Additional Features Research Articles

Enhancing Runoff Simulation Using BTOP-LSTM Hybrid Model in the Shinano River Basin

Runoff simulation is an ongoing challenge in the field of hydrology. Process-based (PB) hydrological models often gain unsatisfactory simulation accuracy due to incomplete physical process representations. While the deep learning (DL) models demonstrate their capacity to grasp intricate hydrological response processes, they still face constraints pertaining to the representative training data and comprehensive hydrological observations. In order to provide unobservable hydrological variables from the PB model to the DL model, this study constructed hybrid models by feeding the output variables of the PB model (BTOP) into the DL model (LSTM) as additional input features. These variables underwent feature dimensionality reduction using the feature selection method (Pearson Correlation Coefficient, PCC) and the feature extraction method (Principal Component Analysis, PCA) before input into LSTM. The results showed that the standalone LSTM performed well across the basin, with NSE values all exceeding 0.70. The hybrid models enhanced the simulation performance of the standalone LSTM. The NSE values increased from 0.75 to nearly 0.80 in a sub-basin. Lastly, if the BTOP output is directly fed into LSTM without feature dimensionality reduction, the model’s accuracy significantly decreases due to noise interference. The NSE value decreased by 0.09 compared to the standalone LSTM in a sub-basin. The results demonstrated the effectiveness of PCC and PCA in removing redundant information within hydrological variables. These findings provide new insights into incorporating physical information into LSTM and constructing hybrid models.

Метод двухэтапной нечеткой кластеризации инцидентов кибербезопасности для субъектов экономической деятельности

The work is aimed at improving the efficiency of cybersecurity management (­CS) of economic entities (­SED) by organizing effective ­CB monitoring, taking into account such features of its process as the heterogeneity of sources of initial ­CB monitoring data, their presentation in different data formats, their inaccuracy, and largely uncertainty and noisiness, as well as a large number of ­KB events processed by heterogeneous components of the ­ERMS ­KB monitoring system. In this paper, in contrast to existing methods, a complex two-stage method for fuzzy clustering of ­SI events is proposed, taking into account the assessment of the criticality of ­SI events and the functionality of the ­ES ­IS monitoring system. At the first stage, the ­KB event clustering model based on the fuzzy c-means method is used. This model allows splitting the set of ­CI events into several fuzzy clusters according to the a priori probability that the ­CI event is an incident. At the second stage, to refine the results of the clustering of ­SI events obtained at the first stage, the model of clustering of ­SI incidents based on the method of extracting α-kernels of fuzzy clusters is used. This model allows you to manually select the thresholds for the degree of belonging of ­SI incidents to fuzzy clusters, taking into account additional information and features of processing ­SI incidents in the ­SI monitoring system of a particular ­EDMS. The paper evaluates the effectiveness of the two-stage method of fuzzy clustering of ­KB incidents in the ­EDMS ­KB monitoring system. The proposed approach makes it possible to increase the efficiency of ­ERMS ­CM monitoring and reduce the period of time required to make a decision on the ­ERMS ­CM management due to the complex consideration of the features of ­CM event processing in the ­ERMS ­CM monitoring system.

Generic Hybrid Models for Prognostics of Complex Systems

Hybrid models combining physical knowledge and machine learning show promise for obtaining accurate and robust prognostic models. However, despite the increased interest in hybrid models in recent years, the proposed solutions tend to be domain-specific. As a result, there is no compelling strategy of what, where, and how physics-derived knowledge can be integrated into deep learning models depending on the available representation of physical knowledge and the quality of data for the development of prognostic models for complex systems. This Ph.D. project aims to develop a general strategy for hybridizing prognostic models by exploring multiple methods to incorporate physical knowledge at various stages of the learning algorithm. The project will prioritize expert knowledge as the primary source of information, while domain-specific knowledge will serve as an additional feature when applicable.

LIFANA - toward developing a meal recommender system as a dietary support app for the elderly.

