检索结果-内蒙古大学图书馆

Deep Learning-Based Lung Cancer Histopathology Classification: Emphasizing Accuracy and Customisation

Biomedical Materials and Devices 2025年 1-13页

作者： Kashyap, Seema Shukla, Arvind Kumar Naim, Iram Pal, Saurabh School of Computer Science and Engineering IFTM University Uttar Pradesh Moradabad India Faculty of Engineering and Technology MJP Rohilkhand University Bareilly India Faculty of Engineering and Technology VBS Purvanchal University Jaunpur India

Lung cancer is a dangerous disease that can be fatal, and a correct diagnosis is essential for figuring out the best way to treat it. The optimum treatment for people with lung cancer requires the classification of the disease into its histological types, such as adenocarcinoma (ADC), small cell lung cancer (SCLC), and squamous cell carcinoma (SCC). Each histological subtype has its features and may react differently to different types of medicine. So, knowing the exact subtype helps guide treatment choices and improve the patient's outcome. Lung cancer subtypes are necessary for personalized treatment. It helps doctors choose tumor-specific treatments such as surgery, radiation, chemotherapy, targeted drugs, and immunotherapies. Precise categorization improves prognosis, avoids needless medicines, and lets patients participate in clinical studies targeting their cancer subtype. Precision medicine improves lung cancer outcomes with accurate categorization. The current algorithms in this domain have shown deficiencies in performance criteria such as specificity, F-score, sensitivity, and precision in recognition. These limitations may stem from challenges such as the complexity and heterogeneity of histopathological images, variations in staining techniques, and the presence of confounding factors. Deep learning methods have made it easier to look at histopathology slides of cancer and see what's going on. Several studies have shown that convolutional neural networks (CNN) are essential for classifying histopathological pictures of different kinds of cancer, like brain, skin, breast, lung, and colon cancer. This study divides lung cancer images into three groups: normal, adenocarcinoma, and squamous cell carcinoma. We have been training deep learning algorithms to identify lung cancer in histopathology slides better, and utilizing deep learning strategies and cutting-edge algorithms such as VGG-19, ResNet-50 v2, EfficientNetB1, and others indicates a comprehensive ap

关键词： And images from histopathology Classification Deep learning EfficientNetB1 Lung cancer ResNet-50 v2 VGG-19

来源：评论

学校读者我要写书评

暂无评论

Assessment of Spring Water Security for Small Community Using Internet of Things (IoT) 7th

Assessment of Spring Water Security for Small Community Usin...

引用

7th International Conference on Architecture and Civil engineering, ICACE 2023

作者： Nadzri, Mohamad Nazrul Hafiz Mohd Othman, Maidiana Razali, Noor Afiza Mat Nordin, Norzaima Department of Civil Engineering Faculty of Engineering Universiti Pertahanan Nasional Malaysia Kuala Lumpur Malaysia Department of Computer Science Faculty of Defence Science and Technology Universiti Pertahanan Nasional Malaysia Kuala Lumpur Malaysia Department of Aeronautic and Aviation Engineering of Computer Science Faculty of Defence Science and Technology Universiti Pertahanan Nasional Malaysia Kuala Lumpur Malaysia

ISBN: (纸本)9789819707508

The securing of clean and sustainable water sources is a fundamental entitlement of individuals and an essential factor in the sustained advancement of societies. Alternative water resources, springs can serve as a primary water source for small, remote communities. The preservation of the security and quality of spring water is of the highest priority. This study provides an assessment of the security of spring water resources within the community, facilitated through the utilization of an Internet of Things (IoT) monitoring system. The study aimed to assess the variations in temperature, turbidity, pH, TDS, and electrical conductivity of spring water on the NDUM campus over the course of a day, specifically during the morning, afternoon, and evening periods. The monitoring was conducted over a span of one year to capture potential patterns and changes. The obtained data is sent to the cloud by using an IoT-based ThingSpeak application to monitor the quality of water. As a result of the collected data, the system provides an efficient water quality parameter monitoring system, and early warning can be taken to reduce any harmful effects to the environment. The outcome of this study may contribute to the proposal of a new way of monitoring water quality on campus by using a real-time system. In addition, the outcome also provides baseline information about water quality for the welfare of society and supports the green campus campaign, which may also help in future water security and sustainability planning for the NDUM campus area. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning Techniques to Maximize Profitability in the Hospitality Industry 6

Using Machine Learning Techniques to Maximize Profitability ...

