Paper Group ANR 598
Towards Automated Melanoma Detection with Deep Learning: Data Purification and Augmentation. Single Versus Union: Non-parallel Support Vector Machine Frameworks. Generalization Bounds in the Predict-then-Optimize Framework. Network of Evolvable Neural Units: Evolving to Learn at a Synaptic Level. Transform-Domain Classification of Human Cells based …
Towards Automated Melanoma Detection with Deep Learning: Data Purification and Augmentation
| Title | Towards Automated Melanoma Detection with Deep Learning: Data Purification and Augmentation |
| Authors | Devansh Bisla, Anna Choromanska, Jennifer A. Stein, David Polsky, Russell Berman |
| Abstract | Melanoma is one of the ten most common cancers in the US. Early detection is crucial for survival, but often the cancer is diagnosed in the fatal stage. Deep learning has the potential to improve cancer detection rates, but its applicability to melanoma detection is compromised by the limitations of the available skin lesion databases, which are small, heavily imbalanced, and contain images with occlusions. We build deep-learning-based tools for data purification and augmentation to counter-act these limitations. The developed tools can be utilized in a deep learning system for lesion classification and we show how to build such a system. The system heavily relies on the processing unit for removing image occlusions and the data generation unit, based on generative adversarial networks, for populating scarce lesion classes, or equivalently creating virtual patients with pre-defined types of lesions. We empirically verify our approach and show that incorporating these two units into melanoma detection system results in the superior performance over common baselines. |
| Tasks | Lesion Segmentation |
| Published | 2019-02-16 |
| URL | https://arxiv.org/abs/1902.06061v2 |
| https://arxiv.org/pdf/1902.06061v2.pdf | |
| PWC | https://paperswithcode.com/paper/skin-lesion-segmentation-and-classification |
| Repo | |
| Framework | |
Single Versus Union: Non-parallel Support Vector Machine Frameworks
| Title | Single Versus Union: Non-parallel Support Vector Machine Frameworks |
| Authors | Chun-Na Li, Yuan-Hai Shao, Huajun Wang, Yu-Ting Zhao, Ling-Wei Huang, Naihua Xiu, Nai-Yang Deng |
| Abstract | Considering the classification problem, we summarize the nonparallel support vector machines with the nonparallel hyperplanes to two types of frameworks. The first type constructs the hyperplanes separately. It solves a series of small optimization problems to obtain a series of hyperplanes, but is hard to measure the loss of each sample. The other type constructs all the hyperplanes simultaneously, and it solves one big optimization problem with the ascertained loss of each sample. We give the characteristics of each framework and compare them carefully. In addition, based on the second framework, we construct a max-min distance-based nonparallel support vector machine for multiclass classification problem, called NSVM. It constructs hyperplanes with large distance margin by solving an optimization problem. Experimental results on benchmark data sets and human face databases show the advantages of our NSVM. |
| Tasks | |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09734v1 |
| https://arxiv.org/pdf/1910.09734v1.pdf | |
| PWC | https://paperswithcode.com/paper/single-versus-union-non-parallel-support |
| Repo | |
| Framework | |
Generalization Bounds in the Predict-then-Optimize Framework
| Title | Generalization Bounds in the Predict-then-Optimize Framework |
| Authors | Othman El Balghiti, Adam N. Elmachtoub, Paul Grigas, Ambuj Tewari |
| Abstract | The predict-then-optimize framework is fundamental in many practical settings: predict the unknown parameters of an optimization problem, and then solve the problem using the predicted values of the parameters. A natural loss function in this environment is to consider the cost of the decisions induced by the predicted parameters, in contrast to the prediction error of the parameters. This loss function was recently introduced in Elmachtoub and Grigas (2017), which called it the Smart Predict-then-Optimize (SPO) loss. Since the SPO loss is nonconvex and noncontinuous, standard results for deriving generalization bounds do not apply. In this work, we provide an assortment of generalization bounds for the SPO loss function. In particular, we derive bounds based on the Natarajan dimension that, in the case of a polyhedral feasible region, scale at most logarithmically in the number of extreme points, but, in the case of a general convex set, have poor dependence on the dimension. By exploiting the structure of the SPO loss function and an additional strong convexity assumption on the feasible region, we can dramatically improve the dependence on the dimension via an analysis and corresponding bounds that are akin to the margin guarantees in classification problems. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11488v1 |
