Proton beam therapy is an advanced form of cancer radiotherapy that uses high-energy proton beams to deliver precise and targeted radiation to tumors. This helps to mit-igate unnecessary radiation exposure in healthy ...
Proton beam therapy is an advanced form of cancer radiotherapy that uses high-energy proton beams to deliver precise and targeted radiation to tumors. This helps to mit-igate unnecessary radiation exposure in healthy tissues. Real-time imaging of prompt gamma rays with Compton cameras has been suggested to improve therapy efficacy. However, the camera's non-zero time resolution leads to incorrect interaction classifications and noisy images that are insufficient for accurately assessing proton delivery in patients. To address the challenges posed by the Compton camera's image quality, machine learning techniques are employed to classify and refine the generated data. These machine-learning techniques include recurrent and feedforward neural networks. A PyTorch model was designed to improve the data captured by the Compton camera. This decision was driven by PyTorch's flexibility, powerful capabilities in handling sequential data, and enhanced G PU usage. This accelerates the model's computations on large-scale radiotherapy data. Through hyperparameter tuning, the validation accuracy of our PyTorch model has been improved from an initial 7 % to over 60 %. Moreover, the PyTorch Distributed Data Parallelism strategy was used to train the RNN models on multiple G PU s, which significantly reduced the training time with a minor impact on model accuracy.
Green software and its products are crucial in solving the problems associated with the long-term use of software, especially from a sustainability point of view. A few studies have proposed green software but are sti...
详细信息
Authenticated key exchange protocols are a fundamental cryptography building block for establishing a secret shared key among participating parties over an open network model. Mohamed et al. proposed a tightly-secure ...
详细信息
Motivated by the tremendous progress we witnessed in recent years, this paper presents a survey of the scientific literature on the topic of Collaborative Simultaneous Localization and Mapping (C-SLAM), also known as ...
详细信息
The practice of code review is widely adopted in industry and has been studied to an increasing degree in the research community. However, the developer experience of code review has received limited attention. Here, ...
The practice of code review is widely adopted in industry and has been studied to an increasing degree in the research community. However, the developer experience of code review has received limited attention. Here, we report on initial results from a mixed-method exploratory study of the developer experience.
Currently, interest in medical-related deep learning is dramatically increasing. Although this interest in deep learning is widely used in other fields, but it is very effective in medical image processing such as CT ...
Currently, interest in medical-related deep learning is dramatically increasing. Although this interest in deep learning is widely used in other fields, but it is very effective in medical image processing such as CT and MRI, which takes a lot of time for simple medical tests and analysis. In general, in deep learning using such image processing, it is possible to determine which algorithm is the most efficient by collecting data, preprocessing data, and using various models This paper conducted a research on cardiovascular CT images collected from Soonchunhyang University Hospital in Korea, and all of them used data collected for 3 years by professional medical staff. In the case of medical data, the number of data is very limited, so the results can vary greatly depending on how it is processed. Therefore, in this paper, research on an efficient deep learning method was conducted through image data preprocessing using Yolo.
Patients with Diabetic Retinopathy (DR) who do not receive appropriate diagnosis and treatment may go blind as the disease affects the retina's blood vessels. Diabetic retinopathy disease must be detected and diag...
详细信息
Environmental damage caused by rapidly increasing end-of-life products can be reduced if they can be properly disassembled and their parts and material can be reused/recycles. Robots can be used to increase the effici...
详细信息
ISBN:
(纸本)9781665417532
Environmental damage caused by rapidly increasing end-of-life products can be reduced if they can be properly disassembled and their parts and material can be reused/recycles. Robots can be used to increase the efficiency of a disassembly line. We can classify disassembly operations into non-destructive and destructive ones. This work presents a mathematical model of a disassembly line balancing problem (DLBP) involving both types of disassembly operations. We propose an improved constrained decomposition grid (CDG) approach to solve the model. Four types of products are disassembled by using CDG, multi-objective evolutionary algorithm based on decomposition (MOEA/D) and non-dominated sorting genetic algorithm II (NSGAII). The results verify CDG’s feasibility, effectiveness and better performance than its two peers’.
Selecting an appropriate clustering method as well as an optimal number of clusters in road accident data is at times confusing and difficult. This paper analyzes shortcomings of different existing techniques applied ...
详细信息
暂无评论