Networked cane system for blind people based on K-nearest neighbor and dynamic time warping algorithms

doi:10.11772/j.issn.1001-9081.2020010122

Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (8): 2441-2448.DOI: 10.11772/j.issn.1001-9081.2020010122

• Frontier & interdisciplinary applications • Previous Articles Next Articles

Networked cane system for blind people based on K-nearest neighbor and dynamic time warping algorithms

XIA Lunteng^1,2, ZHANG Li^1,2

1. College of Biomedical Engineering, South-Central University for Nationalities, Wuhan Hubei 430070, China;
2. Testing and Instrumentation Engineering Center, South-Central University for Nationalities, Wuhan Hubei 430070, China

Received:2020-02-13 Revised:2020-03-17 Online:2020-03-24 Published:2020-08-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (81601586), the Fundamental Scientific Research Funds for the Central Universities (CZY18020).

基于K近邻和动态时间规整算法的盲人物联网手杖系统

夏伦腾^1,2, 张莉^1,2

1. 中南民族大学生物医学工程学院, 武汉 430070;
2. 中南民族大学检测与仪器校级工程中心, 武汉 430070

通讯作者: 张莉(1971-),女,湖北武汉人,教授,博士,主要研究方向:智能医疗与仪器,zhangli1996@163.com
作者简介:夏伦腾(1995-),男,湖北武汉人,硕士研究生,主要研究方向:可穿戴物联网智能医疗设备、嵌入式应用。
基金资助:
国家自然科学基金资助项目（81601586）；中央高校基本科研业务专项资金资助项目（CZY18020）。

Abstract

Abstract: Concerning the safety and monitoring problems of the blind people during traveling, the design of a networked cane system for blind people based on machine learning algorithms was proposed. Multiple functions were added to the system, such as obstacle avoidance, positioning, alarm and communication. First, infrared obstacle avoidance and ultrasonic ranging obstacle avoidance were designed as the basic functions of the system, which could be used to detect road conditions and obstacles for the daily travel of the blind and provide real-time voice and motor vibration reminders. Second, remote communication function for help was added to the system, which was able to send help text messages and phone calls to specific mobile numbers. In addition, Global Positioning System (GPS) function, accelerometer gyroscope attitude angle calculation function and abnormal attitude alarm function based on K-Nearest Neighbor (KNN) and Dynamic Time Warping (DTW) algorithms were also added, which were able to transfer all kinds of information data to the cloud server storage. Finally, the WeChat mini program was used to replace the native APP as the monitoring operation interface, and functions such as one-click alarm, weather query, blind safety information were provided. Test results show that the proposed system has the attitude recognition success rate reached 86%, and has the accuracy improved by nearly 31% compared to the attitude angle system. The networked cane system for blind people can greatly improve the security of the blind during traveling, so that the blind can ask for help in time when an accident occurs, and achieve the safe monitoring and positioning monitoring of the blind postures.

Key words: networked cane system for blind people, remote communication help, attitude angle calculation, K-Nearest Neighbor (KNN), Dynamic Time Warping (DTW) algorithm, WeChat mini program

摘要： 针对盲人出行时的安全和监护问题，提出了一种基于机器学习算法的盲人物联网手杖系统的设计，该系统具有避障、定位、报警和通信等多种功能。首先，该系统具有红外线避障和超声波测距避障的基本功能，可以用于盲人日常出行对路况障碍物的检测，并且实时利用语音和电机震动给予提醒；其次，该系统还具有远程通信求助功能，可以向指定号码发送求助短信及电话；同时，系统还加入了全球定位系统（GPS）、加速度计陀螺仪姿态角度解算功能和以K近邻（KNN）和动态时间规整（DTW）算法为基础的异常姿态报警功能，它能将各类信息数据传输至云端服务器存储；最后，采用微信小程序代替原生APP作为监护操作界面，并提供一键报警、天气查询、盲人安全资讯等功能。测试实验结果表明，所提系统的姿态识别成功率达到了86%，正确率比姿态角系统提高将近31%。该盲人物联网手杖系统可以极大地提高盲人出行的安全性，使盲人能够在发生意外时及时求助，实现了对盲人姿态的安全监护和定位监护。

关键词: 盲人物联网手杖系统, 远程通信求助, 姿态角度解算, K近邻, 动态时间规整算法, 微信小程序

CLC Number:

TP399

XIA Lunteng, ZHANG Li. Networked cane system for blind people based on K-nearest neighbor and dynamic time warping algorithms[J]. Journal of Computer Applications, 2020, 40(8): 2441-2448.

夏伦腾, 张莉. 基于K近邻和动态时间规整算法的盲人物联网手杖系统[J]. 计算机应用, 2020, 40(8): 2441-2448.

