A Survey of Crime Scene Investigation Image Retrieval Using Deep Learning

Crime scene investigation(CSI)image is key evidence carrier during criminal investiga-tion,in which CSI image retrieval can assist the public police to obtain criminal clues.Moreover,with the rapid development of deep learning,data-driven paradigm has become the mainstreammethod of CSI image feature extraction and representation,and in this process,datasets provideeffective support for CSI retrieval performance.However,there is a lack of systematic research onCSI image retrieval methods and datasets.Therefore,we present an overview of the existing worksabout one-class and multi-class CSI image retrieval based on deep learning.According to theresearch,based on their technical functionalities and implementation methods,CSI image retrievalis roughly classified into five categories:feature representation,metric learning,generative adversar-ial networks,autoencoder networks and attention networks.Furthermore,We analyzed the remain-ing challenges and discussed future work directions in this field.

Comparative study of different machine learning models in landslide susceptibility assessment: A case study of Conghua District, Guangzhou, China

Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Conghua District,which is the most prone to landslide disasters in Guangzhou,was selected for landslide susceptibility evaluation.The evaluation factors were selected by using correlation analysis and variance expansion factor method.Applying four machine learning methods namely Logistic Regression(LR),Random Forest(RF),Support Vector Machines(SVM),and Extreme Gradient Boosting(XGB),landslide models were constructed.Comparative analysis and evaluation of the model were conducted through statistical indices and receiver operating characteristic(ROC)curves.The results showed that LR,RF,SVM,and XGB models have good predictive performance for landslide susceptibility,with the area under curve(AUC)values of 0.752,0.965,0.996,and 0.998,respectively.XGB model had the highest predictive ability,followed by RF model,SVM model,and LR model.The frequency ratio(FR)accuracy of LR,RF,SVM,and XGB models was 0.775,0.842,0.759,and 0.822,respectively.RF and XGB models were superior to LR and SVM models,indicating that the integrated algorithm has better predictive ability than a single classification algorithm in regional landslide classification problems.

A Study on the Implementation Path of the Blended Teaching Model in Geological Hazards Investigation and Evaluation

Geological Hazards Investigation and Evaluation is the core course of Environmental Geological Engineering,aiming to cultivate skilled talents with solid theoretical knowledge and excellent practical skills.At present,the course faces several issues,including a teaching environment disconnected from real-world work scenarios,course content that deviates from job-related tasks,a lack of digital teaching resources,and reliance on a single teaching method,leading to students’poor feedback from employers.Based on the concept of outcome-based education,the course team of Geological Hazards Investigation and Evaluation establishes a“five-step double-rotation”blended teaching model with the help of a Small Private Online Course platform.The program is designed to improve the teaching environment and expand the digitalized teaching resources in order to improve students’learning motivation,enhance learning effectiveness,and cultivate skillful talents who meet employers’satisfaction.

Probabilistic outlier detection for sparse multivariate geotechnical site investigation data using Bayesian learning

Various uncertainties arising during acquisition process of geoscience data may result in anomalous data instances(i.e.,outliers)that do not conform with the expected pattern of regular data instances.With sparse multivariate data obtained from geotechnical site investigation,it is impossible to identify outliers with certainty due to the distortion of statistics of geotechnical parameters caused by outliers and their associated statistical uncertainty resulted from data sparsity.This paper develops a probabilistic outlier detection method for sparse multivariate data obtained from geotechnical site investigation.The proposed approach quantifies the outlying probability of each data instance based on Mahalanobis distance and determines outliers as those data instances with outlying probabilities greater than 0.5.It tackles the distortion issue of statistics estimated from the dataset with outliers by a re-sampling technique and accounts,rationally,for the statistical uncertainty by Bayesian machine learning.Moreover,the proposed approach also suggests an exclusive method to determine outlying components of each outlier.The proposed approach is illustrated and verified using simulated and real-life dataset.It showed that the proposed approach properly identifies outliers among sparse multivariate data and their corresponding outlying components in a probabilistic manner.It can significantly reduce the masking effect(i.e.,missing some actual outliers due to the distortion of statistics by the outliers and statistical uncertainty).It also found that outliers among sparse multivariate data instances affect significantly the construction of multivariate distribution of geotechnical parameters for uncertainty quantification.This emphasizes the necessity of data cleaning process(e.g.,outlier detection)for uncertainty quantification based on geoscience data.