| https://arxiv.org/pdf/1905.11488v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalization-bounds-in-the-predict-then |
| Repo | |
| Framework | |
Network of Evolvable Neural Units: Evolving to Learn at a Synaptic Level
| Title | Network of Evolvable Neural Units: Evolving to Learn at a Synaptic Level |
| Authors | Paul Bertens, Seong-Whan Lee |
| Abstract | Although Deep Neural Networks have seen great success in recent years through various changes in overall architectures and optimization strategies, their fundamental underlying design remains largely unchanged. Computational neuroscience on the other hand provides more biologically realistic models of neural processing mechanisms, but they are still high level abstractions of the actual experimentally observed behaviour. Here a model is proposed that bridges Neuroscience, Machine Learning and Evolutionary Algorithms to evolve individual soma and synaptic compartment models of neurons in a scalable manner. Instead of attempting to manually derive models for all the observed complexity and diversity in neural processing, we propose an Evolvable Neural Unit (ENU) that can approximate the function of each individual neuron and synapse. We demonstrate that this type of unit can be evolved to mimic Integrate-And-Fire neurons and synaptic Spike-Timing-Dependent Plasticity. Additionally, by constructing a new type of neural network where each synapse and neuron is such an evolvable neural unit, we show it is possible to evolve an agent capable of learning to solve a T-maze environment task. This network independently discovers spiking dynamics and reinforcement type learning rules, opening up a new path towards biologically inspired artificial intelligence. |
| Tasks | |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07589v1 |
| https://arxiv.org/pdf/1912.07589v1.pdf | |
| PWC | https://paperswithcode.com/paper/network-of-evolvable-neural-units-evolving-to |
| Repo | |
| Framework | |
Transform-Domain Classification of Human Cells based on DNA Methylation Datasets
| Title | Transform-Domain Classification of Human Cells based on DNA Methylation Datasets |
| Authors | Xueyuan Zhao, Dario Pompili |
| Abstract | A novel method to classify human cells is presented in this work based on the transform-domain method on DNA methylation data. DNA methylation profile variations are observed in human cells with the progression of disease stages, and the proposal is based on this DNA methylation variation to classify normal and disease cells including cancer cells. The cancer cell types investigated in this work cover hepatocellular (sample size n = 40), colorectal (n = 44), lung (n = 70) and endometrial (n = 87) cancer cells. A new pipeline is proposed integrating the DNA methylation intensity measurements on all the CpG islands by the transformation of Walsh-Hadamard Transform (WHT). The study reveals the three-step properties of the DNA methylation transform-domain data and the step values of association with the cell status. Further assessments have been carried out on the proposed machine learning pipeline to perform classification of the normal and cancer tissue cells. A number of machine learning classifiers are compared for whole sequence and WHT sequence classification based on public Whole-Genome Bisulfite Sequencing (WGBS) DNA methylation datasets. The WHT-based method can speed up the computation time by more than one order of magnitude compared with whole original sequence classification, while maintaining comparable classification accuracy by the selected machine learning classifiers. The proposed method has broad applications in expedited disease and normal human cell classifications by the epigenome and genome datasets. |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/1912.13167v1 |
| https://arxiv.org/pdf/1912.13167v1.pdf | |
| PWC | https://paperswithcode.com/paper/transform-domain-classification-of-human |
| Repo | |
| Framework | |
Distance Preserving Grid Layouts
| Title | Distance Preserving Grid Layouts |
| Authors | Gladys Hilasaca, Fernando V. Paulovich |
