Prediction of Attention and Short-Term Memory Loss by EEG Workload Estimation

Mental workload plays a vital role in cognitive impairment. The impairment refers to a person’s difficulty in remembering, receiving new information, learning new things, concentrating, or making decisions that seriously affect everyday life. In this paper, the simultaneous capacity (SIMKAP) experiment-based EEG workload analysis was presented using 45 subjects for multitasking mental workload estimation with subject wise attention loss calculation as well as short term memory loss measurement. Using an open access preprocessed EEG dataset, Discrete wavelet transforms (DWT) was utilized for feature extraction and Minimum redundancy and maximum relevancy (MRMR) technique was used to select most relevance features. Wavelet decomposition technique was also used for decomposing EEG signals into five sub bands. Fourteen statistical features were calculated from each sub band signal to form a 5 × 14 window size. The Neural Network (Narrow) classification algorithm was used to classify dataset for low and high workload conditions and comparison was made using some other machine learning models. The results show the classifier’s accuracy of 86.7%, precision of 84.4%, F1 score of 86.33%, and recall of 88.37% that crosses the state-of-the art methodologies in the literature. This prediction is expected to greatly facilitate the improved way in memory and attention loss impairments assessment.

Snowmelt Flood Mapping and Land Surface Short-Term Dynamics Assessment in a “Before-During-After” Scenario Based on Radar and Optical Satellite Imagery: Case Study Around the Lewisville Lake (Dallas/Fort Worth Metropolitan, Texas, USA)

The main goal of this study has been to map flood and assess land surface short-term dynamics in relation with snowy weather. The two recent snowfall events, which happened in, February 14th and 15th, of year 2021, and February 3rd and 4th, of year 2022, were chosen. A pre-analysis correlation was assumed between, the snow events, recurrency of floods, and changes in the land surface characteristics (i.e., wetness, energy, temperature), in a “Before-During-After” scenario. Active and passive microwave satellites data such as, Sentinel-1 synthetic aperture radar (SAR), Sentinel-2 multispectral instrument (MSI) and Landsat-9 Operation Land Imager-2/Thermal Infrared Sensors-2 (OLI-2/TIRS-2), as well as cloud databased global models for water and urban layers were used. The first step of processing was thresholding of SAR image, at 0.25 cutoff, based on bimodal histogram distribution, followed by the change analysis. The following processing consisted in the images transformation, by computing the tasseled cap transformation wetness (TCTw) and the surface albedo on MSI image. In addition, the land surface temperature (LST) was modeled from OLI-2/TIRS-2 image. Then, a 5th order polynomial regression was computed, between TCTw as dependent variable and, albedo and LST as independent variables. As a first result, an area of 5.6 km2 has been mapped as recurrently flooded from the two years assessment. The other output highlighted a constant increase of wetness (TCTw), considered most influential on land surface dynamics, comparatively to energy exchange (albedo) and temperature (LST). The “After” event dependency between the three indicators was highest, with a correlation coefficient, R2 = 0.682, confirming the persistence of wetness after-snowmelt. Validation over topographic layers confirmed that, recurrently flooded areas are mostly distributed on, lowest valley depth points, farthest distances from channel network (i.e., from perennial waters), and lowest relative slope position areas. Whereas, 88.9% of the validation sampling were confirmed in the laboratory, and 86.7% of urban validation points were assessed as recurrently flooded when combining pre-/post-field-work campaign.