An Investigation Into Freshmen＇s Autonomous Learning of English Major

Autonomous learning has been attracting more and more attention in the field of second language teaching and learning since it was put forward. In order to get a better understanding about autonomous learning competence of freshmen of English major in university, this investigation was conducted in the form of questionnaire and was analyzed according to the data collected. The investigation found that autonomous learning competence of freshmen is poor and worrying. Freshmen have strong motivation for English learning, but they keep old learning habit and more rely on teachers. They are incapable of employing metacognitive strategies in their language learning and are not good at utilizing related learning resources available to them. All these deficiencies hinder improvement of them. So they are in great need of fostering the competence of automous learning.

Feasibility Investigation and Development Exploration on Popularizing the Method of English Fragmented Mobile Learning of Undergraduates

This paper attempts to investigate the feasibility and learning effects of English fragmented learning via mobile devices.Questionnaires and interviews were employed to do the survey on 157 undergraduates from 24 universities in China.The research findings reveal that English fragmented learning via mobile devices has some positive effects on the improvement of learners’knowledge and learning ability.In addition,there have been a certain number of useful learning resources and platforms with diversified features.The study has the implications that fragmented mobile learning is feasible and can be popularized in English learning.

An Investigation of Junior Middle School Students'English Learning Motivation and Motivating Strategies

English learning motivation plays a more and more important role in junior middle school students' study,and it is necessary for students to learn English effectively.Therefore,teachers should take responsibilities for stimulating students' English learning motivation.This present thesis investigates 63 students who are from class 1 grade 1,class 2 grade 1 and class 3 grade 1 in NanJie country junior middle school in LinYing town LuoHe city by the way of questionnaire.And the thesis discusses the source of students' learning motivation,for the purpose of putting forward strategies of motivating students' English learning motivation in accordance with students' type of motivation.

企业E-learning现状调查与分析——以TCL集团为研究个案

借助互联网的应用热潮,E-learning这一数字化学习方式已经成为各大企业开展员工培训的重要方式。TCL集团作为我国"数字化学习港"教学改革项目唯一的企业示范点,正努力探索"数字化学习型企业"的建设及运行规律;而企业管理者和员工对E-learning的认识、需求及习惯是创建"数字化学习型企业"的重要依据。本文以TCL集团为个案,通过对其下属公司管理者和员工的问卷调查、访谈与分析,发现企业培训主管和企业员工都对采用E-learning培训有强烈愿望并持肯定态度,但对E-learning的认识尚不够深入;同时企业在E-learning的组织实施及提供学习支持服务等方面仍需进一步探索。

Group Investigation in a College English Program at a Chinese University:A Case Study

This study investigated the application and the effect of Group Investigation(GI) in the College English Program in a Chinese University. A qualitative case study method was used to understand the GI system used by Chinese instructors as well as the achievements acquired and challenges met by the participants. Three instructors and fifteen second-year-undergraduates taking a course titled Sources of European Culture participated. Interviews, observations, and documents were used to collect the data. Data analysis showed Chinese instructors applied a GI technique similar to that discussed by Johnson and Johnson(1999); however, GI in the Chinese context demanded more effort from the teacher for designing tasks and provided help in modeling uses of English and in preparing visual, especially Power Point, presentations. Although participants used their mother tongue at some stages, their autonomy over English learning was activated, and horizons in the course content were broadened.

A generic framework for geotechnical subsurface modeling with machine learning

This study introduces a generic framework for geotechnical subsurface modeling, which accounts for spatial autocorrelation with local mapping machine learning(ML) methods. Instead of using XY coordinate fields directly as model input, a series of autocorrelated geotechnical distance fields(GDFs) is designed to enable the ML models to infer the spatial relationship between the sampled locations and unknown locations. The whole framework using GDF with ML methods is named GDF-ML. This framework is purely data-driven which avoids the tedious work in the scale of fluctuations(SOFs)estimating and data detrending in the conventional spatial interpolation methods. Six local mapping ML methods(extra trees(ETs), gradient boosting(GB), extreme gradient boosting(XGBoost), random forest(RF), general regression neural network(GRNN) and k-nearest neighbors(KNN)) are compared in the GDF-ML framework. The results show that the GDFs are better than the conventional XY coordinate fields based ML methods in both accuracy and spatial continuity. GDF-ML is flexible which can be applied to high-dimensional, multi-variable and incomplete datasets. Among these six methods, GDF with ET method(GDF-ET) clearly shows the best accuracy and best spatial continuity. The proposed GDF-ET method can provide a fast and accurate interpretation of the soil property profile. Sensitivity analysis shows that this method is applicable to very small training dataset size. The associated statistical uncertainty can also be quantified so that the reliability of the subsurface modeling results can be estimated objectively and explicitly. The uncertainty results clearly show that the prediction becomes more accurate when more sampled data are available.

