AI Data center to the Edge INTEL AI course

In this project, using Inception v3 model USA's most stolen cars was analysed and modeled t to predict the most stolen car.

Inception v3

The main hallmark of this architecture is the improved utilization of the computing resources inside the network. This was achieved by a carefully crafted design that allows for increasing the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC 2014 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

The necessary python packages to install is given in environment.yml file

environment.yml

DATASET

This is an overview of the VMMR dataset introduced in "A Large and Diverse Dataset for Improved Vehicle Make and Model Recognition".

Overview Despite the ongoing research and practical interests, car make and model analysis only attracts few attentions in the computer vision community. We believe the lack of high quality datasets greatly limits the exploration of the community in this domain. To this end, we collected and organized a large-scale and comprehensive image database called VMMRdb, where each image is labeled with the corresponding make, model and production year of the vehicle.

Description The Vehicle Make and Model Recognition dataset (VMMRdb) is large in scale and diversity, containing 9,170 classes consisting of 291,752 images, covering models manufactured between 1950 and 2016. VMMRdb dataset contains images that were taken by different users, different imaging devices, and multiple view angles, ensuring a wide range of variations to account for various scenarios that could be encountered in a real-life scenario. The cars are not well aligned, and some images contain irrelevant background. The data covers vehicles from 712 areas covering all 412 sub-domains corresponding to US metro areas. Our dataset can be used as a baseline for training a robust model in several real-life scenarios for traffic surveillance.

VMMRdb data distribution

The distribution of images in different classes of the dataset. Each circle is associated with a class, and its size represents the number of images in the class. The classes with labels are the ones including more than 100 images.

Citation If you use this dataset, please cite the following paper:

A Large and Diverse Dataset for Improved Vehicle Make and Model Recognition F. Tafazzoli, K. Nishiyama and H. Frigui In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2017.

The NHTSA Vehicle Crash Test Database contains engineering data measured during various types of research, the New Car Assessment Program (NCAP), and compliance crash tests. Information in this database refers to the performance and response of vehicles and other structures in impacts. This database is not intended to support general consumer safety issues. For general consumer information please see the NHTSA's information on buying a safer car.

Alesco Data's Automotive records are updated monthly from millions of proprietary sourced vehicle transactions. These incoming transactions are processed through compilation rules and are either added as new, incremental records to our file, or contribute to validating existing records.

Our recent focus is on compiling new vehicle ownership, and the file includes over 14.2 million late model vehicle owners (2020-2025).

We also append our Persistent ID, telephone numbers, and demographics for a complete file that can support your direct mail and email marketing campaigns, lead validation, and identity verification needs. A Persistent ID is assigned to each vehicle record and tracks consumers as they change addresses or phone numbers, and vehicles as they change owners.

The database is not derived from state motor vehicle databases and therefore not subject to the Shelby Act also known as the Driver's Privacy Protection Act (DPPA) of 2000. The data is deterministic and sources include sales and service data, warranty data and notifications, aftermarket repair and maintenance facilities, and scheduled maintenance records.

Fields Included: Make Model Year VIN Data Vehicle Class Code (crossover, SUV, full-size, mid-size, small) Vehicle Fuel Code (gas, flex, hybrid) Vehicle Style Code (sport, pickup, utility, sedan) Mileage Number of Vehicles per Household First seen date Last seen date Email

