Spotted Hyena Optimizer Driven Deep Learning-Based Drug-Drug Interaction Prediction in Big Data Environment

Nowadays,smart healthcare and biomedical research have marked a substantial growth rate in terms of their presence in the literature,computational approaches,and discoveries,owing to which a massive quantity of experimental datasets was published and generated(Big Data)for describing and validating such novelties.Drug-drug interaction(DDI)significantly contributed to drug administration and development.It continues as the main obstacle in offering inexpensive and safe healthcare.It normally happens for patients with extensive medication,leading them to take many drugs simultaneously.DDI may cause side effects,either mild or severe health problems.This reduced victims’quality of life and increased hospital healthcare expenses by increasing their recovery time.Several efforts were made to formulate new methods for DDI prediction to overcome this issue.In this aspect,this study designs a new Spotted Hyena Optimizer Driven Deep Learning based Drug-Drug Interaction Prediction(SHODL-DDIP)model in a big data environment.In the presented SHODL-DDIP technique,the relativity and characteristics of the drugs can be identified from different sources for prediction.The input data is preprocessed at the primary level to improve its quality.Next,the salp swarm optimization algorithm(SSO)is used to select features.In this study,the deep belief network(DBN)model is exploited to predict the DDI accurately.The SHO algorithm is involved in improvising the DBN model’s predictive outcomes,showing the novelty of the work.The experimental result analysis of the SHODL-DDIP technique is tested using drug databases,and the results signified the improvements of the SHODLDDIP technique over other recent models in terms of different performance measures.

Spotted Hyena Optimizer with Deep Learning Driven Cybersecurity for Social Networks

Recent developments on Internet and social networking have led to the growth of aggressive language and hate speech.Online provocation,abuses,and attacks are widely termed cyberbullying(CB).The massive quantity of user generated content makes it difficult to recognize CB.Current advancements in machine learning(ML),deep learning(DL),and natural language processing(NLP)tools enable to detect and classify CB in social networks.In this view,this study introduces a spotted hyena optimizer with deep learning driven cybersecurity(SHODLCS)model for OSN.The presented SHODLCS model intends to accomplish cybersecurity from the identification of CB in the OSN.For achieving this,the SHODLCS model involves data pre-processing and TF-IDF based feature extraction.In addition,the cascaded recurrent neural network(CRNN)model is applied for the identification and classification of CB.Finally,the SHO algorithm is exploited to optimally tune the hyperparameters involved in the CRNN model and thereby results in enhanced classifier performance.The experimental validation of the SHODLCS model on the benchmark dataset portrayed the better outcomes of the SHODLCS model over the recent approaches.

为系统请个“大管家”——HYENA

对于Windows的高手而言,诸如组策略、系统服务、注册表编辑器等计算机管理工具相信一定不会陌生,它们对于优化系统性能、保障系统安全可谓功不可没。但由于各工具相互独立,使用起来总会感觉手忙脚乱,不妨请个“大管家”来帮忙!软件名称:hyenav 6．7d No．

Cloud-based data security transactions employing blowfish and spotted hyena optimisation algorithm

Because of its on-demand servicing and scalability features in cloud computing,security and confidentiality have converted to key concerns.Maintaining transaction information on thirdparty servers carries significant dangers so that malicious individuals trying for illegal access to information data security architecture.This research proposes a security-aware information transfer in the cloud-based on the blowfish algorithm(BFA)to address the issue.The user is verified initially with the identification and separate the imported data using pattern matching technique.Further,BFA is utilised to encrypt and save the data in cloud.This can safeguard the data and streamline the proof so that client cannot retrieve the information without identification which makes the environment secure.The suggested approach’s performance is evaluated using several metrics,including encryption time,decryption time,memory utilisation,and runtime.Compared to the existing methodology,the investigational findings clearly show that the method takes the least time to data encryption.

