Computer Science and Application
ISSN / EISSN : 2161-8801 / 2161-881X
Published by: Hans Publishers (10.12677)
Total articles ≅ 1,531
Latest articles in this journal
Computer Science and Application, Volume 11, pp 1672-1678; https://doi.org/10.12677/csa.2021.116172
水路投送是两栖兵力投送的重要方式之一，针对两栖兵力水路投送的时效问题，提出一种基于网络计划技术的投送时间预测方法。该方法首先确定各工作的时间参数，找出关键点和关键路线，以最优完成整个计划为目标，组织、调整和控制投送计划进度，提升反应能力和指挥效能。 Water delivery is one of the important ways of amphibious force delivery. Aiming at the timeliness of amphibious force water delivery, this paper proposes a delivery time prediction method based on network planning technology. This method first determines the time parameters of each work, finds out the key routes and points, and finally takes the optimal completion of the whole plan as the goal to organize, adjust and control the delivery schedule and improve the response capability and command effectiveness.
Computer Science and Application, Volume 11, pp 1679-1688; https://doi.org/10.12677/csa.2021.116173
随着安卓手机的发展，数据删除已经成为人们保护隐私数据的重要手段，但是安卓手机自带的数据删除是不安全的。自带的数据删除是为了回收存储空间所作的一个快速操作，其操作只是将元数据和文件内容的连接阻断，同时把元数据标识成删除标记，但是它清除的文件还是保存在存储介质内，黑客仍然可以通过相应的数据恢复技术将数据还原，从而导致用户的隐私数据泄露。本文就现阶段的数据删除技术进行深度剖析，设计出一种基于双文件系统存储方式的数据安全删除方案。该方案与之前研究人员的安全删除方案进行多项指标对比分析。发现该方案整体优于之前研究人员的方案，方案评估表明该方案符合安全删除的高效性与可行性。 With the development of Android phones, data deletion has become an important means for people to protect private data, but the data deletion that comes with Android phones is not safe. The built-in data deletion is a quick operation for reclaiming storage space. The operation is only to block the connection between metadata and file content, and at the same time, mark the metadata as a deletion mark, but the files it clears are still stored in the storage medium. Hackers can still restore the data through the corresponding data recovery technology, resulting in the leakage of the user’s private data. This article conducts an indepth analysis of the current data deletion technology, and designs a data security deletion scheme based on the dual-file system storage method. This program compares and analyzes multiple indicators with the previous researcher’s secure deletion program. It was found that the program was better than the previous researcher’s program as a whole, and the evaluation of the program showed that the program meets the efficiency and feasibility of safe deletion.
Computer Science and Application, Volume 11, pp 1689-1697; https://doi.org/10.12677/csa.2021.116174
针对各种场景下的海量终端的部署，本文设计了一套海量数据采集与实时分析系统，具体在数据采集模块，通过借助Kafka消息队列，实现数据的高并发接入；在数据分析模块，借助大数据流处理系统Storm，在保证高可靠性的前提下，实现数据的实时处理，并通过相应的优化设计，解决海量终端接入网络时的高并发访问与数据处理需求；通过可视化设计以及实验验证本文方法的有效性，系统具有低延迟，高吞吐，可拓展等特点，能够满足车联网海量数据处理要求，具有很强的实用价值，目前本文提出的方法已经应用在实际场景中，为20多万台北斗定位终端提供服务。 For the deployment of mass terminals in various scenarios, this paper designs a set of mass data acquisition and real-time analysis system. In the data acquisition module, with the help of Kafka message queue, the high concurrent access of data is realized; in the data analysis module, with the help of the big data stream processing system storm, the real-time data processing is realized on the premise of high reliability, and through the corresponding optimization design, the high concurrent access and data processing requirements of massive terminals accessing the network are solved; through the visual design and experimental verification, the effectiveness of this method, the system has the characteristics of low latency, high throughput, scalability, and can meet the requirements of massive data processing in the Internet of vehicles, which has strong practical value. At present, the method proposed in this paper has been applied in the actual scene, providing services for more than 200,000 BD-based positioning terminals.