Background: Though a variety of eHealth/mHealth dietary solutions exist, many are ill-adapted to the target population and local eating habits. A specific need exists for the elderly, a growing vulnerable population with limited digital literacy. The LIFANA project aimed at developing a mobile nutrition solution, i.e. a dietary meal-recommender app for personalized meal planning useful for the elderly. Methods: In addition to considering age, gender, and physical activity, the app assured sufficient intake of calories and proteins. The solution was optimized to consider local eating culture in Portugal (PT)/The Netherlands (NL) where it was tested. Recipes (>300) were included and aligned with national food composition dietary databases (FCDBs) to analyse their nutritional values for meal planning. Individual dietary preferences, food restrictions (i.e., allergies), and budget considerations were included in the user profile. The development process involved user integration, including focus groups and usability evaluations, followed by longer field trials in Portugal (n=53 participants, age 60-81y, 14 months) and the Netherlands (n=107, age 52-86y, 3 months). Endpoints regarding acceptance/usage frequency, anthropometric measures and (in PT) blood pressure and body fat were collected. Results: 23/34 elderly finalized the trials in PT/NL. No significant changes in anthropometry or other assessed markers, including blood pressure, were observed. 9% (NL) and 47% (PT) of users reported that they would consider using the solution if it were on the market. Conclusions: Via an iterative adaptive process, a dietary app was developed and improved that demonstrated acceptance/user-friendliness comparable to other tools available on the market and allowed - despite the COVID crisis - for stable anthropometric markers and blood pressure. However, it was also observed that additional features, such as a link to an online shopping app, and closer personal follow-up was associated with increased usability and acceptance of the solution and thus further personalization and nudges are warranted to increase employment of such dietary apps.

Linear Fractals with Weights

Linear fractals associated with weights are investigated. Such fractals are important from a conservation law perspective that is relevant in a variety of physical systems such as materials science, sand dune fractals, barred galaxies, as well as in temporal processes like in the electroencephalogram (EEG). The weight associated with fractals is an additional feature that may be associated with distributions consistent with the ubiquitous power law and the first digit phenomenon. These distributions form a bridge to processes and applications in natural, biological, and engineering systems and, therefore, open up the possibility of the application of linear weighted fractals to these subjects. Two linear fractal algorithms that are near optimal in the information theoretic sense are described. A mechanism for the emergence of these fractals is proposed: it is the indistinguishability amongst the particles in the evolution and transformation of physical systems. Since the fractal approach is an established method of signal processing and coding, the newly proposed weighted fractals have the potential to lead to new useful algorithms.

Impact on splicing in Saccharomyces cerevisiae of random 50-base sequences inserted into an intron.

Intron splicing is a key regulatory step in gene expression in eukaryotes. Three sequence elements required for splicing-5' and 3' splice sites and a branchpoint-are especially well-characterized in Saccharomyces cerevisiae, but our understanding of additional intron features that impact splicing in this organism is incomplete, due largely to its small number of introns. To overcome this limitation, we constructed a library in S. cerevisiae of random 50-nt (N50) elements individually inserted into the intron of a reporter gene and quantified canonical splicing and the use of cryptic splice sites by sequencing analysis. More than 70% of approximately 140,000 N50 elements reduced splicing by at least 20%. N50 features, including higher GC content, presence of GU repeats, and stronger predicted secondary structure of its pre-mRNA, correlated with reduced splicing efficiency. A likely basis for the reduced splicing of such a large proportion of variants is the formation of RNA structures that pair N50 bases-such as the GU repeats-with other bases specifically within the reporter pre-mRNA analyzed. However, multiple models were unable to explain more than a small fraction of the variance in splicing efficiency across the library, suggesting that complex nonlinear interactions in RNA structures are not accurately captured by RNA structure prediction methods. Our results imply that the specific context of a pre-mRNA may determine the bases allowable in an intron to prevent secondary structures that reduce splicing. This large data set can serve as a resource for further exploration of splicing mechanisms.