Multiuser Detection for MIMO-OFDM system in Underwater Communication Using a Hybrid Bionic Binary Spotted Hyena Optimizer

Multi Access Interference (MAI) is the main source limiting the capacity and quality of the Multiple-Input Multiple-Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) system which fulfills the demand of high-speed transmission rate and high quality of service for future underwater acoustic (UWA) communication. Multi User Detection (MUD) is needed to overcome the performance degradation caused by MAI. In this research, both local and global optimal solutions are obtained in Bionic Binary Spotted Hyena Optimizer (BBSHO) algorithm using the Position Coordinate Vectors (PCVs) of the social behavior of spotted hyenas to achieve MUD. Further, Extremal Optimization (EO) is introduced in BBSHO algorithm to improve the local search ability within the search space. Hence, a hybrid BBSHO algorithm is proposed for achieving MUD at the receiver of the MIMO-OFDM system whose transceiver model in underwater is implemented using BELLHOP simulation system. By MATLAB simulation, it is shown that the Bit Error Rate (BER) performance of the proposed hybrid algorithm outperforms with best optimal solution within the search space towards MUD for Interference to Noise Ratio (INR) at 10 dB, 20 dB, and 40 dB over conventional detectors and metaheuristic approaches such as Binary Spotted Hyena Optimizer (BSHO), Binary Particle Swarm Optimization (BPSO) in the UWA network.

基于改进斑点鬣狗算法的热轧带钢负荷分配智能优化

针对热连轧过程中由于负荷分配不均匀导致板形控制效果不佳的问题,以传统的轧制机理为基础建立负荷分配均匀、板形良好的目标函数,分别采用斑点鬣狗算法和改进斑点鬣狗算法进行单目标和双目标的负荷分配的优化求解。结果表明,改进斑点鬣狗算法将末机架的相对凸度差从0.000 834 5降低到0.000 014 83和-0.000 026 34,且在允许的范围内,上游机架负荷分配合理,充分发挥了轧机的轧制能力。

Social interactions in striped hyena inferred from camera trap data:is it more social than previously thought?

Understanding the drivers promoting sociality over solitariness in animal species is imperative for predicting future population trends and informing conservation and management.In this study we investigate the social structure of a desert dwelling population of striped hyena Hyaena hyaena.This species is historically regarded as strictly solitary albeit being the least studied of the extant Hyaenids.Accumulating evidence regarding the frequency of social interactions sug-gests a revision of striped hyena social structure is required.We hypothesized that striped hyena has a social structure that is more complex than expected for a strictly solitary species.For that end,we deployed an array of camera-traps in a remote desert region in Israel,and compared observed frequencies of striped hyena co-occurrence against null models to test whether hyena co-occurred more than expected by chance.Seven adults were(re)captured by our camera-traps in 49 different instances over 83 tracking days.Of these,6 exhibited shared space-use around a scarce,isolated perennial water source.Five of them,co-occurred with other hyena(in 3 instan-ces)significantly more frequent than expected by chance(and that timing suggests reproduction is unlikely to be the driving factor).Our findings substantiate evidence of complex social structure in striped hyena,highlight the importance of a scarce resource in space use and sociality,and provide a baseline for future research of striped hyena social structure.We suggest that similar methods be employed to evaluate social structure in other"solitary species"to better under-stand their social dynamics.

基于ISHO-ELM模型的短期电力负荷预测

针对现有电力负荷预测方法中预测误差较大的问题,提出了一种基于改进型斑点鬣狗算法优化极限学习机(improved spotted hyena algorithm optimized-extreme learning machine,ISHO-ELM)的短期电力负荷预测模型。首先,在斑点鬣狗优化算法中引入准反向学习策略和精英策略提高算法的搜索能力,并通过基准测试函数验证了其有效性;其次,采用ISHO算法优选ELM中的随机参数以提高模型的预测精度与稳定性;最后,通过实测数据对构建的短期电力负荷预测模型的先进性与实用性进行了验证。结果表明:提出ISHO-ELM模型的拟合系数相对于已有的ELM和SVM模型分别提高了1.6%和1.7%。本研究对提高电力系统运行稳定具有重要意义。

混合多策略改进的斑点鬣狗优化算法及应用

针对基本斑点鬣狗算法求解精度低、易陷入局部最优值等缺点,提出一种混合多策略改进的斑点鬣狗优化算法。通过Fuch混沌映射实现鬣狗种群的多样性,利用自适应惯性权重平衡斑点鬣狗算法的全局搜索和局部开发能力,引入拉普拉斯算子进行动态交叉操作,提高SHO算法跳出局部最优的能力,将小孔成像反向学习和逐维反向学习机制相结合,使种群更符合迭代规律,提高算法的收敛速度和寻优能力。通过若干基准函数的仿真实验进行比较,其结果表明,LPSHO具有更优越的寻优性能。将改进后LPSHO运用在机械优化设计和桁架结构优化工程问题上,与其它算法对比进一步表明LPSHO能够很好解决这类结构优化问题。

