9Figure 2.6: Coarse for auxiliary and fine for lead head label assigner... CONTENT TOPIC 1:Name of the topic: Identify objects with real-time object detectors Presentation: Le Thi Kieu G
INTRODUCTION
INTRODUCTION
This subject introduces topics on different fields such as AI, Databases, Embedded, and Microchips, for students to have an overview and review the knowledge they have learned.
This course allows students to refresh necessary specialist information while also understanding the real-world working environment Additionally, students get access to engineering-related job possibilities through firms.
CONTENT
Name of the topic: Identify objects with real-time object detectors
Presentation: Le Thi Kieu Giang and Nguyen Hung Thinh
Content: This topic aims to provide students with the foundational knowledge of artificial intelligence and applications, providing learners with the basics of pattern recognition and machine learning.
The report provides some information about YOLOv7.
Name of the topic: Database management applications using C#
Presentation: Le Thi Kieu Giang and Nguyen Hung Thinh
Content: This topic implements database management systems From a user perspective, the course will discuss conceptual data modeling, physical data modeling, data computation, schema design, database querying, and database manipulation. TOPIC 3:
Name of the topic: Researching to automotive embedded with Hella Vietnam Presentation: Le Thi Kieu Giang and Nguyen Hung Thinh
Content: This topic is a workshop from Hella Vietnam company The design, implementation including analysis of embedded system hardware and software.Design, implement, and debug complex software applications on embedded systems.Real-time operating system base for real-time control embedded systems.
SKILLS AND KNOWLEDGE TO BE ACHIEVED AFTER COMPLETING
After completing the course, students can:
- The course also equips skills in programming artificial intelligence applications, using Python language, and building identification applications.
- Program a management application and build a database using C#, WPF.
STRUCTURE OF THE REPORT
Content 1: Identify objects with real-time object detectors
Content 2: Database management applications using C#
Content 3: Researching to automotive embedded with Hella Vietnam
IDENTIFY OBJECTS WITH REAL-TIME OBJECT DETECTORS 3 2.1 INTRODUCTION OF OBJECT RECOGNITION TECHNOLOGY
Overview
Machine vision is one of the key facets of artificial intelligence The field of computer vision encompasses techniques for digital image acquisition, processing,analysis, and recognition, object detection, image generation, and image hyper resolution, among other things Because it is applied so frequently in daily life, object detection is probably the most profound aspect of machine vision.
Development trends
Nowadays, business operations are closely tied to IT, and businesses are competing to invest in IT The field of information technology has long used the term artificial intelligence (AI) In addition, AI describes the application of algorithms to the completion of specific tasks through the analysis of vast amounts of data to derive statistical generalizations or estimates Through the use of these algorithms, a computer program can learn, reason, and make decisions in a manner similar to that of the human brain.
One of the ways that artificial intelligence is used to provide the most accurate images is through object recognition technology, which stores, synthesizes, and statistical data Along with developing and refining algorithms and software tools,accurate object recognition technology also requires high-performance server systems that support numerous GPUs and object-oriented storage devices with significant capacity and quick access times.
Furthermore, one of the drawbacks of this technology is the cost of paying for the investment in capacity packages, access speed, and computer hardware In the future,object recognition technology will be able to identify objects smaller than those that can be seen by the human eye, such as microorganisms, vehicles, and people.Biotechnology industry bacteria support a thriving healthcare sector that safeguards people's health The Yolov7 technology, created by Chien-Yao Wang, AlexeyBochkovskiy, and Hong-Yuan Mark Liao, is among the most well-liked object recognition systems available today.
Career opportunities
Today, AI is having a significant impact across several industries There are several fields that are starting to apply and develop artificial intelligence, particularly object identification, which has been used in high-end apartments, warehouse management, human resource management, working time management, etc There are still many untapped general uses for AI Additionally, it offers a chance to advance and build object recognition AI.
