Primary Contribution Research Articles

DKNN: deep kriging neural network for interpretable geospatial interpolation

Geospatial interpolation plays a pivotal role in spatial analysis because it provides high-quality data support for various spatiotemporal data mining (STDM) tasks. However, statistical methods, such as kriging, face challenges in dealing with complex geo-big data. Additionally, deep-learning-based methods, despite their exceptional performance, suffer from limitations, such as poor interpretability. To harness the complementary advantages of these statistical methods and deep learning approaches, this study proposes a novel geospatial artificial intelligence (GeoAI) framework called deep kriging neural network (DKNN). The primary contribution lies in the development of an asymmetric encoder-decoder structure, which includes a deep-learning-based spatial encoder and a geostatistics-based kriging decoder. The spatial encoder consists of three specialized neural networks, whereas the kriging decoder relies on the proposed unified kriging system. During forward propagation, the kriging decoder leverage messages from the spatial encoder to generate interpolation weights for prediction. Conversely, during backward propagation, the kriging decoder guides the spatial encoder in learning interpretable knowledge. Experiments were conducted using both synthetic and practical datasets. The results demonstrate an average improvement of 20.18% in MAE, 25.04% in RMSE and 24.06% in MAPE when compared to the best-performing baseline method. Furthermore, these results confirm the superior interpretability of our DKNN framework.

DEPRESSION DETECTION BY ANALYZING SOCIAL MEDIA POST OF USER: A REVIEW

In contemporary times, identifying depression at an early stage has become a critical issue within the field of psychology. Mental health problems, notably depression, afflict a significant portion of the global population, with an estimated 300 million individuals currently affected. Leveraging the vast amount of user-generated content on social media platforms, researchers are exploring ways to utilize this data to identify potential mental health issues in users. Depression remains a pressing concern in society and a topic of ongoing research globally. Despite numerous studies attempting to understand various mood disorders such as depression, anxiety, and stress using activity logs from devices like smartphones, accurately predicting depressive episodes remains challenging. Social media analysis has emerged as a popular approach to tackle this challenge. In this paper, we propose a system for assessing depression and detecting suicidal ideation by predicting suicidal tendencies based on the severity of depression. Our study aims to develop effective machine learning algorithms for identifying potential signs of depression in individuals through their social media posts. To achieve this, we trained and tested classifiers to discern whether a person exhibits signs of depression using features extracted from their social media activities. Various machine learning algorithms were employed to train and classify users into different levels of depression on a scale ranging from 0 to 100%. Data in the form of posts were collected and categorized into depressed or non-depressed using machine learning algorithms. Our primary contribution lies in exploring a range of features and their effectiveness in detecting the degree of depression. We aim to build a deep learning model capable of categorizing users with depression by learning from individual-level labels to infer post-level labels. By amalgamating the probabilities of post label categories, we can create temporal posting profiles to classify users with depression. Our findings reveal distinct variations in posting behaviors between depressed and non-depressed users, as indicated by the combined probabilities of post label categories. In our study, we utilized natural language processing (NLP) techniques, employing the BERT algorithm, to efficiently identify potential depression indicators in social media content. This approach offers a more accessible and effective means of detecting depression. Keywords— Machine Learning, NLP, BERT Algorithm, Depression, Classification, Social Media Post.

An analytical decision-making model for integrated green supply chain problems: A computational intelligence solution

This paper presents an integrated mathematical decision-making model to reduce environmental footprints using process integration. By doing so, we address the research question: How can supplier selection, ergonomic factors, and green practices be integrated into mathematical decision-making models based on the vendor-managed inventory policy? We use the Branch and Bound method to provide optimal solutions and a metaheuristic optimization approach in computational intelligence for large-scale problems. This paper employs a multi-criteria decision-making method to compare proposed algorithms results based on six criteria. Our findings reveal that integrating the sourcing process with inventory decisions significantly improves cost performance. Furthermore, our results demonstrate that the proposed model effectively balances environmental and economic objectives using a carbon tax. Moreover, sensitivity analysis results indicate that optimizing water and energy consumption can significantly improve carbon footprints. In addition, the study shows that ergonomic factors, including lighting and temperature, have a substantial impact on performance. The primary contributions of this paper include the incorporation of a multi-sourcing strategy, green practices, ergonomic factors, and supplier selection into vendor-managed inventory decision models.

