Failure prediction using personalized models and an application to heart failure prediction

Background

To reduce disruptions of processes and the cost of maintenance, predicting the onset of failure (or a similar event) of a physical system (or components of a physical system) has become important. Prediction of onset of failure would allow appropriate corrective actions at the right time. In this paper, we present a method to predict the “onset” of failure (the start of a degradation process or similar types of events) of a physical system that minimizes data collection and personalizes it for the physical system. The method applies to situations where one monitors the operating characteristics of the physical system at regular time intervals by means of attached sensors and other measurement instruments. It creates a model of the physical system, during normal operations, using the time-series data produced by the sensors and measurement instruments. However, it does not create or use any time-series models. It simply examines the distribution of time-series data across different time periods. It uses this model of normal operations in subsequent time periods to monitor the physical system for deviations from normality.

Results

We illustrate this method with an application to predict the “onset” of subsequent decompensated heart failures for patients already treated for a heart failure at a hospital. As part of an NIH study, these heart failure patients received two ECG patches, an accelerometer and a bio-impedance measurement device for regular monitoring for a period after their release from the hospital.

Conclusions

When dealing with non-homogenous, disparate physical systems, personalized models can be better predictors of a phenomenon compared to generalized models based on data collected from an assortment of such physical systems. In medicine such models can be a powerful addition to the set of medical diagnostic tools. And such personalized models can be built rather quickly without waiting for extensive data collection.

Six reference-quality genomes reveal evolution of bat adaptations

Bats possess extraordinary adaptations, including flight, echolocation, extreme longevity and unique immunity. High-quality genomes are crucial for understanding the molecular basis and evolution of these traits. Here we incorporated long-read sequencing and state-of-the-art scaffolding protocols1 to generate, to our knowledge, the first reference-quality genomes of six bat species (Rhinolophus ferrumequinum, Rousettus aegyptiacus, Phyllostomus discolor, Myotis myotis, Pipistrellus kuhlii and Molossus molossus). We integrated gene projections from our 'Tool to infer Orthologs from Genome Alignments' (TOGA) software with de novo and homology gene predictions as well as short- and long-read transcriptomics to generate highly complete gene annotations. To resolve the phylogenetic position of bats within Laurasiatheria, we applied several phylogenetic methods to comprehensive sets of orthologous protein-coding and noncoding regions of the genome, and identified a basal origin for bats within Scrotifera. Our genome-wide screens revealed positive selection on hearing-related genes in the ancestral branch of bats, which is indicative of laryngeal echolocation being an ancestral trait in this clade. We found selection and loss of immunity-related genes (including pro-inflammatory NF-κB regulators) and expansions of anti-viral APOBEC3 genes, which highlights molecular mechanisms that may contribute to the exceptional immunity of bats. Genomic integrations of diverse viruses provide a genomic record of historical tolerance to viral infection in bats. Finally, we found and experimentally validated bat-specific variation in microRNAs, which may regulate bat-specific gene-expression programs. Our reference-quality bat genomes provide the resources required to uncover and validate the genomic basis of adaptations of bats, and stimulate new avenues of research that are directly relevant to human health and disease1.

Integrated Multi-Omics Analyses in Oncology: A Review of Machine Learning Methods and Tools

In recent years, high-throughput sequencing technologies provide unprecedented opportunity to depict cancer samples at multiple molecular levels. The integration and analysis of these multi-omics datasets is a crucial and critical step to gain actionable knowledge in a precision medicine framework. This paper explores recent data-driven methodologies that have been developed and applied to respond major challenges of stratified medicine in oncology, including patients' phenotyping, biomarker discovery, and drug repurposing. We systematically retrieved peer-reviewed journals published from 2014 to 2019, select and thoroughly describe the tools presenting the most promising innovations regarding the integration of heterogeneous data, the machine learning methodologies that successfully tackled the complexity of multi-omics data, and the frameworks to deliver actionable results for clinical practice. The review is organized according to the applied methods: Deep learning, Network-based methods, Clustering, Features Extraction, and Transformation, Factorization. We provide an overview of the tools available in each methodological group and underline the relationship among the different categories. Our analysis revealed how multi-omics datasets could be exploited to drive precision oncology, but also current limitations in the development of multi-omics data integration.

Machine-Learned Association of Next-Generation Sequencing-Derived Variants in Thermosensitive Ion Channels Genes with Human Thermal Pain Sensitivity Phenotypes

Genetic association studies have shown their usefulness in assessing the role of ion channels in human thermal pain perception. We used machine learning to construct a complex phenotype from pain thresholds to thermal stimuli and associate it with the genetic information derived from the next-generation sequencing (NGS) of 15 ion channel genes which are involved in thermal perception, including ASIC1, ASIC2, ASIC3, ASIC4, TRPA1, TRPC1, TRPM2, TRPM3, TRPM4, TRPM5, TRPM8, TRPV1, TRPV2, TRPV3, and TRPV4. Phenotypic information was complete in 82 subjects and NGS genotypes were available in 67 subjects. A network of artificial neurons, implemented as emergent self-organizing maps, discovered two clusters characterized by high or low pain thresholds for heat and cold pain. A total of 1071 variants were discovered in the 15 ion channel genes. After feature selection, 80 genetic variants were retained for an association analysis based on machine learning. The measured performance of machine learning-mediated phenotype assignment based on this genetic information resulted in an area under the receiver operating characteristic curve of 77.2%, justifying a phenotype classification based on the genetic information. A further item categorization finally resulted in 38 genetic variants that contributed most to the phenotype assignment. Most of them (10) belonged to the TRPV3 gene, followed by TRPM3 (6). Therefore, the analysis successfully identified the particular importance of TRPV3 and TRPM3 for an average pain phenotype defined by the sensitivity to moderate thermal stimuli.

