General Architecture Research Articles

Paleoenvironments and Sedimentation in the Southeastern Margin of Lake Pannon (Western Smederevsko Podunavlje Area, Serbia)

The Late Miocene - Pliocene Lake Pannon gradually diminished as sediments sourced from the Alps and Carpathians filled its basin and pushed its northern shoreline southward. Sedimentary successions from the southern margin of the lake SE of Belgrade (Smederevsko Podunavlje area) were studied in several outcrops and interpreted together with literature data referring to the area. Three facies associations were distinguished: offshore lacustrine clays, delta front sands, and delta plain sands with paludal huminitic clays. The facies associations are organized into at least four delta-scale (10-50 m thick) transgressive-regressive cycles. Age of the succession spans from the Sarmatian-Pannonian boundary (11.6 Ma) to the Prosodacnomya dainellii Zone (older than 7.2 Ma), and most of the littoral and sublittoral mollusc biozones of that interval are represented by their characteristic fossils in the succession. These patterns suggest very low subsidence rate, low accommodation rate, and low rate of sedimentation. Although the investigated sections do not display any obvious stratigraphic gap, erosion must have been a major factor determining the apparently low average sedimentation rate. Persistent aggradation of lacustrine-deltaic sediments at the southern margin of the Pannonian Basin aligns with the general aggradational architecture of the basin fill in the high-supply endorheic Lake Pannon.

Rapidly developing NLP applications for content curation

AbstractTime and again we are faced, in a number of collaborative research projects, with the challenge of interconnecting various language processing tools to implement certain industry-driven use cases focusing, for the most part, upon digital content curation processes. In this paper we first describe several of the relevant projects and their technology platforms, followed by a description of the corresponding use cases and their requirements. The content curation platform we focus upon in this article and which has been implemented as a prototype makes use of a large number of NLP services, which we also build upon for other use cases and prototypes. In addition to the implemented NLP services, the article presents a workflow manager for the flexible creation and customisation of processing workflows that make use of the above mentioned NLP services. Based on the four key principles of generality, flexibility, scalability and efficiency, we present the first version of the workflow manager by providing details on its custom definition language, explaining the communication components and the general system architecture and setup. The paper also addresses challenges in interoperability across different NLP tasks and hardware-based resource use.

A multi-task framework for breast cancer segmentation and classification in ultrasound imaging

Background:Ultrasound (US) is a medical imaging modality that plays a crucial role in the early detection of breast cancer. The emergence of numerous deep learning systems has offered promising avenues for the segmentation and classification of breast cancer tumors in US images. However, challenges such as the absence of data standardization, the exclusion of non-tumor images during training, and the narrow view of single-task methodologies have hindered the practical applicability of these systems, often resulting in biased outcomes. This study aims to explore the potential of multi-task systems in enhancing the detection of breast cancer lesions. Methods:To address these limitations, our research introduces an end-to-end multi-task framework designed to leverage the inherent correlations between breast cancer lesion classification and segmentation tasks. Additionally, a comprehensive analysis of a widely utilized public breast cancer ultrasound dataset named BUSI was carried out, identifying its irregularities and devising an algorithm tailored for detecting duplicated images in it. Results:Experiments are conducted utilizing the curated dataset to minimize potential biases in outcomes. Our multi-task framework exhibits superior performance in breast cancer respecting single-task approaches, achieving improvements close to 15% in segmentation and classification. Moreover, a comparative analysis against the state-of-the-art reveals statistically significant enhancements across both tasks. Conclusion:The experimental findings underscore the efficacy of multi-task techniques, showcasing better generalization capabilities when considering all image types: benign, malignant, and non-tumor images. Consequently, our methodology represents an advance towards more general architectures with real clinical applications in the breast cancer field.