The Synset Boulevard dataset contains a total of 259,200 synthetically generated images of cars from a frontal traffic camera perspective, annotated by vehicle makes, models and years of construction for machine learning methods (ML) in the scope (task) of vehicle make and model recognition (VMMR). The data set contains 162 vehicle models from 43 brands with 200 images each, as well as 8 sub-data sets each to be able to investigate different imaging qualities. In addition to the classification annotations, the data set also contains label images for semantic segmentation, as well as information on image and scene properties, as well as vehicle color. The dataset was presented in May 2024 by Anne Sielemann, Stefan Wolf, Masoud Roschani, Jens Ziehn and Jürgen Beyerer in the publication: Sielemann, A., Wolf, S., Roschani, M., Ziehn, J. and Beyerer, J. (2024). Synset Boulevard: A Synthetic Image Dataset for VMMR. In 2024 IEEE International Conference on Robotics and Automation (ICRA). The model information is based on information from the ADAC online database (www.adac.de/rund-ums-fahrzeug/autokatalog/marken-modelle). The data was generated using the simulation environment OCTANE (www.octane.org), which uses the Cycles ray tracer of the Blender project. The dataset's website provides detailed information on the generation process and model assumptions. The dataset is therefore also intended to be used for the suitability analysis of simulated, synthetic datasets. The data set was developed as part of the Fraunhofer PREPARE program in the "ML4Safety" project with the funding code PREPARE 40-02702, as well as funded by the "Invest BW" funding program of the Ministry of Economic Affairs, Labour and Tourism as part of the "FeinSyn" research project.

The CVS Database provides a catalogue of original vehicle dimensions, for use in vehicle safety research and collision investigation. The purpose of this database is to provide users with a comprehensive listing of vehicle dimensions commonly used in the field of collision investigation and reconstruction, for the North American fleet of passenger cars, light trucks, vans and SUV’s. The database includes model years dating back to 2011 and is comprised of both commonly available dimensions such as overall length, wheelbase and track widths, and also several dimensions which are not typically readily available from the manufacturers, nor from automotive publications. Note – To obtain database of model years dating back to 1971, please contact Transport Canada.

Motor vehicle sales grew by some 11.9 percent worldwide between 2022 and 2023. Passenger vehicles increased by around 11.3 percent compared to the previous year when some 58.6 million cars were sold worldwide. The current state of the market In 2023, motor vehicle sales reached over 92.7 million units worldwide. China was the largest automobile market worldwide, making up close to 25.8 million of the new car registrations that same year. The United States and Europe ranked second and third, with light vehicle sales reaching approximately 15.5 million units in the U.S. market. The German-based Volkswagen Group and Japanese Toyota Motor were the global leading automakers, with revenues reaching around 348.6 and 311.9 billion U.S. dollars respectively as of May 2024. The path to recovery The automotive chip shortage led to around 11.3 million vehicles being cut from worldwide production in 2021, and forecasts estimate that these disruptions in the automotive supply chain will contribute to the removal of another seven million units from production in 2022. However, despite these challenges, the demand for passenger cars increased in 2021 and 2022, as car sales slowly started to increase. This is partly due to consumers' interest in electric vehicles. Autonomous,electrified, and battery electric vehicles are also forecast to gain popularity in the next decades. Electrified vehicles are projected to make up close to a quarter of car sales worldwide by 2025. By 2040, China is forecast to be one of the largest market for autonomous vehicle sales.

The data set contains registered vehicle population count by various criteria such as vehicle class, vehicle status, vechicle make, vehicle model, vehicle year, plate class, plate declaration, county, weight related class and other vehicle decriptors.

1. Title: 1985 Auto Imports Database

2. Source Information: -- Creator/Donor: Jeffrey C. Schlimmer (Jeffrey.Schlimmer@a.gp.cs.cmu.edu) -- Date: 19 May 1987 -- Sources: 1) 1985 Model Import Car and Truck Specifications, 1985 Ward's Automotive Yearbook. 2) Personal Auto Manuals, Insurance Services Office, 160 Water Street, New York, NY 10038 3) Insurance Collision Report, Insurance Institute for Highway Safety, Watergate 600, Washington, DC 20037

3. Past Usage: -- Kibler,~D., Aha,~D.~W., & Albert,~M. (1989). Instance-based prediction of real-valued attributes. {\it Computational Intelligence}, {\it 5}, 51--57. -- Predicted price of car using all numeric and Boolean attributes -- Method: an instance-based learning (IBL) algorithm derived from a localized k-nearest neighbor algorithm. Compared with a linear regression prediction...so all instances with missing attribute values were discarded. This resulted with a training set of 159 instances, which was also used as a test set (minus the actual instance during testing). -- Results: Percent Average Deviation Error of Prediction from Actual -- 11.84% for the IBL algorithm -- 14.12% for the resulting linear regression equation