考虑天气类型和历史相似日的短期光伏输出功率预测

光伏发电的随机性和不确定性是制约光伏发展的主要原因。为了提高短期光伏发电功率预测精度,提出了一种考虑天气类型和历史相似日的短期光伏输出功率预测方法。针对不同季节和天气类型划分历史数据,根据灰色关联度计算结果确定相似日。采用混沌初始化、控制因子非线性调整和莱维飞行等策略对斑点鬣狗优化(spotted hyena optimizer)算法进行改进,采用改进斑点鬣狗算法(improved spotted hyena optimizer)对核极限学习机进行优化,建立基于改进斑点鬣狗算法优化(kernel extreme learning machine,KELM)的短期光伏输出功率预测模型。利用实际光伏电站监测数据进行仿真分析,结果表明,基于ISHO-KELM的短期光伏输出功率预测模型能够降低光伏输出功率预测过程中的波动性,提高预测精度,验证了所提光伏预测方法的正确性和实用性。

基于SHO-NSGA混合算法的飞机油舱管路自动布局方法

针对飞机油舱内部管路路径规划问题,提出一种基于改进斑鬣狗算法的飞机油舱管路自动布局方法。为了提高斑鬣狗算法的全局搜索能力以及收敛速度,在种群进化过程中引入扩散搜索机制对迭代过程中最优解进行扩散,以达到提高全局搜索能力的目的;在算法迭代后期引入深度包围机制,使其在最优解中随机搜索以提高算法的收敛速度。采用栅格法构建敷设空间数学模型,以管路路径最短为优化目标,以管路路径不与障碍物发生干涉、管路折弯角度及管路折弯半径为约束,建立管路布局优化数学模型。进一步,考虑管路的支臂布局问题,以支臂总长和支臂姿态作为支臂布局双目标优化函数,运用遗传算法NSGA-Ⅱ对管路支臂布局方案进行编码生成初始个体,设计交叉、变异规则,求解管路支臂布局的Pareto解集,进而获得管路支臂布局方案。最后,通过数值算例及管路敷设仿真验证所提方法的有效性。

基于SHO优化SVM的输电线路雷电过电压识别

为提高输电线路雷电过电压识别结果的准确性,以能量谱雷击波头、时域波形、时频谱等特征信息为输入量,采用斑点鬣狗算法对支持向量机进行优化,建立基于斑点鬣狗算法优化支持向量机的输电线路雷电过电压识别模型。仿真分析结果表明,SHO-SVM对非故障性过电压、感应雷过电压、反击故障过电压和绕击故障过电压识别的正确率分别为100%、100%、95%和95%,综合正确率高达97.5%,验证了模型的正确性和优越性。

考虑可再生能源不确定性的最优潮流研究

文章针对含有可再生能源的电网提出了最优潮流优化模型,并对风电出力、光伏出力以及水轮机组出力的不确定性进行了建模。提出了考虑可再生能源不确定性的最优潮流模型,以机组成本以及网络中的网损最小为目标函数,考虑相应的约束条件,利用改进斑点鬣狗优化算法对模型进行求解,引入混沌序列控制向量提升算法整体的寻优性能。最后,在IEEE 30节点系统中对所提的模型和算法进行了仿真分析。

河南栾川孙家洞遗址出土的穿孔标本

孙家洞遗址初步测年为40万年左右,出土了少量石制品、古人类牙齿以及大量动物化石,其中一件骨骼标本存在非常规整的穿孔,其整体形态和大小与人工穿孔比较相似。通过系统的宏观观测与显微镜下分析,并与已明确性质的考古标本(自然穿孔和人工穿孔标本)和实证材料(现代鬣狗洞发掘出土材料)进行对比后发现,孙家洞遗址出土的穿孔标本与食肉类啃咬、甲虫类啮食以及人工造成的穿孔标本存在明显差异,而具备了被鬣狗胃酸腐蚀标本的所有典型特征。

