Improved Shark Smell Optimization Algorithm for Human Action Recognition

Human Action Recognition(HAR)in uncontrolled environments targets to recognition of different actions froma video.An effective HAR model can be employed for an application like human-computer interaction,health care,person tracking,and video surveillance.Machine Learning(ML)approaches,specifically,Convolutional Neural Network(CNN)models had beenwidely used and achieved impressive results through feature fusion.The accuracy and effectiveness of these models continue to be the biggest challenge in this field.In this article,a novel feature optimization algorithm,called improved Shark Smell Optimization(iSSO)is proposed to reduce the redundancy of extracted features.This proposed technique is inspired by the behavior ofwhite sharks,and howthey find the best prey in thewhole search space.The proposed iSSOalgorithmdivides the FeatureVector(FV)into subparts,where a search is conducted to find optimal local features fromeach subpart of FV.Once local optimal features are selected,a global search is conducted to further optimize these features.The proposed iSSO algorithm is employed on nine(9)selected CNN models.These CNN models are selected based on their top-1 and top-5 accuracy in ImageNet competition.To evaluate the model,two publicly available datasets UCF-Sports and Hollywood2 are selected.

检测JavaScript类的内聚耦合Code Smell

Code Smell是软件程序中存在不良设计和不良实现的征兆.正确地检测和识别Code Smell可以指导软件重构,提高软件的可用性和可靠性.通过Code Smell的度量指标,可以量化软件的设计问题.JavaScript已成为最常用的编程语言之一,类是JavaScript的设计模式,优秀类的设计体现为高内聚和低耦合.现有关于JavaScript内聚耦合的Code Smell研究均在微观的层面,即函数和语句上进行.它们可以提供程序实现的重构建议,但无法分析内聚耦合相关的软件系统设计问题.针对FE、DC和Blob这3种类的内聚耦合Code Smell,提出一种JavaScript类的内聚耦合Code Smell检测方法JS4C.该方法基于静态分析,同时适用于客户端和服务端程序.它通过遍历软件系统中所有的类,利用源程序的文本相似度特征和结构特征,识别Code Smell并检测其强度.在结构特征检测中,JS4C使用了经扩展的对象类型推断及非严格的耦合分散度度量法NSCDISP,有效地降低了解释型语言的静态分析过程中,类型信息缺失对检测产生的影响.实验通过对6个开源项目的分析表明,JS4C对内聚耦合设计问题有良好的检测效果.

Code Smell视角下分层Web应用失血及充血现象的量化分析

分层Web应用的领域层由领域模型构成.仅存储数据且不实现行为的领域模型被称作失血领域模型,其状态和数据由非领域层中的类维护,造成后者的充血现象.失血和充血现象损害了Web应用的可维护性,然而,由于缺乏量化分析和研究,其论据多基于主观经验得出.本文度量三种Code Smell(Feature Envy、Blob和Data Class)的强度,将它们作为衡量失血和充血现象的标准,对现象进行量化分析,进而得出它们之间的相关性.本文对一个公开数据集的91个Java Web项目及10个不同领域的开源Java Web应用的多个版本进行了实验,实验发现至少有75%的项目受领域层失血和服务层充血现象的影响,这些现象极少被解决或减弱,两者的强度在不同类间存在相关性,且两者强度的增量在同一软件项目的不同版本间亦存在相关性.

Self-reported Taste and Smell Disorders in Patients with COVID-19:Distinct Features in China