Lifelong Machine Learning Architecture for Classification

Benefiting from the rapid development of big data and high-performance computing, more data is available and more tasks could be solved by machine learning now. Even so, it is still difficult to maximum the power of big data due to each dataset is isolated with others. Although open source datasets are available, algorithms’ performance is asymmetric with the data volume. Hence, the AI community wishes to raise a symmetric continuous learning architecture which can automatically learn and adapt to different tasks. Such a learning architecture also is commonly called as lifelong machine learning (LML). This learning paradigm could manage the learning process and accumulate meta-knowledge by itself during learning different tasks. The meta-knowledge is shared among all tasks symmetrically to help them to improve performance. With the growth of meta-knowledge, the performance of each task is expected to be better and better. In order to demonstrate the application of lifelong machine learning, this paper proposed a novel and symmetric lifelong learning approach for sentiment classification as an example to show how it adapts different domains and keeps efficiency meanwhile.

Big data, privacy and COVID-19 - learning from humanitarian expertise in data protection

The COVID-19 pandemic leads governments around the world to resort to tracking technology and other data-driven tools in order to monitor and curb the spread of SARS-CoV-2. Such large-scale incursion into privacy and data protection is unthinkable during times of normalcy. However, in times of a pandemic the use of location data provided by telecom operators and/or technology companies becomes a viable option. Importantly, legal regulations hardly protect people's privacy against governmental and corporate misuse. Established privacy regimes are focused on individual consent, and most human rights treaties know derogations from privacy and data protection norms for states of emergency. This leaves little safeguards nor remedies to guarantee individual and collective autonomy. However, the challenge of responsible data use during a crisis is not novel. The humanitarian sector has more than a decade of experience to offer. International organisations and humanitarian actors have developed detailed guidelines on how to use data responsibly under extreme circumstances. This article briefly addresses the legal gap of data protection and privacy during this global crisis. Then it outlines the state of the art in humanitarian practice and academia on data protection and data responsibility during crisis.

Efficient Training Procedures for Multi-Spectra Demosaicing

The simultaneous acquisition of multi-spectral images on a single sensor can be efficiently performed by single shot capture using a mutli-spectral filter array. This paper focused on the demosaicing of color and near-infrared bands and relied on a convolutional neural network (CNN). To train the deep learning model robustly and accurately, it is necessary to provide enough training data, with sufficient variability. We focused on the design of an efficient training procedure by discovering an optimal training dataset. We propose two data selection strategies, motivated by slightly different concepts. The general term that will be used for the proposed models trained using data selection is data selection-based multi-spectral demosaicing (DSMD). The first idea is clustering-based data selection (DSMD-C), with the goal to discover a representative subset with a high variance so as to train a robust model. The second is an adaptive-based data selection (DSMD-A), a self-guided approach that selects new data based on the current model accuracy. We performed a controlled experimental evaluation of the proposed training strategies and the results show that a careful selection of data does benefit the speed and accuracy of training. We are still able to achieve high reconstruction accuracy with a lightweight model.

Automated interpretation of the coronary angioscopy with deep convolutional neural networks

BACKGROUND

Coronary angioscopy (CAS) is a useful modality to assess atherosclerotic changes, but interpretation of the images requires expert knowledge. Deep convolutional neural networks (DCNN) can be used for diagnostic prediction and image synthesis.

METHODS

107 images from 47 patients, who underwent CAS in our hospital between 2014 and 2017, and 864 images, selected from 142 MEDLINE-indexed articles published between 2000 and 2019, were analysed. First, we developed a prediction model for the angioscopic findings. Next, we made a generative adversarial networks (GAN) model to simulate the CAS images. Finally, we tried to control the output images according to the angioscopic findings with conditional GAN architecture.

RESULTS

For both yellow colour (YC) grade and neointimal coverage (NC) grade, we could observe strong correlations between the true grades and the predicted values (YC grade, average r=0.80±0.02, p<0.001; NC grade, average r=0.73±0.02, p<0.001). The binary classification model for the red thrombus yielded 0.71±0.03 F1-score and the area under the receiver operator characteristic curve was 0.91±0.02. The standard GAN model could generate realistic CAS images (average Inception score=3.57±0.06). GAN-based data augmentation improved the performance of the prediction models. In the conditional GAN model, there were significant correlations between given values and the expert's diagnosis in YC grade but not in NC grade.

CONCLUSION

DCNN is useful in both predictive and generative modelling that can help develop the diagnostic support system for CAS.