基于改进鬣狗优化算法的多阈值彩色图像分割

针对传统鬣狗优化算法在处理图像分割问题时容易陷入局部最优、收敛效率低等问题,提出基于混沌初始化策略、非线性收敛因子调整策略、莱维飞行策略以及精英反向学习策略的改进鬣狗优化算法(Improved Spotted Hyena Optimizer,ISHO),并应用于多阈值彩色图像分割问题中。该算法不仅提升了在解决复杂性问题时的寻优效率,而且提高了求解精度与质量,避免了受随机因子影响而陷入局部最优的缺陷。为了验证该算法的有效性,利用伯克利图像分割验证,结果表明:该算法在分割速度及效率上具有明显优势,求解精度高,具有较好的工程实用性。

基于模拟退火斑点鬣狗优化算法的特征选择

特征选择问题是一个基于某些标准找到最相关子集的过程,针对特征选择中的评价标准,设计了一种将斑点鬣狗优化(spotted hyena optimization,SHO)算法与模拟退火算法(simulated annealing,SA)相结合的混合模型来解决上述问题,以增强每次迭代后SHO找到的最优解,并通过UCI存储库中的8个数据集来评估优化算法的性能。实验结果表明:SASHO混合算法的表现不仅优于原始SHO算法,而且与其他优化算法相比,提高了分类精度并减少了所选特征的个数,在空间搜索和特征属性选择方面具有一定的工程实用价值。

基于PCA-SHO-SVM和PCA-SHO-BP模型的径流预测

为提高径流预测精度,研究主成分分析(PCA)、斑鬣狗优化(SHO)算法与支持向量机(SVM)、BP神经网络相融合的预测方法。在样本数据筛选上选取PCA方法进行数据降维,使数据样本简洁且更具代表性。利用SHO算法优化SVM关键参数及BP神经网络权阈值,分别提出PCA-SHO-SVM、PCA-SHO-BP径流量预测模型,并与SHO-SVM、PCA-SVM、SVM和SHO-BP、PCA-BP、BP模型的预测结果作对比,通过云南省龙潭水文站年径流量及枯水期月径流量预测为例进行验证。结果表明,PCA-SHO-SVM、PCA-SHO-BP模型对实例年径流量预测的平均相对误差分别为2.34%、2.50%,对月径流量预测的平均相对误差分别为6.15%、6.08%,预测精度均优于其他6种模型,具有较高的预测精度和更强的泛化能力。

基于鬣狗算法神经网络反演林地叶面积指数

针对遥感影像的神经网络模型对林地叶面积指数(LAI)反演容易陷入局部最优、收敛效率低等问题,提出基于GF-1遥感影像和PROSAIL模型反演数据建立鬣狗算法神经网络模型,并与BP神经网络模型进行对比.结果表明,BP神经网络训练集的均方根误差(RMSE)值为0.140,验证集RMSE值为0.137,测试集决定系数(R^(2))为0.525;鬣狗神经网络训练集的RMSE值为0.131,验证集RMSE值为0.132,测试集决定系数(R^(2))为0.703.本研究提出的鬣狗算法,可提升神经网络模型的反演性能,为GF-1卫星在大范围林地LAI反演的应用推广提供了方法思路.

基于改进斑点鬣狗优化算法的同步优化特征选择

针对传统支持向量机(SVM)在封装式特征选择中分类精度低、特征子集选择冗余以及计算效率差的不足,利用元启发式优化算法同步优化SVM与特征选择。为改善SVM分类效果以及选择特征子集的能力,首先,利用自适应差分进化(DE)算法、混沌初始化与锦标赛选择策略对斑点鬣狗优化(SHO)算法改进,以增强其局部搜索能力并提高其寻优效率与求解精度;其次,将改进后的算法用于特征选择与SVM参数调整的同步优化中;最后,在UCI数据集进行特征选择仿真实验,采取分类准确率、选择特征数、适应度值及运行时间来综合评估所提算法的优化性能。实验结果证明,改进算法的同步优化机制能够在高分类准确率下降低特征选择的数目,该算法比传统算法更适合解决封装式特征选择问题,具有良好的应用价值。