检索结果-内蒙古大学图书馆

Transformer-Based Chest X-ray Report Generation Model 1

6th International Conference on Soft Computing and Signal Processing, ICSCSP 2023

作者： Shaikh, Zeeshan Bharti, Jyoti Department of Computer Science and Engineering Maulana Azad National Institute of Technology Bhopal Bhopal India

ISBN: (数字)9789819986286

ISBN: (纸本)9789819986279

In radiological testing for treatment and diagnosis, chest X-rays and medical radiographs are most frequently utilized in clinical practice. A skilled radiologists may require some patience to read and interpret a chest X-ray;less experienced radiologist may find it more challenging;and the common person might find it incredibly difficult. A deep learning-based X-ray report generating system can help doctors with reporting tasks and give radiologists judgment support. In order to generate chest X-ray reports, this paper proposes a deep learning-oriented model that makes use of a transformer method and transfer learning technique. We use a chexnet model that has already been pre-trained and will eventually be trained on X-ray images for visual extraction. Then, an encoder-decoder for a modified transformer is used. We train and evaluate our network using the IU X-ray dataset, one of the most extensive publicly available datasets currently utilized for chest X-ray image captioning. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Stock Prediction Based on Technical Indicators Using Deep Learning Model

引用

computers, Materials & Continua 2022年第1期70卷 287-304页

作者： Manish Agrawal Piyush Kumar Shukla Rajit Nair Anand Nayyar Mehedi Masud Department of Computer Science&Engineering University Institute of TechnologyRajiv Gandhi Proudyogiki VishwavidyalayaBhopal-462033Madhya PradeshIndia Faculty of Department of Computer Science&Engineering University Institute of TechnologyRajiv Gandhi Proudyogiki VishwavidyalayaBhopal-462033Madhya PradeshIndia Faculty of Department of Computer Science&Engineering School of Engineering and TechnologyJagran Lakecity UniversityBhopal462026Madhya PradeshIndia Graduate School Duy Tan UniversityDa Nang550000Vietnam Faculty of Information Technology Duy Tan UniversityDa Nang550000Vietnam Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

Stock market trends forecast is one of the most current topics and a significant research challenge due to its dynamic and unstable *** stock data is usually non-stationary,and attributes are non-correlative to each *** traditional Stock Technical Indicators(STIs)may incorrectly predict the stockmarket *** study the stock market characteristics using STIs and make efficient trading decisions,a robust model is *** paper aims to build up an Evolutionary Deep Learning Model(EDLM)to identify stock trends’prices by using *** proposed model has implemented the Deep Learning(DL)model to establish the concept of *** analysis of the dataset of three most popular banking organizations obtained from the live stock market based on the National Stock exchange(NSE)-India,a Long Short Term Memory(LSTM)is *** datasets encompassed the trading days from the 17^(th) of Nov 2008 to the 15^(th) of Nov *** work also conducted exhaustive experiments to study the correlation of various STIs with stock price *** model built with an EDLM has shown significant improvements over two benchmark ML models and a deep learning *** proposed model aids investors in making profitable investment decisions as it presents trend-based forecasting and has achieved a prediction accuracy of 63.59%,56.25%,and 57.95%on the datasets of HDFC,Yes Bank,and SBI,*** indicate that the proposed EDLA with a combination of STIs can often provide improved results than the other state-of-the-art algorithms.

关键词： Long short term memory evolutionary deep learning model national stock exchange stock technical indicators predictive modelling prediction accuracy

来源：评论

学校读者我要写书评

暂无评论

Self-Sustaining Fish Tank System Using Arduino Uno 6

Self-Sustaining Fish Tank System Using Arduino Uno

引用

6th International Conference on Control and Robotics, ICCR 2024

作者： Fabro, Bernard C. Zoleta, Minerva C. Felipe, Jose C. Utulo, Ador G. Parillas, Kaye Angela Computer Engineering Eulogio 'Amang' Rodriguez Institute of Science and Technology Nagtahan Sampaloc Manila Philippines

