the analysis and learning of massive amounts of unsupervised data, making it a valuable tool for Big Data Analytics where raw data is largely unlabeled and un-categorized. In the present study, we explore how Deep Learning can be utilized for addressing some important problems in Big Data Analytics, including extracting complex patterns from massive volumes of data, semantic indexing, data tagging, fast information retrieval, and simplifying discriminative tasks. We also investigate some aspects of Deep Learning research that need further exploration to incorporate specific challenges introduced by Big Data Analytics, including streaming data, high-dimensional data, scalability of models, and distributed computing. We conclude by presenting insights into relevant future works by posing some questions, including defining data sampling criteria, domain adaptation modeling, defining criteria for obtaining useful data abstractions, improving semantic indexing, semi-supervised learning, and active learning.

/pdf/deep-learning-applications-and-challenges-in-big-data-oblfhz8zye.pdf

Deep learning applications and challenges in big data analytics

to Multimedia Security.- Digital Rights Management for Multimedia.- Multimedia Cryptography.- to Multimedia Encryption.- An Overview of Modern Cryptography.- Important Modern Cryptosystems.- Image Encryption Algorithms.- Video Encryption Algorithms.- Speech and Audio Encryption.- Visual and Audio Secret Sharing.- Multimedia Watermarking.- to Watermarking.- Applications of Digital Watermarking.- Digital Watermarking Concepts.- Digital Watermarking and Binary Images.- Two-Level Marks: Design.- Two-Level Marks: Implementations.- Future of Watermarking.

Multimedia encryption and watermarking

In our society, large volumes of documents are exchanged on a daily basis. Since documents can easily be scanned, modified and reproduced without any loss in quality, unauthorized use and modification of documents is of major concern. An authentication watermark embedded into a document as an invisible, fragile mark can be used to detect illegal document modification. However, the authentication watermark can only be used to determine whether documents have been tampered with, and additional protection may be needed to prevent unauthorized use and distribution of those documents. A solution to this problem is a two-level, multipurpose watermark. The first level watermark is an authentication mark used to detect document tampering, while the second level watermark is a robust mark, which identifies the legitimate owner and/or user of specific document. 
This dissertation introduces a new adaptive two-level multipurpose watermarking scheme suitable for binary document images, such as scanned text, figures, engineering and road maps, architectural drawings, music scores, and handwritten text and sketches. This watermarking scheme uses uniform quantization and overlapped embedding to add two watermarks, one robust and the other fragile, into a binary document image. The two embedded watermarks serve different purposes. The robust watermark carries document owner or document user identification, and the fragile watermark confirms document authenticity and helps detect document tampering. Both watermarks can be extracted without accessing the original document image. 
The proposed watermarking scheme adaptively selects an image partitioning block size to optimize the embedding capacity, the image permutation key to minimize watermark detection error, and the size of local neighborhood in which modification candidate pixels are scored to minimize visible distortion of watermarked documents. Modification candidate pixels are scored using a novel, objective metric called the Structural Neighborhood Distortion Measure (SNDM). Experimental results confirm that this watermarking scheme, which embeds watermarks by modifying image pixels based on their SNDM scores, creates smaller visible document distortion than watermarking schemes which base watermark embedding on any other published pixel scoring method. Document tampering is detected successfully and the robust watermark can be detected even after document tampering renders the fragile watermark undetectable.

Adaptive two-level watermarking for binary document images

Firewalls form an essential element of modern network security, detecting and discarding malicious packets before they can cause harm to the network being protected. However, these firewalls must process a large number of packets very quickly, and so can't always make decisions based on all of the packets' properties (features). Thus, it is important to understand which features are most relevant in determining if a packet is malicious, and whether a simple model built from these features can be as effective as a model which uses all information on each packet. We explore a dataset with real-world firewall data to answer these questions, ranking the features with 22 feature selection techniques and building classification models using four classifiers (learners). Our results show that the top two features are proto and dst (representing the network protocol and destination IP address, respectively), and that models built using these two features in combination with the Naive Bayes learner are highly effective while being minimally computationally expensive. Such models have the potential to replace conventional firewalls while lowering computational needs.

Using feature selection and classification to build effective and efficient firewalls

The proliferation of Big Data processing environments such as Hadoop, Apache Spark, and HPCC Systems is driving the development of performance analysis tools in these distributed systems. The goal is to achieve high performance through the optimization of Big Data applications. However, tuning performance in a fine-grained manner is quite challenging due to the high complexity and massive size of the distributed systems. ECL-Watch is a data-flow based fine-grained comprehensive Big Data performance analysis tool utilizing the high level declarative dataflow programming language ECL in HPCC Systems. As a case study, we implement and optimize the Yinyang K-Means machine learning algorithm in ECL in HPCC Systems. The experimental results show that the performance of the native ECL version of the Yinyang K-Means algorithm increased significantly after tuning: from being about three times slower than the standard K-Means implementation in ECL, to become roughly 15% faster than standard K-Means.

Edin Muharemagic

Papers

Deep learning applications and challenges in big data analytics

Multimedia encryption and watermarking

Adaptive two-level watermarking for binary document images

Using feature selection and classification to build effective and efficient firewalls

ECL-watch: A big data application performance tuning tool in the HPCC systems platform