Human Activity Recognition (HAR) has become a prominent research topic in artificial intelligence, with applications in surveillance, healthcare, and human–computer interaction. Among various data modalities used for HAR, skeleton and point cloud data offer strong potential due to their privacy-preserving and environment-agnostic properties. However, point cloud-based HAR faces challenges like data sparsity, high computation cost, and a lack of large annotated datasets. In this paper, we propose a novel two-stage framework that first transforms radar-based point cloud data into skeleton data using a Skeletal Dynamic Graph Convolutional Neural Network (SK-DGCNN), and then classifies the estimated skeletons using an efficient Spatial Temporal Graph Convolutional Network++ (ST-GCN++). The SK-DGCNN leverages dynamic edge convolution, attention mechanisms, and a custom loss function that combines Mean Square Error and Kullback–Leibler divergence to preserve the structural integrity of the human pose. Our pipeline achieves state-of-the-art performance on the MMActivity and DGUHA datasets, with Top-1 accuracy of 99.73% and 99.25%, and F1-scores of 99.62% and 99.25%, respectively. The proposed method provides an effective, lightweight, and privacy-conscious solution for real-world HAR applications using radar point cloud data.
Due to factors such as changing customer demands and supply disruptions, product design changes are inevitable during the product development process. Selecting an appropriate product change propagation path not only maintains product performance but also reduces generation time and cost. This paper investigates an intelligent optimization method for complex product change propagation paths. Firstly, considering change duration, change cost, and the impact degree on product performance, a parameter network model of the product is constructed based on the parameter linkage relationship between product parts. Secondly, to solve this model a change propagation path optimization method based on an improved ant colony algorithm is proposed. Finally, the effectiveness of the proposed model and algorithm is validated on the design change problem of TV products at Skyworth RGB Co., Ltd. Experimental results demonstrate that the proposed algorithm can generate highly competitive optimal change paths for TV products.
Knowledge-based recommender systems have always had their privileged place among all Decision Support Systems (DSS), given their advantage on several points over other techniques. Our paper presents a framework implementing a hybrid form of Rule-Based Reasoning and Case-Based Reasoning (RBR-CBR), to address the rarely discussed domain of educational planning. The system has been tested and presented outstanding results with a high accuracy, which will benefit educational planners’ decision support. We have also developed a dedicated application for this project to visualize the results obtained.
Objectives. The optical properties of two-dimensional semiconductor materials, specifically monolayered transition metal dichalcogenides, present new horizons in the field of nano- and optoelectronics. However, their practical application is hindered by the issue of low light absorption. When working with such thin structures, it is essential to consider numerous complex factors, such as resonance and plasmonic effects which can influence absorption efficiency. The aim of this study is the optimization of light absorption in a two-dimensional semiconductor in the Kretschmann configuration for future use in optoelectronic devices, considering the aforementioned phenomena. Methods. A numerical modeling method was applied using the finite element method for solving Maxwell’s equations. A parametric analysis was conducted focusing on three parameters: angle of light incidence, metallic layer thickness, and semiconductor layer thickness.Results. Parameters were identified at which the maximum area of absorption peak was observed, including the metallic layer thickness and angle of light incidence. Based on the resulting graphs, optimal parameters were determined, in order to achieve the highest absorption percentages in the two-dimensional semiconductor film.Conclusions. Based on numerical studies, it can be asserted that the optimal parameters for maximum absorption in the monolayer film are: Ag thickness <20 nm and angle of light incidence between 55° and 85°. The maximum absorption in the two-dimensional film was found only to account for a portion of the total absorption of the entire structure. Thus, a customized approach to parameter selection is necessary, in order to achieve maximum efficiency in certain optoelectronic applications.
Whether a new technology can spread smoothly in the market heavily depends on the user's acceptance of the technology. A considerable number of studies have sought to predict user acceptance intention through numerous methods. Most rely on the researcher's design and thus cannot present an optimized model that truly meets the research question. This study aims to provide a machine learning approach to predict the user's technology acceptance intention within the framework of robo-advisors. The new approach implements a predictive model from multiple machine learning algorithms such as regression tree, random forest, gradient boosting, and artificial neural network, and then compares the model with the traditional regression analysis methodology. All machine learning algorithms showed superior prediction performance than linear regression. Specifically, gradient boosting showed the best performance and perceived pleasure showed the greatest importance. This research ultimately provides theoretical implication regarding the perspective of acceptance prediction methodology and practical implication about which factors are crucial to acceptance of robo-advisors.
Galyna Chornous, Yana Fareniuk, Vincentas Rolandas Giedraitis
et al.