Computer Science and Application, Volume 11, pp 1698-1705; https://doi.org/10.12677/csa.2021.116175
故障诊断与预测通过海量数据，采用推断统计、神经网络等研究方法，对监测数据进行分析和预测，从而评估轨道车辆的健康状况，最大限度保证轨道车辆各系统部件健康工作。本文通过研究转向架关键部件的物理特性，结合长短期记忆网络在处理“长期依赖”问题的优势，构建了基于长短期记忆网络的转向架关键参数趋势预测模型。为了验证方法的有效性，本文使用CRH380动车组转向架轴箱轴承和齿轮箱的温度监测数据进行了预测。结果表明，基于长短期记忆网络的转向架关键部件参数趋势预测方法能够有效预测转向架关键参数的变化趋势。 Fault diagnosis and prediction use massive data, inferred statistics, neural network and other research methods to analyze and predict the monitoring data, so as to evaluate the health status of the rail vehicle and ensure the health of each system component of the rail vehicle to the greatest extent. In this paper, by studying the physical characteristics of the key components of the bogie, combined with the advantages of the long and short-term memory network in dealing with the problem of “long-term dependence”, a trend prediction model for the key parameters of the bogie based on the long and short-term memory network is constructed. In order to verify the effectiveness of the method, this paper uses the temperature monitoring data of the CRH380 EMU bogie axle box bearing and gear box to make predictions. The results show that the trend prediction method of bogie key component parameters based on long- and short-term memory network can effectively predict the change trend of bogie key parameters.
Computer Science and Application, Volume 11, pp 1717-1724; https://doi.org/10.12677/csa.2021.116177
针对建筑轮廓提取问题，提出并实现了一种基于MATLAB的影像建筑轮廓自动提取方法。首先，对彩色影像进行阴影去除，将彩色影像转换为灰度影像，进行直方图均匀化以及中值滤波；其次，对中值滤波后的影像进行膨胀和腐蚀操作，通过对膨胀与腐蚀影像进行差分运算，进行地物边缘检测；最后，对边缘检测后的影像二值化处理，并完成建筑物特征点及其坐标的提取。通过实例验证表明，本文方法简洁可行，计算效率要高于深度学习提取建筑物的方法。 Aiming at the problem of building contour extraction, an automatic extraction method of building contour based on MATLAB is proposed and implemented. Firstly, the shadow of the color image is removed, the color image is converted into gray image, histogram homogenization and median filtering are carried out; secondly, the image after median filtering is expanded and corroded, and the ground edge is detected by differential operation of the expansion and corrosion image; finally, the image after edge detection is binarized, and then the building feature points and their coordinates are extracted. The example shows that this method is simple and feasible, and the computational efficiency is much higher than the deep learning method.
Computer Science and Application, Volume 11, pp 1738-1746; https://doi.org/10.12677/csa.2021.116179
该文以旅游人数为研究对象，初步选取影响旅游人数的13个因素，首先建立基于遗传算法优化灰色神经网络模型对旅游人数进行预测。为了进一步提高模型预测精度，采用灰色关联度法和平均值影响法两种方法对影响因素进行变量筛选，选取影响程度大的因素代入模型进行预测。分析比较模型的结果，可得经过平均值影响法变量筛选后的模型预测精度最高，误差最小。 Taking the number of tourists as the research object, this paper preliminarily selects 13 factors that affect the number of tourists, and firstly establishes a grey netural network model based on genetic algorithm to predict the number of tourists. In order to improve the prediction accuracy of the model, grey correlation degree method and average influence method were used to screen the variables of factors, and the factors with high influence degree were selected and substituted into the model for prediction. By analyzing and comparing the results of the model, it can be concluded that the model with the influence of the average value has the highest prediction accuracy and minimum error after selecting the normal variables.
Computer Science and Application, Volume 11, pp 1772-1782; https://doi.org/10.12677/csa.2021.116183
为满足安全有效地控制河段航行的需求，开发实时可靠的视频监控系统。结合现有的内河航道管理模式和监控系统无法高效对船舶进行管控，无法实时检测船舶状态的缺点，对内河航道监控系统的功能需求进行分析，对内河航道应用的系统架构、通信平台架构进行设计，结合相机标定、交通参数统计、交通事件监测算法实现该系统。实验结果表明，该系统能有效弥补现有监控系统的不足，确保监控视频传输的实时性和安全性，保障船舶在通过桥洞、闸道等特殊航段时的安全。该系统有广泛的应用场景，例如，船舶过闸的应用，可以简化过闸流程，缩短船舶滞留时间。 In order to meet the need of controlling navigation safely and effectively, a real-time and reliable video monitoring system is developed. Combined with the shortcomings of the existing inland waterway management mode and monitoring system, which can’t manage and control ships efficiently and detect the status of ships in real time, this paper analyzes the functional requirements of inland waterway monitoring system, designs the system architecture and communication platform architecture of inland waterway application, and realizes the system with camera calibration, traffic parameter statistics and traffic event monitoring algorithms. Experimental results show that the system can effectively make up for the shortcomings of the existing monitoring system, ensure the real-time and security of monitoring video transmission, and ensure the safety of ships passing through special segments such as bridge opening and gates. This system has a wide range of application scenarios, for example, the application of ship crossing can simplify the process of crossing the gate and shorten the detention time of the ship.