The pan-genome effector-triggered immunity landscape of a host-pathogen interaction

Effector-triggered immunity (ETI), induced by host immune receptors in response to microbial effectors, protects plants against virulent pathogens. However, a systematic study of ETI prevalence against species-wide pathogen diversity is lacking. We constructed the Pseudomonas syringae Type III Effector Compendium (PsyTEC) to reduce the pan-genome complexity of 5127 unique effector proteins, distributed among 70 families from 494 strains, to 529 representative alleles. We screened PsyTEC on the model plant Arabidopsis thaliana and identified 59 ETI-eliciting alleles (11.2%) from 19 families (27.1%), with orthologs distributed among 96.8% of P. syringae strains. We also identified two previously undescribed host immune receptors, including CAR1, which recognizes the conserved effectors AvrE and HopAA1, and found that 94.7% of strains harbor alleles predicted to be recognized by either CAR1 or ZAR1.

Gene-Based Clustering Algorithms: Comparison Between Denclue, Fuzzy-C, and BIRCH

The current study seeks to compare 3 clustering algorithms that can be used in gene-based bioinformatics research to understand disease networks, protein-protein interaction networks, and gene expression data. Denclue, Fuzzy-C, and Balanced Iterative and Clustering using Hierarchies (BIRCH) were the 3 gene-based clustering algorithms selected. These algorithms were explored in relation to the subfield of bioinformatics that analyzes omics data, which include but are not limited to genomics, proteomics, metagenomics, transcriptomics, and metabolomics data. The objective was to compare the efficacy of the 3 algorithms and determine their strength and drawbacks. Result of the review showed that unlike Denclue and Fuzzy-C which are more efficient in handling noisy data, BIRCH can handle data set with outliers and have a better time complexity.

Regarding Smart Cities in China, the North and Emerging Economies—One Size Does Not Fit All

This article explores the significance of the “Smart city” concept by reviewing its key components, namely: Internet of Things (IoT), big (urban) data, and urban informatics/analytics, which are discussed against the background of two ongoing trends impacting everyone in the world—the Fourth Paradigm (the digital revolution) and rapid urbanization. China is seen as a great success story in the sense of how urbanization has driven a significant improvement in the economic wellbeing and prosperity of many of its citizens. Chinese expansion has come at a cost, and the question remains concerning the sustainability of the Chinese model. Along with this, the article suggests some of the short comings of the components of the Smart city concept and reflects on the human resource skills that will be required to implement Smart cities in the north. This is contrasted with the piecemeal way in which elements of the Smart city are being implemented in emerging economies. A process that very much seems to reflect fundamental technical and capacity issues that may hinder any blanket application of the Smart city in the emerging economies for a long time.

RETRACTED: A Smart Social Insurance Big Data Analytics Framework Based on Machine Learning Algorithms

Social insurance is an individual’s protection against risks such as retirement, death or disability. Big data mining and analytics are a way that could help the insurers and the actuaries to get the optimal decision for the insured individuals. Dependently, this paper proposes a novel analytic framework for Egyptian Social insurance big data. NOSI’s data contains data, which need some pre-processing methods after extraction like replacing missing values, standardization and outlier/extreme data. The paper also presents using some mining methods, such as clustering and classification algorithms on the Egyptian social insurance dataset through an experiment. In clustering, we used K-means clustering and the result showed a silhouette score 0.138 with two clusters in the dataset features. In classification, we used the Support Vector Machine (SVM) classifier and classification results showed a high accuracy percentage of 94%.

Attacker Behaviour Forecasting Using Methods of Intelligent Data Analysis: A Comparative Review and Prospects

Early detection of the security incidents and correct forecasting of the attack development is the basis for the efficient and timely response to cyber threats. The development of the attack depends on future steps available to the attackers, their goals, and their motivation—that is, the attacker “profile” that defines the malefactor behaviour in the system. Usually, the “attacker profile” is a set of attacker’s attributes—both inner such as motives and skills, and external such as existing financial support and tools used. The definition of the attacker’s profile allows determining the type of the malefactor and the complexity of the countermeasures, and may significantly simplify the attacker attribution process when investigating security incidents. The goal of the paper is to analyze existing techniques of the attacker’s behaviour, the attacker’ profile specifications, and their application for the forecasting of the attack future steps. The implemented analysis allowed outlining the main advantages and limitations of the approaches to attack forecasting and attacker’s profile constructing, existing challenges, and prospects in the area. The approach for attack forecasting implementation is suggested that specifies further research steps and is the basis for the development of an attacker behaviour forecasting technique.

Adaptive Indoor Area Localization for Perpetual Crowdsourced Data Collection

The accuracy of fingerprinting-based indoor localization correlates with the quality and up-to-dateness of collected training data. Perpetual crowdsourced data collection reduces manual labeling effort and provides a fresh data base. However, the decentralized collection comes with the cost of heterogeneous data that causes performance degradation. In settings with imperfect data, area localization can provide higher positioning guarantees than exact position estimation. Existing area localization solutions employ a static segmentation into areas that is independent of the available training data. This approach is not applicable for crowdsoucred data collection, which features an unbalanced spatial training data distribution that evolves over time. A segmentation is required that utilizes the existing training data distribution and adapts once new data is accumulated. We propose an algorithm for data-aware floor plan segmentation and a selection metric that balances expressiveness (information gain) and performance (correctly classified examples) of area classifiers. We utilize supervised machine learning, in particular, deep learning, to train the area classifiers. We demonstrate how to regularly provide an area localization model that adapts its prediction space to the accumulating training data. The resulting models are shown to provide higher reliability compared to models that pinpoint the exact position.