ქართული ისტორიული ეპოსი – ძიებები და ვარაუდები

Our interest towards the Georgian folk epic is determined not only by a professional attitude, but also by the necessity to know our national identity, because no matter how paradoxical it is, in the era of globalization as universal integration, it becomes even more topical to clarify one's own identity among independent nati­ons, which is best preserved by collective memory and folk orality. It is noticeable that in the conditions of Georgian national identity and long-lasting state life, the deficiency of Georgian orality in terms of historical genre texts causes a kind of surprise, such a picture is created as if the memory of the ancestors refused to preserve such cultural heritage. There are various explanations for this, and the majority of Georgian researchers agree with Vakhushti Batonishvili's opinion, who cites the "shor­tness of memory" of the people as the reason for the shortcoming, be­cause the artistic memory of the people does not exceed the common age of four or five generations. We can compare folklore to a constantly renewable jewel, and for the sake of conspicuousness, we can imagine people's dwe­lling place – a house which gets old over time, its door, windows, and roof change. Sometimes a completely new house is built on an old foundation, but the function of the house never changes, its general architecture and purpose, which, if we take it as an example of a historical epic, always preserves a solid structural com­position, a style of artistic environment and metaphorical thinking, a set of signs whose exact identification is provided by the structural-morphological analysis of a text. Here it is necessary to mention that the modern researcher will have to carry out this work not in museums and archives, in the forgotten cen­turies of history or in the deep annals of the history of literature, but in the living process of people's orality, in the depository of collective memory. Our main support in the research process is the complete collection of "Amiraniani" published in the Shota Rustaveli Institute of Literature, along with other folklore materials. This epic, as an expression of the spi­ri­tual wealth of Georgia and a fundamental ar­gument for the historical in­tegrity of the country, is connected with its spread in all parts of Georgia in a unified cultural environment. It has been noted by the researchers that traces of events repre­senting different historical eras can be found in this text. Some of them are so clear and indisputable that, I think, the time has come for a complex observation and interdisciplinary research on it, which will confirm the existence of other epic and historical songs in it, which will further clarify the authen­ticity of the original text and determine its genre context. Nevertheless, "Amiraniani" does not contain specific geogra­phical to­po­nyms or historical eras, today's readers can see not only the signs of tribal battles in it, but also the motive of liberating one's country and the idea of national unity. Our work is related to the search for a completely indepen­dent historical epic "Pharnavaziani" in the epic of "Amiraniani", as well as in the bottomless well of Georgian orality. We think that this kind of text already exists in the form of contamination and it is necessary to separate it and clean it from impurities. For this, we rely on the works of Georgian scientists about the folk epic, the general rule of folklore, the traditional research methodology, as well as the modern theories of sociology, which separate collective and individual creation patterns from each other, and determine the boundaries of genre identity. Naturally, our point of view is legitimate in the manner of raising the issue, and we expect that this initiative will have both supporters and opponents. We hope that future opponents will try to justify or invalidate this opinion based on scientific arguments. Only such a mode of con­fron­tation will define the useful position, which will help to see the positive result of the cultural memory of our nation and preserve it in the future.

GENERALIZED DATASET OF GEOLOGICAL AND GEOPHYSICAL INFORMATION ON THE EASTERN SECTOR OF THE RUSSIAN ARCTIC FOR MACHINE LEARNING – BASED ANALYSIS

The article presents a practical approach to the geological and geophysical spatial data collection and preliminary processing to use in machine learning models for geophysical applications. According to the established principles for estimating efforts in data analysis, which are confirmed by the results of surveys among specialists, this stage is viewed as major time and resource-consuming, amounting up to 80% in total volume of data analysis for a hypothesis testing project. The paper focuses on creating a consistent data set that integrates geological and geophysical information on a given region. We consider problems of different sources in the geodata representation to be related to their format (vector/raster), scale, type of attribute information (quantitative/qualitative) and their availability. The algorithm formalization and synthesis for combining geospatial data and converting them into quantitative vectors is a critical aspect. Combining various data draws on the concept of neighborhood fitting in with the data selection techniques and data consolidation strategy. The paper presents the general architecture of the software and hardware complex which includes a module for data collection and transformation in Python using the Pandas library, a data storage system based on the PostgreSQL DBMS (Database Management System) with the PostGIS extension. It is shown that for the considered class of problems in geophysics, it is sufficient to use a relational DBMS for data storing and processing. If the problem dimension increases, it is proposed to use the Big Data technology based on Apache Hadoop for scaling the system. A practical application of the proposed approach is demonstrated as results of data collection for the Caucasus region and eastern sector of the Russian Arctic. Based on the prepared data, experiments were carried out using machine learning models for recognition of locations of potential strong earthquakes and for sensitivity estimation of several geophysical features of these regions. The article presents the experimental results and evaluation of their efficiency.

