Unsupervised Action Proposals Using Support Vector Classifiers for Online Video Processing

In this work, we introduce an intelligent video sensor for the problem of Action Proposals (AP). AP consists of localizing temporal segments in untrimmed videos that are likely to contain actions. Solving this problem can accelerate several video action understanding tasks, such as detection, retrieval, or indexing. All previous AP approaches are supervised and offline, i.e., they need both the temporal annotations of the datasets during training and access to the whole video to effectively cast the proposals. We propose here a new approach which, unlike the rest of the state-of-the-art models, is unsupervised. This implies that we do not allow it to see any labeled data during learning nor to work with any pre-trained feature on the used dataset. Moreover, our approach also operates in an online manner, which can be beneficial for many real-world applications where the video has to be processed as soon as it arrives at the sensor, e.g., robotics or video monitoring. The core of our method is based on a Support Vector Classifier (SVC) module which produces candidate segments for AP by distinguishing between sets of contiguous video frames. We further propose a mechanism to refine and filter those candidate segments. This filter optimizes a learning-to-rank formulation over the dynamics of the segments. An extensive experimental evaluation is conducted on Thumos’14 and ActivityNet datasets, and, to the best of our knowledge, this work supposes the first unsupervised approach on these main AP benchmarks. Finally, we also provide a thorough comparison to the current state-of-the-art supervised AP approaches. We achieve 41% and 59% of the performance of the best-supervised model on ActivityNet and Thumos’14, respectively, confirming our unsupervised solution as a correct option to tackle the AP problem. The code to reproduce all our results will be publicly released upon acceptance of the paper.

Download Full-text

A Dataset of Photos and Videos for Digital Forensics Analysis Using Machine Learning Processing

Data ◽

10.3390/data6080087 ◽

2021 ◽

Vol 6 (8) ◽

pp. 87

Author(s):

Sara Ferreira ◽

Mário Antunes ◽

Manuel E. Correia

Keyword(s):

Machine Learning ◽

Digital Forensics ◽

State Of The Art ◽

Forensic Analysis ◽

Third Party ◽

Support Vector ◽

Multimedia Content ◽

Digital Forensic ◽

Video Frames ◽

Forensic Tools

Deepfake and manipulated digital photos and videos are being increasingly used in a myriad of cybercrimes. Ransomware, the dissemination of fake news, and digital kidnapping-related crimes are the most recurrent, in which tampered multimedia content has been the primordial disseminating vehicle. Digital forensic analysis tools are being widely used by criminal investigations to automate the identification of digital evidence in seized electronic equipment. The number of files to be processed and the complexity of the crimes under analysis have highlighted the need to employ efficient digital forensics techniques grounded on state-of-the-art technologies. Machine Learning (ML) researchers have been challenged to apply techniques and methods to improve the automatic detection of manipulated multimedia content. However, the implementation of such methods have not yet been massively incorporated into digital forensic tools, mostly due to the lack of realistic and well-structured datasets of photos and videos. The diversity and richness of the datasets are crucial to benchmark the ML models and to evaluate their appropriateness to be applied in real-world digital forensics applications. An example is the development of third-party modules for the widely used Autopsy digital forensic application. This paper presents a dataset obtained by extracting a set of simple features from genuine and manipulated photos and videos, which are part of state-of-the-art existing datasets. The resulting dataset is balanced, and each entry comprises a label and a vector of numeric values corresponding to the features extracted through a Discrete Fourier Transform (DFT). The dataset is available in a GitHub repository, and the total amount of photos and video frames is 40,588 and 12,400, respectively. The dataset was validated and benchmarked with deep learning Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) methods; however, a plethora of other existing ones can be applied. Generically, the results show a better F1-score for CNN when comparing with SVM, both for photos and videos processing. CNN achieved an F1-score of 0.9968 and 0.8415 for photos and videos, respectively. Regarding SVM, the results obtained with 5-fold cross-validation are 0.9953 and 0.7955, respectively, for photos and videos processing. A set of methods written in Python is available for the researchers, namely to preprocess and extract the features from the original photos and videos files and to build the training and testing sets. Additional methods are also available to convert the original PKL files into CSV and TXT, which gives more flexibility for the ML researchers to use the dataset on existing ML frameworks and tools.