Corporate social responsibility and firm performance: Case of Kazakhstan

The research seeks to find a relationship between Corporate Social Responsibility (CSR) and companies' performance. Studied variables were measured and analysed using a sample of companies listed on the Kazakhstan Stock Exchange (KASE). The study employed the regression model and least squares technique as the primary analytical tools. CSR is examined in conjunction with variables such as Return on Assets, Return on Equity, Market Value, and Net Profit Margin. As a result of the research, it was found that firm performance and CSR relate to each other in the studied companies. The research found a positive correlation between CSR practices and Net Profit Margin in Kazakh companies. While this study focused on a single country, its methodology can be applied to research in other emerging and developing nations. The primary contribution of this research is the examination of the relationship between firm performance and CSR practices in the post-Soviet emerging market of Kazakhstan.

Hyperseed: Unsupervised Learning With Vector Symbolic Architectures.

Motivated by recent innovations in biologically inspired neuromorphic hardware, this article presents a novel unsupervised machine learning algorithm named Hyperseed that draws on the principles of vector symbolic architectures (VSAs) for fast learning of a topology preserving feature map of unlabeled data. It relies on two major operations of VSA, binding and bundling. The algorithmic part of Hyperseed is expressed within the Fourier holographic reduced representations (FHRR) model, which is specifically suited for implementation on spiking neuromorphic hardware. The two primary contributions of the Hyperseed algorithm are few-shot learning and a learning rule based on single vector operation. These properties are empirically evaluated on synthetic datasets and on illustrative benchmark use cases, IRIS classification, and a language identification task using the n -gram statistics. The results of these experiments confirm the capabilities of Hyperseed and its applications in neuromorphic hardware.

Rancang Bangun Aplikasi Absensi Karyawan menggunakan QR-Code Berbasis Web pada SMA Candra Naya

This research discusses the development of a web-based employee attendance application using the waterfall method at SMA Candra Naya. The waterfall method was chosen due to its organized structure, starting from requirement analysis to maintenance. The stages involved include requirement analysis, design, implementation, testing, and maintenance. The application utilizes QR-code technology as a unique identification tool for employees, enabling efficient and accurate attendance processes. Evaluation was conducted through internal testing at SMA Candra Naya to assess the performance and reliability of the application. The evaluation results indicate that the application successfully enhances the efficiency of attendance administration and simplifies employee attendance management. The primary contribution of this research is the application of the waterfall method as a systematic approach in developing web-based applications for employee attendance management, which can be adopted by educational institutions and similar organizations to improve the efficiency and accuracy of attendance processes.

Hunting for quantum-classical crossover in condensed matter problems

The intensive pursuit for quantum advantage in terms of computational complexity has further led to a modernized crucial question of when and how will quantum computers outperform classical computers. The next milestone is undoubtedly the realization of quantum acceleration in practical problems. Here we provide a clear evidence and arguments that the primary target is likely to be condensed matter physics. Our primary contributions are summarized as follows: 1) Proposal of systematic error/runtime analysis on state-of-the-art classical algorithm based on tensor networks; 2) Dedicated and high-resolution analysis on quantum resource performed at the level of executable logical instructions; 3) Clarification of quantum-classical crosspoint for ground-state simulation to be within runtime of hours using only a few hundreds of thousand physical qubits for 2d Heisenberg and 2d Fermi-Hubbard models, assuming that logical qubits are encoded via the surface code with the physical error rate of p = 10−3. To our knowledge, we argue that condensed matter problems offer the earliest platform for demonstration of practical quantum advantage that is order-of-magnitude more feasible than ever known candidates, in terms of both qubit counts and total runtime.

What will be the hydrogen and power demands of the process industry in a climate-neutral Germany?