Early Sweet Potato Plant Detection Method Based on YOLOv8s (ESPPD-YOLO): A Model for Early Sweet Potato Plant Detection in a Complex Field Environment

Traditional methods of pest control for sweet potatoes cause the waste of pesticides and land pollution, but the target detection algorithm based on deep learning can control the precise spraying of pesticides on sweet potato plants and prevent most pesticides from entering the land. Aiming at the problems of low detection accuracy of sweet potato plants and the complex of target detection models in natural environments, an improved algorithm based on YOLOv8s is proposed, which can accurately identify early sweet potato plants. First, this method uses an efficient network model to enhance the information flow in the channel, obtain more effective global features in the high-level semantic structure, and reduce model parameters and computational complexity. Then, cross-scale feature fusion and the general efficient aggregation architecture are used to further enhance the network feature extraction capability. Finally, the loss function is replaced with InnerFocaler-IoU (IFIoU) to improve the convergence speed and robustness of the model. Experimental results showed that the mAP0.5 and model size of the improved network reached 96.3% and 7.6 MB. Compared with the YOLOv8s baseline network, the number of parameters was reduced by 67.8%, the amount of computation was reduced by 53.1%, and the mAP0.5:0.95 increased by 3.5%. The improved algorithm has higher detection accuracy and a lower parameter and calculation amount. This method realizes the accurate detection of sweet potato plants in the natural environment and provides technical support and guidance for reducing pesticide waste and pesticide pollution.

Polarimetric image denoising via non-local based cube matching convolutional neural network

Due to rapid advances in deep learning, many polarimetric image denoising networks have been developed and achieved promising results. However, these methods are based on general network architectures that do not fully exploit problem-specific knowledge, leading to over-smoothing results and poor generalization. Inspired by the non-local, which is an effective prior for image restoration, we propose a cube matching convolutional neural network to incorporate non-local operations into denoising models for polarimetric images. Specifically, the cube matching technique allows the denoising network to simultaneously exploit the non-local correlation and polarization relationship between the corresponding voxels of similar cubes. Rather than applying self-similarity directly in an isolated manner, the proposed cube matching module can be flexibly integrated into existing deep networks by combining with 3D convolution, achieving an effect equivalent to non-local means. This design enhances the generalization ability against various types and levels of noise. Experimental results show that using cube matching operations significantly improves denoising performance.

Chimeric U-Net – Modifying the standard U-Net towards explainability

Healthcare guided by semantic segmentation has the potential to improve our quality of life through early and accurate disease detection. Convolutional Neural Networks, especially the U-Net-based architectures, are currently the state-of-the-art learning-based segmentation methods and have given unprecedented performances. However, their decision-making processes are still an active field of research. In order to reliably utilize such methods in healthcare, explainability of how the segmentation was performed is mandated. To date, explainability is studied and applied heavily in classification tasks. In this work, we propose the Chimeric U-Net, a U-Net architecture with an invertible decoder unit, that inherently brings explainability into semantic segmentation tasks. We find that having the restriction of an invertible decoder does not hinder the performance of the segmentation task. However, the invertible decoder helps to disentangle the class information in the latent space embedding and to construct meaningful saliency maps. Furthermore, we found that with a simple k-Nearest-Neighbours classifier, we could predict the Intersection over Union scores of unseen data, demonstrating that the latent space, constructed by the Chimeric U-Net, encodes an interpretable representation of the segmentation quality. Explainability is an emerging field, and in this work, we propose an alternative approach, that is, rather than building tools for explaining a generic architecture, we propose constraints on the architecture which induce explainability. With this approach, we could peer into the architecture to reveal its class correlations and local contextual dependencies, taking an insightful step towards trustworthy and reliable AI. Code to build and utilize the Chimeric U-Net is made available under:https://github.com/kenrickschulze/Chimeric-UNet---Half-invertible-UNet-in-Pytorch

Data Architectures in Cloud Environments

AbstractData architectures are an integral part for developing robust data pipelines. Cloud computing offers various features to build modern data architectures to power data engineering pipelines on a scalable, cost-effective, and secure level.In this article we describe how cloud computing works in the field of data management. We start with brief explanations on cloud computing, general data architectures, and how both worlds fit together by introducing design principles, tools, and services for cloud data architectures.

Toward a Clinical Decision Support System for Monitoring Therapeutic Antituberculosis Medical Drugs in Tanzania (Project TuberXpert): Protocol for an Algorithm' Development and Implementation.

