检索结果-内蒙古大学图书馆

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Enabling Technology Integrated Learning for Autistic Children Using Augmented Reality Based Cognitive Rehabilitation

引用

SN computer science 2024年第1期5卷 151页

作者： Abdullah, A. Sheik Karthikeyan, J. Gomathi, V. Parkavi, R. Rajarajeswari, P. School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering National Engineering College Kovilpatti India Department of Information Technology Thiagarajar College of Engineering Madurai India

Augmented reality (AR)-based rehabilitation is an excellent teaching tool (ICT tool) for simulating daily activities for autistic children. Children with autism may become more mentally capable with this type of AR-based rehabilitation. It is intended to observe the children's performance in terms of concentration, attention, and identification. The observation has been done through placards as a target image to display the 3D objects on a mobile phone or tablet. In this project, observations are made for 21 autism children in the age group of 7–14, out of whom 17 are boys and 5 are girls. Those 21 children are given practice identifying 15 different objects in an augmented reality environment. Their performance was initially evaluated using conventional instructional techniques. The majority of the kids were having more difficulty identifying things during that observation. Then, with an Augmented Reality environment, the identical observation has been made once more. Using a mobile device or tablet, the 3D objects from the provided placard photos are produced in an augmented reality environment with animation and voice in the languages of English and Tamil. Children with autism are able to recognize and also grasp the behaviors of those objects while viewing them in 3D. Their efforts are measured using a two-point scale (0, 1, 2). The pre-assessment and post-assessment reports for the above observations are tabulated. All the observations are made in the presence of the special education teacher (therapist). However, the children observed in this project fall into three different categories: mild, moderate, and severe. In the Mild category, statistical significance is evident with p values of 0.002 in pre-assessment and 0.014 in post-assessment. Likewise, in the Moderate category, where p values are 0.023 in pre-assessment and 0.033 in post-assessment, significance is observed, as all p values fall below the chosen significance level of 0.05. This leads to rejecti

关键词： Augmented reality (AR) Autism ICT tools Observation Rehabilitation Teaching methodology

来源：评论

学校读者我要写书评

暂无评论

WSETO: wild stock exchange trading optimization algorithm enabled routing for NB-IoT tracking system

引用

International Journal of Information Technology (Singapore) 2024年第8期16卷 4895-4905页

作者： Sivadevuni, Sreeparnesh Sharma Naveen, J. Department of Computer Science and Engineering School of Engineering and Technology Christ University Karnataka Bangalore 560001 India

The Narrowband Internet of Things (NB-IoT) communication plays a significant role in the IoT due to the capability of generating broad exploration with the usage of limited power. Over the past few years, the Low Power Wide Area Networks (LPWAN) have been efficient in the data acquisition and remote monitoring area however they failed to generate high data rates, low latency, and the consumption of low power. To solve these problems, NB-IoT technology has developed in long-term asset tracking and it replaces the Global Positioning system (GPS) with its ubiquitous coverage. In this research, the Wild Stock Exchange Trading Optimization technique (WSETO) is proposed for a routing-based NB-IoT tracking system. The WSETO is the combination of the Wild Geese Algorithm (WGA) and SETO. By employing WSETO, the routing to the relevant target location is established effectively. The existing techniques like Low Power Asset Tracking of NB-IoT (LoPATraN), Monitoring system based on NB-IoT and BeiDou system/GPS (BDS/GPS), and Narrowband Physical Uplink Shared Channel (NPUSCH) are used to compare the WSETO approach. In rounds with a value of 2000, the WSETO demonstrates a superior location error of 0.001 in comparison to existing methods such as LoPATraN, a monitoring system utilizing NB-IoT and BDS/GPS, as well as NPUSCH. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Global positioning system Low power wide area networks Narrowband internet of things Stock exchange trading optimization Wild geese algorithm

来源：评论

学校读者我要写书评

暂无评论

Development Arena through Cloud Computing Technology 5

Development Arena through Cloud Computing Technology

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Jain, Archana Bansal, Nidhi Pandey, Mahima Shankar Kumar, Gaurav Sharma, Manoj Kumar Malik, Suraj Maurya, Santosh Kumar Iimt University School of Engineering and Technology Department of Computer Science and Engineering Meerut India Sharda University School of Engineering and Technology Computer Science and Engineering Department Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350383522

Latest measurements correlated to the cloud computing technology, found to be very unreliable. For smooth conduction of cloud technology, the report is getting more than 100 values i.e., being added to the cost of the essential component that has been prepared for succession of the technology. Moreover, with the care of cloud computing technology, very intelligent operational programing has been into running, yet the real parameter of performance measurement is showing the actual output. With tremendous literature survey and feedback, the paper has been able to lay out logical terms about the services availed from cloud side. Trendy services involve trust and reliable factors in terms of benefits accruing from the customer side to the service provider. By offering the combined efforts of public and private cloud, business drivers are moving forward with the freedom to deliver their most effective service to the users and are also able to achieve higher spend. © 2024 IEEE.