Any field, though, must eventually develop AI and have practical features In the area of object recognition, artificial intelligence has some of the following effects: Vehicles: Identification of license plates in parking lots at businesses, schools, and enterprises.
Production: Control product lines on the conveyor belt, classify them, and assess worker performance.
Healthcare: Manage and monitor patients to determine when it is appropriate for them to start taking medication.
In many different industries, AI technology is constantly evolving In addition to that, however, businesses in the technology sector need sufficient human resources.Following finishing a three-month internship and beginning employment there after the internship, an AI engineer can expect to make a minimum salary of 20 to 25 million VND, which is considered to be acceptable by enterprises Companies likeViettle, Mobifone, and Maritime are the ones that are most welcoming to data scientists, artificial intelligence (AI), and data engineering in Vietnam.
IDENTIFY OBJECTS BY YOLOV7 TECHNOLOGY
Real-time object detection is a very important topic in computer vision, as it is often a necessary component in computer vision systems The computing devices that execute real-time object detection is usually some mobile CPU or GPU, as well as various neural processing units (NPU) developed by major manufacturers.
In recent years, the real-time object detector is still developed for different edge device For example, the development of MCUNet and NanoDet.
In this paper, we will present some of the new issues of this paper are summarized as follows:
- We design several trainable bag-of-freebies methods
- The evolution of object detection methods
- We propose “extend” and “compound scaling” methods
- Effectively reduce about 40% parameters and 50% computation of state-of-the-art real-time object detector
- Has faster inference speed and higher detection accuracy
Figure 2.1: Comparison with other real-time object detectors
Unlike the previous YOLOv5 and YOLOv6, YOLOv7 comes from the author ofYOLOv4 Alexey Bochkovskiy Extended efficient layer aggregation networks(E-ELAN), model scaling, and a set of trainable bag-of-freebies are used.
YOLOv7 outperforms all real-time Object Detection models, available at 30 FPS or more on GPU V100, in both speed and accuracy from 5 FPS to 160 FPS, and achieves the highest accuracy with 56.8% AP YOLOv7-E6 (56 FPS on V100, 55.9% AP) outperforms high-end CNN backbones like ConvNeXt-XL Cascade-Mask R-CNN (8.6 FPS on A100, 55.2% AP) with 551% in speed and 0.7% in AP, as well as the Transformer home backbone SWIN-L Cascade-Mask R-CNN (9.2 FPS on And of course, in terms of speed, degree, and accuracy, YOLOv7 outperforms YOLOR, YOLX, Scaled-YOLOv4, YOLOv5, DETR, Deformable DETR, DINO-5scale-R50, ViT-Adapter-B, as well as many other Object Detection networks.
Additionally, YOLOv7 is trained entirely from scratch on COCO without the aid of any pretrained data.
Currently state-of-the-art real-time object detectors are mainly based on YOLO and FCOS.
The state-of-the-art real-time object detector usually requires the following characteristics:
(1) a faster and stronger network architecture;
(2) a more effective feature integration method;
(5) a more efficient label assignment method;
Model re-parameterization techniques merge multiple computational modules into one at inference stage The model re-parameterization technique can be regarded as an ensemble technique, and we can divide it into two categories, module-level ensemble and model-level ensemble.
There are two common practices for model-level re-parameterization:
- One is to train multiple identical models with different training data, and then average the weights of multiple trained models.
- The other is to perform a weighted average of the weights of models at different iteration number.
This type of method splits a module into multiple identical or different module branches during training and integrates multiple branched modules into a completely equivalent module during inference
Model scaling is a method for increasing the size of the model for improved performance With a scaling method that aggregates the depth, width, and resolution dimensions of the input image, model scaling is examined for the first time in EfficientNet.
Additionally, in order to achieve a good trade-off between the number of network parameters, computation, inference speed, and accuracy, the model scaling method typically uses various scaling factors, such as resolution (size of input image), depth (number of layer), width (number of channel), and stage (number of feature pyramid).
