Explore the vast range of titles available.

With the continuous emergence and rapid development of high and new technologies such as big data, cloud computing, artificial intelligence, mobile Internet, and the Internet of Things, the platform economy has developed rapidly and has become the current mainstream business model. This paper first analyzes the external driving factors that promote the rapid development of platform-based business models, then combines the existing research results of scholars to analyze the components of platform-based business models and uses deep learning methods. The research carried out model construction, drew causal relationship diagrams and flow diagrams, selected typical and representative platform-based enterprises for research, collected relevant data, and verified that the model's effectiveness reached 98%. On this basis, the model was compounded. Simulation and sensitivity analysis explores the critical factor driving platform-type enterprises to carry out business model innovation: the service quality coefficient of platform-type enterprises.

A fastIMM-extended Viterbi (fastIMM-EV) algorithm-based maneuvering target tracking method is proposed for the real-time tracking of ground maneuvering targets by a ballistic acoustic array, which firstly adopts the extended Viterbi interactive multi-model (IMM-EV) algorithm to select the best model from a given model set to match the maneuvering target motion pattern; secondly, the α – β filter and α – β – γ filter are used to replace the 2D or 3D Kalman filter in the traditional IMM algorithm, respectively, to form the fastIMM-EV algorithm, which nearly improves the algorithm efficiency, and at the same time, for the switching problem of different fastIMM-EV modules, a target maneuver recognition parameter is defined as the switching factor of the fastIMM-EV module, so that fastIMM-EV to switch the module when the target maneuver occurs; finally, the MATLAB simulation test results verify the practicality and high efficiency of the algorithm in this paper compared with different IMM target tracking methods.

Early detection and diagnosis are the key factors in decreasing the breast cancer mortality rate in medical image analysis. A randomized learning technique called extreme learning machine (ELM) plays a vital role in learning the single hidden layer feed-forward network with fast learning speed and good generalization. The input weight and bias are randomly generated and fixed during the ELM training phase, and subsequently, the analytical procedure determines the output weight. The extreme learning machine’s learning ability is based on three uncertainty factors: the number of hidden nodes, an input weight initialization, and the type of activation function in the hidden layer. Various breast classification works have experimented with extreme learning machine techniques and did not investigate the following factors. This paper evaluates the extreme learning machine model’s performance with different configurations on the standard ultra-sound breast cancer dataset, BUSI. The proposed extreme learning machine configuration model experimented on original and filtered ultra-sound images. A fivefold stratified cross-validation scheme is applied here to enhance the model’s generalization performance. The proposed computer-aided diagnosis (CAD) model provides 100% accuracy with the best extreme learning machine configurations. Then, we compare the classification results of the proposed model with typical variants of extreme learning machines like Hybrid ELM (HELM), online-sequential ELM (OS-ELM), Weighted ELM, and complex ELM (CELM). The experimental results demonstrate that the proposed extreme learning machine model is superior to existing models, offering good generalization without any feature extraction or reduction method.

In the field of health care, anesthesia is a crucial therapeutic measure, but it also carries certain risks. Insufficient or excessive anesthesia can lead to significant consequences for patients, such as intraoperative awareness and impaired spontaneous breathing. Therefore, monitoring the depth of anesthesia is one of the vital life-supporting measures during clinical surgery. Currently, commonly used clinical indicators such as blood pressure, heart rate, and respiratory rate are used to estimate the depth of anesthesia in patients. However, due to variations in patients' physical conditions and anesthesia medications, these indicators exhibit significant differences in their performance such that there is not reliable that analyzing these clinical indicators alone. Therefore, considering that electroencephalogram (EEG) reflects a high degree of brain activity, this paper proposes an intelligent detection for anesthesia based on the transformer framework and EEG signals. First, the original single-channel EEG is preprocessed to extract spectral and differential entropy features. Subsequently, the two types of features are fused and sent to the transformer encoder network to complete the anesthesia depth prediction. Finally, the validation of the proposed algorithm was completed on the sevoflurane anesthesia dataset from Waikato Hospital in Hamilton, New Zealand, and a high prediction probability of 85.32% was achieved.

Project-based learning is a relatively novel learning mode in the modern education industry, which helps to improve students’ various abilities. However, in the specific practical process, project-based learning also has many shortcomings that need further improvement. This article integrated intelligent Internet of Things (IoT) technology, analyzed the characteristics of project-based learning, and analyzes the problems it faces in detail. From this, it also explored a model of project-based learning space to study students’ learning behavior. This article also combined the comprehensive weighted fusion algorithm to further explore the evaluation of project-based learning, and carried out relevant experimental analysis. The experimental results showed that in terms of autonomous learning ability, the average test result of this algorithm was 82.30%, while the average test result of traditional algorithms was 76.94%; In terms of teamwork ability, the average test result of this algorithm was 87.25%, the average test result of the traditional algorithm was 78.64%; In terms of skill application ability, the average test result of this algorithm was 78.37%; while, the average test result of traditional algorithms was 72.68%. In summary, this algorithm can effectively evaluate students’ abilities in various aspects.