Short-TermWind Power Prediction Based on Combinatorial Neural Networks

Wind power volatility not only limits the large-scale grid connection but also poses many challenges to safe grid operation.Accurate wind power prediction can mitigate the adverse effects of wind power volatility on wind power grid connections.For the characteristics of wind power antecedent data and precedent data jointly to determine the prediction accuracy of the prediction model,the short-term prediction of wind power based on a combined neural network is proposed.First,the Bi-directional Long Short Term Memory(BiLSTM)network prediction model is constructed,and the bi-directional nature of the BiLSTM network is used to deeply mine the wind power data information and find the correlation information within the data.Secondly,to avoid the limitation of a single prediction model when the wind power changes abruptly,the Wavelet Transform-Improved Adaptive Genetic Algorithm-Back Propagation(WT-IAGA-BP)neural network based on the combination of the WT-IAGA-BP neural network and BiLSTM network is constructed for the short-term prediction of wind power.Finally,comparing with LSTM,BiLSTM,WT-LSTM,WT-BiLSTM,WT-IAGA-BP,and WT-IAGA-BP&LSTM prediction models,it is verified that the wind power short-term prediction model based on the combination of WT-IAGA-BP neural network and BiLSTM network has higher prediction accuracy.

Short-Term Prediction of Photovoltaic Power Generation Based on LMD Permutation Entropy and Singular Spectrum Analysis

The power output state of photovoltaic power generation is affected by the earth’s rotation and solar radiation intensity.On the one hand,its output sequence has daily periodicity;on the other hand,it has discrete randomness.With the development of new energy economy,the proportion of photovoltaic energy increased accordingly.In order to solve the problem of improving the energy conversion efficiency in the grid-connected optical network and ensure the stability of photovoltaic power generation,this paper proposes the short-termprediction of photovoltaic power generation based on the improvedmulti-scale permutation entropy,localmean decomposition and singular spectrum analysis algorithm.Firstly,taking the power output per unit day as the research object,the multi-scale permutation entropy is used to calculate the eigenvectors under different weather conditions,and the cluster analysis is used to reconstruct the historical power generation under typical weather rainy and snowy,sunny,abrupt,cloudy.Then,local mean decomposition(LMD)is used to decompose the output sequence,so as to extract more detail components of the reconstructed output sequence.Finally,combined with the weather forecast of the Meteorological Bureau for the next day,the singular spectrumanalysis algorithm is used to predict the photovoltaic classification of the recombination decomposition sequence under typical weather.Through the verification and analysis of examples,the hierarchical prediction experiments of reconstructed and non-reconstructed output sequences are compared.The results show that the algorithm proposed in this paper is effective in realizing the short-term prediction of photovoltaic generator,and has the advantages of simple structure and high prediction accuracy.

Identification of the Breach of Short-Term Rental Regulations in Irish Rent Pressure Zones

The housing crisis in Ireland has rapidly grown in recent years. To make a more significant profit, many landlords are no longer renting out their houses under long-term tenancies but under short-term tenancies. Regulating rentals in Rent Pressure Zones with the highest and rising rents is becoming a tricky issue. In this paper, we develop a breach identifier to check short-term rentals located in Rent Pressure Zones with potential breaches only using publicly available data from Airbnb (an online marketplace focused on short-term home-stays) and Irish government websites. First, we use a Residual Neural Network to filter out outdoor landscape photos that negatively impact identifying whether an owner has multiple rentals in a Rent Pressure Zone. Second, a Siamese Neural Network is used to compare the similarity of indoor photos to determine if multiple rental posts correspond to the same residence. Next, we use the Haversine algorithm to locate short-term rentals within a circle centered on the coordinate of a permit. Short-term rentals with a permit will not be restricted. Finally, we improve the occupancy estimation model combined with sentiment analysis, which may provide higher accuracy.

Short-Term Memory Capacity across Time and Language Estimated from Ancient and Modern Literary Texts. Study-Case: New Testament Translations

We study the short-term memory capacity of ancient readers of the original New Testament written in Greek, of its translations to Latin and to modern languages. To model it, we consider the number of words between any two contiguous interpunctions Ip, because this parameter can model how the human mind memorizes “chunks” of information. Since IP can be calculated for any alphabetical text, we can perform experiments—otherwise impossible— with ancient readers by studying the literary works they used to read. The “experiments” compare the IP of texts of a language/translation to those of another language/translation by measuring the minimum average probability of finding joint readers (those who can read both texts because of similar short-term memory capacity) and by defining an “overlap index”. We also define the population of universal readers, people who can read any New Testament text in any language. Future work is vast, with many research tracks, because alphabetical literatures are very large and allow many experiments, such as comparing authors, translations or even texts written by artificial intelligence tools.