Specifics of objectification of the social exclusion, social inclusion categories (territorial aspect) in German

The article deals with specific features of objectification in German related to the categories of social exclusion and social inclusion in the territorial aspect on the example of the concepts «Kaff» and «Einöde». As a result of the definitional analysis of the similar lexemes, denoting these concepts, the author establishes nuclear semantic features – the absence of appropriate social conditions, low-population density area /uninhabited area (Einöde) and its small length, aimlessness of the subject’s existence (Kaff). These notions are described as the semantic field. The study found that the core of the semantic fields of the concepts «Einöde» and «Kaff» are the linguistic units directly indicating the nuclear semantic features and the periphery – the units actualizing the processes of social exclusion and in separate (rare) cases of social inclusion. The author identifies the units expressing spatial remoteness from the center, as well as static, absence of movement, changes as common leading language means expressing the category of social exclusion; as different – the units indicating a small spatial extent, verbs of socially determined movement with certain efforts of the subject (semantic field «Kaff»); verbs of unnoticed, aimless existence of the subject within the given object (semantic field «Einöde»).The results of the research suggest that the lexeme Kaff to a greater extent as compared to the lexeme Einöde objectifies the processes of territorial social exclusion in the context. The author notes that the language units Kaff and Einöde do not have unambiguous equivalents in Russian. As a result of the contextual analysis the author reveals additional semantic features, specifying these concepts, which are not reflected in the glossary of the German language.

Open-source MBSE workflow for automated spacecraft thermal analyses from a system model IAC-22,D1,4B,2,x70017

Model-based systems engineering (MBSE) is an emerging methodology not only in the field of spacecraft systems engineering. The key objective is to store the whole system design in one single source of truth system model. The continuously maintained and customizable open-source MBSE tool Virtual Satellite developed by German Aerospace Center (DLR) offers a framework for storing such a system model. Since the open-source 3D computer aided design (CAD) software FreeCAD has a dedicated Virtual Satellite workbench for importing the 3D model file generated by Virtual Satellite, it is possible to export the 3D model from Virtual Satellite, apply changes to it in FreeCAD, and afterwards reimport it in Virtual Satellite. This paper presents a workflow implementation to conduct automated steady-state and transient thermal analyses using the Virtual Satellite system model as a basis, utilizing the aforementioned features. Part of this effort was to extend Virtual Satellite by thermal modeling capabilities, such as material parameters, surface characteristics, thermal interfaces, boundary conditions and further relevant aspects. With custom Java applications, so-called “Apps”, all aspects of the system model relevant for a thermal analysis are exported from Virtual Satellite and written to accordingly generated text files. Moreover, the before described 3D model export is used to export the model to FreeCAD. The FreeCAD Python console, in combination with the finite element method (FEM) workbench, is used to create a script that executes meshing, application of the boundary and initial conditions, as well as identification of contacts between parts and application of the specified contact conductance values. The obtained files form a complete thermal model and can be fed directly into the open-source FEM software CalculiX for executing the thermal analysis. Then, the result can be processed by an additional Virtual Satellite App. To account for the space thermal environment an additional feature was added to the FreeCAD script. The feature uses orbit information obtained from external mission analysis tools to calculate the approximate combined heat load from Sun, Earth infrared, and albedo radiation at each time point in the specified simulation time interval. This new workflow allows to execute quick thermal analyses at an early design stage and therefore opens new opportunities in the evaluation of different system designs, as early as in a concurrent engineering study. Configuration parameters are provided that also allow more sophisticated analyses in later development phases, such as custom mesh definition and local mesh refinement.

