TSCND:Temporal Subsequence-Based Convolutional Network with Difference for Time Series Forecasting

Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in time series forecasting. However, two problems weaken the performance of TCNs. One is that in dilated casual convolution, causal convolution leads to the receptive fields of outputs being concentrated in the earlier part of the input sequence, whereas the recent input information will be severely lost. The other is that the distribution shift problem in time series has not been adequately solved. To address the first problem, we propose a subsequence-based dilated convolution method (SDC). By using multiple convolutional filters to convolve elements of neighboring subsequences, the method extracts temporal features from a growing receptive field via a growing subsequence rather than a single element. Ultimately, the receptive field of each output element can cover the whole input sequence. To address the second problem, we propose a difference and compensation method (DCM). The method reduces the discrepancies between and within the input sequences by difference operations and then compensates the outputs for the information lost due to difference operations. Based on SDC and DCM, we further construct a temporal subsequence-based convolutional network with difference (TSCND) for time series forecasting. The experimental results show that TSCND can reduce prediction mean squared error by 7.3% and save runtime, compared with state-of-the-art models and vanilla TCN.

Dynamic Multi-Attribute Decision-Making Method with Double Reference Points and Its Application

To better reflect the psychological behavior characteristics of loss aversion,this paper builds a double reference point decision making method for dynamic multi-attribute decision-making(DMADM)problem,taking bottom-line and target as reference pints.First,the gain/loss function is given,and the state is divided according to the relationship between the gain/loss value and the reference point.Second,the attitude function is constructed based on the results of state division to establish the utility function.Third,the comprehensive utility value is calculated as the basis for alternatives classification and ranking.Finally,the new method is used to evaluate the development level of smart cities.The results show that the new method can judge the degree to which the alternatives meet the requirements of the decision-maker.While the new method can effectively screen out the unsatisfactory alternatives,the ranking results of other alternatives are consistent with those of traditional methods.

Wind-Thermal Environmental Characteristic of Multi-Variable Passive Enhanced Natural Ventilation System for High and Large Space Building

Natural ventilation effects in high and large space buildings of tropical areas greatlya ffect the air conditioning energy consumption.Aiming at nearly zero energy building design,thisp aper mainly contributes to provide theoretical basis and reference for thermal comfortable air conditioning system design of high and large space buildings.Taking a theatre in Hainan as study object,a newly composite enhanced natural ventilation system is proposed by integrating theu nderground tunnel-based earth to air heat exchange system and the solar chimney.Ventilationq uantity,air velocity and air temperature field,human vertical temperature gradient differenceu nder24simulation working conditions are considered and analyzed by using ANSYS Fluent.Fort he underground tunnel,results show that Group Two with double underground tunnels and side airs upply location shows its advantages in cooling effects and air supply uniformity.Then for the solar chimney,results show that the solar radiation intensity contributes to larger difference int ransmission power and leads to different cooling effects.On the whole,the system under workingc ondition No.7with120m long,side air supply,double underground tunnel and20m high,1mw ide,0.6°absorber plate angle solar chimney shows its priority in better comprehensive performance.

Non-layered InSe nanocrystalline bulk materials with ultra-low thermal conductivity

Exploring new prototypes for a given chemical composition is of great importance and interest to several disciplines.As a famous semiconducting binary compound,InSe usually exhibits a two-dimensional layered structure with decent physical and mechanical properties.However,it is less noticed that InSe can also adopt a monoclinic structure,denoted as mcl-InSe.The synthesis of such a phase usually re-quires high-pressure conditions,and the knowledge is quite scarce on its chemical bonding,lattice dynamics,and thermal transport.Here in this work,by developing a facile method combining me-chanical alloying and spark plasma sintering,we successfully synthesize mcl-InSe bulks with well-crystallized nanograins.The chemical bonding of mcl-InSe is understood as compared with layered InSe via charge analysis.Low cut-off frequencies of acoustic phonons and several low-lying optical modes are demonstrated.Noticeably,mcl-InSe exhibits a low room-temperature thermal conductivity of 0.6 W·m^(-1)·K^(-1),which is smaller than that of other materials in the IneSe system and many other selenides.Low-temperature thermal analyses corroborate the role of nanograin boundaries and low-frequency optical phonons in scattering acoustic phonons.This work provides new insights into the non-common prototype of the InSe binary compound with potential applications in thermoelectrics or thermal insulation.

Remarkable plasticity and softness of polymorphic InSe van der Waals crystals

Indium selenide(InSe)crystals are reported to show exceptional plasticity,a new property to twodimensional van der Waals(2D vdW)semiconductors.However,the correlation between plasticity and specific prototypes is unclear,and the understanding of detailed plastic deformation mechanisms is inadequate.Here three prototypes of InSe are predicted to be plastically deformable by calculation,and the plasticity of polymorphic crystals is verified by experiment.Moreover,distinct nanoindentation behaviors are seen on the cleavage and cross-section surfaces.The modulus and hardness of InSe are the lowest ones among a large variety of materials.The plastic deformation is further perceived from chemical interactions during the slip process.Particularly for the cross-layer slip,the initial In-Se bonds break while new In-In and Se-Se bonds are newly formed,maintaining a decent interaction strength.The remarkable plasticity and softness alongside the novel physical properties,endow InSe great promise for application in deformable and flexible electronics.