Search

Electric fields (E-fields) induced by transcranial magnetic stimulation (TMS) can be modeled using partial differential equations (PDEs). Using state-of-the-art finite-element methods (FEM), it often takes tens of seconds to solve the PDEs for computing a high-resolution E-field, hampering the wide application of the E-field modeling in practice and research. To improve the E-field modeling's computational efficiency, we developed a self-supervised deep learning (DL) method to compute precise TMS E-fields. Given a head model and the primary E-field generated by TMS coils, a DL model was built to generate a E-field by minimizing a loss function that measures how well the generated E-field fits the governing PDE. The DL model was trained in a self-supervised manner, which does not require any external supervision. We evaluated the DL model using both a simulated sphere head model and realistic head models of 125 individuals and compared the accuracy and computational speed of the DL model with a state-of-the-art FEM. In realistic head models, the DL model obtained accurate E-fields that were significantly correlated with the FEM solutions. The DL model could obtain precise E-fields within seconds for whole head models at a high spatial resolution, faster than the FEM. The DL model built for the simulated sphere head model also obtained an accurate E-field whose average difference from the analytical E-fields was 0.0054, comparable to the FEM solution. These results demonstrated that the self-supervised DL method could obtain precise E-fields comparable to the FEM solutions with improved computational speed.

The vapor-phase antibacterial activity of essential oils makes them suitable for applications in air disinfection and other fields. At present, vapor-phase antibacterial activity of plant-based essential oils has rarely been reported. Herein, we report a new approach to investigate the antimicrobial activity and mechanism of vapor-phase cinnamaldehyde using Escherichia coli (E. coli) and three other pathogenic bacteria (Pseudomonas aeruginosa, Salmonella, Staphylococcus aureus) as model bacteria. Plate fumigation and agar block transfer techniques were used to determine the antimicrobial activities of vapor-phase cinnamaldehyde fumigation on the four types of bacteria, and the mechanism of action was determined by electrical conductivity (EC), OD260nm measurement, transmission electron microscopy (TEM), Fourier transform infrared spectroscopy (FTIR), and fluorescence spectroscopy. Cinnamaldehyde had good vapor-phase antibacterial activity against the four types of bacteria. The TEM, EC, and OD260nm measurements showed that after fumigation with cinnamaldehyde, the ultrastructures of the cells were damaged, and plasmolysis, cell collapse, and leakage of intracellular substances were observed. The FTIR and fluorescence spectroscopy analyses showed that the secondary and tertiary structures of bacterial membrane proteins were altered. These findings indicate that the cell membrane is an important target for plant-based essential oils to exert their vapor-phase antimicrobial effects. The results showed that plant-based essential oils can be developed as volatile broad-spectrum disinfection products and vapor-phase antiseptics.

Deoxyribonucleic Acid (DNA) computing has demonstrated great potential in data encryption due to its capability of parallel computation, minimal storage requirement, and unbreakable cryptography. Focusing on high-dimensional image data for encryption with DNA computing, we propose a novel hash encoding-based DNA computing algorithm, which consists of a DNA hash encoding module and content-aware encrypting module. Inspired by the significant properties of the hash function, we build a quantity of hash mappings from image pixels to DNA computing bases, properly integrating the advantages of the hash function and DNA computing to boost performance. Considering the correlation relationship of pixels and patches for modeling, a content-aware encrypting module is proposed to reorganize the image data structure, resisting the crack with non-linear and high dimensional complexity originating from the correlation relationship. The experimental results suggest that the proposed method performs better than most comparative methods in key space, histogram analysis, pixel correlation, information entropy, and sensitivity measurements.

With the development of various network technologies and the spread of coronavirus disease 2019, many online learning platforms have been built. However, some of them may negatively impact student learning outcomes. Therefore, this study aims to improve the online learning effect of students by comprehensively evaluating their learning behavior by using deep learning algorithms. On this basis, new teaching strategies are proposed. According to the structured deep network embedding model, a network representation learning algorithm is proposed with the help of auto-encoders under deep learning. This study elaborates the concept and structure of the encoder model and tests its performance. After the node labels and dataset are trained, the applicable parameter λ2 of the model is 0.3. During the teaching process, the model’s reliability in distinguishing users is examined. Therefore, this model can be applied to network teaching, is an innovative teaching strategy, and provides a theoretical basis for improving teaching methods.

Real economy has always been a crucial component of China’s economic development, while fictitious economy has experienced rapid growth in past decades. As a result, the connection between the real and fictitious economy has become increasingly complex. This study utilized a hierarchical framework for classifying real economy and conducted a hidden causality test and EEMD method to explore a causal relationship between markets. Monthly data from July 2001 to September 2022 were analyzed using a TVP-SV-VAR model to investigate dynamic relationships among the manufacturing, construction, real estate, and financial industries as well as the mechanisms between the real and fictitious economies. The study outcomes demonstrated that the financial and real estate industries have only short-term positive effects on the manufacturing and construction industries, and in the later period of sample intervals, both industries had negative effects on the construction industry. The construction industry in the real economy has already shown a trend of moving “from Real to Virtual”, while the core manufacturing industry in the real economy has not yet exhibited this trend. To prevent the spread of this trend in the real economy, it is necessary to guide the fictitious economy to serve the real economy by regulating its development appropriately. This study offers a novel perspective for examining the real economy and the fictitious economy in China.

