An Enhanced Ensemble-Based Long Short-Term Memory Approach for Traffic Volume Prediction

With the advancement of artificial intelligence,traffic forecasting is gaining more and more interest in optimizing route planning and enhancing service quality.Traffic volume is an influential parameter for planning and operating traffic structures.This study proposed an improved ensemble-based deep learning method to solve traffic volume prediction problems.A set of optimal hyperparameters is also applied for the suggested approach to improve the performance of the learning process.The fusion of these methodologies aims to harness ensemble empirical mode decomposition’s capacity to discern complex traffic patterns and long short-term memory’s proficiency in learning temporal relationships.Firstly,a dataset for automatic vehicle identification is obtained and utilized in the preprocessing stage of the ensemble empirical mode decomposition model.The second aspect involves predicting traffic volume using the long short-term memory algorithm.Next,the study employs a trial-and-error approach to select a set of optimal hyperparameters,including the lookback window,the number of neurons in the hidden layers,and the gradient descent optimization.Finally,the fusion of the obtained results leads to a final traffic volume prediction.The experimental results show that the proposed method outperforms other benchmarks regarding various evaluation measures,including mean absolute error,root mean squared error,mean absolute percentage error,and R-squared.The achieved R-squared value reaches an impressive 98%,while the other evaluation indices surpass the competing.These findings highlight the accuracy of traffic pattern prediction.Consequently,this offers promising prospects for enhancing transportation management systems and urban infrastructure planning.

Acceleration Workspace of Cooperating Multi-Finger Robot Systems

We present a mathematical method for acceleration workspace analysis of cooperating multi-finger robot systems using a model of point-contact with friction. A new unified formulation from dynamic equations of cooperating multi-finger robots is derived considering the force and acceleration relationships between the fingers and the object to be handled. From the dynamic equation, maximum translational and rotational acceleration bounds of an object are calculated under given constraints of contact conditions, configurations of fingers, and bounds on the torques of joint actuators for each finger. Here, the rotational acceleration bounds can be applied as an important manipulability index when the multi-finger robot grasps an object. To verify the proposed method, we used a set of case studies with a simple multi-finger mechanism system. The achievable acceleration boundary in task space can be obtained successfully with the proposed method and the acceleration boundary depends on the configurations of fingers.

采用喷墨打印机进行低成本微阵列印刷的可行性研究

根据网点形成技术,微阵列制作方法可归结为接触式印刷和非接触式印刷。接触式印刷中,如印刷生物样本时,设备与基底是直接接触。而非接触式印刷中,设备与基底之间不会直接接触。在非接触式印刷中,喷墨印刷技术是相对灵活、简便、便宜的一种方式,同时还减少了污染且避免了更高的数据吞吐量。但是,喷墨印刷需要有能喷射几微微升墨滴的喷嘴和能够精确喷射墨滴的喷嘴位置控制单元。若使用喷墨方法制作微阵列就需要复杂的机构系统,以致成本增加。因此,本论文提出使用已具有喷墨系统的商用喷墨打印机来制作微阵列。

A novel flexure-based uniaxial force sensor with large range and high resolution

High performance force sensors often encounter the conflicting requirements of high resolution and large measurement range.To address this problem,this paper presents a conceptual design of a novel uniaxial force sensor with large range and dual-stage force resolutions which enables us to measure forces within a wide range with satisfied resolutions.The newly developed force sensor features an aluminum alloy body with a probe to transfer external forces into the sensing element.It employs an optical linear encoder to detect the displacement of the sensing body.This sensing scheme may immunize outside electromagnetic noises and therefore enhance the performance of the sensor thanks to its digital signal output.In this paper,an accurate,analytical model for calculating the static stiffness and dynamics of the system was developed by using pseudo-rigid-body-model(PRBM)methodology.To optimize the design,finite element simulations were conducted.After a prototype sensor was fabricated,preliminary characterization tests were carried out to verify the accuracy of the theoretical model and demonstrate the effectiveness of the design.The experiment results indicate that the structure of the new sensor is compact,and it has the ability to measure both micro range and macro range forces within one setup,meanwhile keeps very fine resolutions.

Development of a hybrid scaffold and a bioreactor for cartilage regeneration

We developed a hybrid scaffold and a bioreactor for cartilage regeneration. The hybrid scaffold was developed as combination of two components: a biodegradable framework and hydrogel-containing chondrocytes. We performed the MTT cell proliferation assay to compare the proliferation and viability of chondrocytes on three types of scaffolds: an alginate gel, the hybrid scaffold, and an alginate sponge. Cells were encapsulated in 2% agarose gel. The bioreactor consisted of a circulation system and a compression system. We performed dynamic cell culture on these agarose gels in the bioreactor for 3 days.

Development and test verification of air temperature model for Chinese solar and Spainish Almeria-type greenhouses

Growth can be defined as an increment in biomass or an increment in weight or height of the organs of the plant influenced by physiological processes.Many of these processes have their limits genetically determined,but climate and irrigation play an important role.Because of its importance,microclimate has been extensively studied in the modeling as a surrounding condition which is imposed by the exterior climate.The main objective of this work was to develop a temperature model based on the energy balance dynamics at two different greenhouse locations-South-eastern Spain and Northern China,and the traditional structures of Chinese solar greenhouse and Almería-type multi-span greenhouse were taken into account.The final model was developed by combining the external conditions,the actuator influence and the crop growth,where the temperature is influenced by soil,crop,cover,actuators,back wall and greenhouse geometry.The model took into account the energy lost by convective and conductive fluxes,as well as the energy supplied by solar radiation and heating systems.The soil and the back wall are the main media for energy storage.The temperature dynamic was determined by a physical model,which considered the energy balance from a holistic point of view-as a sub-model for a customizable interface among the external climate,the plant and the greenhouse system.The influences of different subsystems included in the temperature model were analyzed and evaluated.The results showed a high R^(2)value of 0.94 for Beijing and 0.95 for Almeria,and the average error was low,of which the MAE and RMSE were 0.71 and 1.365 for Almeria and 0.62 and 1.102 for Beijing,respectively.Thus,the model can be considered as a powerful tool for control design purposes in microclimate systems.