The end tuberculosis (TB) strategy requires a novel patient treatment approach contrary to the one-size-fits-all model. It is well known that each patient's physiology is different and leads to various rates of drug elimination. Therapeutic drug monitoring (TDM) offers a way to manage drug dosage adaptation but requires trained pharmacologists, which is scarce in resource-limited settings. We will develop an automated clinical decision support system (CDSS) to help practitioners with the dosage adaptation of rifampicin, one of the essential medical drugs targeting TB, that is known for large pharmacokinetic variability and frequent suboptimal blood exposure. Such an advanced system will encourage the spread of a dosage-individualization culture, including among practitioners not specialized in pharmacology. Thus, the objectives of this project are to (1) develop the appropriate population pharmacokinetic (popPK) model for rifampicin for Tanzanian patients, (2) optimize the reporting of relevant information to practitioners for drug dosage adjustment, (3) automate the delivery of the report in line with the measurement of drug concentration, and (4) validate and implement the final system in the field. A total of 3 teams will combine their efforts to deliver the first automated TDM CDSS for TB. A cross-sectional study will be conducted to define the best way to display information to clinicians. In parallel, a rifampicin popPK model will be developed taking advantage of the published literature, complemented with data provided by existing literature data from the Pan-African Consortium for the Evaluation of Antituberculosis Antibiotics (panACEA), and samples collected within this project. A decision tree will be designed and implemented as a CDSS, and an automated report generation will be developed and validated through selected case studies. Expert pharmacologists will validate the CDSS, and finally, field implementation in Tanzania will occur, coupled with a prospective study to assess clinicians' adherence to the CDSS recommendations. The TuberXpert project started in November 2022. In July 2024, the clinical study in Tanzania was completed with the enrollment of 50 patients to gather the required data to build a popPK model for rifampicin, together with a qualitative study defining the report design, as well as the CDSS general architecture definition. At the end of the TuberXpert project, Tanzania will possess a new tool to help the practitioners with the adaptation of drug dosage targeting complicated TB cases (TB or HIV, TB or diabetes mellitus, and TB or malnutrition). This automated system will be validated and used in the field and will be proposed to other countries affected by endemic TB. In addition, this approach will serve as proof of concept regarding the feasibility and suitability of CDSS-assisted TDM for further anti-TB drugs in TB-burdened areas deprived of TDM experts, including second-line treatments considered important to monitor. DERR1-10.2196/58720.

Planning and learning to perceive in partially unknown environments

For applying symbolic planning, an agent acting in an environment needs to know its symbolic state, and an abstract model of the environment dynamics. However, in the real world, an agent has low-level perceptions of the environment (e.g. its position given by a GPS sensor), rather than symbolic observations representing its current state. Furthermore, in many real-world scenarios, it is not feasible to provide an agent with a complete and correct model of the environment, e.g., when the environment is (partially) unknown a priori. Therefore, agents need to dynamically learn/adapt/extend their perceptual abilities online, in an autonomous way, by exploring and interacting with the environment where they operate. In this paper, we provide a general architecture of a planning, learning, and acting agent. Moreover, we propose solutions to the problems of automatically training a neural network to recognize object properties, learning the situations where such properties are better perceivable, and planning to get into such situations. We experimentally show the effectiveness of our approach in simulated and complex environments, and we empirically demonstrate the feasibility of our approach in a real-world scenario that involves noisy perceptions and noisy actions on a real robot.

The Salesforce Einstein Trust Layer for Retrieval-Augmented Generation (RAG) for Enterprise Applications

Generative AI has the potential to revolutionize the enterprise workflows to great extent but it poses privacy, security, and data governance challenges. Companies who want to utilize advanced AI models like Large Language Models, are only allowed to do so under the guidelines of security and regulatory frameworks. Salesforce Einstein Trust Layer proposes a solution to these challenges by not only setting up a trusted layer for deploying Retrieval-Augmented Generation (RAG) models but also ensures that the data privacy standards are met while delivering the AI generated responses. This paper discusses how the Einstein Trust Layer facilitates the safe practical application of RAG in enterprise systems, including its general architecture, functionality, and the precise processes that demonstrate why the Einstein Trust Layer is a reliable means of incorporating LLMs into commercial processes. Keywords: Salesforce Einstein Trust Layer, Retrieval-Augmented Generation (RAG), Generative AI, Large Language Models (LLMs), Data Privacy, AI Governance, Enterprise AI, Data Masking, Toxicity Scoring, Dynamic Grounding, Zero-Data Retention, AI Compliance

Application of energy storage performance regulation of ferroelectric thin films in sports competitions