| Abstract | Distance preserving visualization techniques have emerged as one of the fundamental tools for data analysis. One example are the techniques that arrange data instances into two-dimensional grids so that the pairwise distances among the instances are preserved into the produced layouts. Currently, the state-of-the-art approaches produce such grids by solving assignment problems or using permutations to optimize cost functions. Although precise, such strategies are computationally expensive, limited to small datasets or being dependent on specialized hardware to speed up the process. In this paper, we present a new technique, called Distance-preserving Grid (DGrid), that employs a binary space partitioning process in combination with multidimensional projections to create orthogonal regular grid layouts. Our results show that DGrid is as precise as the existing state-of-the-art techniques whereas requiring only a fraction of the running time and computational resources. |
| Tasks | |
| Published | 2019-03-08 |
| URL | http://arxiv.org/abs/1903.06262v1 |
| http://arxiv.org/pdf/1903.06262v1.pdf | |
| PWC | https://paperswithcode.com/paper/distance-preserving-grid-layouts |
| Repo | |
| Framework | |
Deep recommender engine based on efficient product embeddings neural pipeline
| Title | Deep recommender engine based on efficient product embeddings neural pipeline |
| Authors | Laurentiu Piciu, Andrei Damian, Nicolae Tapus, Andrei Simion-Constantinescu, Bogdan Dumitrescu |
| Abstract | Predictive analytics systems are currently one of the most important areas of research and development within the Artificial Intelligence domain and particularly in Machine Learning. One of the “holy grails” of predictive analytics is the research and development of the “perfect” recommendation system. In our paper, we propose an advanced pipeline model for the multi-task objective of determining product complementarity, similarity and sales prediction using deep neural models applied to big-data sequential transaction systems. Our highly parallelized hybrid model pipeline consists of both unsupervised and supervised models, used for the objectives of generating semantic product embeddings and predicting sales, respectively. Our experimentation and benchmarking processes have been done using pharma industry retail real-life transactional Big-Data streams. |
| Tasks | |
| Published | 2019-03-24 |
| URL | https://arxiv.org/abs/1903.09942v2 |
| https://arxiv.org/pdf/1903.09942v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-recommender-engine-based-on-efficient |
| Repo | |
| Framework | |
Self Multi-Head Attention for Speaker Recognition
| Title | Self Multi-Head Attention for Speaker Recognition |
| Authors | Miquel India, Pooyan Safari, Javier Hernando |
| Abstract | Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to obtain an utterance level speaker representation. In this work we propose the use of an attention mechanism to obtain a discriminative speaker embedding given non fixed length speech utterances. Our system is based on a Convolutional Neural Network (CNN) that encodes short-term speaker features from the spectrogram and a self multi-head attention model that maps these representations into a long-term speaker embedding. The attention model that we propose produces multiple alignments from different subsegments of the CNN encoded states over the sequence. Hence this mechanism works as a pooling layer which decides the most discriminative features over the sequence to obtain an utterance level representation. We have tested this approach for the verification task for the VoxCeleb1 dataset. The results show that self multi-head attention outperforms both temporal and statistical pooling methods with a 18% of relative EER. Obtained results show a 58% relative improvement in EER compared to i-vector+PLDA. |
| Tasks | Speaker Recognition |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.09890v2 |
| https://arxiv.org/pdf/1906.09890v2.pdf | |
| PWC | https://paperswithcode.com/paper/self-multi-head-attention-for-speaker |
| Repo | |
| Framework | |
VQD: Visual Query Detection in Natural Scenes
| Title | VQD: Visual Query Detection in Natural Scenes |
| Authors | Manoj Acharya, Karan Jariwala, Christopher Kanan |
| Abstract | We propose Visual Query Detection (VQD), a new visual grounding task. In VQD, a system is guided by natural language to localize a variable number of objects in an image. VQD is related to visual referring expression recognition, where the task is to localize only one object. We describe the first dataset for VQD and we propose baseline algorithms that demonstrate the difficulty of the task compared to referring expression recognition. |
| Tasks | |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02794v2 |
| http://arxiv.org/pdf/1904.02794v2.pdf | |
| PWC | https://paperswithcode.com/paper/vqd-visual-query-detection-in-natural-scenes |
| Repo | |
| Framework | |
Extraction and Analysis of Fictional Character Networks: A Survey
| Title | Extraction and Analysis of Fictional Character Networks: A Survey |