Soft eSkin: distributed touch sensing with harmonized energy and computing

Inspired by biology, significant advances have been made in the field of electronic skin (eSkin) or tactile skin. Many of these advances have come through mimicking the morphology of human skin and by distributing few touch sensors in an area. However, the complexity of human skin goes beyond mimicking few morphological features or using few sensors. For example, embedded computing (e.g. processing of tactile data at the point of contact) is centric to the human skin as some neuroscience studies show. Likewise, distributed cell or molecular energy is a key feature of human skin. The eSkin with such features, along with distributed and embedded sensors/electronics on soft substrates, is an interesting topic to explore. These features also make eSkin significantly different from conventional computing. For example, unlike conventional centralized computing enabled by miniaturized chips, the eSkin could be seen as a flexible and wearable large area computer with distributed sensors and harmonized energy. This paper discusses these advanced features in eSkin, particularly the distributed sensing harmoniously integrated with energy harvesters, storage devices and distributed computing to read and locally process the tactile sensory data. Rapid advances in neuromorphic hardware, flexible energy generation, energy-conscious electronics, flexible and printed electronics are also discussed. This article is part of the theme issue 'Harmonizing energy-autonomous computing and intelligence'.

Giant virus diversity and host interactions through global metagenomics

Our current knowledge about nucleocytoplasmic large DNA viruses (NCLDVs) is largely derived from viral isolates that are co-cultivated with protists and algae. Here we reconstructed 2,074 NCLDV genomes from sampling sites across the globe by building on the rapidly increasing amount of publicly available metagenome data. This led to an 11-fold increase in phylogenetic diversity and a parallel 10-fold expansion in functional diversity. Analysis of 58,023 major capsid proteins from large and giant viruses using metagenomic data revealed the global distribution patterns and cosmopolitan nature of these viruses. The discovered viral genomes encoded a wide range of proteins with putative roles in photosynthesis and diverse substrate transport processes, indicating that host reprogramming is probably a common strategy in the NCLDVs. Furthermore, inferences of horizontal gene transfer connected viral lineages to diverse eukaryotic hosts. We anticipate that the global diversity of NCLDVs that we describe here will establish giant viruses-which are associated with most major eukaryotic lineages-as important players in ecosystems across Earth's biomes.

Cyber Security: Effects of Penalizing Defenders in Cyber-Security Games via Experimentation and Computational Modeling

Cyber-attacks are deliberate attempts by adversaries to illegally access online information of other individuals or organizations. There are likely to be severe monetary consequences for organizations and its workers who face cyber-attacks. However, currently, little is known on how monetary consequences of cyber-attacks may influence the decision-making of defenders and adversaries. In this research, using a cyber-security game, we evaluate the influence of monetary penalties on decisions made by people performing in the roles of human defenders and adversaries via experimentation and computational modeling. In a laboratory experiment, participants were randomly assigned to the role of "hackers" (adversaries) or "analysts" (defenders) in a laboratory experiment across three between-subject conditions: Equal payoffs (EQP), penalizing defenders for false alarms (PDF) and penalizing defenders for misses (PDM). The PDF and PDM conditions were 10-times costlier for defender participants compared to the EQP condition, which served as a baseline. Results revealed an increase (decrease) and decrease (increase) in attack (defend) actions in the PDF and PDM conditions, respectively. Also, both attack-and-defend decisions deviated from Nash equilibriums. To understand the reasons for our results, we calibrated a model based on Instance-Based Learning Theory (IBLT) theory to the attack-and-defend decisions collected in the experiment. The model's parameters revealed an excessive reliance on recency, frequency, and variability mechanisms by both defenders and adversaries. We discuss the implications of our results to different cyber-attack situations where defenders are penalized for their misses and false-alarms.

Bacterial diversity and functional metagenomics expounding the diversity of xenobiotics, stress, defense and CRISPR gene ontology providing eco-efficiency to Himalayan Hot Springs

Sikkim is one of the bio-diverse states of India, which harbors diverse alkaline and sulfur rich hot springs in its vicinity. However, there is a dearth of data present in terms of microbial and its functional diversity as only a few hot springs have been studied in this area. Thus, in this regard, microbial and functional diversity of two hot springs by NGS, PLFA, and culture-independent approaches were carried out. PLFA and culture-dependent analysis was complementary as the Gram-positive bacteria were abundant in both the hot springs with the dominance of phylum Firmicutes with Geobacillus. Metagenomic analysis revealed the abundance of Proteobacteria, Actinobacteria, and Firmicutes in both hot springs. Functional metagenomics suggested that both Yumthang and Reshi hot spring possess a diverse set of genes analogous to stress such as genes allied to osmotic, heat shock, and acid stresses; defense analogies such as multidrug resistance efflux pump, multidrug transport system, and β-lactamase; and CRISPR analogues such as related to Cas1, Cas2, Cas3, cmr1-5 proteins, CT1972, and CT1133 gene families. The xenobiotic analogues were found against benzoate, nitrotolune, xylene, DDT, and chlorocyclohexane/chlorobenzene degradation. Thus, these defensive mechanisms against environmental and anthropogenic hiccups and hindrances provide the eco-efficiency to such thermal habitats. The higher enzymatic, degradation, defense, stress potential and the lower percentage identity (< 95%) of isolates encourage the further exploration and exploitation of these habitats for industrial and biotechnological purposes.

