Search results for "methodologies"
showing 10 items of 2106 documents
CellMap visualizes protein-protein interactions and subcellular localization [version 2; referees: 2 approved]
2018
Many tools visualize protein-protein interaction (PPI) networks. The tool introduced here, CellMap, adds one crucial novelty by visualizing PPI networks in the context of subcellular localization, i.e. the location in the cell or cellular component in which a PPI happens. Users can upload images of cells and define areas of interest against which PPIs for selected proteins are displayed (by default on a cartoon of a cell). Annotations of localization are provided by the user or through our in-house database. The visualizer and server are written in JavaScript, making CellMap easy to customize and to extend by researchers and developers.
An optimization approach to segment breast lesions in ultra-sound images using clinically validated visual cues
2015
International audience; As long as breast cancer remains the leading cause of cancer deaths among female population world wide, developing tools to assist radiologists during the diagnosis process is necessary. However, most of the technologies developed in the imaging laboratories are rarely integrated in this assessing process, as they are based on information cues differing from those used by clinicians. In order to grant Computer Aided Diagnosis (CAD) systems with these information cues when performing non-aided diagnosis, better segmentation strategies are needed to automatically produce accurate delineations of the breast structures. This paper proposes a highly modular and flexible f…
Data Mining in Cancer Research [Application Notes
2010
This article is not intended as a comprehensive survey of data mining applications in cancer. Rather, it provides starting points for further, more targeted, literature searches, by embarking on a guided tour of computational intelligence applications in cancer medicine, structured in increasing order of the physical scales of biological processes.
Dynamic Integration of Classifiers in the Space of Principal Components
2003
Recent research has shown the integration of multiple classifiers to be one of the most important directions in machine learning and data mining. It was shown that, for an ensemble to be successful, it should consist of accurate and diverse base classifiers. However, it is also important that the integration procedure in the ensemble should properly utilize the ensemble diversity. In this paper, we present an algorithm for the dynamic integration of classifiers in the space of extracted features (FEDIC). It is based on the technique of dynamic integration, in which local accuracy estimates are calculated for each base classifier of an ensemble, in the neighborhood of a new instance to be pr…
Sequential Genetic Search for Ensemble Feature Selection
2005
Ensemble learning constitutes one of the main directions in machine learning and data mining. Ensembles allow us to achieve higher accuracy, which is often not achievable with single models. One technique, which proved to be effective for constructing an ensemble of diverse classifiers, is the use of feature subsets. Among different approaches to ensemble feature selection, genetic search was shown to perform best in many domains. In this paper, a new strategy GAS-SEFS, Genetic Algorithm-based Sequential Search for Ensemble Feature Selection, is introduced. Instead of one genetic process, it employs a series of processes, the goal of each of which is to build one base classifier. Experiment…
Iris : a solution for executing handwritten code
2012
Masteroppgave i informasjons- og kommunikasjonsteknologi IKT590 2012 – Universitetet i Agder, Grimstad This paper presents a novel approach to executing handwritten code, the solution coined Iris. My research falls within the field of mobile app development, handwriting recognition, optical and intelligent character recognition (OCR & ICR), machine learning, as well as various Computer Science-related fields such as domain specific languages, or DSLs. The solution outlined in this paper details a system where one can author code using only a writing utensil (such as a pen), scratch paper (such as a napkin), and a smart phone. Iris leverages the power of the cloud to process an image of hand…
Table S1 from Open data and digital morphology
2017
Summary of main online repositories for 3D digital morphological data.
Interactive Pansharpening and Active Classification in Remote Sensing
2013
This chapter presents two multimodal prototypes for remote sensing image classification where user interaction is an important part of the system. The first one applies pansharpening techniques to fuse a panchromatic image and a multispectral image of the same scene to obtain a high resolution (HR) multispectral image. Once the HR image has been classified the user can interact with the system to select a class of interest. The pansharpening parameters are then modified to increase the system accuracy for the selected class without deteriorating the performance of the classifier on the other classes. The second prototype utilizes Bayesian modeling and inference to implement active learning …
A reliable and unbiased human protein network with the disparity filter
2017
AbstractThe living cell operates thanks to an intricate network of protein interactions. Proteins activate, transport, degrade, stabilise and participate in the production of other proteins. As a result, a reliable and systematically generated protein wiring diagram is crucial for a deeper understanding of cellular functions. Unfortunately, current human protein networks are noisy and incomplete. Also, they suffer from both study and technical biases: heavily studied proteins (e.g. those of pharmaceutical interest) are known to be involved in more interactions than proteins described in only a few publications. Here, we use the experimental evidence supporting the interaction between protei…
An exploration of semi-supervised text classification
2021
Master's thesis in Information- and communication technology (IKT590) Obtaining labeled data to train natural language machine learning algorithms is often expensive and time-consuming, while unlabeled data usually is free and easy to get. Frequently a large amount of labeled data is required by supervised learning to achieve good text classification performance. Semi-supervised learning (SSL) for text classification is an exciting area of research. SSL is a technique exploiting unlabeled and labeled data to achieve better classification performance than using labeled data alone and is particularly useful with limited labeled data. This thesis explores the impact of different parameters on …