In this paper, a lightweight deep neural network (DNN) for direction of arrival (DOA) estimation is proposed, of which the input vector is designed to remove data redundancy as well as remaining DOA information. By exploring the Vandermonde property of the steering vector of a uniform linear array (ULA), the size of the newly designed input vector is greatly reduced. Furthermore, the DOA estimation is designed as a regression problem instead of a classification problem; that is, the lightweight DNN designs the output vector as the estimated DOAs of sources, of which the size is much shorter than that of the spatial spectrum used as the output vector in the conventional DNN. The reductions in the sizes of input and output vectors lead to a reduction in the sizes of hidden layers, achieving lightweightness of the neural network. The analysis illustrates that when the number of sensors is 22, the number of parameters in the lightweight DNN is three orders of magnitude less than that in the conventional DNN. The simulation results demonstrate the lightweight DNN can provide high DOA estimation accuracy with the shortest testing time. It performs better than the conventional DNN. Furthermore, it is superior to traditional solutions such as the multiple signal classification (MUSIC) method and conventional beamforming (CBF) method in harsh conditions like low signal-to-noise ratios (SNRs), closely spaced sources, and few snapshots.

An indirect evaporative cooling system combining with thermoelectric cooling technology (i.e., TIEC system) is proposed, in which a counter-flow plate-fin indirect evaporative cooler is inserted with thermoelectric cooling (i.e., TEC) modules. In hot and humid climate, condensation may occur on the dry channel surface of the cooler. For the TIEC system, with the aid of TEC technology, the surface temperature of the dry channel can be much lower than that of a traditional indirect evaporative cooler, thus, the condensation from the primary air is more likely to take place. A numerical model of this novel TIEC system is developed with specifically taking condensation from primary air into account. Detailed performance analysis of the TIEC system is carried out. Analytical results found that the condensation from primary air reduces the dew point effectiveness by up to 45.0% by weakening the sensible heat transfer but increases the coefficient of performance by up to 62.2% by increasing the latent heat transfer, under given conditions. The effects of main operating conditions, such as the electrical current I and number n of TEC modules, inlet temperature T_p,i, humidity ratio RH_p and velocity V_p of the primary air, and the mass flow rate ratio x of secondary to primary air, are investigated under non-condensation and condensation states. It is shown that condensate is more easily produced under higher I, n, T_p,i, RH_p, x and lower V_p.