Requirements of Data Visualisation Tools to Analyse Big Data: A Structured Literature Review

The continual growth of big data necessitates efficient ways of analysing these large datasets. Data visualisation and visual analytics has been identified as a key tool in big data analysis because they draw on the human visual and cognitive capabilities to analyse data quickly, intuitively and interactively. However, current visualisation tools and visual analytical systems fall short of providing a seamless user experience and several improvements could be made to current commercially available visualisation tools. By conducting a systematic literature review, requirements of visualisation tools were identified and categorised into six groups: dimensionality reduction, data reduction, scalability and readability, interactivity, fast retrieval of results, and user assistance. The most common themes found in the literature were dimensionality reduction and interactive data exploration.

A Conceptual Model of the Challenges of Social Media Big Data for Citizen e-Participation: A Systematic Review

The emergence of Citizen Relationship Management (CzRM) for government plays a central role in developing citizen relationships and e-participation. As such, the South African government has shown its commitment towards citizenry and the provision of effective service delivery. Social Media Analytics (SMA) has emerged as a potential new solution to support decision-making for service delivery in CzRM. It is believed that the demand for SMA adoption will increasingly rise. However, the reality of social media Big Data comes with the challenges of analysing it in a way that brings Big Value. The purpose of this paper is to identify the challenges of social media Big Data Analytics (BDA) and to incorporate these in a conceptual model that can be used by governments to support the e-participation of citizens. The model was developed through a systematic literature review (SLR). The findings revealed that data challenges relate to designing an optimal architecture for analysing data that caters for both historic data and real-time data at the same time. The paper highlight that process challenges relate to all the activities in the data lifecycle such as data acquisition and warehousing; data mining and cleaning; data aggregation and integration; analysis and modelling; and data interpretation. The paper also identifies six types of data management challenges: privacy, security, data governance, data and information sharing, cost/operational expenditures, and data ownership.

Swarm Intelligence in Data Science: Applications, Opportunities and Challenges

The Swarm Intelligence (SI) algorithms have been proved to be a comprehensive method to solve complex optimization problems by simulating the emergence behaviors of biological swarms. Nowadays, data science is getting more and more attention, which needs quick management and analysis of massive data. Most traditional methods can only be applied to continuous and differentiable functions. As a set of population-based approaches, it is proven by some recent research works that the SI algorithms have great potential for relevant tasks in this field. In order to gather better insight into the utilization of these methods in data science and to provide a further reference for future researches, this paper focuses on the relationship between data science and swarm intelligence. After introducing the mainstream swarm intelligence algorithms and their common characteristics, both the theoretical and real-world applications in the literature which utilize the swarm intelligence to the related domains of data analytics are reviewed. Based on the summary of the existing works, this paper also analyzes the opportunities and challenges in this field, which attempts to shed some light on designing more effective algorithms to solve the problems in data science for real-world applications.

Comparing different supervised machine learning algorithms for disease prediction

Background

Supervised machine learning algorithms have been a dominant method in the data mining field. Disease prediction using health data has recently shown a potential application area for these methods. This study ai7ms to identify the key trends among different types of supervised machine learning algorithms, and their performance and usage for disease risk prediction.

Methods

In this study, extensive research efforts were made to identify those studies that applied more than one supervised machine learning algorithm on single disease prediction. Two databases (i.e., Scopus and PubMed) were searched for different types of search items. Thus, we selected 48 articles in total for the comparison among variants supervised machine learning algorithms for disease prediction.

Results

We found that the Support Vector Machine (SVM) algorithm is applied most frequently (in 29 studies) followed by the Naïve Bayes algorithm (in 23 studies). However, the Random Forest (RF) algorithm showed superior accuracy comparatively. Of the 17 studies where it was applied, RF showed the highest accuracy in 9 of them, i.e., 53%. This was followed by SVM which topped in 41% of the studies it was considered.

Conclusion

This study provides a wide overview of the relative performance of different variants of supervised machine learning algorithms for disease prediction. This important information of relative performance can be used to aid researchers in the selection of an appropriate supervised machine learning algorithm for their studies.