Download Full-text

K-mer based classifiers extract functionally relevant features to support accurate Peroxiredoxin subgroup distinction

10.1101/387787 ◽

2018 ◽

Author(s):

Jiajie Xiao ◽

William H. Turkett

Keyword(s):

Active Site ◽

Antioxidant Defense ◽

State Of The Art ◽

Support Vector ◽

Site Analysis ◽

Representative Sequence ◽

Current State ◽

Vector Machines ◽

Sequence Representation ◽

Functional Relevance

AbstractBackgroundThe Peroxiredoxins (Prx) are a family of proteins that play a major role in antioxidant defense and peroxide-regulated signaling. Six distinct Prx subgroups have been defined based on analysis of structure and sequence regions in proximity to the Prx active site. Analysis of other sequence regions of these annotated proteins may improve the ability to distinguish subgroups and uncover additional representative sequence regions beyond the active site.ResultsThe space of Prx subgroup classifiers is surveyed to highlight similarities and differences in the available approaches. Exploiting the recent growth in annotated Prx proteins, a whole sequence-based classifier is presented that employs support vector machines and a k-mer (k=3) sequence representation.Distinguishing k-mers are extracted and located relative to published active site regions.ConclusionsThis work demonstrates that the 3-mer based classifier can attain high accuracy in subgroup annotation, at rates similar to the current state-of-the-art. Analysis of the classifier’s automatically derived models show that the classification decision is based on a combination of conserved features, including a significant number of residue regions that have not been previously suggested as informative by other classifiers but for which there is evidence of functional relevance.

Download Full-text

In silico approaches for the prediction and analysis of antiviral peptides: a review

Current Pharmaceutical Design ◽

10.2174/1381612826666201102105827 ◽

2020 ◽

Vol 26 ◽

Cited By ~ 1

Author(s):

Phasit Charoenkwan ◽

Nuttapat Anuwongcharoen ◽

Chanin Nantasenamat ◽

Md. Mehedi Hasan ◽

Watshara Shoombuatong

Keyword(s):

State Of The Art ◽

Therapeutic Agents ◽

Support Vector ◽

Sequence Information ◽

Accurate Identification ◽

Robust Learning ◽

Current State ◽

Pharmacokinetic Properties ◽

Feature Encoding ◽

Antiviral Peptides

: In light of the growing resistance toward current antiviral drugs, efforts to discover novel and effective antiviral therapeutic agents remain a pressing scientific effort. Antiviral peptides (AVPs) represents promising therapeutic agents due to their extraordinary advantages in terms of potency, efficacy and pharmacokinetic properties. The growing volume of newly discovered peptide sequences in the post-genomic era requires computational approaches for timely and accurate identification of AVPs. Machine learning (ML) methods such as random forest and support vector machine represents robust learning algorithms that are instrumental in successful peptide-based drug discovery. Therefore, this review summarizes the current state-of-the-art on the application of ML methods for identifying AVPs directly from the sequence information. We compare the efficiency of these methods in terms of the underlying characteristics of the dataset used along with feature encoding methods, ML algorithms, cross-validation methods and prediction performance. Finally, guidelines for development of robust AVP models are also discussed. It is anticipated that this review will be serve as a useful guide for the design and development of robust AVP and related therapeutic peptide predictors in the future.

Download Full-text

Use of a Novel Grammatical Inference Approach in Classification of Amyloidogenic Hexapeptides

Computational and Mathematical Methods in Medicine ◽

10.1155/2016/1782732 ◽

2016 ◽

Vol 2016 ◽

pp. 1-8 ◽

Cited By ~ 6

Author(s):

Wojciech Wieczorek ◽

Olgierd Unold

Keyword(s):

Support Vector Machine ◽

Correlation Coefficient ◽

State Of The Art ◽

Superior Performance ◽

Support Vector ◽

Grammatical Inference ◽

Regular Expressions ◽

Inference Algorithm ◽

Current State

The present paper is a novel contribution to the field of bioinformatics by using grammatical inference in the analysis of data. We developed an algorithm for generating star-free regular expressions which turned out to be good recommendation tools, as they are characterized by a relatively high correlation coefficient between the observed and predicted binary classifications. The experiments have been performed for three datasets of amyloidogenic hexapeptides, and our results are compared with those obtained using the graph approaches, the current state-of-the-art methods in heuristic automata induction, and the support vector machine. The results showed the superior performance of the new grammatical inference algorithm on fixed-length amyloid datasets.

Download Full-text

Supervised and Unsupervised Neural Approaches to Text Readability

Computational Linguistics ◽

10.1162/coli_a_00398 ◽

2021 ◽

Vol 47 (1) ◽

pp. 141-179

Author(s):

Matej Martinc ◽

Senja Pollak ◽

Marko Robnik-Šikonja

Keyword(s):

State Of The Art ◽

Comprehensive Analysis ◽

Language Models ◽

Feature Engineering ◽

Data Sets ◽

Data Set ◽

Systematic Comparison ◽

Current State ◽

Text Readability ◽

Unsupervised Approach

Abstract We present a set of novel neural supervised and unsupervised approaches for determining the readability of documents. In the unsupervised setting, we leverage neural language models, whereas in the supervised setting, three different neural classification architectures are tested. We show that the proposed neural unsupervised approach is robust, transferable across languages, and allows adaptation to a specific readability task and data set. By systematic comparison of several neural architectures on a number of benchmark and new labeled readability data sets in two languages, this study also offers a comprehensive analysis of different neural approaches to readability classification. We expose their strengths and weaknesses, compare their performance to current state-of-the-art classification approaches to readability, which in most cases still rely on extensive feature engineering, and propose possibilities for improvements.