To improve the marketing activity and brand management and justify the most effective marketing decisions, organizations should implement different information technologies, mathematical methods and models into the marketing decision support system (MDSS). The goal of this paper is to form an architecture of an MDSS, the model base of which is developed on Data Science tools, in particular regression analysis and machine learning methods. The proposed MDSS is a multi-agent information system comprising nine intellectual agents (market environment monitoring, data processing, marketing mix modeling, price policy support, portfolio management, strategic analysis, forecasting, customer segmentation, and customer classification). The functionality of these agents is realized through Data Science, which allows for the optimization of marketing activities (e.g., an effective brand management strategy and its elements (portfolio strategy, price policy, and media strategy) or solving the problems of attracting new and retaining current customers with the maximal return on marketing investments). The MDSS analyzes the marketing environment, media activity, and business indicators by constructing different models and forecasting various combinations of marketing factors to select the best one. The joint work of MDSS agents provides decision-makers with interactive reports. The research findings offer a scientific basis for making effective marketing decisions based on data, and the proposed MDSS can become part of an intelligent system for planning marketing activities.
M. Yu. Konopel'kin, S. V. Petrov, D. A. Smirnyagina
Objectives. In 2020, development work on the creation of a Russian computer-assisted design system for radars (radar CAD) was completed. Radar CAD provides extensive opportunities for creating simulation models for developing the hardware-software complex of radar algorithms, which take into account the specific conditions of aerospace environment observation. The purpose of the present work is to review and demonstrate the capabilities of radar CAD in terms of implementing and testing algorithms for processing stochastic signals.Methods. The work is based on the mathematical apparatus of linear algebra. Analysis of algorithms characteristics was carried out using the simulation method.Results. A simulation model of a sector surveillance radar with a digital antenna array was created in the radar CAD visual functional editor. The passive channel included the following algorithms: algorithm for detecting stochastic signals; algorithm for estimating the number of stochastic signals; direction finding algorithm for stochastic signal sources; adaptive spatial filtering algorithm. In the process of simulation, the algorithms for detecting and estimating the number of stochastic signals produced a correct detection sign and an estimate of the number of signals. The direction-finding algorithm estimated the angular position of the sources with an accuracy of fractions of degrees. The adaptive spatial filtering algorithm suppressed interfering signals to a level below the antenna's intrinsic noise power.Conclusions. The processing of various types of signals can be simulated in detail on the basis of the Russian radar CAD system for the development of functional radar models. According to the results of the simulation, coordinates of observing objects were obtained and an assessment of the effectiveness of the algorithms was given. The obtained results are fully consistent with the theoretical prediction. The capabilities of radar CAD systems demonstrated in this work can be used by specialists in the field of radar and signal processing.
Rudolf N. Faustov, Vladimir O. Galkin, Elena M. Savchenko
We give a review of the calculations of the masses of tetraquarks with two and four heavy quarks in the framework of the relativistic quark model based on the quasipotential approach and QCD. The diquark-antidiquark picture of heavy tetraquarks is used. The quasipotentials of the quark-quark and diquark-antidiquark interactions are constructed similarly to the previous consideration of mesons and baryons. Diquarks are considered in the colour triplet state. It is assumed that the diquark and antidiquark interact in the tetraquark as a whole and the internal structure of the diquarks is taken into account by the calculated form factor of the diquark-gluon interaction. All parameters of the model are kept fixed from our previous calculations of meson and baryon properties. A detailed comparison of the obtained predictions for heavy tetraquark masses with available experimental data is given. Many candidates for tetraquarks are found. It is argued that the structures in the di-<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>J</mi><mo>/</mo><mi>ψ</mi></mrow></semantics></math></inline-formula> mass spectrum observed recently by the LHCb collaboration can be interpreted as <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>c</mi><mi>c</mi><mover accent="true"><mi>c</mi><mo stretchy="false">¯</mo></mover><mover accent="true"><mi>c</mi><mo stretchy="false">¯</mo></mover></mrow></semantics></math></inline-formula> tetraquarks.
he 4th Industrial Revolution introduced a highly automated and connected business environment. Nevertheless, many organizations are reeling in the wake of the speed and severity of the COVID-19 pandemic's impact, catching many unawares, and placing their sustainability in question. Given the connectedness promulgated by the 4th Industrial Revolution, one might expect organizational resilience to be a given - only time will tell whether this was the case. This article considers the concept of cybernetics as contributing to systems-thinking, which may enable resilience strategies to come to fruition. Cybernetics is a goal-driven approach in which constant feedback is analyzed and applied in correcting the current course. We reflect on the roots and principles of the cybernetic concept, developing it into a management cybernetics concept. We take a non-technological approach in acknowledging organizations as systems. Management theories such as stakeholder and stewardship theories are systems components that can play a crucial role in effectively communicating management information within the cybernetic loop. We conclude that an integrative and cooperative relationship with legitimate stakeholders can play an essential role in an organization's preparedness.