关键词： benefitted primary and secondary services Cloud computing Cloud Service Providers issues Quality measuring factors

来源：评论

学校读者我要写书评

暂无评论

Light Shift Detection Using a Multiple Photodetection Method Suitable for a Chip-Scale Atomic Clock

Light Shift Detection Using a Multiple Photodetection Method...

引用

2023 Joint Conference of the European Frequency and Time Forum and IEEE International Frequency Control Symposium, EFTF/IFCS 2023

作者： Fukuoka, Masahiro Goka, Shigeyoshi Tokyo Metropolitan University Graduate School of System Design Department of Electrical Engineering and Computer Science Tokyo Japan

ISBN: (纸本)9798350311426

In this study, we demonstrated light shift detection in a running atomic clock using the multi-photodetection method. This method enables the observation of atomic resonances with different intensities using the intensity distribution of the laser beam. As it requires only two photodiodes to detect light shifts, it is easily applicable to miniature vapor-cell-based atomic clocks such as chip-scale atomic clocks and miniature atomic clocks. © 2023 IEEE.

关键词： chip-scale atomic clock coherent population trapping intensity distribution laser light shift VCSEL

来源：评论

学校读者我要写书评

暂无评论

Stacked LSTM for Solar Irradiance Forecasting Using Minimum Redundancy Maximum Relevance (MRMR) Feature Selection 1

Stacked LSTM for Solar Irradiance Forecasting Using Minimum ...

引用

1st International Conference on Trends in engineering systems and Technologies, ICTEST 2024

作者： Hari, Ninu G. Jisha, G. Rajagiri School of Engineering and Technology Apj Abdul Kalam Technological University Department of Computer Science and Engineering Kerala India Rajagiri School of Engineering and Technology Department of Computer Science and Engineering Kochi India

ISBN: (纸本)9798350307795

To effectively combat atmospheric pollution caused by greenhouse gases, immediately switching to power plants that rely solely on renewable energy sources is imperative. With the vast availability of solar energy in Kerala throughout the year, it would be wise to make it the primary source for these plants. The spatiotemporal features that impact the Global Horizontal Irradiance (GHI) should also be analysed to choose a better location for solar power plants. The features should be identified and analysed yearly and seasonally to determine the relationship between GHI and those selected features. The Minimum Redundancy Maximum Relevance (MRMR) minimal optimal feature selection algorithm is integrated for seasonal and yearly GHI prediction for finding the feature relation. The stacked LSTM (Long Short-Term Memory) with a 3-layer architecture is used for solar irradiance forecasting and annual and seasonal analysis of the dataset since LSTM is a perfect model for time-series data and stacked LSTM performs better than single-layer LSTM. The study shows that feature identification and selection positively change the forecasting results. The comparison of results also shows that seasonal forecasting needs more focus than yearly forecasting since results fluctuate in different seasons. The tropical monsoon climate forecasting is more complex as it fluctuates most of the year and is considered for experimental analysis. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Design an optimization based ensemble machine learning framework for detecting rice leaf diseases

引用

Multimedia Tools and Applications 2024年第36期83卷 84401-84424页

作者： Rajasekhar, Veeramreddy Arulselvi, Gnanasekaran Babu, K. Suresh Department of Computer Science Engineering Annamalai University Tamilnadu Chidambaram India Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Tamil Nadu Chidambaram India International School of Technology and Sciences for Women East Gonagudem Rajanagaram A.P Rajamahendravaram India

The agriculture industry is currently dealing with serious issues with rice plants as a result of illnesses that decrease the quantity and output of the harvest. Numerous fungi and bacteria diseases harm plants that affect the growth of yield. So identification of the detection of crop diseases is essential for enhancing the productivity of crops. Many techniques have been developed to improve disease detection in crops but there are still some issues such as noise, time consumption, delay, poor segmentation, and less accuracy. To overcome these issues, this paper, designed a Spider Monkey-based Random Forest (SMbRF) model for accurate detection and classification of rice leaf diseases and the designed model was implemented in the Python system. The main aim is to develop an optimization-based random forest technique for accurate prediction of rice leaf disease by exact segmentation. Initially, preprocessing is performed to enhance the data quality and remove errors. Furthermore, separate the lesions using mean shift image segmentation and extract the shape and color features to improve the detection results of the developed model. As well, spider monkey fitness is updated in the RF classification layer for accurate classification of diseases and improves accuracy with less execution time. The experiment results show the reliability and efficiency of the designed model, it attains better performance in accuracy, sensitivity, specificity, and precision. The designed model attained 99.29% accuracy, 99.52% sensitivity, 98.76% precision, and 99% specificity proving the scalability of the designed model. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Fast Parallel Recovery for Transactional Stream Processing on Multicores 40