Current Projection Methods-Induced Biases at Subgroup Detection for Machine-Learning Based Data-Analysis of Biomedical Data

Advances in flow cytometry enable the acquisition of large and high-dimensional data sets per patient. Novel computational techniques allow the visualization of structures in these data and, finally, the identification of relevant subgroups. Correct data visualizations and projections from the high-dimensional space to the visualization plane require the correct representation of the structures in the data. This work shows that frequently used techniques are unreliable in this respect. One of the most important methods for data projection in this area is the t-distributed stochastic neighbor embedding (t-SNE). We analyzed its performance on artificial and real biomedical data sets. t-SNE introduced a cluster structure for homogeneously distributed data that did not contain any subgroup structure. In other data sets, t-SNE occasionally suggested the wrong number of subgroups or projected data points belonging to different subgroups, as if belonging to the same subgroup. As an alternative approach, emergent self-organizing maps (ESOM) were used in combination with U-matrix methods. This approach allowed the correct identification of homogeneous data while in sets containing distance or density-based subgroups structures; the number of subgroups and data point assignments were correctly displayed. The results highlight possible pitfalls in the use of a currently widely applied algorithmic technique for the detection of subgroups in high dimensional cytometric data and suggest a robust alternative.

Text Summarisation Using Laplacian Centrality-Based Minimum Vertex Cover

Outdegree Centrality (OC) is a graph-based centrality measure that captures local connectedness of a node in a graph. The measure has been used in the literature to highlight key sentences in a graph-based optimisation method for summarisation. It is observed in resultant summaries that OC tends to be biased towards selecting introductory sentences of the document producing only generic summaries. The different graph centrality measures lead to different interpretations of a summary. Therefore, the authors propose to use another suitable centrality measure in order to generate more specific summary rather than a generic summary. Such a summary is expected to be highly informative covering all the subtopics of the source document. This requirement has instigated the authors to use Laplacian Centrality (LC) measure to find the significance of the nodes. The essence of this measure lies in highlighting central nodes from subgraphs which contribute non-uniformly towards the common goal of the graph. The modified method has shown significant improvement in informativeness and coherence of summaries and outperformed state-of-the-art results.

Comparative analysis on Facebook post interaction using DNN, ELM and LSTM

This study presents a novel research approach to predict user interaction for social media post using machine learning algorithms. The posts are converted to vector form using word2vec and doc2vec model. These two methods are used to analyse the best approach for generating word embeddings. The generated word embeddings of post combined with other attributes like post published time, type of post and total interactions are used to train machine learning algorithms. Deep neural network (DNN), Extreme Learning Machine (ELM) and Long Short-Term Memory (LSTM) are used to compare the prediction of total interaction for a particular post. For word2vec, the word vectors are created using both continuous bag-of-words (CBOW) and skip-gram models. Also the pre-trained word vectors provided by google is used for the analysis. For doc2vec, the word embeddings are created using both the Distributed Memory model of Paragraph Vectors (PV-DM) and Distributed Bag of Words model of Paragraph Vectors (PV-DBOW). A word embedding is also created using PV-DBOW combined with skip-gram.

PyBDA: a command line tool for automated analysis of big biological data sets

BACKGROUND

Analysing large and high-dimensional biological data sets poses significant computational difficulties for bioinformaticians due to lack of accessible tools that scale to hundreds of millions of data points.

RESULTS

We developed a novel machine learning command line tool called PyBDA for automated, distributed analysis of big biological data sets. By using Apache Spark in the backend, PyBDA scales to data sets beyond the size of current applications. It uses Snakemake in order to automatically schedule jobs to a high-performance computing cluster. We demonstrate the utility of the software by analyzing image-based RNA interference data of 150 million single cells.

CONCLUSION

PyBDA allows automated, easy-to-use data analysis using common statistical methods and machine learning algorithms. It can be used with simple command line calls entirely making it accessible to a broad user base. PyBDA is available at https://pybda.rtfd.io.

Phylogenomics investigation of sparids (Teleostei: Spariformes) using high-quality proteomes highlights the importance of taxon sampling

Sparidae (Teleostei: Spariformes) are a family of fish constituted by approximately 150 species with high popularity and commercial value, such as porgies and seabreams. Although the phylogeny of this family has been investigated multiple times, its position among other teleost groups remains ambiguous. Most studies have used a single or few genes to decipher the phylogenetic relationships of sparids. Here, we conducted a thorough phylogenomic analysis using five recently available Sparidae gene-sets and 26 high-quality, genome-predicted teleost proteomes. Our analysis suggested that Tetraodontiformes (puffer fish, sunfish) are the closest relatives to sparids than all other groups used. By analytically comparing this result to our own previous contradicting finding, we show that this discordance is not due to different orthology assignment algorithms; on the contrary, we prove that it is caused by the increased taxon sampling of the present study, outlining the great importance of this aspect in phylogenomic analyses in general.