The defossilization of industry has far-reaching implications regarding the future demand for hydrogen and other forms of energy. This paper presents and applies a fundamental bottom-up model that relies on techno-economic data of industrial production processes. Its aim is to identify, across a range of scenarios, the most cost-effective low-carbon options considering a variety of production systems. Subsequently, it derives the hydrogen and electricity demand that would result from the implementation of these least-cost low-carbon options in process industries in Germany. Aligning with the German government's target year for achieving climate neutrality, this study's reference year is 2045. The primary contribution lies in analyzing which hydrogen-based and direct electrification solutions would be cost-effective for a range of energy price levels under climate-neutral industrial production and what the resulting hydrogen and electricity demand would be. To this end, the methodology of this paper comprises the following steps: selection of the relevant industries (I), definition of conventional reference production systems and their low-carbon options (II), investigation and processing of the techno-economic data of the standardized production systems (III), establishment of a scenario framework (IV), determination of the least-cost low-carbon solution of a conventional reference production system under the scenario assumptions made (V), and estimation of the resulting hydrogen and electricity demand (VI). According to the results, the expected industrial hydrogen consumption in 2045 ranges from 265 TWh for higher hydrogen prices in or above the range of onshore wind-based green hydrogen supply costs, to up to 473 TWh for very low hydrogen prices corresponding to typical blue hydrogen production costs. Meanwhile, the direct electricity consumption of the process industries in the results ranges from 147 TWh for these rather low hydrogen prices to 338 TWh for the higher hydrogen prices in the region of or above the hydrogen supply costs from the electrolysis of energy from an onshore wind farm. Most of the break-even hydrogen prices that are relevant to the choice of low-carbon options are in the range of the benchmark purchase costs for blue hydrogen and green hydrogen produced from offshore wind power, which span between €40 per MWh and €97 per MWh.

Local near-field scattering data enables unique reconstruction of rough electric potentials

The focus of this paper is the study of the inverse point-source scattering problem, specifically in relation to a certain class of electric potentials. Our research provides a novel uniqueness result for the inverse problem with local data, obtained from the near field pattern. Our work improves the work of Caro and Garcia, who investigated both the direct problem and the inverse problem with global near field data for critically singular and δ -shell potentials. The primary contribution of our research is the introduction of a Runge approximation result for the near field data on the scattering problem which, in combination with an interior regularity argument, enables us to establish a uniqueness result for the inverse problem with local data. Additionaly, we manage to consider a slightly wider class of potentials.

Microstructure evolution of V-containing low carbon ultra-fine bainitic steel during medium-temperature tempering and strengthening-toughening mechanism

In the present study, the microstructure evolution and the corresponding mechanical properties of V-containing low carbon ultra-fine bainitic steel during tempering were studied. The results show that during the initial stages of tempering, part of retained austenite in V-containing ultra-fine bainite steel transforms into bainite. The stability of the retained austenite improves when the tempering period is increased to 5 h. Simultaneously, nano-sized VC precipitates are precipitated in the microstructure. On the one hand, these phases can give full play to the transformation-induced plasticity (TRIP) effect by modulating the carbon content of the retained austenite. On the other hand, they can also reduce the lattice distortion in the matrix and combine it with the lower dislocation density, thereby improving the plasticity of the specimen. At the same time, the fine precipitated phase can also effectively improve the toughness of the cleavage crack region in the transition zone, preventing the micro-cracks from generating at the interface of the precipitated phase and then extending to the adjacent matrix to cause fracture, so that the uniform elongation, total elongation, impact toughness at room temperature and impact toughness at low temperature of the 5 h specimen are as high as 8.8 ± 0.2 %、16.2 ± 0.7 %、113 ± 4 J/cm2 and 76 ± 2 J/cm2, respectively. Furthermore, the primary contribution of the strengthening mechanism in the microstructure has shifted from fine grain strengthening and dislocation strengthening to precipitation strengthening, and part of the retained austenite undergoes a martensitic transformation during cooling, resulting in the highest yield strength of 1086 MPa for the 5 h specimen. The tensile strength is effectively maintained at 1402 MPa by increasing the tempering period, which has good tempering resistance, to achieve the comprehensive performance optimization of bainitic steel.