| Authors | Xavier Bost, Vincent Labatut |
| Abstract | A character network is a graph extracted from a narrative, in which vertices represent characters and edges correspond to interactions between them. A number of narrative-related problems can be addressed automatically through the analysis of character networks, such as summarization, classification, or role detection. Character networks are particularly relevant when considering works of fictions (e.g. novels, plays, movies, TV series), as their exploitation allows developing information retrieval and recommendation systems. However, works of fiction possess specific properties making these tasks harder. This survey aims at presenting and organizing the scientific literature related to the extraction of character networks from works of fiction, as well as their analysis. We first describe the extraction process in a generic way, and explain how its constituting steps are implemented in practice, depending on the medium of the narrative, the goal of the network analysis, and other factors. We then review the descriptive tools used to characterize character networks, with a focus on the way they are interpreted in this context. We illustrate the relevance of character networks by also providing a review of applications derived from their analysis. Finally, we identify the limitations of the existing approaches, and the most promising perspectives. |
| Tasks | Information Retrieval, Recommendation Systems |
| Published | 2019-07-05 |
| URL | https://arxiv.org/abs/1907.02704v2 |
| https://arxiv.org/pdf/1907.02704v2.pdf | |
| PWC | https://paperswithcode.com/paper/extraction-and-analysis-of-fictional |
| Repo | |
| Framework | |
Disparity-based HDR imaging
| Title | Disparity-based HDR imaging |
| Authors | Jennifer Bonnard, Gilles Valette, Céline Loscos |
| Abstract | High-dynamic range imaging permits to extend the dynamic range of intensity values to get close to what the human eye is able to perceive. Although there has been a huge progress in the digital camera sensor range capacity, the need of capturing several exposures in order to reconstruct high-dynamic range values persist. In this paper, we present a study on how to acquire high-dynamic range values for multi-stereo images. In many papers, disparity has been used to register pixels of different images and guide the reconstruction. In this paper, we show the limitations of such approaches and propose heuristics as solutions to identified problematic cases. |
| Tasks | |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.07918v1 |
| https://arxiv.org/pdf/1905.07918v1.pdf | |
| PWC | https://paperswithcode.com/paper/disparity-based-hdr-imaging |
| Repo | |
| Framework | |
Heartbeat Classification in Wearables Using Multi-layer Perceptron and Time-Frequency Joint Distribution of ECG
| Title | Heartbeat Classification in Wearables Using Multi-layer Perceptron and Time-Frequency Joint Distribution of ECG |
| Authors | Anup Das, Francky Catthoor, Siebren Schaafsma |
| Abstract | Heartbeat classification using electrocardiogram (ECG) data is a vital assistive technology for wearable health solutions. We propose heartbeat feature classification based on a novel sparse representation using time-frequency joint distribution of ECG. Fundamental to this is a multi-layer perceptron, which incorporates these signatures to detect cardiac arrhythmia. This approach is validated with ECG data from MIT-BIH arrhythmia database. Results show that our approach has an average 95.7% accuracy, an improvement of 22% over state-of-the-art approaches. Additionally, ECG sparse distributed representations generates only 3.7% false negatives, reduction of 89% with respect to existing ECG signal classification techniques. |
| Tasks | Heartbeat Classification |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.06865v1 |
| https://arxiv.org/pdf/1908.06865v1.pdf | |
| PWC | https://paperswithcode.com/paper/heartbeat-classification-in-wearables-using |
| Repo | |
| Framework | |
Machine Learning: A Dark Side of Cancer Computing
| Title | Machine Learning: A Dark Side of Cancer Computing |
| Authors | Ripon Patgiri, Sabuzima Nayak, Tanya Akutota, Bishal Paul |
| Abstract | Cancer analysis and prediction is the utmost important research field for well-being of humankind. The Cancer data are analyzed and predicted using machine learning algorithms. Most of the researcher claims the accuracy of the predicted results within 99%. However, we show that machine learning algorithms can easily predict with an accuracy of 100% on Wisconsin Diagnostic Breast Cancer dataset. We show that the method of gaining accuracy is an unethical approach that we can easily mislead the algorithms. In this paper, we exploit the weakness of Machine Learning algorithms. We perform extensive experiments for the correctness of our results to exploit the weakness of machine learning algorithms. The methods are rigorously evaluated to validate our claim. In addition, this paper focuses on correctness of accuracy. This paper report three key outcomes of the experiments, namely, correctness of accuracies, significance of minimum accuracy, and correctness of machine learning algorithms. |
