Search

In recent years, skin spectral information has been gradually applied in various fields, such as the cosmetics industry and clinical medicine. However, the high price and the huge size of the skin spectrum measurement device make the related applications of the skin spectrum unable to be widely used in practical applications. We used convolutional neural network (CNN) to achieve a satisfying accuracy of the Fitzpatrick skin-type classification by using a simple self-developed device in 2018. Leveraging on the hardware, firmware, and software app-developing experience, a low-cost miniature skin spectrum measurement system (LMSSMS) using deep neural network (DNN) technology was further studied, and the feasibility of the system is verified in this paper. The developed LMSSMS is divided into three parts: (1) miniature skin spectrum measurement device (MSSMD), (2) DNN model, and (3) mobile app. The MSSMD was developed with innovative low-cost MSSC, 3D printing, and a simple LED light source. The DNN model is designed to enhance measurement accuracy. Finally, the mobile app is used to control and show the measurement results. The developed app also includes a variety of skin-spectrum-related applications, such as erythema index and melanin index (EI/MI) measurement, Fitzpatrick skin-type classification, Pantone SkinTone classification, sun-exposure estimation, and body-fat measurement. In order to verify the feasibility of LMSSMS, we used the standard instrumentation device as a reference. The results show that the accuracy of the LMSSMS can reach 94.7%, which also confirms that this development idea has much potential for further development.

The number of mobile subscribers has increased tremendously in recent years. The orthogonal frequency- division multiplexing (OFDM) system carries the message data on orthogonal subcarriers for parallel transmission, combating the distortion caused by the frequency selective channel or equivalently, the inter-symbol-interference in the multi-path fading channel. Carrier frequency offset (CFO) in OFDM systems, which can induce the loss of orthogonality among subcarriers and result in significant performance degradation, is critical to be estimated and compensated for. In this paper, the pilot symbol is used to estimation CFO in OFDM systems. We use a Bisection method to obtain estimation performance of CFO well and fast.

Carrier frequency offset (CFO) is a major factor that degrades performance of the orthogonal frequency division multiplexing (OFDM) system. For orthogonal frequency division multiple access (OFDMA) uplink systems, there are multiple CFOs need to be estimated simultaneously, which is a very challenging task. Particle swarm optimization (PSO) algorithm has been recognized a potential approach for CFOs estimation. However, its performance deteriorates as the number of users increases due to insufficient particles diversity. To overcome this difficulty, an enhanced PSO called MRPSO is proposed to increase particles diversity by employing mutation and repulsive operations. Furthermore, a least square (LS) scheme is adopted to improve the estimated CFOs. Simulation results indicate that the proposed MRPSO attains best BER and MSE performances in CFOs estimation as compared to other PSO-based schemes.

In multi-carrier code-division multiple-access (MC-CDMA) system the multiple access interference (MAI) is a critical factor that significantly degrades system performance. In this research the genetic algorithm (GA) is employed for joint channel estimation and multi-user detection. For improving exploration and exploitation strengths of GA, a GA-based approach called SAM-GA is developed by incorporating the simulated annealing (SA) to mutation operation. Furthermore, a threshold-based mutation is proposed to refine the SAM-GA scheme. The resulting scheme is called modified SAM-GA for simplicity. Experimental result demonstrates that the proposed modified SAM-GA scheme achieves the best performance in terms of mean squared error (MSE), bit error rate (BER), and convergence rate for joint CIR estimation and multi-user detection in the MC-CDMA system as compared to other schemes.

In future communications, cooperative communication with relay networks will be the one of the most effective scheme to enlarge coverage area and to boost data rate. In the recent research results, the path selection, power allocation and relay protocols on relay networks are the most important factors to improve the system performance. However, the channel quality of direct transmission path and the relay path will be the influential effect on the performance of relay networks. Therefore, in this paper, we proposed an adaptive path selection (APS) scheme to effectively select the optimal path for cooperative communications.

In this paper, we propose a method that joints channel estimation and interference cancellation for direct-sequence ultra-wideband (DS-UWB) systems. For the channel estimation, we apply an expectation-maximization algorithm which adopts an iterative computation of maximum-likelihood parameter estimates, with a few number of iterations, the channel coefficient in each finger of Rake receiver can be efficiently estimated. A fuzzy step size LMS algorithm that adopts a variable step size for the interference cancellation is proposed in the multiuser transmission environment. To achieve a better performance, the joint of expectation-maximization (EM) algorithm and fuzzy adaptive filter is presented for the DS-UWB systems and the simulation result is investigated as well.

In this paper, we propose an adaptive particle swarm optimization (APSO) based partial parallel interference cancellation scheme for direct-sequence code-decision multiple access (CDMA) communication system over frequency selective fading channels. However, the partial cancellation tries to reduce the cancellation error in parallel interference cancellation schemes due to the wrong interference estimations in the early stages. Thus, in order to reduce the computational complexity and improve the performacne of the CDMA system, particle swarm optimization (PSO), which has the ability of solution to complex combinatorial optimization problem, is employed in searching the optimal weight for multiple access interference cancellation. Experiments have been carried out on the method can improved on the multiuser detection in CDMA system, the simulation results show that APSO detector can achieve the global optimization in fast convergence rate, and also show that the proposed detector is obviously superior to convenentional receiver and multiuser detectors based on some optimum algorithm in terms of the multiple access interfere and the mitigation of near-far effect.

This paper proposes that the Hopfield neural network (HNN) with hyperbolic tangent activation is introduced and applied to multiuser detection in direct sequence-ultra-wideband (DS-UWB) systems. It can approximate to maximum likelihood (ML) detector by mathematical analysis. The HNN with hyperbolic tangent activation (tanhHNN) can enhance the performance of HNN detector. According to the HNN technology, the computer simulation results show that they have good performances and much lower computational complexity in a multiuser environment.