Computer Science and Application, Volume 11, pp 1791-1801; https://doi.org/10.12677/csa.2021.116185
文章研究了基于视频的乒乓球球员动作识别问题。在计算机视觉领域，人体动作识别具有一定挑战性。基于专业乒乓球运动员在乒乓球发球机的接发动作视频，构建了乒乓球击球动作视频数据集，将其分为正手击球、反手击球、正手拉球、反手拉球和非击球动作5类。提出通过人体密集姿态(Dense Pose)处理数据集，将把人体形态从环境中进行提取，随后提出一种改进的C3D卷积网络，用于学习数据集上连续帧的时空特征。结果表明，文章设计的算法对于光线、环境等干扰因素具有较好的鲁棒性，泛化性能好，为基于视频的动作分类识别问题提出了一种可行解决方案。 Motion recognition of table tennis players based on video is studied in this paper. Recognition of human action is challenging in the field of computer vision. Based on videos of ball strike of professional table tennis players against table tennis ball machine, a data set of ball strike of table tennis players is constructed and divided into 5 catalogs of forehand shots, backhand shots, forehand shots, backhand shots and non-stike action. Dense pose of the human body is used to process the constructed data set and extract human body shape from the environment, and then an improved C3D convolutional network is proposed to learn the spatiotemporal features of continuous frames on the data set. Results show that the algorithm proposed in the article has good robustness to interference factors such as light and environment, and good generalization performance, demonstrating a feasible solution to the problem of video-based action classification and recognition.
Computer Science and Application, Volume 11, pp 1401-1410; https://doi.org/10.12677/csa.2021.115143
随着互联网普及，在网络上出现了大量带有个人主观性的文本，这些文本含有大量情感相关信息和个人的主观观点，目前通常的卷积网络处理这些文本无法将信息进行关联，处理起来无法达到想要的效果，判断文本情感倾向不够准确，所以本文使用国内百度开发的PaddlePaddle框架，构建双向LSTM (Long Short-Term Memory)网络从众多文本信息和数据中准确而高效地分析出文本中所蕴含的情感，并判断情感极性，对情感倾向做出分类。实验中对美食评论信息进行情感预测，首先利用Embedding来计算出词向量，通过双向LSTM提取特征和融合，借助softmax函数构建分类器，获得文本信息的情感倾向，实验结果较为理想。 With the popularity of the Internet, a large number of personally subjective texts appear on the Internet. These text messages contain a large amount of emotional related information and personal subjective opinions. Some of these information are useless and may cause information explosion. At present, the usual convolutional network processing these texts cannot associate the information, and the processing cannot achieve the desired effect, so we use the PaddlePaddle developed by Baidu in China based on the bidirectional LSTM (Long Short-Term Memory) network built by us to obtain a large amount of text information, to analyze the emotion contained in the text accurately and efficiently from the data and judge the polarity of the emotion, classify the emotion, and apply it in practice. The model first uses Embedding to calculate the word vector, then uses the two-way LSTM to extract features and fusion, and finally uses the softmax function to construct a classifier to obtain the emotional tendency of the text information.
Computer Science and Application, Volume 11, pp 1381-1389; https://doi.org/10.12677/csa.2021.115141
根据弱信号环境中传统捕获算法无法直接捕获到信号的问题，分析了部分算法在捕获灵敏度和捕获效率上的不足。而后根据DBZP (双块补零)算法的分块思想，以及在块内添加FFT模块的基本理念，对信号进行半比特分块进行相邻块的差分运算，并对相邻块进行差分运算，提出并验证一种基于DBZP和半比特交替算法的DBZP-半比特差分算法，既获得了很高的信噪比增益，又保证了捕获速度，同时也降低了频率搜索单元的复杂度。同时就改进方法进行了讨论和仿真验证，能够在实际情况下取得良好的捕获性能。 According to the problem that traditional capture algorithms cannot capture signals directly in weak signal environment, the shortcomings of some algorithms in acquisition sensitivity and acquisition efficiency are analyzed. Then, according to the block idea of DBZP (double block zero padding) algorithm and the basic idea of adding FFT module to the block, the signal is divided into half bits and the adjacent blocks are divided into two blocks. Then, the difference operation is carried out for the adjacent blocks. A DBZP half bit difference algorithm based on DBZP and half bit alternating algorithm is proposed and verified. It obtains high signal-to-noise ratio gain, ensures the acquisition speed of the signal-to-noise ratio, and also reduces the complexity of frequency search unit. At the same time, the improved method is discussed and verified by simulation, which can achieve good capture performance in actual situation.