Identifying the sentiment polarity of movie customer group reviews may inspire the platform to optimize movie recommendation algorithms and improve services and provide suggestions for consumers' movie choices. A MABM sentiment polarity recognition model is proposed based on the multi-head self-attention bidirectional long-short term mechanism. Using the online review data of the well-known movie review website Douban Review as the corpus, text mining tools are used to pre-process the data. Then dividing the data into training and test sets according to 8:2, and using 10 machine learning models and 4 deep learning models as the control group, the effectiveness and robustness of the MABM model are evaluated by cross-validation and test set validation comparison. In the two sets of comparison experiments, it is found that the deep neural network model predicts overall better than the machine learning model, and the MABM model used as the control set has the best classification results. The MABM model can effectively identify the sentiment polarity of consumer reviews, providing management insights and algorithm improvement suggestions for movie recommendation platforms.

To measure the development status, spatial and temporal divergence and development trend of the seven industries in North America, East Asia and Europe, Dagum Gini coefficient, Kernel density estimation and Markov chain method were used for empirical analysis. It is found that there are regional differences in the development levels of the seven industries in the three major regions, and the differences within different regions are ranked from high to low, and the main source of the overall gap is inter-regional differences; in addition, the probability of inter-stage transfer of the development levels of the seven industries is relatively small, with a certain degree of neighbor dependence. Based on both temporal and spatial dimensions, the current development status of the seven global industries is assessed, and the regional industrial development trends are predicted to provide evidence to support the current development status of key industries, and to provide a reference for the national decision on the global regional layout of key industries as well as the development direction.

Assume that the investment portfolio includes an derivative，we study the optimal investment and proportional reinsurance strategies for ambiguity averse insurers, who are concerned about the potential model ambiguity and aim to seek the robust optimal investment and reinsurance strategies. The ambiguity-averse insurers are allowed to purchase reinsurance treaty to mitigate individual claim risks; and can invest in a financial market consisting of one risk-free asset, one risky stock and one derivative. The ambiguity-averse insurers assumed to have exponential utility, and we formulate the optimization problem as an utility maximization problem. By applying the dynamic programming approach, we derive the HJB equation for the value function. Meanwhile, we obtain the closed-form solutions to the optimal investment and reinsurance strategies. Finally, we provide some numerical simulations together with sound economic implications. More important, we demonstrate the utility improvement when considering derivative trading and parameter ambiguity, and find that derivative trading can significantly improve utility when return volatility increases.

Aiming at the problem of consensus enhancement in opinion dynamics of social network, a consensus opinion enhancement with intelligent perception (COEIP) model based on multi-agent reinforcement learning is proposed. In the Markov decision-making process in opinion dynamics, firstly, the decision-making model of agent is designed through bidirectional recurrent neural network to solve the problem of uncertain-length perception. Then, through the idea of difference reward, an effective reward function is designed for the three objectives of convergence efficiency, connectivity and communication cost. Finally, in order to optimize COEIP model, a multi-agent exploration and collaborative update algorithm based on policy gradient is designed, which can enable agents to adaptively learn the neighborhood selection strategy with multi-objective trade-off ability through the reward value in the process of interaction with each other. A large number of simulations verify that COEIP can effectively reconcile the contradictions between agents and reduce the number of clusters when the system is stable in the scenario of opinion dynamics of social network, thus enhancing the consensus opinion of the system. This model provides a new solution for improving the unity of people's opinions under large-scale social networks, which has important theoretical guiding significance.

To improve the tracking accuracy of the gait trajectory of the lower limb exoskeleton robot (LLER) , an experimental method of parameter identification is proposed for the LLER’s two-link dynamic model, including static and dynamic experiment. Combined with the wearer’s human parameters, the accurate dynamic model of the LLER human-machine collaborative system is deduced. The sliding mode control (SMC) with the upper bound of the model and a low-pass filter are adopted to track the gait trajectory precisely by MATLAB. The simulation shows that the waveforms of the hip and knee torques measured by experiment are basically consistent with the theoretical values by calculation, and the dynamic parameter identification results are correct. The human-machine collaborative system based on SMC can realize the accurate tracking of the reference gait trajectories of the hip and knee joints, and the low-pass filter can effectively reduce the high-frequency chattering caused by SMC. This research provides a solution for the identification of the dynamic parameters of LLER, a reference model for the model-based control method, and a reference method for precisely tracking the gait trajectory of LLER human-machine collaborative system