With the continuous improvement of sports competition level and technological progress, accurate recording and analysis of athletes’ physical condition and training data have become increasingly important. In sports competitions, finding a new type of material that can store the training abilities of athletes has become a challenge. As an emerging energy storage material, ferroelectric thin films have unique advantages in energy storage performance and flexibility. This article explored the application of energy storage performance regulation of ferroelectric thin films in sports competitions, and analyzed that the biological monitoring indicators and health management of athlete training needed to comprehensively consider multiple aspects, including physical and physiological indicators. The measured data of multiple athletes were collected and the relationships among the multiple indicators were analyzed through t-tests. The article explored the capture and conversion of motion kinetic energy, and analyzed the general architecture of motion capture systems as an example. In terms of the energy storage performance of ferroelectric thin films, data before and after the enhancement of sports equipment in the sports field was collected for research based on the energy storage performance of ferroelectric thin films. In the evaluation and exploration of the application effect of ferroelectric thin films in the sports field, combined with multiple tests and satisfaction feedback, it was found that the satisfaction rate of male athletes reached 94% −98% at week 7, while the satisfaction rate of female athletes reached 94% −96% at week 7. With the progress of technology and continuous innovation, it is believed that ferroelectric thin film energy storage technology can play a greater role in the field of sports in the future.

A Family of General Architectures Toward Interconnection Networks and Data Center Networks

A Family of General Architectures Toward Interconnection Networks and Data Center Networks

Expression of Mgp in Calcification Leiomyoma uterus in postmenopausal women

The Matrix Gla protein (MGP) is an extracellular polypeptide that can inhibit calcification in tissues that express Mgp molecules. An analysis employing histology and immunohistochemistry unveiled the general architecture and detected calcification within the fibroid. The study included gathering twelve samples after confirming through histological examination that the samples were affected by fibroid cysts. Each of these specimens was conserved in a 10% formalin solution. A histological examination was performed using two dyes, hematoxylin and eosin, to demonstrate the general histological organization. The Van Kossa stain was employed to detect the buildup of calcium anions in the tissue. Moreover, the immunohistochemical technique was used to detect the elevated expression of Mgp in the myofibers of leiomyoma-affected myometrium tissue.

Automatic architecture design for distributed quantum computing

Abstract In distributed quantum computing (DQC), quantum hardware design mainly focuses on providing as many as possible high-quality inter-chip connections. Meanwhile, quantum software tries its best to reduce the required number of remote quantum gates between chips. However, this “hardware first, software follows” methodology may not fully exploit the potential of DQC. Inspired by classical software–hardware co-design, this paper explores the design space of application-specific DQC architectures. More specifically, we propose AutoArch, an automated quantum chip network (QCN) structure design tool. With qubits grouping followed by a customized QCN design, AutoArch can generate a near-optimal DQC architecture suitable for target quantum algorithms. Experimental results show that the DQC architecture generated by AutoArch can outperform other general QCN architectures when executing target quantum algorithms.

The Ovary Structure in Terrestrial Parasitengona Mites: The Case of Trombidiidae (Acariformes: Parasitengona).

Species of mites (Chelicerata: Arachnida) show a great variety of structures of the female gonads. In both evolutionary lines, Acariformes and Parasitiformes, the panoistic ovary, in which all germline cysts differentiate into oocytes, and the meroistic ovary, in which the oocytes grow supported by the nurse cells, have been documented. A less pronounced variation in the gonad structure could be expected at lower systematic levels, hence, we ask about the degree of differences within the family that is subordinate to Acariformes and represents the cohort Parasitengona. Based on the members of Trombidiidae (Acariformes: Trombidiformes, Parasitengona, Trombidioidea), we test the hypothesis that the general ovary type is constant at the family level. Our previous research on the female gonad in Allothrombium fuliginosum revealed that the meroistic ovary occurs in these mites. Here, we proceed with a detailed insight into the ovary structure in A. fuliginosum and examine the structure of the female gonad in other members of Trombidiidae, focusing on the following representatives of its nominotypical genus Trombidium: Trombidium brevimanum, Trombidium holosericeum, Trombidium heterotrichum, and Trombidium latum. For all species, studied with light, fluorescence, and transmission electron microscopy, we could confirm the presence of the meroistic ovary that is highly similar with respect to general architecture. The germline cysts show similarities in general morphology and the mode of germline cell differentiation; they consist of a few nurse cells and one oocyte. The connection between the nurse cells and oocytes is maintained by trophic cords that serve for the transport of organelles and macromolecules. Our results confirm the constancy of the structure of the female gonad at the intrageneric level and provide further support for the hypothesis on the lack of differences at the intrafamily level.

Comprehensive Assessment of Context-Adaptive Street Lighting: Technical Aspects, Economic Insights, and Measurements from Large-Scale, Long-Term Implementations.