基于多维气象信息时空融合和MPA-VMD的短期电力负荷组合预测模型

为提高电力负荷预测精度,需考虑区域内不同地区多维气象信息对电力负荷影响的差异性。在空间维度上,提出多维气象信息时空融合的方法,利用Copula理论将多座气象站的风速、降雨量、温度、日照强度等气象信息与电力负荷进行非线性耦合分析并实现时空融合。在时间维度上,采用海洋捕食者算法(MPA)实现变分模态分解(VMD)核心参数的自动寻优,并采用加权排列熵构造MPA-VMD适应度函数,实现负荷序列的自适应分解。通过将时间维度各分量与空间维度各气象信息进行融合构造长短期记忆(LSTM)网络模型与海洋捕食者算法-最小二乘支持向量机(MPA-LSSVM)模型的输入集,得到各分量预测结果,根据评价指标选择各分量对应的预测模型,重构得到整体预测结果。算例分析结果表明,所提预测模型优于传统预测模型,有效提高了电力负荷预测精度。

儿童吉兰-巴雷综合征脑脊液神经丝蛋白轻链特点分析

目的探讨脑脊液神经丝蛋白轻链(NfL)对儿童吉兰-巴雷综合征(GBS)患者早期诊断及预后的评估价值。方法回顾性分析2020年11月至2022年5月收治的GBS患儿的临床资料,选择同期诊断为偏头痛、儿童情绪障碍患者作为对照组,比较两组脑脊液-NfL水平,分析脑脊液-NfL水平与临床特征的相关性。结果GBS组患儿26例,男14例、女12例,中位年龄5.0(3.8~8.0)岁;对照组48例,男30例、女18例,中位年龄8.0(5.0~9.0)岁。入院时GBS组脑脊液-NfL和脑脊液蛋白水平高于对照组,差异有统计学意义(P<0.05)。联合检测脑脊液-NfL和蛋白早期诊断GBS的灵敏度、特异度、阳性预测值、阴性预测值和准确度分别为92.3%、95.8%、92.3%、95.8%和94.6%。入院时GBS患儿脑脊液蛋白水平及疾病高峰时Hughes评分均与脑脊液-NfL水平呈显著正相关(P<0.05)。预后不良组患儿脑脊液-NfL水平显著高于预后良好组,差异有统计学意义(P<0.05)。结论脑脊液-NfL与脑脊液蛋白水平、疾病严重程度及短期预后相关,对于早期辅助诊断GBS、评估短期预后有一定帮助。

基于CNN-SAEDN-Res的短期电力负荷预测方法

基于深度学习的序列模型难以处理混有非时序因素的负荷数据,这导致预测精度不足。提出一种基于卷积神经网络(CNN)、自注意力编码解码网络(SAEDN)和残差优化(Res)的短期电力负荷预测方法。特征提取模块由二维卷积神经网络组成,用于挖掘数据间的局部相关性,获取高维特征。初始负荷预测模块由自注意力编码解码网络和前馈神经网络构成,利用自注意力机制对高维特征进行自注意力编码,获取数据间的全局相关性,从而模型能根据数据间的耦合关系保留混有非时序因素数据中的重要信息,通过解码模块进行自注意力解码,并利用前馈神经网络回归初始负荷。引入残差机制构建负荷优化模块,生成负荷残差,优化初始负荷。算例结果表明,所提方法在预测精度和预测稳定性方面具有优势。