Last December 2019,a cluster of viral pneumonia cases identified as coronavirus disease 2019(COVID-19)was reported in Wuhan,China.We aimed to explore the frequencies of nasal symptoms in patients with COVID-19,including loss of smell and taste,as well as their presentation as the first symptom of the disease and their association with the severity of COVID-19.In this retrospective study,1206 laboratory-confirmed COVID-19 patients were included and followed up by telephone one month after discharged from Tongji Hospital,Wuhan.Demographic data,laboratory values,comorbidities,symptoms,and numerical rating scale scores(0–10)of nasal symptoms were extracted from the hospital medical records,and confirmed or reevaluated by the telephone follow-up.From patients(n=1172)completing follow-up,199(17%)subjects had severe COVID-19 and 342(29.2%)reported nasal symptoms.20.6%COVID-19 patients had loss of taste(median score=6),while 11.4%had loss of smell(median score=5).Loss of taste scores,but not loss of smell scores,were significantly increased in severe vs.nonsevere COVID-19 patients.Interleukin(IL)-6 and lactose dehydrogenase(LDH)serum levels were positively correlated with loss of taste scores.About 80%of COVID-19 patients recovered from smell and taste dysfunction in 2 weeks.In this cohort,only 1 out of 10 hospital admitted patients had loss of smell while 1 out of 5 reported loss of taste which was associated to severity of COVID-19.Most patients recovered smell and taste dysfunctions in 2 weeks.

Animals Sense of Smell

Odors that induce psychological orbehavioral changes in the same species——fright in a catfish^2,sexual arousal in abull—are called pheromones^3.And nowheredo such odors have more profound aneffect than among the bees,wasps,ants,and termites^4:Pheromones are the chemicalmessages that these insects use to organizetheir complex societies.The queen honeybee preserves hermonarchy^5 by exuding^6 an odor thatnhibits worker bees from laying eggs

Code Smell Detection Using Whale Optimization Algorithm

Software systems have been employed in many fields as a means to reduce human efforts;consequently,stakeholders are interested in more updates of their capabilities.Code smells arise as one of the obstacles in the software industry.They are characteristics of software source code that indicate a deeper problem in design.These smells appear not only in the design but also in software implementation.Code smells introduce bugs,affect software maintainability,and lead to higher maintenance costs.Uncovering code smells can be formulated as an optimization problem of finding the best detection rules.Although researchers have recommended different techniques to improve the accuracy of code smell detection,these methods are still unstable and need to be improved.Previous research has sought only to discover a few at a time(three or five types)and did not set rules for detecting their types.Our research improves code smell detection by applying a search-based technique;we use the Whale Optimization Algorithm as a classifier to find ideal detection rules.Applying this algorithm,the Fisher criterion is utilized as a fitness function to maximize the between-class distance over the withinclass variance.The proposed framework adopts if-then detection rules during the software development life cycle.Those rules identify the types for both medium and large projects.Experiments are conducted on five open-source software projects to discover nine smell types that mostly appear in codes.The proposed detection framework has an average of 94.24%precision and 93.4%recall.These accurate values are better than other search-based algorithms of the same field.The proposed framework improves code smell detection,which increases software quality while minimizing maintenance effort,time,and cost.Additionally,the resulting classification rules are analyzed to find the software metrics that differentiate the nine code smells.

Human Beings’Sense of smell^1

Somerset Maugham2 inquired of one of H·G·Wells’s3 mistresses4 why such a paunchy5, homely6 writer had such success with women.He smells of honey, she said. Body odors are the smell of acids produced by bacteria metabolizing skin secretions.7 The most repellent8 odors result from the apocrine glands9, associated with underarm and genital hair10 and activated11 when we’re frightened, excited, or aroused. Men have more and larger apocrine glands than women, blacks more than Caucasians,12 Caucasians more than Orientals.13 Varying skin acidity controls the size of

Smell and Sound

Once there was a stingy(小气的)baker.He was angry at a poor man who would standoutside the bakery(面包房)every day,savoring(品尝)the scent of baking bread.The bakerfelt that anyone who smelled his delicious products should have to pay for the privilege.So

Anatomophysiological relationships and clinical considerations of taste and smell loss in patients with COVID-19