Research on Personal Credit Risk Assessment Model Based on Instance-Based Transfer Learning

Personal credit risk assessment is an important part of the development of financial enterprises. Big data credit investigation is an inevitable trend of personal credit risk assessment, but some data are missing and the amount of data is small, so it is difficult to train. At the same time, for different financial platforms, we need to use different models to train according to the characteristics of the current samples, which is time-consuming. In view of these two problems, this paper uses the idea of transfer learning to build a transferable personal credit risk model based on Instance-based Transfer Learning (Instance-based TL). The model balances the weight of the samples in the source domain, and migrates the existing large dataset samples to the target domain of small samples, and finds out the commonness between them. At the same time, we have done a lot of experiments on the selection of base learners, including traditional machine learning algorithms and ensemble learning algorithms, such as decision tree, logistic regression, xgboost and so on. The datasets are from P2P platform and bank, the results show that the AUC value of Instance-based TL is 24% higher than that of the traditional machine learning model, which fully proves that the model in this paper has good application value. The model’s evaluation uses AUC, prediction, recall, F1. These criteria prove that this model has good application value from many aspects. At present, we are trying to apply this model to more fields to improve the robustness and applicability of the model;on the other hand, we are trying to do more in-depth research on domain adaptation to enrich the model.

多元生源背景下高职学生自适应学习探析

为探索高职个性化、多样化、定制化教育及提高教学改革的针对性和有效性,以某高职院校10028名在校生为研究对象,通过问卷调查开展实证研究,通过对比、关联、聚类分析和关键词词频统计分析等数据处理方式,探析多元生源背景下高职学生个性化学习表征和自适应学习模式,提出了强化职业生涯规划教育、建立健全教学管理与校企合作办学制度、优化职业教育课程体系和深化课程考核评价改革四个方面的关键举措以满足高职学生自适应学习需求。

基于在线学习平台问卷调查的混合式教学在妇科教学中的应用

目的观察基于在线学习平台问卷调查的混合式教学对妇科理论教学效果的影响。方法选取2021年7月—2022年7月滨州医学院2018级全日制本科临床医学专业学生113名作为研究对象,随机分为研究组57名和对照组56名。研究组采用在线学习平台调查问卷与线下教学相结合的教学模式,对照组采用传统教学模式,比较2组学生课堂表现、课后知识测评成绩和满意度问卷调查。结果研究组测评成绩(86.61±8.37)分,对照组成绩(82.07±12.25)分,研究组高于对照组,差异有统计学意义(t=2.304,P<0.05),满意度问卷调查结果显示研究组教学方法更得到学生的肯定(P<0.05)。结论基于慕课堂授课前后问卷调查混合教学模式适合当前教学形势,能有效提高学生学习主动性,提高教学质量。

本科生科研学习投入现状及影响因素——基于某地方本科院校的调查

本科生科研是高校创新型人才培养的有效途径,而科研学习投入是衡量本科生科研学习质量的重要过程性指标。通过对某地方高校424名有科研学习经历的本科生进行问卷调查,结果显示:科研学习投入呈现中等偏低的水平,且存在年级差异;导师与同伴支持、院校信息支持及角色挑战对本科生科研学习投入产生重要影响。为提升地方高校本科生科研学习投入质量,从院校改进视角提出如下建议:夯实研究基础,培养和提升学生学术素养;完善指导者体系,提升指导与反馈质量;丰富信息资源,改善研究环境。

高校师生“教”与“学”双向认可度提升策略与实践研究

基于多所高校的调查研究数据,开展了影响高校教师和学生相互认可度高低的因素研究,并对调研数据进行了重构分析,构建出认可度权重值α提升的驱动模型。通过该模型对比教师与学生认可度权重值α,可发现认可度方面的弱项及其影响因素,并由此提出弱项改善的实践途径和方法。基于重构后的数据结果,提出了有助于高校师生“教”与“学”双向认可度提升的6点策略:提升个人涵养;加强学生的情感教育;推进课程思政教育;融合信息技术;注重理论与实践相结合;更新教学模式。