Educational innovation reform is used as the background. In response to the need to propose innovative educational programs, the concepts of Distributed Deep Neural Network (DDNN) and deep learning under edge computing are used as the basis. A teaching program for Science Technology Engineering Mathematics (STEM) is proposed. The average training method is used to verify the performance of the model. Sampling rate means the number of samples per second taken from a continuous signal to form a discrete signal. The accuracy and sample ratio obtained are higher than 95%. The communication volume is 309 bytes, which is in a good range. On this basis, a university uses STEM teaching plans and questionnaires to influence the psychological mobilization factors of students' deep learning effects. Challenging learning tasks and learning motivation have the greatest impact on deep learning, and conclusions that both are positive effects are obtained. Therefore, STEM innovative teaching programs can be widely used. The plan provides a reference theory for improving teaching innovation in the context of the basic educational curriculum reform in China. STEM curriculum is the dual subject of teachers and students, and the learning community includes multi-stakeholders. There are hierarchical relationships among the subjects. In terms of financial support, the first two funds come from the school. Learning communities have dedicated sponsorship partners complemented by clear financial planning. There is not much difference in course resources. Still, the learning community will provide more diversified media forms and special websites, and other auxiliary resources are open to all users. They can obtain first-hand resources without applying. In terms of project form, in addition to the core classroom teaching, the latter two can provide richer activities and realize the diversity of time, space, and information exchange.

There are many films and televisions (FATs) on the Internet, but the quality is uneven. This study explores the ability of college students to screen good films and resist bad films in television works in such a large environment. In the deep learning model of FAT, the ability of college students to think about the ideas expressed and the degree of influence on college students’ values are analyzed. Based on this conceptual basis, a questionnaire is designed for the intention and influencing factors of college students’ FAT innovation and entrepreneurship. It reflects the influence of concentration on FAT learning, the cognitive level of deep learning, the ability to process deep learning ideas, the feeling of the teaching process, and the process of self-learning, which all positively impact college students’ FAT entrepreneurial intentions. The importance of innovative deep learning is highlighted, which proves that a good deep learning course guidance method can improve students’ interest and ability and provide a reference for relevant colleges and universities to cultivate pertinent talents of the field of FAT.

Medical diagnostic imaging is essential for the differential diagnosis of cervical lymphadenopathy. Here we develop an ultrasound radiomics method for accurately differentiating cervical lymph node tuberculosis (LNTB), cervical lymphoma, reactive lymph node hyperplasia, and metastatic lymph nodes especially in the multi-operator, cross-machine, multicenter context. The inter-observer and intra-observer consistency of radiomics parameters from the region of interest were 0.8245 and 0.9228, respectively. The radiomics model showed good and repeatable diagnostic performance for multiple classification diagnosis of cervical lymphadenopathy, especially in LNTB (area under the curve, AUC: 0.673, 0.662, and 0.626) and cervical lymphoma (AUC: 0.623, 0.644, and 0.602) in the whole set, training set, and test set, respectively. However, the diagnostic performance of lymphadenopathy among skilled radiologists was varied (Kappa coefficient: 0.108, *p < 0.001). The diagnostic performance of radiomics is comparable and more reproducible compared with those of skilled radiologists. Our study offers a more comprehensive method for differentiating LNTB, cervical lymphoma, reactive lymph node hyperplasia, and metastatic LN.

The purpose of the study is to promote college students to actively respond to the national “Public Entrepreneurship and Mass Innovation” policies and calls, improve college students’ entrepreneurial enthusiasm and their entrepreneurial ability, and cultivate their good entrepreneurial psychological states. First, the relevant content of entrepreneurship psychology and causal attribution theory is displayed. Second, the questionnaire of college students’ entrepreneurship education is formulated and a questionnaire survey is conducted on University N based on the relevant content of entrepreneurship psychology. Subsequently, the management system of new venture A is taken as the research object to construct the management strategy of new ventures and simulate the implementation process. Finally, the questionnaire survey results of college students’ entrepreneurship education are analyzed and the corresponding entrepreneurship education path is formulated. Meanwhile, the implementation effect of the management strategy of new ventures is evaluated. After the questionnaire is sorted out, it is found that there are some problems in college students’ entrepreneurship education, such as weak awareness of entrepreneurship, insufficient publicity, outdated curriculum, and unqualified teachers. The reasons for these problems are the constraints of traditional concepts, insufficient attention, and incomplete system construction. Therefore, a plan is made for overall entrepreneurship education, the publicity of the concept of entrepreneurship education is strengthened, and the setting of entrepreneurship education curriculum and the ability of the teachers for entrepreneurship education are improved. Through the evaluation of the simulation implementation of a new enterprise management strategy, it is found that the new management strategy can achieve the expected effect. Therefore, this study provides some references for the development of college students’ entrepreneurship education and the management strategy of new ventures.