Figure 2.2: Compound scaling with EfficientNet
In most of the literature on designing, the main considerations are number of parameters, the amount of computation, and the computational density.
Figure 2.3: Extended efficient layer aggregation networks
Instead of adjusting the gradient transmission path of the original architecture, the proposed extended ELAN (E-ELAN) uses group convolution to raise the cardinality of the added features and combines the features of various groups in a way that shuffles and merges attribute values This mode of operation can improve the use of parameters and calculations as well as the features that are learned by various feature maps. The architecture of CSPVoVNet, which is a variation of VoVNet and is depicted in Figure 2.3(b), also analyzes the gradient path, allowing the weights of various layers to learn more varied features.
Beside, A deeper network can efficiently learn and converge by controlling the shortest longest gradient path, according to ELAN in Figure 2.3(c) Finally, in this paper, we propose Extended-ELAN (E-ELAN) based on ELAN and its main architecture is shown in Figure 2.3 (d).
The main purpose of model scaling is to adjust some attributes of the model and generate models of different scales The Scaling factors include in Resolution, Depth, Width and Stage.
Figure 2.4: Model scaling for concatenation-based models
From (a) to (b), we mention that the output width of a computational block also grows when depth scaling is applied to concatenation-based models The input width of the subsequent transmission layer will grow as a result of this phenomenon. Therefore, we suggest (c), which states that only the depth in a computational block needs to be scaled when performing model scaling on concatenation-based models, with the remaining transmission layer being performed with corresponding width scaling.
The trainable bag-of-freebies (BoF) are techniques added in training that can increase accuracy without increasing model processing time.
Model Level Ensemble performs a weighted average of the weights of models at different iteration number Additionally, it has some function such as train multiple identical models with different training data, averages the weights of multiple trained models and splits and integrates the branched modules into a completely equivalent module.
Re-parameterization techniques involve averaging a set of model weights to create a model that is more robust to general patterns that it is trying to model.
Figure 2.5: Planned re-parameterized model
A layer with residual or concatenation connections, its RepConv should not have an identity connection, according to our findings in the proposed planned re-parameterized model In this case, RepConvN, which lacks identity connections, can take its place In addition, RepConv actually combines 3×3 convolution, 1×1 convolution, and identity connection in one convolutional layer.
Deep supervision is a method that is frequently applied when deep networks are being trained Its main idea is to increase the number of auxiliary heads in the middle layers of the network, while using assistant loss as a guide to weight the shallow layers of the network.
The model will be assisted in classifying and labeling objects to speed up high recognition speed if Auxiliary head is applied to all Classification or Semantic Segmentation lessons.
Figure 2.6: Coarse for auxiliary and fine for lead head label assigner.
In contrast to the standard model (a), the schema in (b) has an auxiliary head We suggest a lead head guided label assigner (d) and a coarse-to-fine lead head guided label assigner (e) in contrast to the conventional independent label assigner (c). Furthermore, to obtain the labels of the training lead head and auxiliary head simultaneously, the proposed label assigner is optimized by lead head prediction and the ground truth Details of the coarse-to-fine implementation method will be elaborated, as well as the constraint design.
Additionally, in order to apply the coarse for auxiliary and fine for lead losses method, we must pay attention to crucial factors such as Detection, Depth, Lead Head,
The main components in the optimization of labeling and prediction in this model include in The Lead Head and Aux Head (coarse-to-fine lead head guided) The lead head guided label assigner is primarily calculated using the lead head's prediction result and the ground truth, and it generates soft labels via the optimization process.The coarse-to-fine lead head guided label assigner also used the lead head's predicted result and the ground truth to generate soft label.
DATABASE MANAGEMENT APPLICATIONS USING C#
Overview
A database is an organized collection of data so that it can be easily accessed To manage these databases, Database Management Systems (DBMS) are used.
Structured Query Language (SQL) is a standard query language that is used to work with relational databases.
- and many more database operations
C# is pronounced "C-Sharp" It is a Microsoft object-oriented programming language that runs on the NET Framework.