基于ConvLSTM-CNN预测太平洋长鳍金枪鱼时空分布趋势

海洋渔场的变动由空间与环境因子共同驱动,渔场时空演变信息的精准预测是海洋捕捞的关键。本研究利用1995-2018年太平洋海域长鳍金枪鱼(Thunnus alalunga)的渔业生产统计数据,结合同期海洋环境数据包括海表面温度(Sea Surface Temperature,SST)、海表面盐度(Sea Surface Salinity,SSS)、初级生产力(Primary Productivity,PP)和溶解氧浓度(Dissolved Oxygen Concentration,DO),提出了一种融合卷积长短期记忆网络(Convolutional Long Short-Term Memory Networks,ConvLSTM)和卷积神经网络(Convolutional Neural Networks,CNN)的渔场时空分布预测模型。该模型引入特征提取模块,对时空因子进行编码,提取时空特征信息,同时采用CNN提取海洋环境变量的抽象特征,采用ConvLSTM提取渔业数据的高层时空关联信息,最后融合多种特征对渔场时空演变趋势进行预测。结果表明,模型的均方根误差为0.1036,较随机森林、BP神经网络和长短期记忆网络(Long Short Term Memory,LSTM)等传统渔场预报模型的预测误差降低15%~40%,预测的高产渔区与实际作业的高渔获量区匹配度为89%。该研究构建的渔场时空预测模型能够准确地预测出太平洋长鳍金枪鱼的时空分布,为太平洋长鳍金枪鱼的延绳钓渔业提供科学参考依据。

基于CEEMD-SE的CNN&LSTM-GRU短期风电功率预测

为进一步提升短期风电功率的预测精度,提出了一种基于互补集合经验模态分解-样本熵(complementary ensemble empirical mode decomposition-sample entropy,CEEMD-SE)的卷积神经网络(convolutional neural network,CNN)和长短期记忆-门控循环单元(longshorttermmemory-gatedrecurrentunit,LSTM-GRU)的短期风电功率预测模型。首先,利用互补集合经验模态分解将原始风电功率序列分解为若干本征模态函数(intrinsic mode function,IMF)分量和一个残差(residual,RES)分量,利用样本熵算法将相近的分量进行重构;其次,搭建卷积神经网络和长短期记忆网络的并行网络结构,提取数据的局部特征和时序特征,并将特征融合后输入门控循环单元网络中进行学习预测;最后,通过算例进行验证,结果表明采用该模型后预测精度得到了有效提升,其均方根误差降低了15.06%、平均绝对误差降低了15.22%、决定系数提高了1.91%。

基于CBAM-CNN的电力系统暂态电压稳定评估

为进一步提高电力系统暂态电压稳定评估模型的特征提取能力和模型在系统拓扑结构发生变化时的适应性,提出一种将改进的卷积神经网络与迁移学习相结合的方法。首先,在卷积神经网络的卷积层后插入卷积块注意力模块,对输入的数据从通道和空间两个独立的维度依次提取特征,提高卷积神经网络对系统暂态电压状态的识别能力。然后,将该模块与微调技术相结合,提高模型在系统拓扑结构改变时的在线更新速度。最后,算例分析验证了所提模型的有效性。

基于残差修正CNN-BiLSTM的空中目标航迹短期预测算法

针对因深度学习自身局限性和递归预测策略产生的累积误差,导致航迹预测精度不高的问题,提出了一种基于残差修正CNN-BiLSTM的空中目标航迹短期预测算法。首先,引入卷积模块用于提取航迹数据之中具有潜在关联的空间位置特征,利用双向长短时记忆网络提取航迹数据中的时序特征,并实现对空中目标的实时单步预测和多步超前预测;其次,引入整合移动平均自回归为残差修正模型,对实时单步预测产生的残差建模,计算混合神经网络模型多步超前预测时的残差值;最后,将混合神经网络模型和残差修正模型的输出结果进行融合,得到最终的航迹预测值。实验结果表明,该算法大大降低了神经网络因自身局限性产生的误差和因递归策略预测产生的累积误差,能够显著提高空中目标航迹短期预测的精度。