References

[1] 周瑛,顾朝兵. 我国盲人信息获取障碍问题研究[J]. 现代情报, 2014, 34(7):10-13. (ZHOU Y, GU C B. Research on obstacles of information access for the blind in China[J]. Journal of Modern Information, 2014, 34(7):10-13)
[2] 赖婧瑜,王蓉晖. 盲人手杖智能化的研究[J]. 黑龙江科技信息, 2016(32):60. (LAI J Y, WANG R H. Research on blind cane intelligence[J]. Heilongjiang Science and Technology Information, 2016(32):60.)
[3] 马洪连,丁男,宁兆龙,等. 物联网感知识别与控制技术[M]. 2版.北京:清华大学出版社,2017:1-6. (MA H L, DING N, NING Z N, et al. Internet of Things Perception Recognition and Control Technology[M]. 2nd ed. Beijing:Tsinghua University Press, 2017:1-6)
[4] 尹宝才,王文通,王立春. 深度学习研究综述[J]. 北京工业大学学报, 2015, 41(1):48-59. (YIN B C, WANG W T, WANG L C. Review of deep learning[J]. Journal of Beijing University of Technology, 2015, 41(1):48-59.)
[5] 丁益,钱文波,关维娟. 微信小程序市场现状与发展前景的分析统计与管理[J]. 统计与管理, 2018(12):76-78. (DING Y, QIAN W B, GUAN W J. Analysis of the current situation and development prospects of WeChat mini program market[J]. Statistics and Management, 2018(12):76-78.)
[6] 刘红卫.微信小程序应用探析[J].无线互联科技,2016(23):11-12,40. (LIU H W. Application of wechat applet[J].Wireless Internet Technology, 2016(23):11-12, 40.)
[7] IKEGAMI T, HASHIMOTO Y, OKA M. Open-ended evolution and a mechanism of novelties in Web services[J]. Artificial Life, 2019, 25(2):168-177.
[8] 文耀锋. 一种实时的跌倒姿态检测和心率监护系统的研究[D]. 杭州:浙江大学, 2008:22-25. (WEN Y F. Research on a real-time falling posture detection and heart rate monitoring system[D]. Hangzhou:Zhejiang University, 2008:22-25.)
[9] 邓健志,程小辉,邓卓洪. 物联网盲人智能手杖的设计[J]. 电视技术, 2015, 39(22):19-22. (DENG J Z, CHENG X H, DENG Z H. Design of the blind smart cane for the Internet of things[J]. Video Engineering, 2015, 39(22):19-22.)
[10] ATA O W. An extended-AMATA indoor propagation model for GSM 900/1800 MHz and Wi-Fi 2.4 GHz frequencies[J].Wireless Personal Communications, 2017, 92(3):993-1009.
[11] HO Y C, STASZEWSKI R B, MUHAMMAD K, et al. Charge-domain signal processing of direct RF sampling mixer with discrete-time filters in bluetooth and GSM receivers[J]. EURASIP Journal on Wireless Communications and Networking, 2006, 2006:No.062905.
[12] 赵亮,刘皓,王伟强,等. 基于北斗/GPS和GPRS的车载定位终端的研究与实现[J]. 石河子大学学报(自然科学版), 2015, 33(3):391-396. (ZHAO L, LIU H, WANG W Q, et al. Research and implementation for vehicle tracking terminal system based on BD/GPS and GPRS[J]. Journal of Shihezi University (Natural Science), 2015, 33(3):391-396.)
[13] 李士琳,王春光. 基于MPU6050的轮式机器人姿态检测系统设计[J]. 南方农机, 2019, 50(17):16, 19.(LI S L, WANG C G. Design of wheeled robot attitude detection system based on MPU6050[J]. China Southern Agricultural Machinery, 2019, 50(17):16, 19.)
[14] 张伯源,高国伟. 改进的卡尔曼滤波在MEMS陀螺仪信号处理的应用[J]. 传感器世界, 2019, 25(3):18-24. (ZHANG B Y, GAO G W. Application of improved Kalman filter in signal processing of MEMS gyroscopes[J]. Sensor World, 2019, 25(3):18-24.)
[15] 李方硕,李朝阳,何理. 基于单位四元数的姿态加权融合算法研究[J].工业控制计算机, 2019, 32(10):101-102. (LI F S, LI C Y, HE L. Research on orientation weighting-blending algorithm based on unit quaternion[J]. Industrial Control Computer, 2019, 32(10):101-102.)
[16] 郭永祥. 立体视觉惯性信息紧耦合自主机器人定位研究[D]. 北京:北京交通大学, 2018:10-12. (GUO Y X. Research on stereo vision inertial information tightly coupled autonomous robot positioning[D]. Beijing:Beijing Jiaotong University, 2018:10-12.)
[17] XU X, SUN Y, TIAN X, et al. A proposed attitude estimator with reliability test criteria for sensor data fusion[J]. Measurement, 2020, 150:No.107046.
[18] 冯智勇,曾瀚,张力,等. 基于陀螺仪及加速度计信号融合的姿态角度测量[J]. 西南师范大学学报(自然科学版), 2011, 36(4):137-141. (FENG Z Y, ZENG H, ZHANG L, et al. Angle measurement based on gyroscope and accelerometer signal fusion[J]. Journal of Southwest China Normal University (Natural Science Edition), 2011, 36(4):137-141.)
[19] RANAZZI P H, SAMPAIO M A. Influence of the Kalman gain localization in adaptive ensemble smoother history matching[J]. Journal of Petroleum Science and Engineering, 2019, 179:244-256.
[20] 冷雨泉,张会文,张伟,等. 机器学习入门到实战——Matlab实践应用[M]. 北京:清华大学出版社, 2019:53-63. (LENG Y Q, ZHANG H W, ZHANG W, et al. Machine Learning Introduction to Practice-Practical Application of Matlab[M]. Beijing:Tsinghua University Press, 2019:53-63.)
[21] 周驰,李智,徐灿. 基于DTW算法的空间目标结构识别研究[J]. 计算机仿真, 2019, 36(9):98-102. (ZHOU C, LI Z, XU C. Research on space object structure recognition based on DTW algorithm[J]. Computer Simulation, 2019, 36(9):98-102.)
[22] 范冰飞. 人体运动姿态传感器抗磁场和大加速度干扰的方法及其步态分析应用研究[D]. 杭州:浙江大学, 2019:5-7. (FAN B F. Research on anti-magnetic field and high acceleration interference methods of human motion posture sensors and application of gait analysis[D]. Hangzhou:Zhejiang University, 2019:5-7.)
[23] LUO J, KLEIN T, JI Q, et al. Forecasting realized volatility of agricultural commodity futures with infinite hidden Markov HAR models[J]. International Journal of Forecasting, 2019, 12(2):56-58.
[24] 张斌,吴水才,邵明刚. 一种新型老人定位与运动监护系统的设计[J].中国医疗设备, 2017, 32(6):23-27. (ZHANG B, WU S C, SHAO M G. Design of a new positioning and physical activity monitoring system for the elderly[J]. China Medical Equipment, 2017, 32(6):23-27.)