| Tasks | |
| Published | 2019-03-17 |
| URL | http://arxiv.org/abs/1903.07167v1 |
| http://arxiv.org/pdf/1903.07167v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-a-dark-side-of-cancer |
| Repo | |
| Framework | |
MediaRank: Computational Ranking of Online News Sources
| Title | MediaRank: Computational Ranking of Online News Sources |
| Authors | Junting Ye, Steven Skiena |
| Abstract | In the recent political climate, the topic of news quality has drawn attention both from the public and the academic communities. The growing distrust of traditional news media makes it harder to find a common base of accepted truth. In this work, we design and build MediaRank (www.media-rank.com), a fully automated system to rank over 50,000 online news sources around the world. MediaRank collects and analyzes one million news webpages and two million related tweets everyday. We base our algorithmic analysis on four properties journalists have established to be associated with reporting quality: peer reputation, reporting bias / breadth, bottomline financial pressure, and popularity. Our major contributions of this paper include: (i) Open, interpretable quality rankings for over 50,000 of the world’s major news sources. Our rankings are validated against 35 published news rankings, including French, German, Russian, and Spanish language sources. MediaRank scores correlate positively with 34 of 35 of these expert rankings. (ii) New computational methods for measuring influence and bottomline pressure. To the best of our knowledge, we are the first to study the large-scale news reporting citation graph in-depth. We also propose new ways to measure the aggressiveness of advertisements and identify social bots, establishing a connection between both types of bad behavior. (iii) Analyzing the effect of media source bias and significance. We prove that news sources cite others despite different political views in accord with quality measures. However, in four English-speaking countries (US, UK, Canada, and Australia), the highest ranking sources all disproportionately favor left-wing parties, even when the majority of news sources exhibited conservative slants. |
| Tasks | |
| Published | 2019-03-18 |
| URL | https://arxiv.org/abs/1903.07581v2 |
| https://arxiv.org/pdf/1903.07581v2.pdf | |
| PWC | https://paperswithcode.com/paper/mediarank-computational-ranking-of-online |
| Repo | |
| Framework | |
A Comprehensive Analysis of 2D&3D Video Watching of EEG Signals by Increasing PLSR and SVM Classification Results
| Title | A Comprehensive Analysis of 2D&3D Video Watching of EEG Signals by Increasing PLSR and SVM Classification Results |
| Authors | Negin Manshouri, Temel Kayikcioglu |
| Abstract | Despite the development of two and three dimensional (2D&3D) technology, it has attracted the attention of researchers in recent years. This research is done to reveal the detailed effects of 2D in comparison with 3D technology on the human brain waves. The impact of 2D&3D video watching using electroencephalography (EEG) brain signals is studied. A group of eight healthy volunteers with the average age of 31+-3.06 years old participated in this three-stage test. EEG signal recording consisted of three stages: After a bit of relaxation (a), a 2D video was displayed (b), the recording of the signal continued for a short period of time as rest (c), and finally the trial ended. Exactly the same steps were repeated for the 3D video. Power spectrum density (PSD) based on short time Fourier transform (STFT) was used to analyze the brain signals of 2D&3D video viewers. After testing all the EEG frequency bands, delta and theta were extracted as the features. Partial least squares regression (PLSR) and Support vector machine (SVM) classification algorithms were considered in order to classify EEG signals obtained as the result of 2D&3D video watching. Successful classification results were obtained by selecting the correct combinations of effective channels representing the brain regions. |
| Tasks | EEG |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05636v1 |
| http://arxiv.org/pdf/1903.05636v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-analysis-of-2d3d-video |
| Repo | |
| Framework | |
