Use of NIRS technology with a remote reflectance fibre-optic probe for predicting major components in bee pollen

In the present work, we study the use of near infra-red spectroscopy (NIRS) technology together with a remote reflectance fibre-optic probe for determination of the major components in bee pollen. The method allows immediate control of the bee pollen without prior sample treatment or destruction through direct application of the fibre-optic probe to the sample.The regression method employed was modified partial least squares (MPLS). The calibration results obtained using 45 samples of bee pollen allowed the measurement of protein, moisture, ash, reducing sugars, and pH with multiple correlation coefficients (RSQ) and prediction corrected standard errors (SEPC) of 0.91, 0.56% for protein, of 0.78 and 0.49% for moisture; 0.92 and 0.049% for ash; 0.81 and 1.32 g of glucose/100 g of bee pollen; 0.84 and 0.15 for pH, respectively.The prediction capacity of the pattern was checked by applying it to samples of unknown pollen in external validation.     

Genetic Bee Colony (GBC) algorithm: A new gene selection method for microarray cancer classification

Naturally inspired evolutionary algorithms prove effectiveness when used for solving feature selection and classification problems. Artificial Bee Colony (ABC) is a relatively new swarm intelligence method. In this paper, we propose a new hybrid gene selection method, namely Genetic Bee Colony (GBC) algorithm. The proposed algorithm combines the used of a Genetic Algorithm (GA) along with Artificial Bee Colony (ABC) algorithm. The goal is to integrate the advantages of both algorithms. The proposed algorithm is applied to a microarray gene expression profile in order to select the most predictive and informative genes for cancer classification. In order to test the accuracy performance of the proposed algorithm, extensive experiments were conducted. Three binary microarray datasets are use, which include: colon, leukemia, and lung. In addition, another three multi-class microarray datasets are used, which are: SRBCT, lymphoma, and leukemia. Results of the GBC algorithm are compared with our recently proposed technique: mRMR when combined with the Artificial Bee Colony algorithm (mRMR-ABC). We also compared the combination of mRMR with GA (mRMR-GA) and Particle Swarm Optimization (mRMR-PSO) algorithms. In addition, we compared the GBC algorithm with other related algorithms that have been recently published in the literature, using all benchmark datasets. The GBC algorithm shows superior performance as it achieved the highest classification accuracy along with the lowest average number of selected genes. This proves that the GBC algorithm is a promising approach for solving the gene selection problem in both binary and multi-class cancer classification.     

无线传感器网络通信技术与标准化分析

通过分析现有无线传感器网络标准,并对Zig Bee、蓝牙以及Wi-Fi这3种最常用标准的优缺点进行详细比较,探讨了无线传感器网络通信技术面临的挑战,进一步研究策略和未来发展趋势。     

Synthesis of satellite footprint patterns from rectangular planar array antenna by using swarm‐based optimization algorithms

A pattern synthesis method based on Firefly Algorithm (FA) and Artificial Bee Colony (ABC) optimization has been presented to generate satellite footprint patterns from a rectangular planar array of isotropic antennas by modifying the amplitude, phase, and the state of the array elements. Three cases comprising three different footprints of rectangular, square, and circular boundary are generated from the same array by using two different swarm‐based optimization algorithms FA and ABC. Both the algorithms, following the proposed procedures are able to generate the three different footprint patterns while maintaining a satisfactory lower peak side lobe level and ripple. A comparative analysis has been carried out between FA, ABC, and Genetic Algorithm (GA) for the presented problem in terms of fitness value for the three different cases. The superiority of FA and ABC over GA has been established in terms of finding better solutions for all the three cases of the proposed problem. Copyright © 2013 John Wiley & Sons, Ltd.     

六种蜂花粉的红外光谱三级鉴别研究

采用傅里叶变换红外光谱(FTIR)结合二阶导数谱和热扰动下的二维相关红外光谱技术对6种不同花粉,即杏花花粉、油菜花粉、茶花花粉、西瓜花粉、荷花花粉和虞美人花粉,进行了快速无损的鉴别。结果表明,在一维红外光谱图上,不同花粉的蛋白质、脂肪和糖类物质的特征吸收峰在相对峰强和峰位上均存在一定的差异,在二阶导数谱上差异很明显。而在二维红外谱图上,由于6种花粉的自动峰及相关峰峰簇的位置和数量不同,其差别体现得更为明显和直观。因此,三级红外宏观指纹图谱法是鉴别不同蜂花粉种类的一种有效和快速检测方法。     

一种基于ABC的量子神经网络训练算法

传统的量子神经网络的训练方法容易使得算法陷入局部极小值,将Artificial Bee Colony(ABC)算法引入到原训练算法中,并且对人工蜂群算法进行改进.利用改进后的人工蜂群算法来优化传统量子神经网络,使优化后的量子神经网络具有结构简单、参数少、收敛速度快和可跳出局部极小值等优点.实验结果表明,相比原训练算法该优化算法提高了量子神经网络收敛解的精度.     

ZigBee信标同步算法设计与仿真

由于受到时钟准确性和精度要求的影响,传统网络中的时间同步算法已经不能满足无线传感器网络的要求.根据ZigBee郊术的特点,研究了基于CSMA-CA机制的具有针对性的信标同步算法.给出了相应的算法分析、算法流程,以及在NS2平台中的仿真结果与性能分析,同时给出了在信标网络与非信标网络中的效果对比.     

基于 GPU 加速的细粒度并行人工蜂群算法

为了改善人工蜂群算法对于大规模数据、高复杂度问题的执行效率,采用开放计算语言(OpenCL )并行编程模型,提出一种基于图形处理器(GPU )加速的并行人工蜂群算法.将每只采蜜蜂映射到 OpenCL 的一个工作组,跟随蜂采用局部轮盘赌选择,使得人工蜂群算法在 GPU 中加速执行.实验结果表明,并行人工蜂群算法取得了较好的优化效果,提高了算法的运算速度.     

微波消解-石墨炉原子吸收光谱法测定蜂花粉中铅、镉和铜

建立蜂花粉中铅、镉和铜3种重金属含量的测定方法。采用浓硝酸和过氧化氢(体积比4:1)混合液对样品进行微波消解,石墨炉原子吸收光谱法测定铅、镉和铜的含量。该方法对花粉样品中铅、镉和铜测定的加标回收率分别为93.3%、101.0%和99.4%,相对标准偏差(RSD)分别为1.1%、6.0%和3.0%,准确度和精密度良好。本法用微波溶样,石墨炉原子光谱法测定铅、镉和铜,具有简便快速、灵敏准确,重复性好的特点,并且节省试剂、污染少。该法可为蜂花粉质量控制提供方法参考。     

一种强鲁棒性的盲分离混合矩阵估计方法

针对传统盲分离混合矩阵估计鲁棒性差、易受初始值影响、精度不高等问题,该文将人工蜂群算法(ABC)用到盲分离中,结合稀疏信号混合矩阵估计的特点,提出一种基于不同搜索策略和编码方式的两阶段蜂群算法的混合矩阵估计方法,通过新的蜜蜂搜索行为和子蜂群之间的协同作业,明显加快了算法的收敛速度,提高了混合矩阵的估计精度。仿真实验表明,该方法在源个数较多、弱稀疏、低信噪比的情况下仍然可以很好地估计混合矩阵。相比已有方法,该方法不仅具有很强的鲁棒性和很高的估计精度,而且不需要太大的计算量。