共同富裕背景下浙江省高职院校学情调查分析

共同富裕的重要标志和动能是壮大中等收入群体,要扩大中等收入群体需要发挥高等职业教育塑造新生中等收入群体的功用。对11万多名学生抽样调查发现,浙江高职院校的生源主要来自县城及以下,家庭经济收入以中等及偏下为主,来自乡镇的学生有上升的趋势;高年级学生的学习满意度显著高于低年级学生,师生沟通和学生的时间控制呈现下降趋势;“双高计划”建设院校学生的满意度总体高于其他院校,而国家高水平学校建设单位和高水平专业群建设院校在人才培养方面不分伯仲;高职院校的人才培养成效与区域经济发展呈正相关性,位于区域经济发展强的高职院校学生满意度显著高于其他区域的学生,存在一定程度区域发展的不均衡性。赋能共富示范区建设,需要高等职业教育在兜底高等教育的同时增强学生获取和维护技能的意愿和能力,着力培育工匠精神;着力增强学生的数字技能等专业核心能力;在“双高计划”建设中更加强化人才培养的基础地位,将人才培养质量作为评价“双高计划”建设的重要指标;强化省域统筹,协同发展并推进优质高职资源下沉县域。

基于新搜索策略的改进法医调查算法

为解决法医搜索算法的搜索方程存在振荡等问题,构建一种改进的法医调查算法。引入均值机制和莱维飞行策略对分析调查结果进行改进,提高算法的勘探能力;调查方向充分使用当前个体的有效信息,引入自适应动态调整缩放因子及最优个体引导机制,增强算法的探索活力;利用趋优避劣方法对算法的追捕行动进行改进,改善种群个体质量;追捕行动扩展采用单优学习策略解决振荡问题。求解11个标准函数和无线传感网络覆盖问题的结果显示,与对比算法比较,改进算法的优化能力具有显著优势。

基于钻进参数实时预测土体力学性质的Stacking集成模型

岩土体物理力学参数对工程勘察、设计、施工等作业不可或缺,但常规取样试验或原位检测均存在明显的精度误差。据此本文提出基于勘察钻探的实时钻进参数,建立基于机器学习的随钻土体物理力学参数模型。通过采集位于珠海市国家高新技术产业开发区内20 m勘探孔的真实数据,将EP-200G型钻机实时随钻采集的钻压、扭矩和三轴振动作为输入数据,将全孔土体粘聚力、内摩擦角、含水量与弹性模量试验数据作为输出。基于建模数据分析,证明使用单算法的3类机器学习模型(支持向量机、神经网络和决策树)的预测精度最高仅为0.78,而基于Stacking理念的集成模型可将预测精度提升至最高0.98。结合该模型,进行了随钻参数与土体参数间的敏感性分析,证实当不同土体参数发生变化时,不同随钻参数会发生明显变化,证明了随钻参数预测土体参数的可靠性与适用性。

特殊教育专业本科生学习现状的调查研究及改进建议——以甘肃省某高校为例

全面、客观、深入地了解特殊教育专业本科生学习现状,对深化特殊教育专业教育教学改革,提升学生学习效能有重大意义。通过学习动机、学习态度、学习投入、学习方法和学习收获五个维度的调研,发现特殊教育专业本科生学习中存在内在动机不足、互动意识不强、学习行动力匮乏、深度学习精神缺乏、理论与实践分离等问题。鉴于此,提出加强学生专业引领、增强学生的深度学习倾向、提供多维的学习体验、提供学生实践的平台、提升教师教育教学能力等改进建议。

听觉词汇学习测验对于轻度认知障碍转归的预测价值研究

目的研究听觉词汇学习测验(auditory vocabulary learning test,AVLT)对轻度认知障碍(mild cognitive impairment,MCI)进展为痴呆的预测能力。方法对257例MCI患者进行纵向随访,然后根据临床结果将其分为痴呆进展组和非痴呆进展组。比较这些组的基线人口统计学信息和AVLT评分。构建受试者工作特征(receiver operating characteristic,ROC)曲线以评估AVLT评分对MCI转归的区分值。结果在6年后的随访中,有45例受试者进展为痴呆,归为痴呆进展组(MCI progression,MCIp),3例受试者恢复正常认知,209例受试者维持MCI,一同归为非痴呆进展组(MCI non-progression,MCInp)。在基线时,MCIp组的AVLT评分明显低于MCInp,差异有统计学意义(P<0.05)。ROC曲线分析显示,AVLT延迟回忆(delayed recall,AVLT-DR)在区分MCI患者进展为痴呆方面有最大的曲线下面积(largest area under the curve,AUC),是重要预测指标。结论AVLT,尤其是AVLT-DR评分较低能较好预测MCI进展为痴呆,但由于其特异度偏低,需要联合其他特异度高的量表综合使用来运用于临床工作。