Chart features, data quality, and scale in cartographic sounding selection from composite bathymetric data

ABSTRACT Cartographic sounding selection is a constraint-based bathymetric generalization process for identifying navigationally relevant soundings for nautical chart display. Electronic Navigational Charts (ENCs) are the premier maritime navigation medium and are produced according to international standards and distributed around the world. Cartographic generalization for ENCs is a major bottleneck in the chart creation and update process, where high volumes of data collected from constantly changing seafloor topographies require tedious examination. Moreover, these data are provided by multiple sources from various collection platforms at different levels of quality, further complicating the generalization process. Therefore, in this work, a comprehensive sounding selection algorithm is presented that focuses on safe navigation, leveraging both the Digital Surface Model (DSM) of multi-source bathymetry and the cartographic portrayal of the ENC. A taxonomy and hierarchy of soundings found on ENCs are defined and methods to identify these soundings are employed. Furthermore, the significant impact of depth contour generalization on sounding selection distribution is explored. Incorporating additional ENC bathymetric features (rocks, wrecks, and obstructions) affecting sounding distribution, calculating metrics from current chart products, and introducing procedures to correct cartographic constraint violations ensures a shoal-bias and mariner-readable output. This results in a selection that is near navigationally ready and complementary to the specific waterways of the area, contributing to the complete automation of the ENC creation and update process for safer maritime navigation.

Bike sharing and cable car demand forecasting using machine learning and deep learning multivariate time series approaches

In this paper the performance of different Machine Learning and Deep Learning approaches is evaluated in problems related to green mobility in big cities. Specifically, the forecasting of bike sharing demand in Madrid and Barcelona (Spain) is approached, for different prediction time-horizons, and also a problem of cable car demand forecasting in Madrid city. An important number of predictive variables are considered, which are grouped into four different sets (categorical/calendrical, persistence-based, meteorological and, as a novelty of the paper, information about analogue past instances), whose relevance is studied for all cases. A feature selection mechanism is also incorporated in order to improve the prediction accuracy of the proposed algorithms. A total of 12 different multivariate regression techniques are implemented, covering from Machine Learning methods to time-series Deep Learning approaches. Excellent results in all the prediction problems approached are reported. Finally, the consequences of obtaining accurate prediction in these three problem of green mobility in big cities are discussed. In addition, it is studied how the results could be exported to other similar cases in more general urban mobility studies. Novelties of the work include: (1) Addressing the forecast problem of passenger flow on a cable car using ML and DL multivariate techniques; (2) using the demand of analogous past instances as an additional feature to solve the demand prediction problems; and (3) the extraction of global conclusions about feature relevance when addressing a demand forecasting problem in green mobility.

Depletion Calculations for an Integral Small Molten Salt Reactor With Serpent

Abstract The molten salt reactor (MSR) concept is among the Generation IV designs considered feasible for providing clean, safe, sustainable, and economical energy supplies to the world's population. The depletion of fuel for a small modular fluoride molten salt reactor (sm-FMSR) with a closed fuel cycle based on the integral molten salt reactor concept has been investigated using Serpent. The Monte Carlo transport code Serpent has burnup capability and flow features that can be used to model fuel circulation and online fuel addition in an MSR. Three fueling schemes to control Serpent depletion cycles have been simulated and compared: step fueling (SF), continuous fueling with all fission products (FPs) accumulating in the reactor system (CFA), and continuous fueling with insoluble FPs separated from fuel (CFS). CFA and CFS require fewer depletion cycles that are longer in duration than the cycles required by SF, in order to maintain the effective multiplication factor (keff) within a working range over the seven years of the reactor fuel cycle. sm-FMSRs with SF and with CFA require similar quantities of “top-up” fuel, consume similar fuel (fissile) amounts, and result in similar fuel isotopic concentrations if keff is kept within a similar range. However, with separation of insoluble FPs from the circulating fuel, CFS gains a large reactivity worth due to the removal of FP poisons. This allows for reduction of fuel enrichment in both initial and total top-up fuel and leads to savings of a considerable fissile quantity in fueling MSR and in spent fuel. The Serpent depletion calculations require manual arithmetic calculations for adjustment of the Serpent built-in settings before the start of every calculation cycle for all three fueling schemes. Implementation of additional Serpent flow features in changing material volumes and flow constants would facilitate the simulation of the fuel depletion process and allow for more realistic simulations of fuel circulation.

A Screening Platform for Hearing Loss and Cognitive Decline: WHISPER (Widespread Hearing Impairment Screening and PrEvention of Risk).

