This work presents a deep learning-based object detection technique for identifying branches and endpoints in two-dimensional brain vessel images alongside its hyperparameter optimization. Although traditional image p...
详细信息
This work focuses on ongoing research within the EU-funded EnerMan project aiming at improving the energy efficiency of manufacturing systems. Industrial use cases are generally too constrained to easily proceed to th...
详细信息
Federated Average algorithm (FEDAVG) is the preferred algorithm for federated learning (FL) because of its simplicity and low communication cost However, if all clients's local data aren't independent and equa...
详细信息
It is important to find an area of focus that is related to a career path that aligns with engineering students' abilities, technical background, and long-term goals. Due to the array of available specializations ...
详细信息
It is important to find an area of focus that is related to a career path that aligns with engineering students' abilities, technical background, and long-term goals. Due to the array of available specializations in industry categories, selecting the best fit for their interests is a big challenge for engineering students. For example, the computer science category includes information technology, programming languages, softwareengineering, networks, etc. Most departments focus on one industry category and under each category there are concentrations. When students start their journey through college, they focus on a specific concentration that they think they will succeed in. Some students, after starting some of the courses, find that their selected area of focus no longer fits with their abilities or their interests. Some of them try to change their concentration, program, or college, while some of them leave college because they think that their ability is not enough to continue studying. Today, Artificial Intelligence (AI) can be used to improve the education process by helping students learn better and faster when paired with high-quality learning materials and instruction. Also, AI systems can help students get back on track faster by alerting teachers to potential problems. This paper proposes a Deep Learning Neural Networks approach that helps students select their best-fit specialization in a specific category. Deep learning is a subset of machine learning, but it can determine whether a prediction is accurate through its own neural network- no human help is required [1]. The proposed system will use a dataset that contains student data that is related to the general education courses required for their program, such as grades, the number of hours spent on each course's materials, the opinion of the student about the content of each course, and the course(s) that the student enjoyed the most. Additional data will be included in the dataset such as the stu
The state of charge (SOC) of lithium-ion batteries is predicted by using neural network and random forest. According to the battery discharge state in different periods, the entire discharge process is divided into pl...
详细信息
This study focuses on the current state of programming landscape that uses high level programming languages along with several dependencies that are added using package managers. These advances make the life of a deve...
详细信息
ISBN:
(数字)9798331532925
ISBN:
(纸本)9798331532932
This study focuses on the current state of programming landscape that uses high level programming languages along with several dependencies that are added using package managers. These advances make the life of a developer much easier; they can conveniently access libraries that contain functions needed for their project. They make software reuse a possibility. However, they also result in bloated software which requires large file sizes and more processing power. This study proposes a set of recommendations to reduce the software bloat to make the software development more sustainable by encouraging mindful dependency management, optimization practices, and green computing awareness as early as possible during their softwareengineering education.
This research work presents a home automation system based on Li-Fi (Light Fidelity) technology as an alternative to the RF communication systems such as Wi-Fi or Bluetooth. Li-Fi uses visible light for transmitting s...
详细信息
Detecting code smells in softwaresystems is crucial for maintaining and evaluating their quality. Code smells are structural issues in the code that can make it harder to understand, modify, and ultimately lead to bu...
详细信息
The traditional fire warning system with a single threshold value is widely used. However, due to the development process of fire, the variation of parameters in each stage is quite different, so it is difficult to ac...
详细信息
One approach to software testing is known as model-based testing, where test cases are generated from a model that represents the functional aspects of the system under test. If the system model is explicitly defined ...
详细信息
ISBN:
(纸本)9789819717231
One approach to software testing is known as model-based testing, where test cases are generated from a model that represents the functional aspects of the system under test. If the system model is explicitly defined and accurately reflects the system’s behaviour, it can serve as a shared and reusable artefact. For example, the model can be utilized to generate a comprehensive test suite for the system under test (SUT), a methodology commonly referred to as model-based testing (MBT). Over time, the efficiency, capability, and maintainability of both computer code design and model-based systems have continually improved. However, there has been relatively little effort made to gather evidence to assess the precise relationship, boundaries, and practical challenges between the two. This review study aims to address the creation and prioritization of test cases, with a specific focus on reducing redundancy in test cases to enhance the system’s efficiency and effectiveness. In addition to addressing redundancy, this study proposes the use of finite state machines (FSM) as a modelling paradigm. Refactoring, which involves making changes to an application’s source code without altering its external functionality, is introduced to enhance code readability, complexity, extensibility, and maintainability. Code smells, which lead to the generation of redundant test cases, are mitigated through these refactoring techniques. Statistical analysis and methods are employed in this study to proactively reduce test cases by identifying instances of "lazy class code." By assessing code cohesion and dependencies and implementing inline class refactoring techniques before test case generation, the study significantly reduces the number of redundant test cases produced. The primary objective of this work is to construct a test model from a UML activity diagram. From this test model, test paths for composite testing are derived. The study also provides various criteria for constructing t
暂无评论