C# has origins in the C family and is related to other popular languages such as C++ and Java.
In 2002, the first version was released C# 11, the most recent version, was published in November 2022.
C# is used in the following applications:
- It is one of the most widely used programming languages on the planet.
- It is simple to learn and utilise.
- It enjoys widespread community backing.
- C# is an object-oriented programming language that offers applications a clear structure and allows code to be reused, saving development costs.
- As C# is related to C, C++ and Java, it makes it easier for programmers to convert to C# or vice versa
Development trends
There are various database management trends, and understanding how to take advantage of them will help your organisation The following are some current trends:
1 Databases that bridge SQL/NoSQL
The most recent database product trends are ones that do not adhere to a particular database schema Instead, the databases bridge the gap between SQL and NoSQL, providing users with the best of both worlds This includes, for example, solutions that allow users to access a NoSQL database in the same manner they would a relational database.
2 Databases in the cloud/Platform as a Service
Organizations are carefully assessing the trade-offs associated with public vs private cloud as developers continue to drive their operations to the cloud. Additionally, developers are evaluating how to integrate cloud services with existing applications and infrastructure Database administrators have several alternatives when it comes to cloud service providers Making the journey towards the cloud doesn't imply altering organisational priorities, but selecting goods and services that assist your company fulfil its goals.
Another developing trend is database automation The collection of such approaches and technologies aims to make maintenance, patching, provisioning, updates and upgrades, and even project workflow easier However, the trend may be of limited utility because database maintenance typically need human interaction.
4 An increased focus on security
Database administrators must also collaborate with the security team to identify and eradicate possible internal flaws that might expose data These might include network privilege concerns, as well as hardware or software misconfigurations that could be abused, resulting in data breaches.
Similar problems abound in the data warehousing sector, such as columnar vs row-based relational tables, the growth of in-memory databases, the usage of flash or solid-state drives (which also relates to transaction processing), clustered versus no-clustered systems, and so on.
To be clear, big data does not always imply a large amount of data What it truly means is the capacity to process any form of data, including semi-structured and unstructured data, as well as structured data Current thought is that they will generally coexist as different technologies alongside traditional solutions, at least in big organisations, although this may not always be the case.
Career opportunities
These professionals are responsible for writing the queries and codes for the server-side.
Software developers create and maintain software SQL is essential in full-stack and all other types of developments.
As data is quickly becoming one of the most significant parts of growth, NET is no special case .NET developers ought to have experience in SQL databases as well as NoSQL.
These professionals deal with huge volumes of data They draw insights from the data and send it to the quality team to deal with the pros and cons we find in the result.
The Reporting engineer generates and automates the delivery of multiple reports using Power BI, Reporting Services, and Excel or other technologies.
These professionals are responsible for providing solutions for a given business problem.
Quality Assurance professionals ensure that the product made and sent to the market is of industrial standards.
Database administrators keep a check on who can access and perform operations on the database.
They maintain the database and ensure that no proxy access to the database is working.
BUILD DATABASE MANAGEMENT APPLICATIONS USING C# SOFTWARE, WPF PROGRAMMING AND MICROSOFT SQL
We built a Mobile management application using Microsoft SQL to store data and programming C# to create interface.
To create the software, we built the block diagram as below:
Figure 3.1: Management program block of Mobile
When starting the program, the interface "ĐANG NHAP" appears with a blank space including username and password.
Figure 3.2: The interface “ĐANG NHAP”
After logging in, we will come to the main interface.
Figure 3.3: The interface “QUAN LY MOBILE”
In the display QUAN LY MOBILE interface, there are tags: product (SAN PHAM), product type (LOAI SAN PHAM), supplier (NHA CUNG CAP) and customer (KHACH HANG) Besides, it also displays the current remaining quantity of goods.
Going to SAN PHAM will have the interface as below, similarly we will perform the following operations:
Figure 3.4: The interface “SAN PHAM”
In this interface, we can create to information of mobile including: Name of product, Type of product, Supplier, QR Code and Bar Code.