基于VMD-LILGWO-LSSVM短期风电功率预测

目的为了减小风电功率并入国家电网时产生的频率波动,提高风电功率预测精度,方法提出一种结合变分模态分解(VMD)、改进灰狼算法(LILGWO)和最小二乘支持向量机(LSSVM)的风电功率短期预测方法。首先通过VMD方法将风电功率序列分解重构成3个复杂程度性不同的模态分量,降低风电功率的波动性;其次使用LSSVM挖掘各分量的特征信息,对各分量分别进行预测,针对LSSVM模型中重要参数的选取对预测精度影响较大问题,引入LILGWO对参数进行寻优;最后将各分量预测结果叠加重构,得到最终预测风电功率。结果以宁夏回族自治区某地区风电站实际数据为例,对未来三天分别进行预测取平均值,本文方法的预测平均绝对误差(mean absolute error,MAE)为2.7068 kW,均方根误差(root mean square error,RMSE)为2.0211,拟合程度决定系数(R-Square,R^(2))为0.9769,与对比方法3~6相比,RMSE分别降低了40.93%,25.21%,14.7%,6.24%;MAE分别降低了42.34%,28.04%,16.97%,7.77%;R^(2)分别提升了4.21%,1.78%,0.82%,0.28%。预测时长方面,BP和LSSVM平均训练时间分别是10,138 s,虽然LSSVM预测时间较长但效果最好,采用PSO、GWO、LILGWO对LSSVM进行寻优后训练时间分别平均缩短了39,44,58 s。结论仿真验证了所提方法在短期风电功率预测方面的有效性。

结合太阳辐射量计算与CNN-LSTM组合的光伏功率预测方法研究

为了提高模型预测性能,提出一种综合太阳辐射模型及深度学习的光伏功率预测模型。首先,利用太阳辐射机理建立太阳辐射模型(SRM),估算出水平面上总辐射值,再由斜面辐照度转换方法计算出光伏组件所接收的斜面辐射值。其次,通过皮尔逊相关分析法筛选出对光伏功率影响较大的主要因素,将斜面辐射计算值及主要影响因素作为输入,采用卷积神经网络(CNN)和长短期记忆网络(LSTM)建立光伏功率SRM-CNN-LSTM预测模型。分别利用春夏秋冬四季典型日的数据开展对比实验,结果表明:与几种其他方法相比,该文方法具有更好的预测效果。

基于Encoder-Decoder LSTM的船舶轨迹预测方法

船舶轨迹预测的准确性是预警事故和确保安全航行的关键,但精度和稳定性是目前亟待解决的问题。为了应对这一挑战,提出一种基于Encoder-Decoder LSTM的船舶轨迹预测方法。首先对船舶AIS轨迹数据进行去噪、分段、插值、停留点检测和归一化等预处理,提取船舶的航行轨迹。然后构建了一种基于Encoder-Decoder LSTM架构的船舶轨迹预测模型,并对模型参数进行初始化。最后使用长江江苏段天生港水域渡轮的真实AIS数据对提出的模型进行训练和验证,并与其他广泛使用的轨迹预测方法进行比较。定量分析表明,该方法可实现对船舶轨迹较为准确的预测,且所预测轨迹具有一定的参考价值。

基于自注意力机制和改进的K-BiLSTM的水产养殖水体溶解氧含量预测模型

为精确预测水产养殖水体溶解氧含量,本研究提出一种基于自注意力机制(ATTN)和改进的K-means聚类-基于残差和批标准化(BN)的双向长短期记忆网络(BiLSTM)的水产养殖水体溶解氧含量预测模型。首先,根据环境数据的相似性,使用改进的K-means算法将数据划分成若干个类别;然后,在BiLSTM基础上构建残差连接和加入BN完成高层次特征提取,利用BiLSTM的长期记忆能力保存特征信息;最后,引入自注意力机制突出不同时间节点数据特征的重要性,进一步提升模型的性能。试验结果表明,本研究提出的基于自注意力机制和改进的K-BiLSTM模型的平均绝对误差为0.238、均方根误差为0.322、平均绝对百分比误差为0.035,与单一的BP模型、CNN-LSTM模型、传统的K-means-基于残差和BN的BiLSTM-ATTN等模型相比具有更优的预测性能和泛化能力。

