呼叫中心智能排班系统关键技术

分析学习率和训练精度对BP神经网络训练最大次数、收敛时间和话务量预测精度的影响;根据呼叫中心历史话务量数据的日变化特点,提出并验证采用分时间段多次调用BP神经网络模型的方法比整体预测所得话务量预测结果精度更高;基于话务量预测结果,使用Erlang-C公式进行坐席数预测,结合呼叫中心的典型班次、设定的服务水平等参数进行坐席数曲线拟合,得到每个典型班次对应的话务员数量;开发呼叫中心智能排班系统,通过合理的排班实现大型呼叫中心资源的合理配置。     

A new fast motion estimation algorithm using fast mode decision for high-efficiency video coding standard

High-efficiency video coding is the latest standardization effort of the International Organization for Standardization and the International Telecommunication Union. This new standard adopts an exhaustive algorithm of decision based on a recursive quad-tree structured coding unit, prediction unit, and transform unit. Consequently, an important coding efficiency may be achieved. However, a significant computational complexity is resulted. To speed up the encoding process, efficient algorithms based on fast mode decision and optimized motion estimation were adopted in this paper. The aim was to reduce the complexity of the motion estimation algorithm by modifying its search pattern. Then, it was combined with a new fast mode decision algorithm to further improve the coding efficiency. Experimental results show a significant speedup in terms of encoding time and bit-rate saving with tolerable quality degradation. In fact, the proposed algorithm permits a main reduction that can reach up to 75 % in encoding time. This improvement is accompanied with an average PSNR loss of 0.12 dB and a decrease by 0.5 % in terms of bit-rate.     

Robust‐Adaptive Control Strategies for a Time Delay Bioelectrochemical Process Using Interval Observers

The paper addresses the design and the analysis of adaptive and robust‐adaptive control strategies for a complex recycled wastewater treatment bioprocess. The design procedures are developed under the realistic assumptions that the bacterial growth rates are unknown and the influent flow rates are time‐varying and uncertain, but some lower and upper bounds of these uncertainties are known. The proposed control structures are achieved by combining a linearizing control law with an appropriately (asymptotic or interval based) state observer and with a parameter estimator used for on‐line estimation of unknown kinetics. These approaches are applied to a complex time delay bioprocess resulting from the association of a recycling bioreactor with an electrochemical reactor. Numerical simulations are performed in order to validate the proposed algorithms.     

Image blur and energy broadening effects in XPEEM

We report image blurring and energy broadening effects in energy-filtered XPEEM when illuminating the specimen with soft X-rays at high flux densities. With a flux of 2×10¹³ photons/s, the lateral resolution in XPEEM imaging with either core level or secondary electrons is degraded to more than 50 nm. Fermi level broadening up to several hundred meV and spectral shift to higher kinetic energies are also systematically observed. Simple considerations suggest that these artifacts result from Boersch and Loeffler effects, and that the electron-electron interactions are strongest in the initial part of the microscope optical path. Implications for aberration corrected instruments are discussed.     

Subquadratic Algorithms for 3SUM

We obtain subquadratic algorithms for 3SUM on integers and rationals in several models. On a standard word RAM with w-bit words, we obtain a running time of . In the circuit RAM with one nonstandard AC ⁰ operation, we obtain . In external memory, we achieve O(n ²/(MB)), even under the standard assumption of data indivisibility. Cache-obliviously, we obtain a running time of . In all cases, our speedup is almost quadratic in the “parallelism” the model can afford, which may be the best possible. Our algorithms are Las Vegas randomized; time bounds hold in expectation, and in most cases, with high probability.     

Interpretation of MR images using self-organizing maps and knowledge-based expert systems

A new image segmentation system is presented to automatically segment and label brain magnetic resonance (MR) images to show normal and abnormal brain tissues using self-organizing maps (SOM) and knowledge-based expert systems. Elements of a feature vector are formed by image intensities, first-order features, texture features extracted from gray-level co-occurrence matrix and multiscale features. This feature vector is used as an input to the SOM. SOM is used to over segment images and a knowledge-based expert system is used to join and label the segments. Spatial distributions of segments extracted from the SOM are also considered as well as gray level properties. Segments are labeled as background, skull, white matter, gray matter, cerebrospinal fluid (CSF) and suspicious regions.     

Photosensitized free radical polymerization using pyridinium salts

Summary The polymerization of methyl methacrylate (MMA), ethyl acrylate (EA), styrene (St) and 2-vinyl pyridine (VP) is initiated upon irradiation at >350 nm of dichloromethane solutions containing N-ethoxy-2-methylpyridinium hexafluorophosphate (EMP⁺PF₆ ^-) and anthracene or thioxanthone. Initiation mechanisms involving the formation of ethoxyl radicals during the decomposition of EMP⁺ ions via electron transfer are proposed.     

Evaluation of hydrogen bonding ability of liquids and solids by C-13 NMR. Silica gel as a strong hydrogen bond donor

The chemical shift difference between signals of C() and C() of unsaturated ketones, , which we used before to measure acid strengths, has now been used to evaluate the hydrogen bond donor ability of solvents which are not acidic enough to hydronate the indicator. For such solvents there is no general correlation between H-bond donor ability and acid strength: hexa-fluoroisopropanol is a much weaker acid than acetic acid, but it is a stronger H-bond donor. The method can be applied to evaluate the H-bonding properties of solid surfaces, and it was thus found that silica gel has a much stronger H-bond donor ability than methanol or acetic acid.     

Optimal Deep Learning Based Intruder Identification in Industrial Internet of Things Environment

With the increased advancements of smart industries, cybersecurity has become a vital growth factor in the success of industrial transformation. The Industrial Internet of Things (IIoT) or Industry 4.0 has revolutionized the concepts of manufacturing and production altogether. In industry 4.0, powerful Intrusion Detection Systems (IDS) play a significant role in ensuring network security. Though various intrusion detection techniques have been developed so far, it is challenging to protect the intricate data of networks. This is because conventional Machine Learning (ML) approaches are inadequate and insufficient to address the demands of dynamic IIoT networks. Further, the existing Deep Learning (DL) can be employed to identify anonymous intrusions. Therefore, the current study proposes a Hunger Games Search Optimization with Deep Learning-Driven Intrusion Detection (HGSODL-ID) model for the IIoT environment. The presented HGSODL-ID model exploits the linear normalization approach to transform the input data into a useful format. The HGSO algorithm is employed for Feature Selection (HGSO-FS) to reduce the curse of dimensionality. Moreover, Sparrow Search Optimization (SSO) is utilized with a Graph Convolutional Network (GCN) to classify and identify intrusions in the network. Finally, the SSO technique is exploited to fine-tune the hyper-parameters involved in the GCN model. The proposed HGSODL-ID model was experimentally validated using a benchmark dataset, and the results confirmed the superiority of the proposed HGSODL-ID method over recent approaches.