Networked cane system for blind people based on K-nearest neighbor and dynamic time warping algorithms

基于K近邻和动态时间规整算法的盲人物联网手杖系统

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 11

Recommended Articles

Metrics

[1]	WANG Yue, JIANG Yiming, LAN Julong. Intrusion detection based on improved triplet network and K-nearest neighbor algorithm [J]. Journal of Computer Applications, 2021, 41(7): 1996-2002.
[2]	ZHANG Chao, LI Ke, FAN Pingzhi. Online-hot video cache replacement policy based on cooperative small base stations and popularity prediction [J]. Journal of Computer Applications, 2019, 39(7): 2044-2050.
[3]	XIE Xiaoyu, LIU Zhejie. Dynamic gesture recognition method based on EMG and ACC signal [J]. Journal of Computer Applications, 2017, 37(9): 2700-2704.
[4]	YANG Wei GAN Tao LAN Gang. Texture clustering matting algorithm [J]. Journal of Computer Applications, 2013, 33(11): 3213-3216.
[5]	TENG Shaohua CHEN Haitao ZHANG Wei. Multi-pose cooperative face detection based on hypersphere support vector machine [J]. Journal of Computer Applications, 2013, 33(07): 1988-1990.
[6]	ZHOU Jing. KNN algorithm of average mutual information and class distinction pruning rules [J]. Journal of Computer Applications, 2013, 33(02): 558-562.
[7]	DANG Xin-peng LIU Wen-ping. Face recognition algorithm based on multi-level texture spectrum features and PCA [J]. Journal of Computer Applications, 2012, 32(08): 2316-2319.
[8]	Jing ZHOU Jin-sheng LIU. Improved K-nearest neighbor algorithm for feature union entropy [J]. Journal of Computer Applications, 2011, 31(07): 1785-1788.
[9]	. Density-based detection for outliers and noises [J]. Journal of Computer Applications, 2010, 30(3): 802-805.
[10]	. KNN query on P2P networks [J]. Journal of Computer Applications, 2010, 30(05): 1156-1158.
[11]	. Multi-feature fusion method based on support vector machine and k-nearest neighbor classifier [J]. Journal of Computer Applications, 2009, 29(3): 833-835.