Fast Parallel Recovery for Transactional Stream Processing o...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Zhao, Jianjun Liu, Haikun Zhang, Shuhao Duan, Zhuohui Liao, Xiaofei Jin, Hai Zhang, Yu School of Computer Science and Technology Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350317152

Transactional stream processing engines (TSPEs) have gained increasing attention due to their capability of processing real-time stream applications with transactional semantics. However, TSPEs remain susceptible to system failures and power outages. Existing TSPEs mainly focus on performance improvement, but still face a significant challenge to guarantee fault tolerance while offering high-performance services. We revisit commonly-used fault tolerance approaches in stream processing and database systems, and find that these approaches do not work well on TSPEs due to complex data dependencies. In this paper, we propose a novel TSPE called MorphStreamR to achieve fast failure recovery while guaranteeing low performance overhead at runtime. The key idea of MorphStreamR is to record intermediate results of resolved dependencies at runtime, and thus eliminate data dependencies to improve task parallelism during failure recovery. MorphStreamR further mitigates the runtime overhead by selectively tracking data dependencies and incorporating workload-aware log commitment. Experimental results show that MorphStreamR can significantly reduce the recovery time by up to 3.1 x while experiencing much less performance slowdown at runtime, compared with other applicable fault tolerance approaches. © 2024 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Botnet Detection Through Flow-Based Deep Feature Extraction and Ensemble Classification

引用

Journal of The Institution of Engineers (India): Series B 2025年 1-14页

作者： Geetha, K. Brahmananda, S.H. Department of Computer Science and Engineering GITAM School of Technology Karnataka Bengaluru India Ashtaksha Labs Pvt Ltd Karnataka Bengaluru India

As Internet of Things (IoT) devices are networked and thus susceptible to many forms of attacks, cyber security risk is the primary concern in the IoT field. To tackle this issue, this study employs machine learning and deep learning techniques to identify botnet attacks. The proposed method uses a random forest classifier or other machine learning techniques to organize the data after extracting detailed characteristics using Bidirectional Long Short-Term Memory (Bi-LSTM). This methodology yields superior outcomes for challenges involving binary and multiclass classification. The IoT-23 and N-BaIoT databases were used. The IoT-23 collection consists of three normal samples and twenty malware samples from different IoT devices, whereas the N-BaIoT dataset includes scenarios like Mirai and Bashlite attacks. In the context of IoT risks, the proposed technique successfully differentiates between benign and malicious traffic data. In terms of multiclass classification, the accuracy rates for N-BaIoT and the IoT-23 dataset are 100% and 99.9%, respectively, while the acquired accuracy rates for binary classification are 99.9% for N-BaIoT and 97% for the IoT-23 dataset. © The Institution of Engineers (India) 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Early Detection and Classification of Tomato Leaf Blight Disease Using Deep Neural Networks 2

Early Detection and Classification of Tomato Leaf Blight Dis...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Halder, Anangsha Guha Neogi, Subhrendu Dutta, Shibdas Khamaru, Koustov Bhattacharya, Arghya Roy, Shovan The Neotia University Department of Computer Science and Engineering Sarisha India Dcg Data-Core System India Department of Information Technology Kolkata India University of Engineering and Management Department of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798350373110

The world population relies on agricultural plants for food, and illnesses reduce yield, but proper plant disease monitoring can help to resolve such issues. computer vision and machine learning methods can detect plant illnesses early, reducing their negative consequences and overcoming the drawbacks of continual human monitoring. After pre-processing of input images, the target region needs to be isolated. The proposed models analyzes images for detection and classification to identify edges, colors, and textures. This research has agricultural applications for early disease identification. This study examined ResNet, MobileNet, DenseNet, InceptionV3 and modified CNN model on the PlantVillage dataset to classify tomato illnesses. The F1 score, accuracy, sensitivity, and specificity can evaluate models. This paper evaluates these models using a diverse collection of tomato leaf pictures, contributing to automated disease detection systems and may be helpful for improving farm management and sustainability. © 2024 IEEE.

关键词： Fruits

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：