ISBN: (纸本)9798331518158

In the field of aquaculture, numerous studies indicate that traditional fishkeeping faces significant challenges due to the manual maintenance required, leading to inefficiencies such as inconsistent cleaning, feeding, and water quality management, that can be improved by integrating automation and smart technologies. This experimental research, conducted in Metro Manila, Philippines, aims to test and refine the Self-sustaining Fish Tank System. By evaluating the accuracy and effectiveness of integrated sensors and automated components, the study seeks to enhance the system's performance in maintaining optimal aquatic conditions. An experimental research approach was employed, utilizing multiple methods including observation for data collection. Quantitative data analysis using descriptive and paired two-test statistical tools assessed the performance of the Self-sustaining Fish Tank System using Arduino Uno. The study's findings highlighted significant improvements in sensor reliability and consistency during operational tests with and without fish. Specifically, the water level sensor demonstrated enhanced responsiveness during pump activations, while the pH sensor stabilized effectively with fish present. The fish feeder consistently dispensed food every 12 hours, ensuring reliable feeding throughout the study periods. The study concludes that variations in sensor performance, particularly in pH and turbidity measurements, highlight the need for continued refinement to ensure consistent control across different environmental conditions. Future research should explore advanced sensor integration for improved accuracy and reliability, especially for critical parameters like water quality. Additionally, the adoption of IoT-based solutions with wireless modules is recommended for enhanced real-time monitoring and remote control via mobile apps or web interfaces. © 2024 IEEE.

关键词： pH sensors

来源：评论

学校读者我要写书评

暂无评论

Detection of Brain Tumors in MRI Images through Machine Learning, Deep Learning, Faster R-CNN & YOLOv5 1

Detection of Brain Tumors in MRI Images through Machine Lear...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Ghufran, Fayez Kumar, Ashutosh Kumar, Ashish Kaushik, Avneesh Saxena, Sandeep Greater Noida Institute of Technology Department of Computer Science and Engineering Greater Noida201308 India

ISBN: (纸本)9798350356816

As the tenth greatest cause of death, brain tumors have become a major worldwide health problem in recent years. The fast growth of brain tumors, which results in a short life expectancy for patients if detection and treatment are delayed, underscores the necessity of tackling this issue. Artificial intelligence has shown to be quite helpful in helping radiologists discover tumors without the need for intrusive techniques. Using the Faster R-CNN and YOLOv5 algorithms, this comprehensive work presents two deep learning-based approaches for tumor identification and classification. As the fifth version of the You Only Look Once paradigm, the YOLOv5 method is used since it is less computationally demanding than previous models and is very efficient. A 9-layer convolutional neural network is the foundation of our recommended approach, which is intended to identify and categorize tumors according to their shape, texture, and geographic distribution. The Brain Tumor Segmentation - MRI dataset, which has been downloaded from Kaggle, is used in this work. It comprises fifteen hundred brain MRI scans with infections and the same amount without. With an accuracy of 98.21%, the CNN model surpassed conventional machine learning techniques in our testing. Comprehensive metric computations assist this feat, and graphic displays give a clear view of the final outcomes. These findings are important for clinical decision-making, providing clinicians with better diagnostic precision for brain malignancies. This survey highlights the significance of applying deep learning in medical imaging and provides insight into how YOLOv5 and Faster R-CNN algorithms may be used to speed up and improve the process of detecting brain cancers. The promising results illustrate the vital role that technology plays in tackling urgent medical challenges and open the way for further breakthroughs in the field of artificial intelligence and healthcare. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Streaming Histogram Publication over Weighted Sliding Windows Under Differential Privacy

引用

Tsinghua science and technology 2024年第6期29卷 1674-1693页

作者： Xiujun Wang Lei Mo Xiao Zheng Zhe Dang School of Computer Science and Technology Anhui University of TechnologyMa’anshan 243032China Institute for Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Baosight Software(Anhui)Co.Ltd. Ma’anshan 243000China School of Electrical Engineering and Computer Science Washington State UniversityPullman 99164WAUSA