4. Relevant Information: -- Description This data set consists of three types of entities: (a) the specification of an auto in terms of various characteristics, (b) its assigned insurance risk rating, (c) its normalized losses in use as compared to other cars. The second rating corresponds to the degree to which the auto is more risky than its price indicates. Cars are initially assigned a risk factor symbol associated with its price. Then, if it is more risky (or less), this symbol is adjusted by moving it up (or down) the scale. Actuarians call this process "symboling". A value of +3 indicates that the auto is risky, -3 that it is probably pretty safe.

   The third factor is the relative average loss payment per insured vehicle year. This value is normalized for all autos within a particular size classification (two-door small, station wagons, sports/speciality, etc...), and represents the average loss per car per year.

   -- Note: Several of the attributes in the database could be used as a "class" attribute.

5. Number of Instances: 205

6. Number of Attributes: 26 total -- 15 continuous -- 1 integer -- 10 nominal

7. Attribute Information:
   Attribute: Attribute Range:

   1. symboling: -3, -2, -1, 0, 1, 2, 3.
   2. normalized-losses: continuous from 65 to 256.
   3. make: alfa-romero, audi, bmw, chevrolet, dodge, honda, isuzu, jaguar, mazda, mercedes-benz, mercury, mitsubishi, nissan, peugot, plymouth, porsche, renault, saab, subaru, toyota, volkswagen, volvo
   4. fuel-type: diesel, gas.
   5. aspiration: std, turbo.
   6. num-of-doors: four, two.
   7. body-style: hardtop, wagon, sedan, hatchback, convertible.
   8. drive-wheels: 4wd, fwd, rwd.
   9. engine-location: front, rear.
   10. wheel-base: continuous from 86.6 120.9.
   11. length: continuous from 141.1 to 208.1.
   12. width: continuous from 60.3 to 72.3.
   13. height: continuous from 47.8 to 59.8.
   14. curb-weight: continuous from 1488 to 4066.
   15. engine-type: dohc, dohcv, l, ohc, ohcf, ohcv, rotor.
   16. num-of-cylinders: eight, five, four, six, three, twelve, two.
   17. engine-size: continuous from 61 to 326.
   18. fuel-system: 1bbl, 2bbl, 4bbl, idi, mfi, mpfi, spdi, spfi.
   19. bore: continuous from 2.54 to 3.94.
   20. stroke: continuous from 2.07 to 4.17.
   21. compression-ratio: continuous from 7 to 23.
   22. horsepower: continuous from 48 to 288.
   23. peak-rpm: continuous from 4150 to 6600.
   24. city-mpg: continuous from 13 to 49.
   25. highway-mpg: continuous from 16 to 54.
   26. price: continuous from 5118 to 45400.

8. Missing Attribute Values: (denoted by "?") Attribute #: Number of instances missing a value:

   1. 41
   2. 2
   3. 4
   4. 4
   5. 2
   6. 2
   7. 4

The NHTSA Product Information Catalog and Vehicle Listing (vPIC) is a consolidated platform that presents data collected within the manufacturer reported data from CFR 49 Parts 551 - 574 for use in a variety of modern tools. NHTSA's vPIC platform is intended to serve as a centralized source for basic Vehicle Identification Number (VIN) decoding, Manufacturer Information Database (MID), Manufacturer Equipment Plant Identification and associated data. vPIC is intended to support the Open Data and Transparency initiatives of the agency by allowing the data to be freely used by the public without the burden of manual retrieval from a library of electronic documents (PDFs). While these documents will still be available online for viewing within the Manufacturer Information Database (MID) module of vPIC one can view and use the actual data through the VIN Decoder and Application Programming Interface (API) modules.

