路面條件和駕駛使用智能手機(jī)的行為分析 外文翻譯

《路面條件和駕駛使用智能手機(jī)的行為分析 外文翻譯》由會員分享，可在線閱讀，更多相關(guān)《路面條件和駕駛使用智能手機(jī)的行為分析 外文翻譯（6頁珍藏版）》請?jiān)谘b配圖網(wǎng)上搜索。

　　　　　　 畢業(yè)設(shè)計(jì)外文資料 翻譯 題 目: 路面條件和駕駛使用智能手機(jī)的行為分析 院系名稱：設(shè)計(jì)藝術(shù)學(xué)院 專業(yè)班級： 工設(shè)F1202 學(xué)生姓名： 學(xué) 號： 指導(dǎo)教師： 教師職稱： 地 點(diǎn): 18號樓產(chǎn)品設(shè)計(jì)工作室（I） 　 　 指導(dǎo)教師評語： 簽名： 年 月 日 附件1：外文資料翻譯譯文 路面條件和駕駛使用智能手機(jī)的行為分析 在發(fā)展中國家的道路質(zhì)量不是很好，迅速惡化，這使得系統(tǒng)可以實(shí)時(shí)檢測道路違規(guī)行為，可以使用戶安全駕駛。此外，車隊(duì)運(yùn)營商想確保他們的客戶安全的出行。這可以通過跟蹤和維護(hù)一個(gè)歷史的驅(qū)動程序的驅(qū)動模式，此外，個(gè)人還想評估他們的駕駛風(fēng)格，并成為安全的驅(qū)動程序可實(shí)施的另一個(gè)原因。在這方面，一個(gè)具有成本效益的解決方案，用于檢測道路以及跟蹤驅(qū)動程序使用智能手機(jī)的駕駛行為已被開發(fā)。該解決方案依賴于安裝在智能手機(jī)上的傳感器，從而使其成本有效。雖然該系統(tǒng)不使用商業(yè)級傳感器，但我們的準(zhǔn)確數(shù)字表明，該解決方案是足夠好的商業(yè)部署。 基于智能手機(jī)的一些非常流行的方法，使用通過傳感器收集的數(shù)據(jù)，用于用戶的活動檢測各種環(huán)境（室內(nèi)定位[ 3 ]，交通檢測使用智能手機(jī)收集數(shù)據(jù)是一種很有前途的替代,因?yàn)樗牡统杀竞鸵子谑褂玫奶攸c(diǎn)。本文提出了一種非侵入式的方法，使用傳感器目前在智能手機(jī)上，其中大部分人都是預(yù)期的進(jìn)行，因此不需要任何專業(yè)就可以在車輛或在路邊安裝的硬件。在這里,我們已經(jīng)擴(kuò)展了各種以前的研究，以提高基于使用的加速度計(jì)，全球定位系統(tǒng)和算法用于交通和道路異常的地磁傳感器讀數(shù)檢測。具體的操作是在確定制動事件—經(jīng)常剎車指示-擁擠的交通狀況和公路路面的異常特征。使用駕駛行為分析，包括硬加速/減速，剎車，轉(zhuǎn)彎，頻繁的車道變化等，我們提出了一種方法，以獲得駕駛分?jǐn)?shù)考慮到大量的參數(shù)，這使得它成為比以往任何工作更準(zhǔn)確。因?yàn)?，每天在道路上行駛的通勤者，這使得這一解決方案更為重要且意義重大。 一個(gè)Android應(yīng)用程序（s-road協(xié)助，已經(jīng)在谷歌Play商店）來從各種傳感器如加速度計(jì)的智能手機(jī)，目前的重力數(shù)據(jù)采集，磁強(qiáng)計(jì)和定位（GPS）傳感器。應(yīng)用程序支持的驅(qū)動模式檢測，并自動啟動自己收集和接收器的數(shù)據(jù)服務(wù)器。驅(qū)動方式檢測算法通過計(jì)算根使用三軸加速度計(jì)平均值在手機(jī)應(yīng)用設(shè)備上每一次改變方向的平方加速，而我們將每一秒重新定位在數(shù)據(jù)窗口的算法，重新定位傳感器的值，所有的窗口都需要照顧的傳感器的影響，如果它停留的時(shí)間較長，例如，如果用戶占用了一個(gè)呼叫。 一個(gè)完整的工作系統(tǒng)，上面提到的方法并提出了解決方案已經(jīng)在開發(fā)中。安卓應(yīng)用“s-road協(xié)助”上可以找到谷歌Play商店。目標(biāo)是幫助提高駕駛經(jīng)驗(yàn)，協(xié)助用戶提高駕駛技能。這是由分析引擎檢測后對記錄數(shù)據(jù)的分析，這就回到了智能手機(jī)的使用同一個(gè)應(yīng)用程序生產(chǎn)，為即將到來的事件的通知警報(bào)，沿路線提醒。大數(shù)據(jù)分析關(guān)鍵是克服在數(shù)據(jù)采集過程中所做的檢測。進(jìn)一步強(qiáng)調(diào)，解決不再需要專門的硬件，只需要在智能手機(jī)上，它不會限制在車輛里面（可在任意方向或位置），從而使解決方案具有成本效益。該技術(shù)的系統(tǒng)將有一定的幫助避免很多道路傷亡和提高駕駛。在這里，智能手機(jī)作為一種資產(chǎn)記錄數(shù)據(jù)，以查明的被通知用戶的道路異常從而把智能手機(jī)變成一個(gè)“保護(hù)電話”。 外文資料摘自： [3] H. Lu, W. Pan, N. D. Lane, T. Choudhury, and A. T. Campbell, Soundsense: Scalable sound sensing for people-centric applications on mobile phones, In Proc. of the 7th Int. Conf. on Mobile systems, MobiSys’09. 附件2：外文原文 Road surface conditions and Driving Behavior analysis using Smartphones In developing countries road quality is not very good and deteriorates quickly, this makes a system which can detect road irregularities and notify user regarding risky driving in real-time, valuable. Moreover, fleet operators would like to ensure safe trips to their customers. This can be accomplished by tracking and maintaining a history of the driving patterns of the drivers employed by them. Further, individuals would also like to assess their driving style and become safe drivers. In this regard, a cost effective solution for detecting road artifacts as well as tracking the driving behavior of drivers using smartphones has been developed. The solution relies on the sensors installed on the smarphone only thereby making it cost effective. Although the system does not use commercial grade sensors, yet our accuracy numbers indicate that the solution is good enough for commercial deployment. Few