[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117182-en":3,"doc-seo-117182-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117182,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","Recognition of Road Irregularities by means of Low-Cost Sensors and Machine Learning Techniques","The thesis focuses on automatically recognizing road irregularities such as potholes and bumps using low-cost sensors installed on soft-mobility vehicles (electric kickscooters and electric bikes) combined with machine learning. The workflow is structured into data acquisition, signal processing, and model training with performance assessment. Sensors including sonars, inexpensive cameras, and accelerometers are connected to an Arduino MKR1010 Wi‑Fi board and streamed to a computer for labeling. After preprocessing and filtering, multiple classifiers are trained and validated in a real testbed, enabling comparison and selection of the most effective approach.","UNIVERSITÀ DEGLI STUDI DI PADOVA  \nDEPARTMENT OF INFORMATION ENGINEERING Master degree in ICT for Internet and Multimedia  \nRecognition of Road Irregularities by means of Low-Cost Sensors and Machine Learning Techniques  \nSupervisor Master Candidate  \nProfessor Andrea Zanella Mattia Pasti  \nID Number 2055738  \nAcademic Year  \n2022–2023  \nii  \nTo my family and friends.  \niv  \nAbstract  \nThe work of this thesis aims at automatically recognize road irregularities (potholes, bumps, etc.) with the aid of a variety of low-cost sensors mounted in soft-mobility means (i.e., electric kickscooters and electric bikes) and machine learning techniques. The work can be divided into three main steps: data acquisition, signal processing and training and performance assessment. In the first part, low-cost sensors (sonars, cheap cameras, accelerometers) are mounted in the vehicle and connected to an Arduino MKR1010 Wi-Fi board that sends the signals to another board connected to the computer through a Wi-Fi connection. Several runs with different road conditions have been taken into account and the signals have been labeled accordingly. The dataset collected during the first step is preprocessed, filtered and then given in input to a variety of machine learning classifiers in order to train the model to automatically recognize different road irregularities. Once the classifiers are trained, the model is tested in a real testbed and the performances of all the algorithms taken into account evaluated, finally selecting the most suitable algorithm.  \nvi  \nContents  \nAbstract v  \nList of figures ix  \nList of tables xi  \n1 Introduction 1  \n1. 1 Related work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2  \n1.1.1 Collaborative approaches ............................. 2  \n1.1.2 Standalone approach ................................ 3  \n2 Methodology 7  \n2. 1 Hardware . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7  \n2.1. 1 Arduino MKR WiFi 1010 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7  \n2.1.2 HC-SR04 Ultrasonic Ranging Module ...................... 8  \n2.1.3 MPU-6050 GY-521 Accelerometer-Gyro Module ................ 10  \n2.1.4 GY-NEO6MV2 GPS Module . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11  \n2.1.5 External battery . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11  \n2.2 Final scheme . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11  \n3 Machine Learning Techniques 13  \n3.1 Supervised Learning .................................... 14  \n3.1.1 Support Vector Machines (SVM) ......................... 15  \n3.1.2 Random Forest (RF) ................................ 16  \n3.2 Unsupervised Learning .................................. 19  \n3.2.1 Clustering Method – K-Means .......................... 19  \n4 Data Collection and Implementation 21  \n4. 1 Data Collection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21  \n4.1. 1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22  \n4.2 Implementation ....................................... 24  \n5 SVM Classifier – Results 33  \n5.1 Binary Classification .................................... 33  \n5.1.1 Only p2p Matrix ................................... 33  \n5.1.2 Only std Matrix ................................... 35  \n5.1.3 p2p and std Matrix Combined ........................... 36  \n5.2 Multiclass Classification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36  \n5.2.1 Only p2p Matrix ................................... 37  \n6 Random Forest – Results 41  \n6.1 Binary Classification .................................... 41  \n6.1.1 Only p2p Matrix ................................... 41  \n6.1.2 Only std Matrix ................................... 43  \n6.1.3 p2p and std Matrices Combined .......................... 43  \n6.2 Multicalss Classification . . . . . . . . . . . . . .","cbCaicEeCmQwUWbh","https://ap.wps.com/l/cbCaicEeCmQwUWbh","pdf",21540373,1,82,"English","en",105,"# Abstract\n# List of figures\n# List of tables\n# 1 Introduction\n## 1.1 Related work\n# 2 Methodology\n## 2.1 Hardware\n# 3 Machine Learning Techniques\n## 3.1 Supervised Learning\n## 3.2 Unsupervised Learning\n# 4 Data Collection and Implementation\n## 4.1 Data Collection\n## 4.2 Implementation\n# 5 SVM Classifier – Results\n## 5.1 Binary Classification\n## 5.2 Multiclass Classification\n# 6 Random Forest – Results\n## 6.1 Binary Classification\n## 6.2 Multicalss Classification\n# 7 K-Means – Results\n## 7.1 Binary Classification\n## 7.2 Multiclass Classification\n# 8 Conclusions and Future Work\n## 8.1 Summary of the Results\n## 8.2 Conclusions\n## 8.3 Possible Follow-Up","[{\"question\":\"What road issues does the thesis aim to detect automatically?\",\"answer\":\"It targets road irregularities such as potholes and bumps, recognizing them from sensor data collected while traveling.\"},{\"question\":\"How is the sensor system organized in the data acquisition step?\",\"answer\":\"Low-cost sensors are mounted on the vehicle and connected to an Arduino MKR1010 Wi‑Fi board, which transmits signals to another board and then to a computer over Wi‑Fi.\"},{\"question\":\"How are the machine learning models evaluated to choose the best algorithm?\",\"answer\":\"After preprocessing and training on the labeled dataset, the classifiers are tested in a real testbed and their performances are compared to select the most suitable algorithm.\"}]","Recognition of Road Irregularities by means of Low-Cost Sensors and Machine Learning Techniques | PDF",1785674255,207,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"recognition-of-road-irregularities-by-means-of-low-cost-sensors-and-machine-learning-techniques","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/recognition-of-road-irregularities-by-means-of-low-cost-sensors-and-machine-learning-techniques/117182/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-02",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What road issues does the thesis aim to detect automatically?","Question",{"text":76,"@type":77},"It targets road irregularities such as potholes and bumps, recognizing them from sensor data collected while traveling.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is the sensor system organized in the data acquisition step?",{"text":81,"@type":77},"Low-cost sensors are mounted on the vehicle and connected to an Arduino MKR1010 Wi‑Fi board, which transmits signals to another board and then to a computer over Wi‑Fi.",{"name":83,"@type":74,"acceptedAnswer":84},"How are the machine learning models evaluated to choose the best algorithm?",{"text":85,"@type":77},"After preprocessing and training on the labeled dataset, the classifiers are tested in a real testbed and their performances are compared to select the most suitable algorithm.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]