With the Cambridge Analytica/Facebook scandal, online surveillance clearly showed its negative effects. However, few individuals were able to recover any damages from the data protection violation that occurred. The EU General Data Protection Regulation contains legal tools to coordinate the interests of data subjects together in the case of infringements that occur across member states of the European Union, not only at the national level (Article 80), but potentially at the transnational level, as implied by Article 81. However, only a reform addressing the rules applicable to the standing of associations and non-governmental organisations in transnational claims as well as those concerning jurisdiction and international lis pendens would allow EU citizens to take full advantage of this opportunity.
Auliya Rahman Isnain, Agus Sihabuddin, Yohanes Suyanto
Currently, the discussion about hate speech in Indonesia is warm, primarily through social media. Hate speech is communication that disparages a person or group based on characteristics such as (race, ethnicity, gender, citizenship, religion and organization). Twitter is one of the social media that someone uses to express their feelings and opinions through tweets, including tweets that contain expressions of hatred because Twitter has a significant influence on the success or destruction of one's image.
This study aims to detect hate speech or not hate Indonesian speech tweets by using the Bidirectional Long Short Term Memory method and the word2vec feature extraction method with Continuous bag-of-word (CBOW) architecture. For testing the BiLSTM purpose with the calculation of the value of accuracy, precision, recall, and F-measure.
The use of word2vec and the Bidirectional Long Short Term Memory method with CBOW architecture, with epoch 10, learning rate 0.001 and the number of neurons 200 on the hidden layer, produce an accuracy rate of 94.66%, with each precision value of 99.08%, recall 93, 74% and F-measure 96.29%. In contrast, the Bidirectional Long Short Term Memory with three layers has an accuracy of 96.93%. The addition of one layer to BiLSTM increased by 2.27%.
Across the globe, net neutrality policy consultations have sought the input of an engaged networked public by recursively mobilising the very technology of the internet itself as a kind of policy participation. This paper examines such cases, where regulators in the United States, Canada, India, and the European Union intended to more accurately represent public interest perspectives. However, as I argue, appeals to the participatory culture of the internet risk reifying participation itself while ignoring systemic inequalities that structure the concept of networked publics according to the exclusionary norms of internet discourse.
هدف: هدف از پژوهش حاضر بررسی تأثیر کتابخانههای عمومی بر آموزش و ترویج مهارتهای شهروندی از دیدگاه مدیران کتابخانههای عمومی بود. روش: روش پژوهش از نوع پپیمایشی-تحلیلی بود. جامعه آماری شامل کلیه مدیران کتابخانههای عمومی وابسته به نهاد کتابخانههای عمومی شهر تهران به تعداد 45 نفر در تابستان 1396 بود. ابزار گردآوری اطلاعات پرسشنامه محقق ساخته بود. یافتهها: شاخص اهمیت آموزش و ترویج مهارتهای شهروندی از سوی کتابخانههای عمومی و نیز اثرگذاری کتابخانهها در این زمینه بیشترین پاسخها را به خود اختصاص داده است. از میان روشها و شیوههای مؤثر در ترویج و آموزش مهارتهای شهروندی در کتابخانههای عمومی از نظر مدیران، نمایش کتابهای مرتبط و برگزاری دورۀ مهارتهای سواد اطلاعاتی از اولویت بیشتری برخوردار بود. نتیجهگیری: نهادهای آموزشی مانند کتابخانه و مراکز اطلاعاتی سهم و نقش بسیار مهمی در ترویج و آموزش مهارتهای شهروندی دارند. همچنین تنوع در ارائه انواع خدمات میتواند در ارتقای انواع مهارتهای شهروندی مؤثر واقع شود.
Opinion Mining or Sentiment Analysis is the task of extracting people final opinion about something through their unstructured sentiments. The Opinion Mining process is as follows: first, product features which are most important to a user are extracted from his/her comments. Then, sentiments will be emotionally classified using their emotional implications. In this paper we propose an opinion classification method based on Fuzzy Logic. Up to now, a few methods have taken advantage of fuzzy logic in opinion classification and all of them have imported fuzzy rules into system as background knowledge. But the main challenge here is finding the fuzzy rules. Our contribution is to automatically extract fuzzy rules and their parameters from training data. Here we have used the Particle Swarm Optimization (PSO) algorithm to extract fuzzy rules from training data. Also, for better results we have devised a mutation-based PSO. All proposed methods have been implemented and tested on relevant data. Results confirm that our method can reach better accuracy than current state of the art methods in this domain.
Current works have been focused on the robustness of single network and interdependent networks. However, to be more correct, the dependence of many real systems should be described as unidirectional. To study the structural robustness of networks with unidirectional dependence, the dependent networks named UDN are proposed, the description of the propagation of failures in them is given, as well as the introduction of the attack strategies that the probability of a node being attacked depends on the degree (DP attack) or on the betweenness (BP attack) of this node. The simulated results show that UDN is more vulnerable to BP attack when is first attacked a node with high betweenness. Compared with the Interacting Networks (IN), the UDN is more fragile under the two attack’s strategies.