We can perform Add information, Edit/Update information and Delete information.
Besides, it also displays the current information of existing products such as: ID of product, Name of product, Type of product, Supplier For example: ID: 00a3356a-920a-430c-badc-bb9417d3678f, Ten san pham: Xiaomi Mi 11, Loai san pham: Xiaomi, Nha cung cap: Xiaomi
In tag “LOAI SAN PHAM”, we have interface as below:
Figure 3.5: The interface “LOAI SAN PHAM”
In this interface, we just can create to information of Product type name.
And can perform Add information, Edit/Update information and Delete information.
Besides, it also displays the current information of existing Type of products such as: ID Product type name, Product type name For example: ID: 1, Ten: Apple.Tag “NHA CUNG CAP” show below:
Figure 3,6: The interface “NHA CUNG CAP”
In the interface “NHA CUNG CAP”, we can create to information of supplier including: Name of supplier, Address, Phone number, Email, More information and coopertion day.
Like in the interface SAN PHAM, we can perform Add information, Edit/Update information and Delete information.
Besides, it also displays the current information of existing Supplier such as: ID, Name of supplier, Address, Phone number, Email, More information and coopertion day For example: ID: 1, Ten Nha Cung Cap: Apple, Dia chi: America, Dien thoai: +1-800-854-3680, Email:Apple@gmail.com,
Going to KHACH HANG will have the interface as below:
Figure 3.7: The interface “KHACH HANG”
In the interface “KHACH HANG”, we can create to information of supplier including: Name of customer, Address, Phone number, Email, More information and product purchase day.
Like in the interface SAN PHAM, we can perform Add information, Edit/Update information and Delete information.
RESEARCHING TO AUTOMOTIVE EMBEDDED WITH HELLA
INTRODUCTION TO HELLA COMPANY
HELLA Vietnam Company Limited is the Vietnamese subsidiary of the German automotive brand HELLA Vietnam, as a new member of the HELLA family, provides a fresh viewpoint on the local Asian market.
HELLA was founded in 2013 in HCM City and has had tremendous growth, with an increase in employee development from 20 to over 200 members and a four-floor office expansion in recent years.
General introduction to Hella Vietnam with some contents:
- Customer including: BMW, VM, Audi…
- Hella Software Development in Automotive Industry
- Software Engineer in FORVIA Hella
SOFTWARE ENGINEER IN FORVIA HELLA
4.2.1 Software Engineer in FORVIA Hella
+ Develop: analyze software requirement > develop software architecture > develop software module and unit design > plan software module test
+ Construct and test software module: develop and test software module + Integrate software: plan software integration > perform software integration
- Software Engineer development skill set:
+ Technical: Microcontrollers or MCUs, Automotive specific knowledge, HW diagnostic Debugger skill, Programming languages, Development process
4.2.2 How do we test in Hella?
- Allocate to different test levels
- Writing up test plan for product (support)
- Concepting and implementing of development tests
- Executing test cases according to specification
- Evaluating and analysing test results
- Documenting of faults & supporting on fault analysis if needed 4.2.4 To become a Tester Engineer in Hella
- Definition of Software quality (ISO/IEC 25010)
- Motivation and definition of ASPICE
- Definition of process & The V-Model
CAREER OPPORTUNITIES
- The content shared in the content Tester Engineer must have professional knowledge as well as skills for the job, the skills required of a QA, specific job positions in a project, provides useful information for job orientation.
- The information shared in the introduction to Hella Vietnam opens up many job opportunities, specifically jobs suitable for each specialty, discipline, for example:Tester Engineer, QA, …
SOME PHOTOS OF THE WORKSHOP
CONCLUSION
Students who complete the course will be able to:
- Program artificial intelligence applications in detection apps using Python language, and create identification applications.
- Creating management apps and databases in C# and WPF.
- Can develop embedded systems encompassing design, implementation,including analysis of embedded system hardware and software.