This work aims to explore the effectiveness of the fuzzy analytic hierarchy process (FAHP) in project engineering risk management and comprehensively investigate the application of genetic algorithm (GA) and neuro-fuzzy system in this field. Experimental research methods are employed, and three different types of projects, namely construction engineering, information technology projects, and manufacturing projects, are selected for risk evaluation. In the research process, an evaluation index system is established by identifying and analyzing the risk factors of each project, and a FAHP model is constructed. To more accurately assess the mutual influences and weights of the factors, fuzzy mathematics, and fuzzy logic methods are applied to fuzzify the parameters during the risk factor stratification and model construction stages. Besides, the GA and neuro-fuzzy system are applied to the model to further construct a decision support system. The research results indicate that the proposed model has an error rate of less than 10%, demonstrating high reliability and accuracy. Furthermore, the use of FAHP can improve the accuracy of risk management control. Compared to the traditional simple hierarchy analysis method, the proposed method improves accuracy by 9.6% and precision by 8.5%. This work provides a new and effective approach for project engineering risk evaluation, which can assist project managers in more accurately evaluating and managing risks, thereby enhancing the efficiency and quality of project management. This work has practical value in improving the efficiency and quality of project management.

In this paper, two new graph labeling techniques are introduced, namely difference amicable labeling and sum amicable labeling, which together are named the twin graph labelings. Here, the formulation of labelings and verification of a few simple, finite, and undirected graphs including cubic graphs, quartic graphs, and multi-regular graphs are verified to be twin graphs. Two new mathematical board games and two coding techniques are introduced and presented as applications.

In order to improve the reliability of wireless communication systems under a malicious jamming environment, a novel anti-jamming algorithm based on PER-DQN which can reach the optimized anti-jamming decisions in the join frequency–power domain is proposed in this paper. In the proposed algorithm, the anti-jamming problem of a wireless communication system is modeled as a Markov decision process and the proposed algorithm engrafts DQN scheme with a prioritized replay strategy to improve its learning efficiency. Simulation results show that the proposed algorithm can overcome the shortcomings of existing schemes and improve the performance of previous anti-jamming algorithms, such as Q -learning and DQN anti-jamming algorithms, in terms of signal transmission gain and algorithm convergence speed.

Emotion recognition using biological brain signals needs to be reliable to attain effective signal processing and feature extraction techniques. The impact of emotions in interpretations, conversations, and decision-making, has made automatic emotion recognition and examination of a significant feature in the field of psychiatric disease treatment and cure. The problem arises from the limited spatial resolution of EEG recorders. Predetermined quantities of electroencephalography (EEG) channels are used by existing algorithms, which combine several methods to extract significant data. The major intention of this study was to focus on enhancing the efficiency of recognizing emotions using signals from the brain through an experimental, adaptive selective channel selection approach that recognizes that brain function shows distinctive behaviors that vary from one individual to another individual and from one state of emotions to another. We apply a Bernoulli–Laplace-based Bayesian model to map each emotion from the scalp senses to brain sources to resolve this issue of emotion mapping. The standard low-resolution electromagnetic tomography (sLORETA) technique is employed to instantiate the source signals. We employed a progressive graph convolutional neural network (PG-CNN) to identify the sources of the suggested localization model and the emotional EEG as the main graph nodes. In this study, the proposed framework uses a PG-CNN adjacency matrix to express the connectivity between the EEG source signals and the matrix. Research on an EEG dataset of parents of an ASD (autism spectrum disorder) child has been utilized to investigate the ways of parenting of the child's mother and father. We engage with identifying the personality of parental behaviors when regulating the child and supervising his or her daily activities. These recorded datasets incorporated by the proposed method identify five emotions from brain source modeling, which significantly improves the accuracy of emotion recognition in comparison with the existing algorithms. The results show a 1% to 2% increase in classification accuracy in absolute terms. Furthermore, an experiment indicates the proposed method performs better than similar methods. We also discovered that the suggested approach performs admirably when using conventional classification techniques.

For the pricing model, a solid economic foundation is the key node to improve the pricing model. This is not only true for stocks and other profitable assets, but also for other assets such as creditor’s rights. This study is mainly based on the empirical asset pricing model, constructs a stochastic equilibrium model, and uses the generalized matrix method to analyze the asset pricing model. The estimation results show that these parameters are significant at the 5% or even 1% significance level, and the estimated values of the parameters meet the economic expectations, which can be tested by over-identification of tool variables. The experimental results prove that the empirical asset pricing model in this paper can effectively improve the effect of the single feedforward neural network model, and emphasize the necessity of feature learning, especially nonlinear unsupervised feature learning, in the application of machine learning in the field of empirical finance, which enriches the relevant research in the cross field of machine learning and empirical finance and has potential practical value.