Bridging excellence, knowledge management and sustainability: Introducing the ‘Knowledge Management Excellence Model 21′, a model for sustainable development goals alignment

This paper aims to introduce a new sustainable business excellence model, called Knowledge Management Excellence Model 21 (KMEM21), a theoretical framework that combines Knowledge Management and Business Excellence Models (BEMs), proposing an approach applicable to organizations to directly contribute towards achieving the United Nations Sustainable Development Goals (SDGs). The paper through a qualitative-exploratory methodology makes an analysis and benchmarking, emphasizes the integration of Knowledge Management and three specific Business Excellence Models (Management Excellence Model (MEG) from Brazil, Baldrige Excellence Framework, and EFQM). This integration uncovers relationships between organizational concepts associated with Knowledge Management and BEMs, which contributes to new insights in the literature regarding these concepts' interplay. BEMs are presented as tools that can catalyze the power of Knowledge Management towards achieving SDGs. However, it's noted that the existing BEMs might not be adequate, as the goal extends beyond organizational improvement and excellence to encompass sustainable development aligned with SDGs. The article suggests that specific organizational concepts, identified through a literature review and aligned with Knowledge Management and BEMs, can be selected as indicators associated with the constructed KMEM21 and the SDGs. These indicators are intended to form a bridge between the new model and the SDGs. However, given the comprehensive nature of the theory, model development, application, result acquisition, and analysis, the article's primary contribution will be in its focus on elaborating the instrument and technique, demonstrating the creation of a theoretical framework for the SDGs. Future works will showcase the application of the proposed KMEM21 method in five Brazilian organizations, members of Global Compact, to compare the achieved objectives and the results obtained with the organizations' performance and their sustainability reports.

Role of responsible leadership influence to reduce turnover intentions: a double-mediation framework

PurposeThis study aims to propose a double-mediation effect of organizational justice and affective commitment (AC) through which responsible leadership (RL) influences to reduce turnover intention (TI).Design/methodology/approachThe association between responsible leadership and TI, as well as the double-mediating effect of organizational justice and AC, was investigated using an integrated model. Structural equation modeling and Process Macro were used to validate the hypothesized correlations by analyzing the responses of 391 employees working in the Indian health-care sector.FindingsThe outcomes revealed a significant positive association between responsible leadership, organizational justice and AC, as well as a negative association between organizational justice, AC and TI. Moreover, the findings verified the association between responsible leadership and TI.Practical implicationsThis study explored the double-mediating impact of organizational justice and AC on the association between responsible leadership and TI. It also supports the expert in guiding and performing the policy review as an outcome of this relationship.Originality/valueThe primary theoretical contribution of this study is to examine the relationship between RL and TI. This study examined the role of organizational justice (OJ) and AC as double mediators in the relationship between RL and TIs. Moreover, it has significant effects on the development of literature about RL, OJ, AC and TI.

Hardware-in-the-loop dynamic load emulation of robotic systems actuated by fluidic artificial muscles

Hardware-in-the-loop (HIL) testing is a popular control system testing method because it bridges the gap between modeling/simulation and experiments. Instead of designing a full hardware-based experiment to validate the results of a simulation, the plant hardware can be replaced with an emulator device that responds to exogenous inputs and effectively emulates the dynamic behavior of a system. This approach can be more cost-effective and modular, since the emulated plant system can be modeled in a simulation environment, implemented on a simplified piece of hardware and changed quickly without having to fabricate new parts. This paper develops the hardware and control scheme for a certain type of HIL device called a dynamic load emulator that consists of a 1-DOF linear hydraulic dynamometer equipped with in-line sensing to measure both its own position and the force exerted on it by a device-under-test. This measured force is passed to a real-time model of the emulated dynamic system. The model outputs the emulated system position, and a closed-loop controller is used to emulate this position. The emulator controller incorporates both model-based feedforward and standard feedback PI control. This paper characterizes the dynamometer-based dynamic load emulator and its controller, determining its hardware limitations and validating its capabilities when experiencing a force input from a linear spring with known parameters. Additionally, this paper demonstrates the ability of the emulator to represent the dynamics of a 1-DOF robotic joint when actuated by a pair of fluidic artificial muscles (FAMs). The primary contribution of this work is to allow for more comprehensive testing of FAM configurations, topologies, and controllers for a wide range of parameters, because the same hardware can be used to emulate multiple systems. As a result, this work will lead to more cost-effective, time-efficient, and energy-efficient designs of robotic systems and the FAMs used to actuate them.