Fuel Cell Electric Vehicle Sales: ytd: Honda data was reported at 154.000 Unit in Dec 2022. This stayed constant from the previous number of 154.000 Unit for Sep 2022. Fuel Cell Electric Vehicle Sales: ytd: Honda data is updated quarterly, averaging 154.000 Unit from Jun 2022 (Median) to Dec 2022, with 3 observations. The data reached an all-time high of 154.000 Unit in Dec 2022 and a record low of 154.000 Unit in Dec 2022. Fuel Cell Electric Vehicle Sales: ytd: Honda data remains active status in CEIC and is reported by Cox Automotive. The data is categorized under Global Database’s United States – Table US.RA008: Electric Vehicle Sales: by Brand and Model: ytd.

United States Electric Vehicle Sales: Hyundai: Hyundai IONIQ 5 data was reported at 8,611.000 Unit in Mar 2025. This records a decrease from the previous number of 14,082.000 Unit for Dec 2024. United States Electric Vehicle Sales: Hyundai: Hyundai IONIQ 5 data is updated quarterly, averaging 7,676.500 Unit from Dec 2021 (Median) to Mar 2025, with 14 observations. The data reached an all-time high of 14,082.000 Unit in Dec 2024 and a record low of 153.000 Unit in Dec 2021. United States Electric Vehicle Sales: Hyundai: Hyundai IONIQ 5 data remains active status in CEIC and is reported by Cox Automotive. The data is categorized under Global Database’s United States – Table US.RA007: Electric Vehicle Sales: by Brand and Model.

Electric Vehicle Sales: ytd: Fisker: Fisker Ocean data was reported at 3,787.000 Unit in Jun 2024. This records an increase from the previous number of 1,660.000 Unit for Mar 2024. Electric Vehicle Sales: ytd: Fisker: Fisker Ocean data is updated quarterly, averaging 2,164.500 Unit from Sep 2023 (Median) to Jun 2024, with 4 observations. The data reached an all-time high of 3,787.000 Unit in Jun 2024 and a record low of 997.000 Unit in Sep 2023. Electric Vehicle Sales: ytd: Fisker: Fisker Ocean data remains active status in CEIC and is reported by Cox Automotive. The data is categorized under Global Database’s United States – Table US.RA008: Electric Vehicle Sales: by Brand and Model: ytd.

Total vehicle registration counts per month by county

The fields available include make, model, year, trim, style, fuel type, MSRP, and many more.

We have developed this file to be tied to our Consumer Demographics Database so additional demographics can be applied as needed. Each record is ranked by confidence and only the highest quality data is used. This file contains over 180 million records in addition to over 1 million+ fresh automotive intender records per day.

Note - all Consumer packages can include necessary PII (address, email, phone, DOB, etc.) for merging, linking, and activation of the data.

BIGDBM Privacy Policy: https://bigdbm.com/privacy.html

Author: Marko Bohanec, Blaz Zupan
Source: UCI - 1997
Please cite: UCI

Car Evaluation Database
This database was derived from a simple hierarchical decision model originally developed for the demonstration of DEX (M. Bohanec, V. Rajkovic: Expert system for decision making. Sistemica 1(1), pp. 145-157, 1990.).

The model evaluates cars according to the following concept structure:

CAR           car acceptability
. PRICE         overall price
. . buying        buying price
. . maint        price of the maintenance
. TECH          technical characteristics
. . COMFORT       comfort
. . . doors       number of doors
. . . persons      capacity in terms of persons to carry
. . . lug_boot      the size of luggage boot
. . safety        estimated safety of the car

Input attributes are printed in lowercase. Besides the target concept (CAR), the model includes three intermediate concepts: PRICE, TECH, COMFORT. Every concept is in the original model related to its lower level descendants by a set of examples (for these examples sets see http://www-ai.ijs.si/BlazZupan/car.html).

The Car Evaluation Database contains examples with the structural information removed, i.e., directly relates CAR to the six input attributes: buying, maint, doors, persons, lug_boot, safety. Because of known underlying concept structure, this database may be particularly useful for testing constructive induction and structure discovery methods.