引用

6th International Conference on Computing and Informatics, ICCI 2024

作者： Shallan, Mohammed S. Moawad, Ibrahim F. El Naggar, Rasha Montasser, Hend Faculty of Commerce and Business Administration Helwan University Cairo Egypt Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Faculty of Computer Science and Engineering New Mansoura University Cairo Egypt

ISBN: (纸本)9798350373875

In the highly competitive hospitality industry, customer satisfaction is critical, and online reviews and ratings are instrumental in influencing hotel booking decisions. Tourists prioritize hotels offering exceptional services, making it vital for hospitality businesses to understand and address customer concerns promptly and effectively. Machine learning algorithms have become essential tools for analyzing online reviews and ratings. This paper analyzes over 70,000 reviews from TripAdvisor, focusing particularly on negative reviews with low ratings. The proposed methodology encompasses both unsupervised and supervised learning Methods. The unsupervised learning phase utilizes the K-Means algorithm to cluster similar reviews and identify prevalent themes and issues. The supervised learning phase employs five distinct algorithms: Support Vector Machine (SVM), Naive Bayes, XGBoost, Logistic Regression, and Random Forest, to classify reviews. These algorithms are evaluated on accuracy, precision, recall, and F-score metrics. Among them, the SVM algorithm demonstrates superior performance, achieving an accuracy rate of 76%%. The findings reveal that SVM is highly effective in analyzing online reviews, offering valuable insights for strategic decision-making in the hospitality sector. The results suggest practical implications for hospitality businesses in enhancing service quality and customer satisfaction. © 2024 IEEE.

关键词： Hotels

来源：评论

学校读者我要写书评

暂无评论

Selective feature-based ovarian cancer prediction using MobileNet and explainable AI to manage women healthcare

引用

Multimedia Tools and Applications 2024年 1-22页

作者： Almujally, Nouf Abdullah Alzahrani, Abdulrahman Hakeem, Abeer M. Attiah, Afraa Umer, Muhammad Alsubai, Shtwai Polsinelli, Matteo Ashraf, Imran Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer Science and Engineering College of Computer Science and Engineering University of Hafr Al Batin Hafr Al Batin39524 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Computer Science The Islamia University of Bahawalpur Bahawalpur Pakistan Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University P.O. Box 151 Al-Kharj11942 Saudi Arabia Department of Management & amp Innovation Systems University of Salerno Fisciano84084 Italy Department of Information and Communication Engineering Yeungnam University Gyeongsan38541 Korea Republic of

Ovarian cancer is a global health concern due to the unavailability of an effective screening strategy and is often diagnosed at a late stage with approximately 70% of the case which reduces the survival chances of patients. Initial diagnosis is challenging due to inconspicuous symptoms in its initial stages which complicate its timely diagnosis. Regular screenings, such as pelvic exams, ultrasounds, and blood tests targeting specific biomarkers can be helpful for early diagnosis. In addition, the use of machine learning models can help automate this process thereby assisting medical experts for accurate diagnosis. This study aims at timely and accurate detection of ovarian cancer using a transfer learning approach that uses the MobileNet model. Moreover, the Chi-square technique is used to extract the most impactful features for better accuracy. For experiments, the Soochow University ovarian cancer dataset is employed. Extensive experiments are performed using all features from the dataset, as well as, using Chi-square-based selective features. The best accuracy of 90.88% is achieved with the Xception model when all features are used. Experimental results show a substantial increase when selective features are used indicating a 98.49% accuracy using the MobileNet model with 20 most important features. In addition, precision, recall, and F1 scores of 99.13%, 99.27%, and 99.20% are obtained showing the model’s robustness and generalization. This study also employs Shapley additive explanations to explain the importance of various features toward the model’s output thereby providing transparency for the model’s decision-making process. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A survey of Detecting Flakiness in Automated Test Regression Suite 21

A survey of Detecting Flakiness in Automated Test Regression...

引用

21st International Learning and Technology Conference, L and T 2024

作者： Elgazzar, Mohamed Hossny, Eman Omara, Fatma A. Faculty of Computers and Informaiton Software Engineering Dept Cairo Egypt Faculty of Computers and Informaiton Computer Science Dept Cairo Egypt

ISBN: (纸本)9798350393569

Recently, Flaky Tests have gotten the attention of the research community. These tests not only waste time and resources, but also undermine the reliability of the automated tests and hence the software systems are affected. So, the detection of Flaky Tests is very important and has a wide audience from both industry and academia. In addition, the research work is very promising having a great potential for the contribution that maps to a true value added to the up-to-date industry projects. Although lots of effort has been done to detect Flakiness in the software systems, the majority of the existed works focuses on different techniques in isolation. The aim of the work in this paper is to overlook the existed flakiness detection techniques, try to analyze them, and hold a comparison, indicating the proper context for each one. Most of the existed flakiness detection techniques are done on unit tests and library/technical projects. According to the comparative study among these techniques, it is found gaps and wide potential for contribution. On the other hand, flakiness detection techniques can be clustered under three main headers;First, study the phenomena under different testing levels by trying to focus on projects with integration, system, and end-toend tests. Second, study the phenomena under different Project types and data sets by studying business projects with user interfaces and mobile applications and so on. Third, study the phenomena toward a faster delivery cycle by studying flake tests in the context of parallel execution and Continuous Integration and Continuous Deployment (CI/CD). We can conclude that not all detection techniques have the same potential where some techniques are very competent while others still struggle to achieve considerable efficiency. © 2024 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Education: Rethinking the Way Programming is Taught Using AI Tools and Reversed Bloom's Taxonomy 21

AI-Powered Education: Rethinking the Way Programming is Taug...

