Search

Alzheimer's disease (AD) is an irreversible neurodegenerative disease, and the early diagnosis and effective intervention of AD is essential for patients and doctors. Intelligence diagnosis based on magnetic resonance imaging and deep learning has become one of the useful methods for AD identification. To improve the diagnosis effect of AD in early stages, a novel multi‐scale classification model of AD, called MSFNet‐2SE, is proposed. First, a new multi‐scale fusion (MSF) feature extraction module is designed based on the idea of the feature maps split into feature subsets of Res2Net. Second, a channel attention module is embedded into the MSF module through integrating two Squeeze‐and‐Excitation (SE) blocks. Finally, a gradient centralization Adam optimizer is used to improve the model classification performance. Experimental results illustrate that, compared with other available state‐of‐the‐art classification models of AD, the proposed model has excellent classification performance. It is helpful to improve the clinical diagnosis efficiency. [ABSTRACT FROM AUTHOR]

A Sigma-Delta modulator (SDM) realized with a fully differential third-order single-loop cascaded integrator feedforward (CIFF) architecture is proposed. A pair of low-frequency chopper switches are nested outside the chopper amplifier to further reduce the residual offset voltage. To reduce the power consumption and ensure linearity, a high-speed dynamic comparator is also used to implement a one-bit quantizer. The proposed architecture and the corresponding functionality are first simulated in MATLAB Simulink at the behavioral level. The results show that the designed modulator has an SNDR of 124.9 dB corresponding to an ENOB of 20.46 bits at a clock frequency of 256 kHz and 312.5 Hz input with a differential-mode voltage of 700 mV sinusoidal waveform. Based on SMIC 180 nm/1.8 V standard CMOS process on the Cadence platform, the subcircuit-level simulation is also performed, while the result shows that the proposed modulator can effectively achieve 115.52 dB SNDR, 18.90-bit ENOB, and 8.40 mW power consumption, which correspond to FoM W and FoM schreier of 0.067 pJ/step and 163.27 dB, respectively. The proposed modulator shows a significant advantage to be applied for high-precision analog-to-digital conversion applications such as high-quality equipment for audio, ECG and EEG signal sensing. [ABSTRACT FROM AUTHOR]

A novel algorithm is proposed for optimal extraction of GaN HEMT small-signal model parameters. The proposed Quantum Genetic Algorithm (QGA) exploits the superposition, entanglement and interference of quantum states, which solves the problems of high number of iterations and slow convergence when obtaining optimal solutions using Genetic Algorithms (GA). Meanwhile, it is solved that the Particle Swarm Optimisation (PSO) algorithm produces premature convergence and easily falls into the local optimum solution. In order to avoid the influence of distributed parasitic effects in large size devices under high-frequency conditions, a suitable frequency range is determined and combined with direct extraction techniques to determine the range of parameter values. The model parameter values are optimised step by step using QGA. In order to verify the superiority of QGA, QGA and PSO algorithms are both used to optimise GaN HEMT small-signal model parameters. By comparing the modelled S-parameter effects of the QGA and the PSO algorithm, it can be found that the QGA has better consistency with the measured data. [ABSTRACT FROM AUTHOR]

Uncertain differential equations are important mathematical models in uncertain environments. This paper investigates uncertain multi-dimensional and multiple-factor differential equations. First, the solvability of the equations is analyzed. The α-path distributions and expected values of solutions are given. Then, structure preserving uncertain differential equations, uncertain Hamiltonian systems driven by Liu processes, which possess a kind of uncertain symplectic structures, are presented. A symplectic scheme with six-order accuracy and a Yao-Chen algorithm are applied to design an algorithm to solve uncertain Hamiltonian systems. At last, numerical experiments are given to investigate four uncertain Hamiltonian systems, which highlight the efficiency of our algorithm.

The feasibility of underground gasification of Yan 9 coal seam of the middle-lower Jurassic Yan ′an Formation in J148 area of Dongsheng gas field is systematically studied from the perspectives of geological structure, hydrogeology and coal gasification characteristics, and the prospects of carbon sequestration by using the pore layer, aquifer layer and tight gas layer in the deep coal gasification cavity are discussed.The results show that the coal seam of Yan 9 in this area is stable when the buried depth is 1 264~1 285 m and the dip angle is less than 1°.In the interior of the gasification target constituency, the structural faults are not developed, the joint cracks are not developed, there are occasional cracks but the section is fresh and closed, and the cavity of the coal seam after gasification has a good tightness, which has little influence on the construction and expansion of coal gasification furnace, and can meet the implementation of large-scale coal gasification projects.There is a continuous water barrier layer on the top and bottom of Yan 9 coal seam, which can prevent the influence of groundwater on the direct water filling of coal seam, and is conducive to the layout of underground gasifier.The thickness of the roof water-barrier layer is less than the height of the water-conducting fissure zone, there is a risk of indirect water filling through the roof aquifer, but the roof aquifer is a weak water-rich aquifer, and the risk of small water inflow is controllable.The thickness of the floor water barrier layer is greater than the safe thickness of the floor water barrier layer, which can effectively prevent the risk of direct water filling to the coal seam.In general, Yan 9 coal seam has moderate thickness, little waste, low ash, low sulfur, high calorific value non-stick coal, high coke reactivity, and has a good development prospect.In view of the large amount of CO2 emission from large-scale gasification mining of deep coal seam, the feasibility of CO2 safe geological storage by using coal seam burning and caving area, top and bottom aquifer and lower tight natural gas layer was discussed.The analysis shows that 60.8 % ~88.2 % of CO2 produced by coal seam gasification can be stored in the pore layer and the top and bottom aquifer in the gas-burning and air-burning zone of Yan 9 coal seam.Combined with the development of tight natural gas in the Upper Paleozoic of Dongsheng gas field, it is expected to achieve near-zero carbon emissions in the process of deep coal seam gasification mining by using CO2 generated by coal gasification for natural gas displacement and storage.