BACKGROUND There are numerous conflicting discussions about the outbreak of the new coronavirus 2019(COVID-19).AIM To present some anatomical and physiological considerations about two of the symptoms reported by patients:The loss or reduction of smell and taste.METHODS The loss or reduction of smell and taste is presented in a peculiar way,with some cases of persistence even after COVID-19.For this,it was searched in three databases,PubMed/MEDLINE,Web of Science,and Scopus,using the following keywords:"Smell","Taste","Smell AND COVID-19","Taste AND COVID-19",with no publication time restriction,only in English with full text available,excluding also brief communications,letters to the editor,editorials,reviews,comments,and conference abstracts.RESULTS The search found 776 articles in the PubMed/MEDLINE database,1018 in the Web of Science database,and 552 in the Scopus database,from which duplicates were removed(104 articles).Finally,17 studies were selected for detailed analysis within the eligibility criteria,with titles and abstracts related to central nervous system lesions responsible for smell and taste.This review suggests that viral mechanisms of action may be related to lesions both at the local level and at the level of the central nervous system,lasting up to 3 to 4 wk.It is considered persistent if it exceeds this period,as reported in one case in this review.There are still few studies about the treatment,and among those addressed in this review,only two studies reported possible treatments and emphasized the scarcity of data,with the best option being treatments that do not cause harm,such as gustatory and olfactory physiotherapy CONCLUSION Given the scarcity of data,this review emphasizes the importance of prevention,through the correct use of personal protective equipment by health professionals and respect for local behavioral indications.It is also emphasized,through five studies,that there is a predominance of such symptoms in patients with COVID-19,which can be a tool to control dissemination,through the early isolation of patients until the results are ready.

TCM analysis and strategy for COVID-19 associated loss of smell and taste

Coronavirus disease 2019(COVID-19)is caused by SARS-CoV2 and is still not yet under complete control and no cure is available until this moment.It is still unpredictable to expect vaccination available worldwide in the near future.Early diagnosis hence becomes extremely important.Various papers have proven that early identification of loss of smell and taste is of significance in the diagnosis of this disease.Some patients of COVID-19 may carry on suffering from loss of smell and taste even long after the other symptoms of the infection subside.The aetiology,pathology,and mechanism of loss of smell and taste are discussed in this article,pointing out that impairment of meridians,disturbed Brain-Shen and dysfunction of the Zang-Fu organs are the key pathology of loss of smell and taste by COVID-19.Traditional Chinese medicine resolution with acupuncture and Chinese herbs are therefore demonstrated accordingly,aiming to establish some practical and effective strategies to deal with loss of smell and taste.This unique presentation in the treatment illustrate that even though loss of smell and taste being a single symptom,it requires a profound understanding on the complicated and sophisticated background mechanism of the COVID-19,which is urgently in need of comprehensive treatment in time.Loss of smell and taste by COVID-19 is not only a minor suffering of the infection,but also a very critical part of a fully recovery of COVID-19,it shall not be left untreated.

A Strong Smell of Fish

Once an old couple stayed over night at a small hotel in the countryside. Their room wasvery hot in the night, so the husband got up in the dark to open the door. When he got back, hiswife asked him what kind of night it was. "I don t think it s raining," he replied. "But it s pitch-dark(漆黑的), and there is a

基于预训练模型与BiLSTM-CNN的多标签代码坏味检测方法

为了提高多标签代码坏味检测的准确率,提出一种基于预训练模型与BiLSTM-CNN的多标签代码坏味检测方法DMSmell(deep multi-smell)。首先,利用静态分析工具获取源代码中的文本信息和结构度量信息,并采用2种检测规则对代码坏味实例进行标记;其次,利用CodeBERT预训练模型生成文本信息对应的词向量,并分别采用BiLSTM和CNN对词向量和结构度量信息进行深度特征提取;最后,结合注意力机制和多层感知机,完成多标签代码坏味的检测,并对DMSmell方法进行了性能评估。结果表明:DMSmell方法在一定程度上提高了多标签代码坏味检测的准确率,与基于分类器链的方法相比,精确匹配率提高了1.36个百分点,微查全率提高了2.45个百分点,微F1提高了1.1个百分点。这表明,将文本信息与结构度量信息相结合,并利用深度学习技术进行特征提取和分类,可以有效提高代码坏味检测的准确性,为多标签代码坏味检测的研究和应用提供重要的参考。

