The ability to explain in understandable terms, why a machine learning model makes certain prediction is becoming immensely important, as it ensures trust and transparency the decision process of model. Complex models, such ensemble or deep are hard interpret. Various methods have been proposed that deal with this matter. Shapley values provide accurate explanations, they assign each feature an importance value for particular prediction. However, exponential complexity their calculation...

The topic of this paper is the exploration various characteristics wavelet tree data structure, a structure that was initially proposed for text compression applications but has found plethora other uses in indexing and retrieval. Issues concerning efficient maintenance plus its handling are explored. Our main aim to provide computer science researchers would like explore specific area, an up-to-date comprehensive material covering wide range applications. This kind survey missing from...

This work proposes a methodology for source code quality and static behaviour evaluation of software system, based on the standard ISO/IEC-9126.It uses elements automatically derived from enhanced with expert knowledge in form characteristic rankings, allowing engineers to assign weights attributes.It is flexible terms set metrics attributes employed, even ISO/IEC-9126 characteristics be assessed.We applied two case studies, involving five open one proprietary system.Results demonstrated...

The identification of influential users in social media communities has been recently major concern, since these can contribute to viral marketing campaigns. In our approach we extend the notion influence from networks and consider personality as a key characteristic for identifying networks. We describe Twitter Personality based Influential Communities Extraction (T-PICE) system that creates best network graph considering users' personality. then expand existing approaches extraction by...

The high costs of acquiring and maintaining high-performance computing (HPC) resources pose significant barriers for medium-sized enterprises educational institutions, often forcing them to rely on expensive cloud-based solutions with recurring costs. This paper introduces CommC, a multi-purpose commodity hardware cluster designed reduce operational expenses extend lifespan by repurposing underutilized resources. By integrating virtualization (KVM Proxmox) containerization (Kubernetes...

The identification of social media communities has recently been major concern, since users participating in such can contribute to viral marketing campaigns. In this work, we focus on users' communication considering personality as a key characteristic for identifying communicative networks i.e., with high information flows. We describe the Twitter Personality based Communicative Communities Extraction (T-PCCE) system that identifies most network graph personality. then expand existing...

In this paper we introduce the Weighted Suffix Tree, an efficient data structure for computing string regularities in weighted sequences of molecular data. Molecular Sequences can model important biological processes such as DNA Assembly Process or DNA-Protein Binding Process. Thus pattern matching identification repeated patterns, is a very procedure translation gene expression and regulation. We present time space algorithms constructing suffix tree some applications proposed to problems...

During the past few years, pharmacophore modeling has become one of key components in computer-aided drug design and modern discovery. DrugOn is a fully interactive pipeline designed to exploit advantages programming overcome command line barrier with two friendly environments for user (either novice or experienced field Computer Aided Drug Design) perform through an efficient combination PharmACOphore, Gromacs, Ligbuilder PDB2PQR suites. Our platform features novel workflow that guides each...

Automated retina vessel segmentation of the human eye plays a vital role as it can significantly assist ophthalmologists in identifying many diseases, such diabetes, stroke, arteriosclerosis, cardiovascular disease, and other illnesses. The fast, automatic accurate eyes is very desirable. This paper introduces novel fully convolutional autoencoder for task. proposed model consists eight layers, each consisting convolutional2D MaxPooling Batch Normalisation layers more. Our has been trained...

In this paper we propose a unified clustering algorithm for both homogeneous and heterogeneous XML documents. Depending on the type of documents, proposed modifies its distance metric in order to properly adapt special structural characteristics We compare quality formed clusters with those one latest algorithms show that our outperforms it case

Over the last years, advent of social networks has changed way human communication giving users ability to express their thoughts and opinions. In this paper, we present a work on analyzing interaction in Twitter. The aim is get indicative factors about user's behavior as well public stance attitude towards various events around globe. methodology initially analyzes users' tweets determines emotional content based Ekman scale. Then, characteristics Twitter are analyzed influence network...

Presently, due to the extended availability of gigantic information networks and beneficial application graph analysis in various scientific fields, necessity for efficient highly scalable community detection algorithms has never been more essential. Despite significant amount published research, existing methods—such as Girvan–Newman, random-walk edge betweenness, vertex centrality, InfoMap, spectral clustering, etc.—have virtually proven incapable handling real-life social graphs intrinsic...