We propose a software platform that integrates methods and tools for multi-objective parameter auto-tuning in tissue image segmentation workflows. The goal of our work is to provide an approach for improving the accur...
详细信息
In large-scale learning problem, the scalability of learning algorithms is usually the key factor affecting the algorithm practical performance, which is determined by both the time complexity of the learning algorith...
详细信息
In large-scale learning problem, the scalability of learning algorithms is usually the key factor affecting the algorithm practical performance, which is determined by both the time complexity of the learning algorithms and the amount of supervision information (i.e., labeled data). Learning with label proportions (LLP) is a new kind of machine learning problem which has drawn much attention in recent years. Different from the well-known supervised learning, LLP can estimate a classifier from groups of weakly labeled data, where only the positive/negative class proportions of each group are known. Due to its weak requirements for the input data, LLP presents a variety of real-world applications in almost all the fields involving anonymous data, like computer vision, fraud detection and spam filtering. However, even through the required labeled data is of a very small amount, LLP still suffers from the long execution time a lot due to the high time complexity of the learning algorithm itself. In this paper, we propose a very fast learning method based on inversing output scaling process and extreme learning machine, namely Inverse Extreme Learning Machine (IELM), to address the above issues. IELM can speed up the training process by order of magnitudes for large datasets, while achieving highly competitive classification accuracy with the existing methods at the same time. Extensive experiments demonstrate the significant speedup of the proposed method. We also demonstrate the feasibility of IELM with a case study in real-world setting: modeling image attributes based on ImageNet Object Attributes dataset.
The 2016 edition of the Linked data Mining Challenge, conducted in conjunction with Know@LOD 2016, has been the fourth edition of this challenge. This year's dataset collected music album ratings, where the task w...
详细信息
The 2016 edition of the Linked data Mining Challenge, conducted in conjunction with Know@LOD 2016, has been the fourth edition of this challenge. This year's dataset collected music album ratings, where the task was to classify well and badly rated music albums. The best solution submitted reached an accuracy of almost 92:5%, which is a clear advancement over the baseline of 69:38%.
The Web usage mining techniques are used to scrutinize the web usage patterns for a web site. Web page prediction plays a vital role by predicting next set of web pages that a user may visit based on the knowledge of ...
详细信息
The Web usage mining techniques are used to scrutinize the web usage patterns for a web site. Web page prediction plays a vital role by predicting next set of web pages that a user may visit based on the knowledge of the previously visited pages. Web page prediction is the focus of attention of many researchers in recent times and different web page prediction frameworks have been proposed. In this paper, a comparative analysis between two different approaches of web page prediction, namely, Latest Substring Association Rule mining (LSA) and Hidden Markov Model (HMM) has been represented. Web page prediction is implemented by using both the approaches and the experimental results are provided. Finally, an improved approach for web page prediction is proposed at the end of the paper.
BACKGROUND:Copy number variants (CNVs) increase risk for neurodevelopmental conditions. The neurobiological mechanisms linking these high-risk genetic variants to clinical phenotypes are largely unknown. An important ...
详细信息
BACKGROUND:Copy number variants (CNVs) increase risk for neurodevelopmental conditions. The neurobiological mechanisms linking these high-risk genetic variants to clinical phenotypes are largely unknown. An important question is whether brain abnormalities in individuals carrying CNVs are associated with their degree of penetrance.
METHODS:We investigated if increased CNV-penetrance for schizophrenia and other developmental disorders was associated with variations in cortical and subcortical morphology. We pooled T1-weighted brain magnetic resonance imaging and genetic data from 22 cohorts from the ENIGMA-CNV consortium. In the main analyses, we included 9,268 individuals (aged 7 to 90 years, 54% females), from which we identified 398 carriers of 36 neurodevelopmental CNVs at 20 distinct loci. A secondary analysis was performed including additional neuroimaging data from the ENIGMA-22q consortium, including 274 carriers of the 22q11.2 deletion and 291 non-carriers. CNV-penetrance was estimated through penetrance scores that were previously generated from large cohorts of patients and controls. These scores represent the probability risk to develop either schizophrenia or other developmental disorders (including developmental delay, autism spectrum disorder and congenital malformations).
RESULTS:For both schizophrenia and developmental disorders, increased penetrance scores were associated with lower surface area in the cerebral cortex and lower intracranial volume. For both conditions, associations between CNV-penetrance scores and cortical surface area were strongest in regions of the occipital lobes, specifically in the cuneus and lingual gyrus.
CONCLUSIONS:Our findings link global and regional cortical morphometric features with CNV-penetrance, providing new insights into neurobiological mechanisms of genetic risk for schizophrenia and other developmental disorders.
In this talk we will present material on the semantics, computability, and algorithms for the evolution of hybrid dynamical systems, and an overview of the tool Ariadne for verification of hybrid systems [1]. Hybrid s...
详细信息
暂无评论