of the very popular methods based on smartphones, use data collected through sensors for user activity detection in various environments (Indoor localization [3], traffic detection Using smartphone to collect data is a promising alternative because of its low cost and easy to use features in addition to its potentially wide population coverage as probe devices. This paper proposes a non-intrusive method that uses sensors present on smartphones, which most of the people are expected to carry, thus obviating the need for any specialized hardware to be installed in vehicle or on the roadside. Here, we have extended various prior studies to improve the algorithms based on using accelerometer, GPS and magnetometer sensor readings for traffic and road anomaly detection. Specific interest is in identifying braking events - frequent braking indicates congested traffic conditions and anomalies on the roads to characterize the type of road. Using driving behavior analysis including hard acceleration/deceleration, braking, turns, frequent lane changes, etc. we propose a way to derive driving score considering multitudes of parameters, which makes it to be more accurate than any prior work. Since, we have a large number of commuters who daily travel on road, that makes this solution even more important and significant. An android application (S-Road Assist, already on Google Play Store) is developed to collect data from various sensors present in smartphone like accelerometer, gravity, magnetometer and location (GPS) sensor. Application does support the driving mode detection and automatically launches itself to collect and sink data to servers. Driving mode detection algorithm makes use of 3-axis accelerometer values by calculating root mean square acceleration on the device applied every time the phone changes orientation, whereas we apply the re-orientation algorithm over a data window, say every 1 sec. Re-orienting sensor values over all the windows takes care of the impact on the sensor, if it stays for a longer duration, for instance if user takes up a call. A complete working system with above mentioned approaches and proposed solution is already in development. Android application named “S-Road Assist” can be found on Google Play Store. The objective is to help improve driving experience and assist users in improving driving skills. Events (road artifacts), that are detected by the analytics engine after the analysis of recorded data, are pushed back to the smartphone using the same application for producing notification alerts of upcoming events along the route in advance. Big data analysis or crowdsourcing is the key to overcome the compromises made during data collection, preprocessing or detection. To emphasize further, solution obviates the need for any specialized hardware and relies only on the smartphone, which may or may not be docked inside the vehicle (can be in any arbitrary orientation or position), thereby making the proposed solution cost-effective. Building a system using the proposed techniques will surely help in avoiding many road casualties and improve the driving experience by many folds. Smartphone here act as an asset to record data to identify road anomalies which later is notified to the user, thus turning the smartphone into a “saver phone”.