基于BERT-BiLSTM-CRF模型的畜禽疫病文本分词研究

针对畜禽疫病文本语料匮乏、文本内包含大量疫病名称及短语等未登录词问题,提出了一种结合词典匹配的BERT-BiLSTM-CRF畜禽疫病文本分词模型。以羊疫病为研究对象,构建了常见疫病文本数据集,将其与通用语料PKU结合,利用BERT(Bidirectional encoder representation from transformers)预训练语言模型进行文本向量化表示;通过双向长短时记忆网络(Bidirectional long short-term memory network,BiLSTM)获取上下文语义特征;由条件随机场(Conditional random field,CRF)输出全局最优标签序列。基于此,在CRF层后加入畜禽疫病领域词典进行分词匹配修正,减少在分词过程中出现的疫病名称及短语等造成的歧义切分,进一步提高了分词准确率。实验结果表明,结合词典匹配的BERT-BiLSTM-CRF模型在羊常见疫病文本数据集上的F1值为96.38%,与jieba分词器、BiLSTM-Softmax模型、BiLSTM-CRF模型、未结合词典匹配的本文模型相比,分别提升11.01、10.62、8.3、0.72个百分点,验证了方法的有效性。与单一语料相比,通用语料PKU和羊常见疫病文本数据集结合的混合语料,能够同时对畜禽疫病专业术语及疫病文本中常用词进行准确切分,在通用语料及疫病文本数据集上F1值都达到95%以上,具有较好的模型泛化能力。该方法可用于畜禽疫病文本分词。

基于特征选择及ISSA-CNN-BiGRU的短期风功率预测

针对风电功率随机性大、平稳性低,以及直接输入预测模型往往难以取得较高精度等问题,提出了一种基于特征选择及改进麻雀搜索算法(ISSA)优化卷积神经网络-双向门控循环单元(CNN-BiGRU)的短期风电功率预测方法。首先,利用变分模态分解(VMD)将原始功率分解为一组包含不同信息的子分量,以降低原始功率序列的非平稳性,提升可预测性,同时通过观察中心频率方式确定模态分解数。其次,对每一分量采用随机森林(RF)特征重要度的方法进行特征选择,从风速、风向、温度、空气密度等气象特征因素中,选取对各个分量预测贡献度较高的影响因素组成输入特征向量。然后,建立各分量的CNN-BiGRU预测模型,针对神经网络算法参数难调、手动配置参数随机性大的问题,利用ISSA对模型超参数寻优,自适应搜寻最优参数组合。最后,叠加各分量的预测值,得到最终的预测结果。以中国内蒙古某风电场实际数据进行仿真实验,与多种单一及组合预测方法进行对比,结果表明,本文所提方法相比于其他方法具有更高的预测精度,其平均绝对百分比误差值达到2.644 0%;在其他4个数据集上进行的模型准确性及泛化性验证结果显示,模型平均绝对百分比误差值分别为4.385 3%、3.174 9%、1.576 1%和1.358 8%,均保持在5.000 0%以内,证明本文所提方法具有较好的预测精度及泛化能力。

CEEMDAN-WPE-CLSA超短期风电功率预测方法研究

提出了一种结合自适应噪声完全集合经验模态分解、加权排列熵、卷积神经网络、长短期记忆网络和自注意力机制的超短期风电功率预测方法。首先,利用自适应噪声完全集合经验模态分解将原始风电功率时间序列自适应分解为一系列的模态分量,降低原始序列的非线性和波动性;其次,根据加权排列熵计算各模态分量间的相似性并对相似的分量进行重组,以修正自适应噪声完全集合经验模态分解的过度分解问题,使得修正后的模态分量更具规律性;最后,将重组后的分量输入卷积长短期记忆网络进行时序建模,并利用自注意力机制对卷积长短期记忆网络的神经元权重进行重新分配,提高了卷积长短期记忆网络对输入特征不确定性的适应能力。在此基础上,明确了自注意力机制和自适应噪声完全集合经验模态分解、加权排列熵在风电功率预测中的作用机制,以及风电功率信号包含的重要物理信息,证明了自适应噪声完全集合经验模态分解、加权排列熵以及自注意力机制在风电功率信号模态分解和长短期记忆网络隐层输出权重分配中的有效性。