The WHISPER (Widespread Hearing Impairment Screening and PrEvention of Risk) platform was recently developed for screening for hearing loss (HL) and cognitive decline in adults. It includes a battery of tests (a risk factors (RF) questionnaire, a language-independent speech-in-noise test, and cognitive tests) and provides a pass/fail outcome based on the analysis of several features. Earlier studies demonstrated high accuracy of the speech-in-noise test for predicting HL in 350 participants. In this study, preliminary results from the RF questionnaire (137 participants) and from the visual digit span test (DST) (78 participants) are presented. Despite the relatively small sample size, these findings indicate that the RF and DST may provide additional features that could be useful to characterize the overall individual profile, providing additional knowledge related to short-term memory performance and overall risk of HL and cognitive decline. Future research is needed to expand number of subjects tested, number of features analyzed, and the range of algorithms (including supervised and unsupervised machine learning) used to identify novel measures able to predict the individual hearing and cognitive abilities, also including components related to the individual risk.

Modeling aircraft similarity with musical auditory feature extraction

The increased use of unmanned aircraft systems for drone delivery and air taxis means the psychological effects of these systems (annoyance and perception) must be considered. Though aircraft perception is frequently evaluated with simple level-based metrics, higher level cognitive processes such as classification, identification, and localization benefit from additional signal features. To explore other non-level metrics, a pair-wise similarity experiment with four categories of sounds (including non-aircraft, rotorcraft, jets, and propeller aircraft) was performed by a panel of participants. These similarity ratings were decomposed into a timbre space using a two dimensional multidimensional scaling (MDS) analysis. This approach provided groupings that served as the baseline data for machine learning models to extract dominant features required to categorize aircraft signals. To model human responses, a musical feature extraction toolbox was used to obtain a set of audio attributes from the signals. These features were passed through a random decision forest, coupled with recursive feature elimination. The strength of this model is that it uses a data-driven approach to determine the appropriate mixture of waveform (or envelope) and spectral attributes that best capture participants' judgments. The model was validated by introducing a set of signals not presented to the participants, which were successfully placed in the timbre space corresponding to the correct category.

ChatGPT on guidelines: Providing contextual knowledge to GPT allows it to provide advice on appropriate colonoscopy intervals.

Colonoscopy is commonly used in screening and surveillance for colorectal cancer. Multiple different guidelines provide recommendations on the interval between colonoscopies. This can be challenging for non-specialist healthcare providers to navigate. Large language models like ChatGPT are a potential tool for parsing patient histories and providing advice. However, the standard GPT model is not designed for medical use and can hallucinate. One way to overcome these challenges is to provide contextual information with medical guidelines to help the model respond accurately to queries. Our study compares the standard GPT4 against a contextualized model provided with relevant screening guidelines. We evaluated whether the models could provide correct advice for screening and surveillance intervals for colonoscopy. Relevant guidelines pertaining to colorectal cancer screening and surveillance were formulated into a knowledge base for GPT. We tested 62 example case scenarios (three times each) on standard GPT4 and on a contextualized model with the knowledge base. The contextualized GPT4 model outperformed the standard GPT4 in all domains. No high-risk features were missed, and only two cases had hallucination of additional high-risk features. A correct interval to colonoscopy was provided in the majority of cases. Guidelines were appropriately cited in almost all cases. A contextualized GPT4 model could identify high-risk features and quote appropriate guidelines without significant hallucination. It gave a correct interval to the next colonoscopy in the majority of cases. This provides proof of concept that ChatGPT with appropriate refinement can serve as an accurate physician assistant.

Spectroscopically dark phosphate features revealed by chemical exchange saturation transfer.