An Innovative Fingerprint Location Algorithm for Indoor Positioning Based on Array Pseudolite

Since the signals of the global navigation satellite system (GNSS) are blocked by buildings, accurate positioning cannot be achieved in an indoor environment. Pseudolite can simulate similar outdoor satellite signals and can be used as a stable and reliable positioning signal source in indoor environments. Therefore, it has been proposed as a good substitute and has become a research hotspot in the field of indoor positioning. There are still some problems in the pseudolite positioning field, such as: Integer ambiguity of carrier phase, initial position determination, and low signal coverage. To avoid the limitation of these factors, an indoor positioning system based on fingerprint database matching of homologous array pseudolite is proposed in this paper, which can achieve higher positioning accuracy. The realization of this positioning system mainly includes the offline phase and the online phase. In the offline phase, the carrier phase data in the indoor environment is first collected, and a fingerprint database is established. Then a variational auto-encoding (VAE) network with location information is used to learn the probability distribution characteristics of the carrier phase difference of pseudolite in the latent space to realize feature clustering. Finally, the deep neural network is constructed by using the hidden features learned to further study the mapping relationship between different carrier phases of pseudolite and different indoor locations. In the online phase, the trained model and real-time carrier phases of pseudolite are used to predict the location of the positioning terminal. In this paper, by a large number of experiments, the performance of the pseudolite positioning system is evaluated under dynamic and static conditions. The effectiveness of the algorithm is evaluated by the comparison experiments, the experimental results show that the average positioning accuracy of the positioning system in a real indoor scene is 0.39 m, and the 95% positioning error is less than 0.85 m, which outperforms the traditional fingerprint positioning algorithms.

A review of knowledge discovery process in control and mitigation of avian influenza

In the last several decades, avian influenza virus has caused numerous outbreaks around the world. These outbreaks pose a significant threat to the poultry industry and also to public health. When an avian influenza (AI) outbreak occurs, it is critical to make informed decisions about the potential risks, impact, and control measures. To this end, many modeling approaches have been proposed to acquire knowledge from different sources of data and perspectives to enhance decision making. Although some of these approaches have shown to be effective, they do not follow the process of knowledge discovery in databases (KDD). KDD is an iterative process, consisting of five steps, that aims at extracting unknown and useful information from the data. The present review attempts to survey AI modeling methods in the context of KDD process. We first divide the modeling techniques used in AI into two main categories: data-intensive modeling and small-data modeling. We then investigate the existing gaps in the literature and suggest several potential directions and techniques for future studies. Overall, this review provides insights into the control of AI in terms of the risk of introduction and spread of the virus.

Comparison of CNN Applications for RSSI-based Fingerprint Indoor Localization

The intelligent use of deep learning (DL) techniques can assist in overcoming noise and uncertainty during fingerprinting-based localization. With the rise in the available computational power on mobile devices, it is now possible to employ DL techniques, such as convolutional neural networks (CNNs), for smartphones. In this paper, we introduce a CNN model based on received signal strength indicator (RSSI) fingerprint datasets and compare it with different CNN application models, such as AlexNet, ResNet, ZFNet, Inception v3, and MobileNet v2, for indoor localization. The experimental results show that the proposed CNN model can achieve a test accuracy of 94.45% and an average location error as low as 1.44 m. Therefore, our CNN model outperforms conventional CNN applications for RSSI-based indoor positioning.

Review of Big Data and Processing Frameworks for Disaster Response Applications

Natural hazards result in devastating losses in human life, environmental assets and personal, and regional and national economies. The availability of different big data such as satellite imageries, Global Positioning System (GPS) traces, mobile Call Detail Records (CDRs), social media posts, etc., in conjunction with advances in data analytic techniques (e.g., data mining and big data processing, machine learning and deep learning) can facilitate the extraction of geospatial information that is critical for rapid and effective disaster response. However, disaster response systems development usually requires the integration of data from different sources (streaming data sources and data sources at rest) with different characteristics and types, which consequently have different processing needs. Deciding which processing framework to use for a specific big data to perform a given task is usually a challenge for researchers from the disaster management field. Therefore, this paper contributes in four aspects. Firstly, potential big data sources are described and characterized. Secondly, the big data processing frameworks are characterized and grouped based on the sources of data they handle. Then, a short description of each big data processing framework is provided and a comparison of processing frameworks in each group is carried out considering the main aspects such as computing cluster architecture, data flow, data processing model, fault-tolerance, scalability, latency, back-pressure mechanism, programming languages, and support for machine learning libraries, which are related to specific processing needs. Finally, a link between big data and processing frameworks is established, based on the processing provisioning for essential tasks in the response phase of disaster management.

A feature learning approach based on XGBoost for driving assessment and risk prediction

This study designs a framework of feature extraction and selection, to assess vehicle driving and predict risk levels. The framework integrates learning-based feature selection, unsupervised risk rating, and imbalanced data resampling. For each vehicle, about 1300 driving behaviour features are extracted from trajectory data, which produce in-depth and multi-view measures on behaviours. To estimate the risk potentials of vehicles in driving, unsupervised data labelling is proposed. Based on extracted risk indicator features, vehicles are clustered into various groups labelled with graded risk levels. Data under-sampling of the safe group is performed to reduce the risk-safe class imbalance. Afterwards, the linkages between behaviour features and corresponding risk levels are built using XGBoost, and key features are identified according to feature importance ranking and recursive elimination. The risk levels of vehicles in driving are predicted based on key features selected. As a case study, NGSIM trajectory data are used in which four risk levels are clustered by Fuzzy C-means, 64 key behaviour features are identified, and an overall accuracy of 89% is achieved for behaviour-based risk prediction. Findings show that this approach is effective and reliable to identify important features for driving assessment, and achieve an accurate prediction of risk levels.