Unmanned aerial vehicles (UAVs) have found important applications in wireless communications and internet of things (IoT) due to their advantages of on-demand and swift deployment, high mobility, and high-quality line-of-sight communication links with ground users. In this paper, a UAV-enabled data collection system is studied, where a UAV collects data from multiple sensors and relays the collected data back to a fusion center. In order to maximize the end-to-end throughput of the data collection system, an optimization problem is formulated to jointly optimize the transmit power and bandwidth of the sensors, as well as the transmit power and flight trajectory of the UAV.The optimization problem is subject to the minimum data transmission constraint, the information-causality constraint, the average and peak transmit power constraint, the bandwidth allocation constraint, and the UAV mobility constraint, and this is a non-convex optimization problem which is difficult to solve. To tackle such a difficulty, this paper proposes an efficient alternative optimization algorithm based on the block coordinate descent method and the successive convex optimization method. The algorithm divides the original problem into a transmit power and bandwidth optimization sub-problem; and a UAV trajectory optimization sub-problem.These two sub-problems are both transformed into convex optimization problems by introducing slack variables and applying the first-order Taylor expansion method,then they can be solved iteratively and alternately. Computer simulation results show that the proposed algorithm can strike a balance between the data collection links and the data forwarding links, and can significantly improve the end-to-end throughput of the system, as compared to other three benchmark schemes, which demonstrates the necessity of optimizing power, bandwidth and flight trajectory jointly.

To improve the performance of shunt hybrid active power filter, a specific sub-harmonic compensation control strategy based on linear active disturbance rejection controller is proposed. By establishing a mathematical model of the shunt hybrid active power filter, the third-order system control problem is simplified into a first-order active disturbance rejection control problem by combining the characteristics of active disturbance rejection control. At the same time, a first-order active disturbance rejection control for harmonic current tracking and a double-closed-loop active disturbance rejection control for the DC bus voltage are designed. Finally, by comparing the traditional PI control through simulation, the strategy makes the harmonic current tracking more stable, the DC-side voltage overshoot is 0, and the current and voltage shocks are effectively suppressed. The harmonic distortion of the grid current after compensation is 1.26%. The results show that the control strategy has good tracking and anti-disturbance capability, the algorithm is simple and has some engineering application value.

A millimeter wave low noise amplifier (LNA) fabricated in 100nm gallium nitride (GaN) high electron mobility transistor (HEMT) process is presented. With a three-stage cascade topology and an optimum concurrent design, this LNA, covering a frequency range from 24 to 30 GHz for 5G millimeter wave Band n257 and n258 applications, achieves low noise figure of 2.4~2.5 dB, small signal gain of 21.1~24.1 dB, and output 1 dB power compression point of greater than 14.4 dBm.

The problem of current algorithms is lack of timeliness and reliability in bridge crack detection. In this paper, a real-time algorithm on embedded platform is proposed. Firstly, moving average method is used to segment the image coarsely. Then, candidate crack fragments are selected by region growing method using the geometric features of their contours. Finally, a crack merging model with two criteria is built to merge the crack fragments recursively and suppress interference, based on the prior condition of bridge cracks. Experimental results show that the proposed method performs better than several existing methods by 115% at least, especially on extracting hairline cracks and complex cases with uneven illumination and dirty mark. Dealing with an image with 15 megapixel on embedded platform, it costs only 1.73 s.

In order to clarify the effect of high temperature aging on light-stable modified asphalt materials, hindered amine light stabilizer was selected to prepare modified asphalt. The light-stablized modified asphalt is subjected to thermal aging treatment under different temperature and time conditions. The influence of thermal aging on the road performance of light-stabilized modified asphalt binder was studied by means of three index tests and Brookfield viscosity test. Atomic Force Microscope (Atomic Force Microscope, AFM) was used to characterize the surface roughness changes of light-stablized modified asphalt under different thermal aging conditions. The influence of thermal aging on the microscopic morphology of asphalt was analyzed by 3D morphology reconstruction and the influence of thermal aging on light-stable modified asphalt was clarified. The results showed that T770 modifier can alleviate the effect of thermal aging on asphalt binder. When the heat aging time exceeded 6 hours, honeycomb structures appeared in the base asphalt. As the aging time increased, the special structure formed on the surface of the base asphalt became smaller gradually. At 6h and 9h, honeycomb structure appeared in the T770 modified asphalt. According to the comparison of roughness data, the surface undulation of modified asphalt was greater than that of base asphalt, which indicated that under the action of heat aging the surface roughness of T770 modified asphalt was slightly higher than that of the base asphalt binder, demonstrating that the light-stable modified asphalt material had the higher sensitivity to heat aging.