Phosphate is an essential anion in the human body, comprising approximately 1% of the total body weight, and playing a vital role in metabolism, cell membranes, and bone formation. We have recently provided spectroscopic, microscopic, and computational evidence indicating that phosphates can aggregate much more readily in solution than previously thought. This prior work provided indirect evidence through the observation of unusual P NMR relaxation and line-broadening effects with increasing temperature. Here, we show that, under conditions of slow exchange and selective RF saturation, additional features become visible in chemical exchange saturation transfer (CEST) experiments, which appear to be related to the previously reported phosphate clustering. In particular, CEST shows pronounced dips several ppm upfield of the main phosphate resonance at low temperatures, while direct P spectroscopy does not produce any signals in that range. We study the pH dependence of these new spectroscopic features and present exchange and spectroscopic parameters based on fitting the CEST data. These findings could be of importance in the investigation of phosphate dynamics, especially in the biological milieu.

Determining epitope specificity of T-cell receptors with transformers.

T-cell receptors (TCRs) on T cells recognize and bind to epitopes presented by the major histocompatibility complex in case of an infection or cancer. However, the high diversity of TCRs, as well as their unique and complex binding mechanisms underlying epitope recognition, make it difficult to predict the binding between TCRs and epitopes. Here, we present the utility of transformers, a deep learning strategy that incorporates an attention mechanism that learns the informative features, and show that these models pre-trained on a large set of protein sequences outperform current strategies. We compared three pre-trained auto-encoder transformer models (ProtBERT, ProtAlbert, and ProtElectra) and one pre-trained auto-regressive transformer model (ProtXLNet) to predict the binding specificity of TCRs to 25 epitopes from the VDJdb database (human and murine). Two additional modifications were performed to incorporate gene usage of the TCRs in the four transformer models. Of all 12 transformer implementations (four models with three different modifications), a modified version of the ProtXLNet model could predict TCR-epitope pairs with the highest accuracy (weighted F1 score 0.55 simultaneously considering all 25 epitopes). The modification included additional features representing the gene names for the TCRs. We also showed that the basic implementation of transformers outperformed the previously available methods, i.e. TCRGP, TCRdist, and DeepTCR, developed for the same biological problem, especially for the hard-to-classify labels. We show that the proficiency of transformers in attention learning can be made operational in a complex biological setting like TCR binding prediction. Further ingenuity in utilizing the full potential of transformers, either through attention head visualization or introducing additional features, can extend T-cell research avenues. Data and code are available on https://github.com/InduKhatri/tcrformer.

Joint Representation Learning with Generative Adversarial Imputation Network for Improved Classification of Longitudinal Data

Generative adversarial networks (GANs) have demonstrated their effectiveness in generating temporal data to fill in missing values, enhancing the classification performance of time series data. Longitudinal datasets encompass multivariate time series data with additional static features that contribute to sample variability over time. These datasets often encounter missing values due to factors such as irregular sampling. However, existing GAN-based imputation methods that address this type of data missingness often overlook the impact of static features on temporal observations and classification outcomes. This paper presents a novel method, fusion-aided imputer-classifier GAN (FaIC-GAN), tailored for longitudinal data classification. FaIC-GAN simultaneously leverages partially observed temporal data and static features to enhance imputation and classification learning. We present four multimodal fusion strategies that effectively extract correlated information from both static and temporal modalities. Our extensive experiments reveal that FaIC-GAN successfully exploits partially observed temporal data and static features, resulting in improved classification accuracy compared to unimodal models. Our post-additive and attention-based multimodal fusion approaches within the FaIC-GAN model consistently rank among the top three methods for classification.

A genotype-phenotype correlation in split-hand/foot malformation type 1: further refinement of the phenotypic subregions within the 7q21.3 locus.