This paper addresses the growing importance of efficient street lighting management, driven by rising electricity costs and the need for municipalities to implement cost-effective solutions. Central to this study is the UNI 11248 Italian regulation, which extends the European EN 13201-1 standard introduced in 2016. These standards provide guidelines for designing, installing, operating, and maintaining lighting systems in pedestrian and vehicular traffic areas. Specifically, the UNI 11248 standard introduces the possibility to dynamically adjust light intensity through two alternative operating modes: (a) Traffic Adaptive Installation (TAI), which dims the light based solely on real-time traffic flow measurements; and (b) Full Adaptive Installation (FAI), which, in addition to traffic measurements, also requires evaluating road surface luminance and meteorological conditions. In this paper, we first present the general architecture and operation of an FAI-enabled lighting infrastructure, which relies on environmental sensors and a heterogeneous wireless communication network to connect intelligent, remotely controlled streetlights. Subsequently, we examine large-scale, in-field FAI infrastructures deployed in Vietnam and Italy as case studies, providing substantial measurement data. The paper offers insights into the measured energy consumption of these infrastructures, comparing them to that of conventional light-control strategies used in traditional installations. The measurements demonstrate the superiority of FAI as the most efficient solution.

Improving surveillance of emergency department activity through natural language processing

Objective and ApproachManagers, clinicians and policymakers have limited information on near-real time patterns of attendance at emergency departments (ED). Our aim was to develop a surveillance system through extracting information from the presenting complaint to develop and feed activity dashboards, improve injury surveillance and support research. We developed a Natural Language Processing (NLP) pipeline using the General Architecture for Text Engineering (GATE) system. The pipeline produced Unified Medical Language System (UMLS) codes from ED presenting complaint records and also implemented the Joint Action on Monitoring Injuries in Europe (JAMIE) Minimum Dataset. We classified complaints into 31 common problem presentations (Coughs, Bleeds, Mental Health, Dizziness...), along with categories from JAMIE (Mechanism of Injury, Location, Activity, Intent…). ResultsPreliminary results are from a pilot study of 86,416 presenting complaints from Morriston Hospital in 2014. The most common terms used for grouped symptoms/categories were “Injury” (38.6%, n=28691), “Pain” (22.8%, n=19420), “Unwell” (7.2%, n=6117), “Bleeding” (6.7%, n=5760), and “Shortness of Breath” (3.8%, n=3255). 32.3% of records contained Mechanism of Injury codes, including, falls (15.2%, n=13174), struck by/against (6.9%, n=5960), cuts (5.6%, n=4833), road traffic collisions (2.5%, n=2124) and poisoning (1%, n=900). We are continuing to refine and validate the categories using precision and recall and with comparison with coded diagnoses. Conclusions and Implications NLP can be used to extract valuable additional detailed information from ED data. We will further develop the algorithms for all hospitals in Wales for data from 2023 and design dashboards to produce a near-real time surveillance system.

Metafeature Selection via Multivariate Sparse-Group Lasso Learning for Automatic Hyperparameter Configuration Recommendation.

The performance of classification algorithms is mainly governed by the hyperparameter settings deployed in applications, and the search for desirable hyperparameter configurations usually is quite challenging due to the complexity of datasets. Metafeatures are a group of measures that characterize the underlying dataset from various aspects, and the corresponding recommendation algorithm fully relies on the appropriate selection of metafeatures. Metalearning (MtL), aiming to improve the learning algorithm itself, requires development in integrating features, models, and algorithm learning to accomplish its goal. In this article, we develop a multivariate sparse-group Lasso (SGLasso) model embedded with MtL capacity in recommending suitable configurations via learning. The main idea is to select the principal metafeatures by removing those redundant or irregular ones, promoting both efficiency and performance in the hyperparameter configuration recommendation. To be specific, we first extract the metafeatures and classification performance of a set of configurations from the collection of historical datasets, and then, a metaregression task is established through SGLasso to capture the main characteristics of the underlying relationship between metafeatures and historical performance. For a new dataset, the classification performance of configurations can be estimated through the selected metafeatures so that the configuration with the highest predictive performance in terms of the new dataset can be generated. Furthermore, a general MtL architecture combined with our model is developed. Extensive experiments are conducted on 136 UCI datasets, demonstrating the effectiveness of the proposed approach. The empirical results on the well-known SVM show that our model can effectively recommend suitable configurations and outperform the existing MtL-based methods and the well-known search-based algorithms, such as random search, Bayesian optimization, and Hyperband.