RAFTS3G: an efficient and versatile clustering software to analyses in large protein datasets

BACKGROUND

Clustering methods are essential to partitioning biological samples being useful to minimize the information complexity in large datasets. Tools in this context usually generates data with greed algorithms that solves some Data Mining difficulties which can degrade biological relevant information during the clustering process. The lack of standardization of metrics and consistent bases also raises questions about the clustering efficiency of some methods. Benchmarks are needed to explore the full potential of clustering methods - in which alignment-free methods stand out - and the good choice of dataset makes it essentials.

RESULTS

Here we present a new approach to Data Mining in large protein sequences datasets, the Rapid Alignment Free Tool for Sequences Similarity Search to Groups (RAFTS3G), a method to clustering aiming of losing less biological information in the processes of generation groups. The strategy developed in our algorithm is optimized to be more astringent which reflects increase in accuracy and sensitivity in the generation of clusters in a wide range of similarity. RAFTS3G is the better choice compared to three main methods when the user wants more reliable result even ignoring the ideal threshold to clustering.

CONCLUSION

In general, RAFTS3G is able to group up to millions of biological sequences into large datasets, which is a remarkable option of efficiency in clustering. RAFTS3G compared to other "standard-gold" methods in the clustering of large biological data maintains the balance between the reduction of biological information redundancy and the creation of consistent groups. We bring the binary search concept applied to grouped sequences which shows maintaining sensitivity/accuracy relation and up to minimize the time of data generated with RAFTS3G process.

OrthoVenn2: a web server for whole-genome comparison and annotation of orthologous clusters across multiple species

OrthoVenn is a powerful web platform for the comparison and analysis of whole-genome orthologous clusters. Here we present an updated version, OrthoVenn2, which provides new features that facilitate the comparative analysis of orthologous clusters among up to 12 species. Additionally, this update offers improvements to data visualization and interpretation, including an occurrence pattern table for interrogating the overlap of each orthologous group for the queried species. Within the occurrence table, the functional annotations and summaries of the disjunctions and intersections of clusters between the chosen species can be displayed through an interactive Venn diagram. To facilitate a broader range of comparisons, a larger number of species, including vertebrates, metazoa, protists, fungi, plants and bacteria, have been added in OrthoVenn2. Finally, a stand-alone version is available to perform large dataset comparisons and to visualize results locally without limitation of species number. In summary, OrthoVenn2 is an efficient and user-friendly web server freely accessible at https://orthovenn2.bioinfotoolkits.net.

Learning and Searching Pseudo-Boolean Surrogate Functions from Small Samples

When searching for input configurations that optimise the output of a system, it can be useful to build a statistical model of the system being optimised. This is done in approaches such as surrogate model-based optimisation, estimation of distribution algorithms, and linkage learning algorithms. This article presents a method for modelling pseudo-Boolean fitness functions using Walsh bases and an algorithm designed to discover the non-zero coefficients while attempting to minimise the number of fitness function evaluations required. The resulting models reveal linkage structure that can be used to guide a search of the model efficiently. It presents experimental results solving benchmark problems in fewer fitness function evaluations than those reported in the literature for other search methods such as EDAs and linkage learners.

Streaming Data Fusion for the Internet of Things

To achieve the full analytical potential of the streaming data from the internet of things, the interconnection of various data sources is needed. By definition, those sources are heterogeneous and their integration is not a trivial task. A common approach to exploit streaming sensor data potential is to use machine learning techniques for predictive analytics in a way that is agnostic to the domain knowledge. Such an approach can be easily integrated in various use cases. In this paper, we propose a novel framework for data fusion of a set of heterogeneous data streams. The proposed framework enriches streaming sensor data with the contextual and historical information relevant for describing the underlying processes. The final result of the framework is a feature vector, ready to be used in a machine learning algorithm. The framework has been applied to a cloud and to an edge device. In the latter case, incremental learning capabilities have been demonstrated. The reported results illustrate a significant improvement of data-driven models, applied to sensor streams. Beside higher accuracy of the models the platform offers easy setup and thus fast prototyping capabilities in real-world applications.

A Wavelet Scattering Feature Extraction Approach for Deep Neural Network Based Indoor Fingerprinting Localization

The performance of an Artificial Neural Network (ANN)-based algorithm is subject to the way the feature data is extracted. This is a common issue when applying the ANN to indoor fingerprinting-based localization where the signal is unstable. To date, there is not adequate feature extraction method that can significantly mitigate the influence of the receiver signal strength indicator (RSSI) variation that degrades the performance of the ANN-based indoor fingerprinting algorithm. In this work, a wavelet scattering transform is used to extract reliable features that are stable to small deformation and rotation invariant. The extracted features are used by a deep neural network (DNN) model to predict the location. The zero^th and the first layer of decomposition coefficients were used as features data by concatenating different scattering path coefficients. The proposed algorithm has been validated on real measurements and has achieved good performance. The experimentation results demonstrate that the proposed feature extraction method is stable to the RSSI variation.