Exploring eustress and fear: A new perspective on protection motivation in information security policy compliance within the financial sector

Information security policy (ISP) compliance has emerged as a significant challenge for contemporary businesses. This underscores the crucial role of employing fear appeals to encourage employee compliance with ISP. However, the existing literature is rife with mixed and inconsistent findings regarding the influence of fear appeals on employees' intentions to comply with ISP. In an effort to address this inconsistency and delve into the mechanisms through which fear appeals impact ISP compliance, we expanded the Protection Motivation Theory by incorporating the Transactional Model of Stress and Coping. Notably, we introduced a positive emotion, eustress, into the mediating mechanism alongside fear. Our hypothesis posited that fear appeals not only generate fear but also evoke eustress, subsequently positively influencing ISP compliance. We conducted a study among financial sector employees and validated our hypothesis using structural equation modeling techniques. Our primary theoretical contributions include highlighting the critical role of eustress in enhancing ISP compliance and proposing a parallel mechanism through which fear appeals impact ISP compliance. From a practical standpoint, we demonstrate that eustress plays a more significant role in motivating employees to comply with ISP. Furthermore, we provide insights into how organizations can design fear appeal messages by incorporating the concept of eustress, thereby optimizing their effectiveness in promoting ISP compliance.

Exploring Quaternion Neural Network Loss Surfaces

This paper explores the superior performance of quaternion multi-layer perceptron (QMLP) neural networks over real-valued multi-layer perceptron (MLP) neural networks, a phenomenon that has been empirically observed but not thoroughly investigated. The study utilizes loss surface visualization and projection techniques to examine quaternion-based optimization loss surfaces for the first time. The primary contribution of this research is the statistical evidence that QMLP models yield smoother loss surfaces than real-valued neural networks, which are measured and compared using a robust quantitative measure of loss surface “goodness” based on estimates of surface curvature. Extensive computational testing validates the effectiveness of these surface curvature estimates. The paper presents a comprehensive comparison of the average surface curvature of a tuned QMLP model and a tuned real-valued MLP model on both a regression task and a classification task. The results provide strong support for the improved optimization performance observed in QMLPs across various problem domains.

Improving Eye-Tracking Data Quality: A Framework for Reproducible Evaluation of Detection Algorithms.

High-quality eye-tracking data are crucial in behavioral sciences and medicine. Even with a solid understanding of the literature, selecting the most suitable algorithm for a specific research project poses a challenge. Empowering applied researchers to choose the best-fitting detector for their research needs is the primary contribution of this paper. We developed a framework to systematically assess and compare the effectiveness of 13 state-of-the-art algorithms through a unified application interface. Hence, we more than double the number of algorithms that are currently usable within a single software package and allow researchers to identify the best-suited algorithm for a given scientific setup. Our framework validation on retrospective data underscores its suitability for algorithm selection. Through a detailed and reproducible step-by-step workflow, we hope to contribute towards significantly improved data quality in scientific experiments.

Ensuring cybersecurity of FPGA as a service with the use of penetration testing of components

The subject of study in this article is modern penetration testing technologies, in which the test object is the implementation of a service based on a platform using Field Programmable Gate Array (FPGA) resources. The goal of this study is to improve modern methods of penetration testing of services provided by FPGA as a Service (FaaS) to find vulnerabilities for further fixing and increasing the level of services security and trust. Task: to analyze the technological capabilities for the development of FPGA as a Service; to analyze possible threats for FPGA as a Service platform; to analyze the structure of the FPGA as a Service platform and the peculiarities of attacks on it; to analyze options for using the penetration testing standard; to propose the classification of possible use of FPGA as a Service platform for solving of cybersecurity tasks; and to propose the sequence of critical components of ensuring of the cybersecurity of FPGA as a Service platform. The following results were obtained based on the tasks. The analysis of the capabilities of existing chips, FPGA accelerator cards, programming technologies, and the integrated environments of a leading company for creation of FPGA as a Service is performed. A study on the cybersecurity problems of FPGA as a Service platforms is conducted, and a set of components to ensure the cybersecurity of FPGA as a Service Platform is proposed. Modern cybersecurity threats of FPGA as a Service platforms are analyzed. A threat structure for FPGA as a Service is proposed. The possibility of applying a penetration testing standard to FPGA services is considered. Regular audits and penetration testing are crucial elements of a cybersecurity strategy and help maintain customer and user trust in FPGA services. Based on the analysis of the possible use of FPGA as a Service to solve cybersecurity tasks, a classification of five variants considering FPGA as an object and tool is proposed. The sequence of critical components of ensuring of the cybersecurity of FPGA as a Service platform is proposed to correspond to modern known threats. Complex activities, including the software updates, security monitoring, auditing, and penetration testing, based on security standards. Conclusions. The primary contribution and scientific novelty of the obtained results is the research into the possibilities of penetration testing for services, where the test object is a platform with access to FPGA. As in many other areas, ensuring the cybersecurity of FPGA as a Service platform is complex, and ignoring any component can lead to critical consequences. Applying only penetration testing is not enough; therefore, a comprehensive list of cybersecurity measures for FPGA as a Service platforms is provided, underlining the urgency and necessity of their implementation.