Continuously publishing histograms in data streams is crucial to many real-time applications,as it provides not only critical statistical information,but also reduces privacy leaking *** the importance of elements usually decreases over time in data streams,in this paper we model a data stream by a sequence of weighted sliding windows,and then study how to publish histograms over these windows *** existing literature can hardly solve this problem in a real-time way,because they need to buffer all elements in each sliding window,resulting in high computational overhead and prohibitive storage *** this paper,we overcome this drawback by proposing an online algorithm denoted by Efficient Streaming Histogram Publishing(ESHP)to continuously publish histograms over weighted sliding ***,our method first creates a novel sketching structure,called Approximate-Estimate Sketch(AESketch),to maintain the counting information of each histogram interval at every time instance;then,it creates histograms that satisfy the differential privacy requirement by smartly adding appropriate noise values into the sketching *** experimental results and rigorous theoretical analysis demonstrate that the ESHP method can offer equivalent data utility with significantly lower computational overhead and storage costs when compared to other existing methods.

关键词： differential privacy randomized algorithm streaming data publication weighted sliding window approximate statistics data usability computational complexity

来源：评论

学校读者我要写书评

暂无评论

An Integrated Mobility-Oriented Wireless Charging Scheme for Wireless Sensor Network 3

An Integrated Mobility-Oriented Wireless Charging Scheme for...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Mathada, Mallikarjuna Amgoth, Tarachand Indian Institute of Technology Indian School of Mines Department of Computer Science & Engineering Dhanbad India

ISBN: (纸本)9798350372120

Wireless charging is one of the most practical procedures to replenish the energy of the resource-constrained nodes in a Wireless Sensor Network (WSN) that contributes mainly towards enhanced network lifetime. After reviewing the existing methodologies of wireless charging schemes, it is noted that there is still a wide scope for improvement owing to various open sets of problems. Therefore, considering the mobility-oriented charging policy, this study presents a unique computational model that may restore energy for the energy-depleted sensor nodes. The proposed study introduces a scheme where both static and mobile chargers are used for energy replenishment using a Reinforcement Learning scheme. Further, the proposed scheme also introduces a dual topology scheme that can perform mobile charging on variable dynamic environmental conditions in WSN. The simulated outcome of the study shows the proposed model to acquire a 50% increase in residual energy, 28% enhanced charging efficiency, 92% reduced delay, and 43% effective packet delivery ratio under increasing number of sensor nodes. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Capsule Network Approach for Image Classification 4th

Capsule Network Approach for Image Classification

引用

4th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2023

作者： Marjit Singh, Moirangthem Kumar Sarkar, Nayan Department of Computer Science and Engineering North Eastern Regional Institute of Science and Technology Arunachal Pradesh Itanagar India

ISBN: (纸本)9789819994410

Numerous deep learning (DL) models based on convolutional neural network (CNN) have been developed for image classification. Though the CNN models attained outstanding performance, its architecture contains certain limitations such as loss of information in the pooling layer and no spatial relationship among the features of an object. The development of capsule network (CapsNet) has overcome the drawbacks of CNN. The CapsNet works on a set of capsules, and each capsule comprises a set of features. The CapsNet consists of a convolution layer, a primary capsule layer, image caps and a fully connected (FC) layer. In this paper, a variant of CapsNet approach is proposed by tuning the parameters of the original CapsNet and replacing ReLU with AReLU activation function in each FC layer. The classification performance of the proposed approach is evaluated on the Plant Village (PV) and Tomato datasets. 80% of the datasets were trained and 20% were tested. The proposed approach considering filter size of 5 × 5 in the feature extraction layer with AReLU activation function in each FC layer delivers 94.02% and 94.06% classification accuracies on PV and Tomato datasets respectively. Compared to other modern approaches, the proposed approach delivered better results. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Garbage Detection System Using Robot and Advanced YOLO Algorithm 5th

Garbage Detection System Using Robot and Advanced YOLO Algo...