In this study, cement-fly ash composite slurry was used to modify the surface of steel slag aggregate. The evolution law of parameters such as the mass loss rate, dynamic elastic modulus, and compressive strength of the modified material was obtained through the erosion test, and the sulfate erosion was investigated by X-ray diffraction and scanning electron microscopy techniques. The results show that the modification of steel slag aggregate can significantly reduce damage to steel slag concrete during the erosion process. The quality and dynamic elastic modulus of concrete both increased first and then decreased with the erosion time. The compressive strength after erosion was higher than that of ordinary steel slag. Aggregate concrete and ordinary concrete increased by 5.7% and 15.6%, respectively. The microscopic characteristic analysis found that the modified coating filled the pores and microcracks on the surface of the steel slag, making it difficult for SO42- to invade. The number of corrosion products inside the sample was significantly reduced. Additionally, the steel slag aggregate and the active components in the modified coating could interact, resulting in the hydration products effectively filling in the pores and microcracks of the modified concrete, so that the compactness of the modified steel slag aggregate concrete was significantly improved.

Roadside unit (RSU) cloud and its vehicle-to-infrastructure (V2I) connectivity can enable various security, entertainment, and shared mobility applications for vehicles in intelligent transportation systems (ITS) through wireless communications. In this article, the deep programmability of software-defined networking (SDN) is employed to dynamically reconfigure network hosting services and their data forwarding information for effectively meeting the basic shared mobility applications’ needs in vehicle ad hoc networks (VANETs). Multipath is also enabled to forward data flow for balancing network links utilization rate and SDN is thus utilized to achieve the minimum cloud delay with the least number of hosts, which can be summarized as a mixed-integer linear programming (MILP) problem. The joint optimization (JO) algorithm is proposed and in contrast to the two single-objective algorithms which are the delay optimization (DO) algorithm and host optimization (HO) algorithm, respectively. Results show that, for the single-threading instance, the JO and DO algorithms are the same in essence. For the multithreading instance, the JO algorithm generally outperforms the two single-objective optimization algorithms, respectively, under given demands. Furthermore, results also demonstrate that the services should be deployed globally in a distributed manner rather than in the centralized manner for achieving the minimized cloud delay in designing an RSU cloud.

This study aims to evaluate the practical application value of the teaching method under the guidance of educational psychology and artificial intelligence (AI) design, taking the deep learning theory as the basis of teaching design. The research objects of this study involve all the teachers, students, and students' parents of Ningbo Middle School. The questionnaires are developed to survey the changes in the performance of students before and after the implementation of the teaching design and the satisfaction of all teachers, students, and parents to different teaching methods by comparing the two results and the satisfaction ratings. All objects in this study volunteer to participate in the questionnaire survey. The results suggest the following: (1) the effective return rates of the questionnaires to teachers, students, and parents are 97, 99, and 95%, respectively, before implementation; whereas those after implementation are 98, 99, and 99%, respectively. Comparison of the two return results suggests that there was no significant difference statistically (P > 0.05). (2) Proportion of scoring results before and after implementation is given as follows: the proportions of levels A, B, C, and D are 35, 40, 15, and 10% before implementation, respectively; while those after implementation are 47, 36, 12, and 5%, respectively. After the implementation, the proportion of level A is obviously higher than that before the implementation, and the proportions of other levels decreased in contrast to those before the implementation, showing statistically obvious differences (P < 0.05). (3) The change in the performance of each subject after 1 year implementation is significantly higher than that before the implementation, and the change in the average performance of each subject shows an upward trend. In summary, (1) the comparison on the effective return rate of the satisfaction survey questionnaire proves the feasibility of its scoring results. (2) The comparison of the survey scoring results shows that people are more satisfied with the new educational design teaching method. (3) The comparison of the change in the performance of each subject before and after the implementation indirectly reflects the drawbacks of partial subject education, indicating that the school should pay the same equal attention to every subject. (4) Due to various objective and subjective factors, the results of this study may be different from the actual situation slightly, and its accuracy has to be further explored in the future.

Motivated by the call of the International Maritime Organization to meet the emission targets of 2030, this study considers two important practical aspects of quay crane scheduling: efficiency and energy consumption. More precisely, we introduce the bi-objective quay crane scheduling problem where the objective is to minimize the vessel’s completion time and the crane’s energy consumption. This is done by formulating a bi-objective mixed-integer programming model. A branch-and-bound algorithm was developed as the exact solution approach to find the full set of Pareto-optimal solutions. We consider (i) various lower bounds for both objectives, (ii) specific upper bounds, (iii) additional branching criteria, and (iv) fathoming criteria to detect Pareto-optimal solutions. Numerical experiments on benchmark instances show that the branch-and-bound algorithm can efficiently solve small- and medium-sized problems.