Background: Split-hand/foot malformation type 1 (SHFM1) refers to the group of rare congenital limb disorders defined by the absence or hypoplasia of the central rays of the autopods with or without accompanying anomalies, such as hearing loss, craniofacial malformation, and ectodermal dysplasia. Consequently, the condition is characterized by clinical variability that hinders diagnostic and counseling procedures. SHFM1 is caused by pathogenic variants affecting the DLX5/6 genes and/or their tissue-specific enhancers at the 7q21.3 locus. Herein, we report on seven patients from five unrelated Polish families affected by variable symptoms of the SHFM1 spectrum, all harboring 7q21.3 or 7q21.2-q21.3 rearrangements, and provide a genotype-phenotype correlation in the studied cohort. Methods: We applied GTG banding, array-based comparative genomic hybridization (aCGH), and whole-genome sequencing (WGS) in order to identify the causative aberrations in all affected patients. Results: The identified pathogenic structural variants included deletions and/or translocations involving the 7q21.3 locus, i.e., t(7;10)(q21.3;q22.2) and t(7;12)(q21.3;q21.2) in all affected individuals. Interestingly, a sporadic carrier of the latter aberration presented the SHFM1 phenotype with additional features overlapping with Baker-Gordon syndrome (BAGOS), which resulted from the translocation breakpoint at chromosome 12 within the SYT1 gene. Conclusion: Clinical variability of the studied cohort reflects the composition of the DLX5/6 regulatory elements that were dislocated from their target genes by chromosomal rearrangements. The correlation of our data with the previously published observations enabled us to update the phenotypic subregions and regulatory units within the SHFM1 locus. In addition, we present the first case of SHFM1 and BAGOS-like phenotype that resulted from translocation breakpoints at chromosomes 7 and 12, both of which were pathogenic, and consequently, we show the first evidence that BAGOS can also result from the regulatory loss-of-function SYT1 mutations. In this paper, we emphasize the utility of sequence-based approaches in molecular diagnostics of disorders caused by regulatory structural variants.

Colossal Trajectory Mining: A unifying approach to mine behavioral mobility patterns

Spatio-temporal mobility patterns are at the core of strategic applications such as urban planning and monitoring. Depending on the strength of spatio-temporal constraints, different mobility patterns can be defined. While existing approaches work well in the extraction of groups of objects sharing fine-grained paths, the huge volume of large-scale data asks for coarse-grained solutions. In this paper, we introduce Colossal Trajectory Mining (CTM) to efficiently extract heterogeneous mobility patterns out of a multidimensional space that, along with space and time dimensions, can consider additional trajectory features (e.g., means of transport or activity) to characterize behavioral mobility patterns. The algorithm is natively designed in a distributed fashion, and the experimental evaluation shows its scalability with respect to the involved features and the cardinality of the trajectory dataset.

A novel self-adaptive multi-population quadratic approximation guided jaya for solving real-parameter constrained optimization problems

Despite the inherent stability of Quadratic Approximation based Jaya (JaQA) in solving constrained optimization problems, its effectiveness in exploring the search space is limited. Furthermore, the user-defined penalty parameter utilized to mitigate constraint violation poses another impediment to the efficiency of JaQA. In light of these drawbacks, this paper introduces a new meta-heuristic algorithm, namely Self-adaptive Multi-population Quadratic Approximation guided Jaya (SMP-JaQA). The three additional key features of the SMP-JaQA over JaQA are (i) the inclusion of a multi-population technique to ensure sufficient diversity in the search process (to address the exploration), (ii) a self-adaptation strategy to make it more user-friendly for complex problems in various domains (to address the exploration further), and (iii) a dynamic penalty factor (to automate the penalty parameter). These novel changes help strike a balance between exploration and exploitation too by identifying potential areas in the search space and reduces the likelihood of getting stuck in a local optima. The validity of SMP-JaQA is tested over 18 and 28 benchmark functions of varying dimensions from the CEC-2010 and CEC-2017 test suites, respectively. In order to justify the wide applicability of the proposed algorithm, a set of four real-life constrained problems (includes two mechanical design problems, an electronics design problem and an agricultural problem) are being solved through SMP-JaQA. A thorough analysis of computational outcomes, exploration–exploitation phases, and scalability are presented to shed light on the efficacy and stability levels of SMP-JaQA. The results are compared with those of other state-of-the-art meta-heuristics using Friedman's and Wilcoxon Signed-Rank tests. The outcomes indicate that SMP-JaQA produces reasonable solutions in terms of global optimality and solution quality.