Changes with respect to car (1)

The ordinal variables are stored as ordered factors in this version.

Relevant papers:

M. Bohanec and V. Rajkovic: Knowledge acquisition and explanation for multi-attribute decision making. In 8th Intl Workshop on Expert Systems and their Applications, Avignon, France. pages 59-78, 1988.

M. Bohanec, V. Rajkovic: Expert system for decision making. Sistemica 1(1), pp. 145-157, 1990.

from: https://archive.ics.uci.edu/ml/datasets/car+evaluation

1. Title: Car Evaluation Database

2. Sources: (a) Creator: Marko Bohanec (b) Donors: Marko Bohanec (marko.bohanec@ijs.si) Blaz Zupan (blaz.zupan@ijs.si) (c) Date: June, 1997

3. Past Usage:

   The hierarchical decision model, from which this dataset is derived, was first presented in

   M. Bohanec and V. Rajkovic: Knowledge acquisition and explanation for multi-attribute decision making. In 8th Intl Workshop on Expert Systems and their Applications, Avignon, France. pages 59-78, 1988.

   Within machine-learning, this dataset was used for the evaluation of HINT (Hierarchy INduction Tool), which was proved to be able to completely reconstruct the original hierarchical model. This, together with a comparison with C4.5, is presented in

   B. Zupan, M. Bohanec, I. Bratko, J. Demsar: Machine learning by function decomposition. ICML-97, Nashville, TN. 1997 (to appear)

4. Relevant Information Paragraph:

   Car Evaluation Database was derived from a simple hierarchical decision model originally developed for the demonstration of DEX (M. Bohanec, V. Rajkovic: Expert system for decision making. Sistemica 1(1), pp. 145-157, 1990.). The model evaluates cars according to the following concept structure:

   CAR car acceptability . PRICE overall price . . buying buying price . . maint price of the maintenance . TECH technical characteristics . . COMFORT comfort . . . doors number of doors . . . persons capacity in terms of persons to carry . . . lug_boot the size of luggage boot . . safety estimated safety of the car

   Input attributes are printed in lowercase. Besides the target concept (CAR), the model includes three intermediate concepts: PRICE, TECH, COMFORT. Every concept is in the original model related to its lower level descendants by a set of examples (for these examples sets see http://www-ai.ijs.si/BlazZupan/car.html).

   The Car Evaluation Database contains examples with the structural information removed, i.e., directly relates CAR to the six input attributes: buying, maint, doors, persons, lug_boot, safety.

   Because of known underlying concept structure, this database may be particularly useful for testing constructive induction and structure discovery methods.

5. Number of Instances: 1728 (instances completely cover the attribute space)

6. Number of Attributes: 6

7. Attribute Values:

   buying v-high, high, med, low maint v-high, high, med, low doors 2, 3, 4, 5-more persons 2, 4, more lug_boot small, med, big safety low, med, high

8. Missing Attribute Values: none

9. Class Distribution (number of instances per class)

   class N N[%]

   unacc 1210 (70.023 %) acc 384 (22.222 %) good 69 ( 3.993 %) v-good 65 ( 3.762 %)

Complete database of steering wheel measurements for vehicles by year, make, and model

Electric Vehicle Sales: ytd: Rivian data was reported at 8,553.000 Unit in Mar 2025. This records a decrease from the previous number of 51,579.000 Unit for Dec 2024. Electric Vehicle Sales: ytd: Rivian data is updated quarterly, averaging 17,087.000 Unit from Dec 2021 (Median) to Mar 2025, with 14 observations. The data reached an all-time high of 51,579.000 Unit in Dec 2024 and a record low of 583.000 Unit in Dec 2021. Electric Vehicle Sales: ytd: Rivian data remains active status in CEIC and is reported by Cox Automotive. The data is categorized under Global Database’s United States – Table US.RA008: Electric Vehicle Sales: by Brand and Model: ytd.