引用

5th Doctoral Symposium on Computational Intelligence, DoSCI 2024

作者： Maurya, Saransh Prachi Tiwari, Ayush Singh, Aryan Dwivedi, Shashank Computer Science and Engineering United Institute of Technology Uttar Pradesh Naini Prayagraj 211010 India

ISBN: (纸本)9789819763177

Escalating urbanization has exacerbated challenges in waste management, demanding innovative solutions. This study introduces a smart waste management system integrating the YOLOv5-OCDS (Object Counting Detection System) with TensorFlow and IoT technologies. The YOLOv5-OCDS algorithm, trained on a diverse dataset, efficiently categorizes paper, cardboard, glass, metal, and plastic waste, ensuring rapid and precise results with minimal background noise. The system utilizes a camera module and servomotor on a Raspberry Pi 4 for efficient waste sorting. An ultrasonic sensor monitors bin fill levels, and GPS technology provides real-time location data. The LoRa(Long Range) module transmits bin status at 915 MHz, enhancing remote monitoring. Electronic work is secured by Radio Frequency Identification(RFID)-dependent locker accessible only with authorized badges for maintenance. The system, framed around robotics, neural networks, IoT, and deep learning, demonstrates superior speed and accuracy in garbage detection compared to existing methods. YOLOv5-OCDS’s real-time prediction capability streamlines detection, offering precise results with minimal background noise and exceptional learning capabilities. This research contributes to efficient waste management in urban areas, addressing the escalating challenges of increasing garbage output. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Ultrasonic sensors

来源：评论

学校读者我要写书评

暂无评论

Research on predicting legal judgments by incorporating key information 7

Research on predicting legal judgments by incorporating key ...

引用

7th International Conference on computer Information science and Application technology, CISAT 2024

作者： Xu, Fan Liu, Wei Guo, Kao Wang, Zihao Wuhan Institute of Technology School of Computer Science & Engineering School of Artificial Intelligence Wuhan China

ISBN: (纸本)9798350375107

The prediction of legal judgments is based on the description of case facts to predict the final charges. Through judgment prediction technology, the judicial system can handle a large number of cases more efficiently and provide more accurate judgment results. However, in reality, the types of charges are numerous and complex. To address the issues of severe data imbalance and easily confusable charges, this paper proposes a legal judgment model that incorporates key information. Firstly, it combines the ALBERT (A Lite BERT) pre-trained model and the bidirectional Gated Recurrent Unit (GRU) model to encode cases, efficiently capturing the contextual semantic information in case descriptions. Then, the concept of key information is introduced, using attention mechanisms and statistical methods to extract two distinguishable parts of key information from the cases, which are then concatenated with the case encoding for the final prediction. Additionally, category classification weights are employed to enhance the model's ability to predict low-frequency samples. The proposed method has achieved good results on real legal judgment datasets. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Research on Named Entity Recognition in the Diabetes Field Based on Improved LEBERT 7

Research on Named Entity Recognition in the Diabetes Field B...

引用

7th International Conference on computer Information science and Application technology, CISAT 2024

作者： Li, Zhuli Yao, Feng Huang, Yucheng Li, Dianzhen Wuhan Institute of Technology School of Computer Science & Engineering School of Artificial Intelligence Wuhan China

ISBN: (纸本)9798350375107

The complexity of medical terminologies, variations in professional terms, and the presence of nested entities in the diabetes domain pose challenges for named entity recognition, which has been a focal point of research in intelligent medicine. To address these issues, this study proposes the Lexicon and Syntax Information Enhanced BERT (SLEBERT) model for named entity recognition in the diabetes domain. Building upon the LEBERT model, the SLEBERT model introduces contextual features and syntactic information instances. The SLEBERT model matches the sentence with external medical dictionaries to construct character-word pairs and analyzes syntactic information based on characters. The lexicon-syntax adapter then integrates character information vectors, word information vectors, and syntactic information vectors for feature fusion, which is subsequently incorporated between the initial layers of BERT. Additionally, a diabetes domain corpus dataset is constructed and annotated using the BIOE sequence labeling method. On the self-built DiaNer dataset and the CCKS2019 Chinese electronic medical record dataset, SLEBERT outperforms other comparative models in this study, demonstrating superior entity recognition performance and validating the effectiveness of this approach. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：