Research on the thermal adaptation behavior of the elderly in hot-humid rural areas of China is significant to the energy-saving optimization of village and town houses. This paper selects 7 residential houses in Chatang Village, Tanbu Town, Huadu District, Guangzhou City as the research object. Through the actual measurement of different environmental physical parameters and the subjective questionnaire survey method, the characteristics of thermal adaptation behavior of the elderly during the research are studied. The differences in the thermal adaptation behavior and personality of the elderly will be discussed. The results show that in summer, the elderly in hot-humid rural areas mainly use windows, curtains, electric fans, and change the activity space and other thermal adaptation behaviors for personalized thermal regulation. Among them, the analysis results of the frequency of opening/closing windows, curtains, and electric fans show that the thermal adaptation behaviors have nothing to do with gender, but there are significant age differences. The regulation behavior of the on/off electric fan has no significant effect on the indoor air temperature of the house, but it has a negative correlation with the indoor relative humidity. The rate of going out of the elderly in villages and towns is positively correlated with indoor air temperature and negatively correlated with relative humidity. The subjective thermal perception of the elderly in hot-humid rural areas has no major influence on their thermal adaptation behaviors such as opening windows and turning on electric fans, but has a greater influence on their outing rate.

Organic Rankine cycle (ORC) power generation technology has a wide application potential in the recovery of medium-to-low temperature waste heat and medium-to-low temperature solar thermal power generation. The system optimization design is of great significance to improve system power generation efficiency and reduce the annual generation cost of the system. A synchronous optimization model of the equipment structure parameters and system operation parameters of the solar-driven ORC system is established. Considering the characteristics of solar radiation and ambient temperature changes with time, based on the time series aggregation method, five aggregation points were obtained as design conditions, and the optimal design schemes under the five aggregation design conditions are obtained. The results show that the solar radiation and the environmental design temperature are different, and the designed system structure parameters and operating schemes are different; When the solar radiation is low and the solar radiation value is high, the electricity production cost (EPC) is the lowest and the ORC efficiency is the highest.

Through mild heat treatment of soybeans at an elevated temperature, soybeans show an ordered porous structure, then the static adsorption method and FTIR analysis are used to study the adsorption of neutral red dyes and heavy metal ions. The research contents mainly include: the influence of initial concentration and the initial pH value on the adsorption, and the adsorption kinetic process. It is observed that in the range of acid to weak alkali, the removal rate to neutral red dye is better than other pH value range, and best when the pH is equal to 7. The initial concentration on the adsorption is also an important factor affecting the removal rate and adsorption capacity. At the same time, the removal rate of the adsorbent and the adsorbate in the first 20 minutes of contact is above 80% during the adsorption process. By fitting, the adsorption behavior is more consistent with the quasi-second-order kinetic model. Porous soybean is not only friendly to human beings, but also demonstrates the advantages of high adsorption capacity and low cost. Therefore, it will be a promising environmental cleaning material .

Based on the perspective of government management and the development of institutions themselves, this paper constructs the evaluation index system of new R&D institutions in Guangdong Province, and evaluates the performance of new R&D institutions in Guangdong Province by Data Envelopment Analysis (DEA) method, It is found that there are significant differences in the input-output efficiency of the new-type R&D institutions in different regions, different attributes and different types of R&D. On the basis of the research results, the corresponding countermeasures and suggestions are put forward to provide theoretical support and practical guidance for the follow-up management and high-quality development.

In order to increase the diversity and novelty of structural design in the structural innovation design of automated warehouse, the extension innovation method is applied to the structural design of shuttle shelf, and the general process of its structural extension design given. According to the user's demand and original data, the extension model of shuttle shelf is established, and the mapping relationship among function event element, component matter element and connection relation element is analyzed, and the implication system of function event element set is established. The relevant analysis network of automated warehouse shelf structure design is established, the analysis and implement the corresponding active transformation expanded, and then the creative strategy set of automated warehouse structure design obtained. The optimal strategy has been applied to enterprise production, with good practicability.

The transaction volume of cosmetics is surging, as e-commerce advances rapidly in the context of the Internet and big data, resulting in a large amount of packaging waste that is difficult to recycle. To address the contradictory issues between the high cost of recycling and processing and the low recycling value in the plastic recycling and processing system for cosmetic bottles, reducing the cost of recycling and processing to within target cost range, and improving recycling efficiency to promote the recycling of cosmetics bottles, this paper applies the first creating method to the design idea generation of a plastic recycling and processing system for cosmetics bottles. We first analyzed the unmet needs of the recycling party, established an Extenics model of the contradictory problem, and determined the functional affair-element, the property characteristic-element and the substantial characteristic-element of the recycling system. We then performed extensible analysis and extension transformation on the conjugate part, obtained multiple schemes, judged whether the contradictory problem was solved or not, and used the dependent function of superiority evaluation method to derive the optimal creativity and deepen it. Using the superiority evaluation method, it was calculated that creativity S₃ has the highest degree of superiority, the actual cost of recycling and processing was lower than the target cost after the enterprise assessment, and the contradiction problem was solvedand the creativity has been adopted by the enterprise. Finally, we verify the validity of the application of the first creating method in the design of plastic recycling and processing system for cosmetic bottles.