Using machine learning algorithms based on patient admission laboratory parameters to predict adverse outcomes in COVID-19 patients

Amidst the global COVID-19 pandemic, the urgent need for timely and precise patient prognosis assessment underscores the significance of leveraging machine learning techniques. In this study, we present a novel predictive model centered on routine clinical laboratory test data to swiftly forecast patient survival outcomes upon admission. Our model integrates feature selection algorithms and binary classification algorithms, optimizing algorithmic selection through meticulous parameter control. Notably, we developed an algorithm coupling Lasso and SVM methodologies, achieving a remarkable area under the ROC curve of 0.9277 with the use of merely 8 clinical laboratory parameters collected upon admission. Our primary contribution lies in the utilization of straightforward laboratory parameters for prognostication, circumventing data processing intricacies, and furnishing clinicians with an expeditious and precise prognostic assessment tool.

Improving anaerobic digestion sludge properties via heterogeneous activation of peroxydisulfate by CuMgAl-layered double hydroxide

Improving anaerobic digestion sludge (ADS) properties by conditioning technology is necessary for subsequent treatment and disposal. In this study, CuMgAl-layered double hydroxide (CuMgAl-LDH) was prepared by co-precipitation method and applied to activate peroxydisulfate (PDS) for ADS conditioning. Experimental results indicated that under the optimal treatment condition (0.15 g LDH/g TS and 0.2 g PDS/g TS addition), the water content of sludge cake and the time to filter decreased from initial 90.83 % to 82.91 % and 75 min to 39.5 min, respectively, and ortho-P as well as non-biodegradable organics contents in the AD liquor (ADL) also decreased remarkably, which was beneficial for ADS dewatering and subsequent ADL backflow treatment. CuMgAl-LDH activating PDS could produce abundant reactive oxygen species (ROS), resulting in microbial cell disruption, bound water release, sludge particle size decrease and non-biodegradable organics degradation. Mechanisms investigation based on the X-ray photoelectron spectroscopy, electron paramagnetic resonance and ROS quenching experiments results indicated that Cu(I)/Cu(II) redox cycle was responsible for PDS activation, and SO4−· made primary contribution to sludge flocs and cells disruption. This research provided preliminary guideline to design copper-based LDH/PDS system for ADS conditioning in wastewater treatment plants.

AC Networks With Microgrids: Passivity-Based Controllers in Single Phase Electric Network

—This paper is an investigation of the possible integration of distributed energy resources (DERs) in single-phase alternating current networks, using voltage-controlled converters, based on passivity-based control theory. In closed-loop operation, Hamiltonian representations facilitate the development of passive controllers that guarantee stability. The trajectory tracking problem can be solved as a regulation problem by transforming the non-autonomous dynamical model into an incremental model. In this work, the primary contribution is the ability to control active and reactive power flows between DERs and the grid according to the availability of primary energy resources and converter capacity. Simulated results indicate that all passive controllers achieve the control objective, maintaining asymptotic stability and achieving the same dynamic performance as integral proportional controllers. SimPowerSystems library is used to develop all simulations under the MATLAB/Simulink environment. The paper presents a novel approach to integrating distributed energy resources into single-phase alternating current networks, utilizing voltage-controlled converters and leveraging passivity-based control theory.