Bagging异构集成的代码异味检测与重构优先级划分

代码异味是不良的设计和代码实现的症状,可能阻碍代码理解、增加代码更改和出错的可能性。以前的研究专注于单一模型在代码异味上的检测,并且无法为开发人员提供重构建议。针对上述问题,提出一种基于Bagging异构集成模型的代码异味检测与重构优先级划分方法,该方法利用分类器间的异质性,通过F1集成策略来检测Complex Class、Long Method、Spaghetti Code等三种代码异味,并将模型输出的异味概率转化为可能性分布后,为开发人员提供重构意见。实验在6个开源系统的32个版本上验证、评估:(1)基分类器的稳定性以及与代码异味的关系;(2)Bagging异构集成模型检测上述代码异味的性能;(3)将异味概率转化为可能性分布并作为重构优先级的有效性。实验结果表明,最佳基分类器因代码异味类型而异。同时,Bagging异构集成模型相较于基分类器,F1提高0.06~40.51个百分点,AUC提高0.45~28.37个百分点。最后将Bagging异构集成模型的重构优先级与6名受访者的重构优先级进行Kappa一致性检验,两者具有高度一致性。

深度学习策略下缓慢循环异味检测方法

缓慢循环是一种Android特有代码异味,对Android应用程序的可维护性产生负面影响.针对传统基于静态程序分析方法误检率较高的问题,本文提出基于深度学习的检测方法.首先,使用代码文本信息作为模型输入的特征集.然后,使用两种深度学习模型进行异味检测.此外,为了快速、准确获得模型所需的大量样本数据,提出了一种基于开源Android项目构造正负样本的方法并实现工具ASSD.最后,使用开源Android数据集对提出的方法进行实验验证.实验结果表明,本文方法优于现有基于程序静态分析的检测方法,其中检测效果最好的是CNN模型,其F1值平均提高了28.7%.此外,本文方法优于基于机器学习的检测方法,相对于检测效果最好的随机森林模型,CNN模型的F1值平均提高了9.43%.

Predicting Code Smells and Analysis of Predictions: Using Machine Learning Techniques and Software Metrics

Code smell detection is essential to improve software quality, enhancing software maintainability, and decrease the risk of faults and failures in the software system. In this paper, we proposed a code smell prediction approach based on machine learning techniques and software metrics. The local interpretable model-agnostic explanations (LIME) algorithm was further used to explain the machine learning model's predictions and interpretability. The datasets obtained from Fontana et al. were reformed and used to build binary-label and multi-label datasets. The results of 10-fold cross-validation show that the performance of tree-based algorithms (mainly Random Forest) is higher compared with kernel-based and network-based algorithms. The genetic algorithm based feature selection methods enhance the accuracy of these machine learning algorithms by selecting the most relevant features in each dataset. Moreover, the parameter optimization techniques based on the grid search algorithm significantly enhance the accuracy of all these algorithms. Finally, machine learning techniques have high potential in predicting the code smells, which contribute to detect these smells and enhance the software's quality.

从络脉探讨新型冠状病毒感染后嗅觉异常

新型冠状病毒感染(COVID-19)从发生到现在为止已3年有余,疫情期间中医中药发挥了重要的作用,取得了很好的疗效,但随着时间推移,感染过的人数增多,发现感染后嗅觉异常患者越来越多,西医对其治疗以刺激神经或使其自愈为主,但效果因人而异且治疗周期长,而嗅觉异常会使患者生活体验感降低、心理状态改变,如焦虑、抑郁等,还会诱发其他系统疾病,所以对于嗅觉异常的情况不容小觑,中医对其认识、治疗有独特之处,故文章从COVID-19致嗅觉异常的现代研究、中医认识及药物应用等方面阐述了嗅觉异常的原因及从络脉入手如何拓展治疗思路进行治疗。