Download Full-text

Learning on the Move in the Web 2.0

K-12 Education ◽

10.4018/978-1-4666-4502-8.ch097 ◽

2013 ◽

pp. 1693-1714

Author(s):

Carlos Baladrón ◽

Javier M. Aguiar ◽

Lorena Calavia ◽

Belén Carro ◽

Antonio Sánchez-Esguevillas

Keyword(s):

Web 2.0 ◽

Mobile Devices ◽

State Of The Art ◽

New Approach ◽

Collaborative Tools ◽

Research And Innovation ◽

Current State ◽

Pros And Cons ◽

Approach To Teaching ◽

The Web

This work aims at presenting the current state of the art of the m-learning trend, an innovative new approach to teaching focused on taking advantage of mobile devices for learning anytime, anywhere and anyhow, usually employing collaborative tools. However, this new trend is still young, and research and innovation results are still fragmented. This work aims at providing an overview of the state of the art through the analysis of the most interesting initiatives published and reported, studying the different approaches followed, their pros and cons, and their results. And after that, this chapter provides a discussion of where we stand nowadays regarding m-learning, what has been achieved so far, which are the open challenges and where we are heading.

Download Full-text

Gender Classification Based on Multiscale Facial Fusion Feature

Mathematical Problems in Engineering ◽

10.1155/2018/1924151 ◽

2018 ◽

Vol 2018 ◽

pp. 1-6 ◽

Cited By ~ 3

Author(s):

Chunyu Zhang ◽

Hui Ding ◽

Yuanyuan Shang ◽

Zhuhong Shao ◽

Xiaoyan Fu

Keyword(s):

Local Binary Pattern ◽

State Of The Art ◽

Support Vector ◽

Gender Classification ◽

Local Phase ◽

New Approach ◽

Local Phase Quantization ◽

Face Images ◽

Phase Quantization ◽

Fusion Feature

For gender classification, we present a new approach based on Multiscale facial fusion feature (MS3F) to classify gender from face images. Fusion feature is extracted by the combination of Local Binary Pattern (LBP) and Local Phase Quantization (LPQ) descriptors, and a multiscale feature is generated through Multiblock (MB) and Multilevel (ML) methods. Support Vector Machine (SVM) is employed as the classifier to conduct gender classification. All the experiments are performed based on the Images of Groups (IoG) dataset. The results demonstrate that the application of Multiscale fusion feature greatly improves the performance of gender classification, and our approach outperforms the state-of-the-art techniques.

Download Full-text

The Role of Kinetics as Key Determinant in Toxicity of Pyrrolizidine Alkaloids and Their N-Oxides

Planta Medica ◽

10.1055/a-1582-9794 ◽

2021 ◽

Author(s):

Frances Widjaja ◽

Yasser Alhejji ◽

Ivonne M. C. M. Rietjens

Keyword(s):

Animal Studies ◽

Pyrrolizidine Alkaloids ◽

Liver Toxicity ◽

State Of The Art ◽

New Approach ◽

Current State ◽

Plant Constituents ◽

Relative Differences

AbstractPyrrolizidine alkaloids (PAs) are a large group of plant constituents of which especially the 1,2- unsaturated PAs raise a concern because of their liver toxicity and potential genotoxic carcinogenicity. This toxicity of PAs depends on their kinetics. Differences in absorption, distribution, metabolism, and excretion (ADME) characteristics of PAs may substantially alter the relative toxicity of PAs. As a result, kinetics will also affect relative potency (REP) values. The present review summarizes the current state-of-the art on PA kinetics and resulting consequences for toxicity and illustrates how physiologically-based kinetic (PBK) modelling can be applied to take kinetics into account when defining the relative differences in toxicity between PAs in the in vivo situation. We conclude that toxicokinetics play an important role in the overall toxicity of pyrrolizidine alkaloids. and that kinetics should therefore be considered when defining REP values for combined risk assessment. New approach methodologies (NAMs) can be of use to quantify these kinetic differences between PAs and their N-oxides, thus contributing to the 3Rs (Replacement, Reduction and Refinement) in animal studies.

Download Full-text