健康成年男性嗅觉脑功能性磁共振成像分析

目的 探讨应用功能性磁共振成像技术(fMRI)对正常嗅觉的青年和中年男性进行对比分析,观察二者嗅觉刺激后大脑功能活化区的异同,分析年龄对嗅觉中枢兴奋性的影响。方法 选取44例右利手、无嗅觉障碍的健康男性,按年龄分为青年组21例,中年组23例,经过嗅觉检测正常,给予受试者相同的嗅觉刺激任务,刺激剂为异戊酸,fMRI扫描获得成像数据,采用SPM 8.0软件进行数据处理,并将结果进行统计学分析。结果 青年组激活区域位于右侧海马旁回、右侧颞叶、右侧额叶、右侧额上回、右侧额内侧回、左侧额中回;中年组激活区域位于右侧额中回、右侧额下回、右侧额叶、右侧扣带回、右侧颞中回、左侧海马旁回、右侧颞下回。经独立样本t检验,二者在整个激活脑区的体素对比差异无统计学意义(t=1.166,P>0.05)。结论 嗅觉中枢影响情绪与记忆,影响着大脑空置状态、记忆的空间及记忆编码顺序,并且与这些功能共同编码存在。嗅觉具有右侧优势偏向,正常青年人与中年人嗅觉中枢无差异,临床可将嗅觉脑fMRI作为嗅觉功能检测的客观方法。

Application of Sargassum fusiforme(Harv.)Setch.Extract in Cigarettes

[Objectives]This study was conducted to investigate the application of Sargassum fusiforme(Harv.)Setch.in cigarettes.[Methods]Tobacco-specific nitrosamines in the smoke of cigarettes added with ethanol extract of S.fusiforme were determined,and the compounds related to the aroma of S.fusiforme were identified by flavor-smelling experiment.[Results]With the addition of the ethanol extract of S.fusiforme,the decrease in the total amount of four tobacco-specific nitrosamines in mainstream cigarette smoke reached 16.42%.The results of the flavor-smelling experiment showed that the aroma of S.fusiforme might be related to(R)-5,6,7,7A-tetrahydro-4,4,7A-trimethyl-2(4H)-benzofuranone,glycerol,ethyl palmitate,methyl palmitate,ethyl linoleate,methyl(Z,Z,Z)-9,12,15-octadecatrienoate,ethyl(Z,Z,Z)-9,12,15-octadecatrienoate,phytol,and tetradecanoic acid.[Conclusions]The ethanol extract of S.fusiforme has the potential function of reducing the content of tobacco-specific nitrosamines in smoke and improving the taste of cigarettes.

《中医四诊操作规范第2部分:闻诊》国家标准解读

2021年11月26日,国家市场监督管理总局和国家标准化管理委员会联合发布GB/T 40665.2—2021《中医四诊操作规范第2部分:闻诊》标准。经过专业领域多位专家决策,多轮研讨和论证,由湖南中医药大学朱文锋教授牵头,北京中医药大学、福建中医药大学、云南中医药大学的专家参与,制定《中医四诊操作规范第2部分:闻诊》国家标准。标准详细描述闻诊的定义、基本要求、闻诊内容、14项与听声音有关的判断要求,4项与嗅气味有关的判断要求及闻诊操作注意事项。总结闻诊所涉及的主要内容,系统回顾闻诊的定义,基本要求,听声音、嗅气味的指标判断和操作注意事项。通过内容解读,为临床医师闻诊疾病、中医学生闻诊学习提供规范与指导。

基于嗅觉和听觉刺激的驾驶员疲劳唤醒方法研究

针对驾驶员在疲劳状态下易引发交通事故的问题,提出一种基于嗅觉和听觉刺激的驾驶员疲劳唤醒方法,研究以薄荷气体和阿尔法脑波音乐作为刺激源的唤醒效果,采用主观疲劳问卷和心电(ECG)、脉搏(PPG)以及呼吸(RESP)生理信号作为疲劳唤醒有效性判断指标。结果表明,两种方案的心电、脉搏以及呼吸生理数据均显示能有效干预驾驶疲劳,与主观疲劳问卷调查结果相一致,验证了基于嗅觉和听觉刺激的驾驶员疲劳唤醒方法的有效性,且基于听觉刺激的唤醒方案唤醒效果更佳。