引用

21st International Conference on Information Technology Based Higher Education and Training, ITHET 2024

作者： Pesovski, Ivica Vorkel, Daniela Trajkovik, Vladimir Brainster Next College Computer Science and Innovation Skopje Macedonia Independent Researcher Leipzig Germany Ss. Cyril and Methodius University Faculty of Computer Science & Engineering Skopje Macedonia

ISBN: (纸本)9798331516635

Artificial intelligence (AI) is revolutionizing the way programming is taught and learnt and is redefining t he way programming skills are assessed in the continuously changing field of computer science education. This paper introduces a novel approach for teaching and evaluating programming knowledge by reversing Bloom's taxonomy in order to accommodate AI-powered learning. Traditionally, Bloom's taxonomy progresses from basic cognitive skills like remembering and understanding to advanced skills like creating. With AI tools such as *** and Anthropic Artifacts now capable of generating sophisticated outputs, the focus shifts away from students' ability to create, as these tools handle that task effectively. Instead, this paper proposes placing a higher emphasis on students' ability to understand and critically analyze AI -generated solutions, assessing their comprehension and ability to reverse-engineer existing work. We call this the Reverse Bloom Taxonomy, where students begin with creation and then move toward deeper understanding of the subject matter. This paper outlines the methodology for applying this reversed framework in programming education and presents a promising concept for improving student learning outcomes. The discussion addresses challenges in implementation and emphasizes the strategic integration of AI -driven learning to prepare students for a technology-driven workforce. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Practical Indoor Positioning System Based on Collaborative PDR and Wi-Fi Fingerprinting 4

A Practical Indoor Positioning System Based on Collaborative...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Dwijaksara, Made Harta Safaraz, Raissa Tito Asyraf, Muhammad Nugroho, Julius Prayoga Raka Thiagarajah, Siva Priya University of Indonesia Faculty of Computer Science West Java16424 Indonesia Multimedia University Faculty of Engineering Selangor 63100 Malaysia

ISBN: (纸本)9798331506490

An Indoor Positioning System (IPS) is vital in pro-viding location-based service (LBS) indoors. The shortcomings of the Global Positioning System (GPS) indoors have led to the development of many alternative solutions for IPS. Wi-Fi finger-printing is a promising solution due to its ability to accurately predict indoor locations. Moreover, the widespread deployment of Wi-Fi infrastructures makes the Wi-Fi fingerprinting-based IPS technique readily applicable. However, this technique re-quires high overhead due to the need to define many reference points (RPs) within the subject area. Multiple Wi-Fi received signal strength (RSS) samples shall be collected from each RP, introducing extensive manual work. This fact makes the Wi-Fi fingerprinting-based IPS is less practical. This issue is addressed by employing pedestrian dead reckoning (PDR) as part of the proposed technique. Realizing a practical IPS based on collaborative use of PDR and Wi-Fi fingerprinting. In the proposed method, most of the time, the location prediction will be based on PDR. When the step count reaches a threshold, a switch from PDR to Wi-Fi fingerprinting is made to decide the user's location. Then, the system resets the step count and uses the PDR again. This approach significantly reduces the total number of RPs needed by the system. The numerical results show that the proposed technique has 99% lower overhead than the conventional Wi-Fi fingerprinting technique and achieves 55.6% better prediction accuracy than the standalone PDR technique. The results justify the benefits of the proposed IPS based on collaborative PDR and Wi-Fi fingerprinting. © 2024 IEEE.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

Indoor Uncertain Semantic Trajectory Similarity Join

引用

Journal of computer science & Technology 2024年第6期39卷 1441-1465页

作者： Hong-Bo Yin Dong-Hua Yang Kai-Qi Zhang Hong Gao Jian-Zhong Li Faculty of Computing Harbin Institute of TechnologyHarbin 150001China Center of Analysis Measurement and ComputingHarbin Institute of TechnologyHarbin 150001China Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

With the widespread deployment of indoor positioning systems, an unprecedented scale of indoor trajectories is being produced. By considering the inherent uncertainties and the text information contained in such an indoor trajectory, a new definition named Indoor Uncertain Semantic Trajectory is defined in this paper. In this paper, we focus on a new primitive, yet quite essential query named Indoor Uncertain Semantic Trajectory Similarity Join (IUST-Join for short), which is to match all similar pairs of indoor uncertain semantic trajectories from two sets. IUST-Join targets a number of essential indoor applications. With these applications in mind, we provide a purposeful definition of an indoor uncertain semantic trajectory similarity metric named IUS. To process IUST-Join more efficiently, both an inverted index on indoor uncertain semantic trajectories named 3IST and the first acceleration strategy are proposed to form a filtering-and-verification framework, where most invalid pairs of indoor uncertain semantic trajectories are pruned at quite low computation cost. And based on this filtering-and-verification framework, we present a highly-efficient algorithm named Indoor Uncertain Semantic Trajectory Similarity Join Processing (USP for short). In addition, lots of novel and effective acceleration strategies are proposed and embedded in the USP algorithm. Thanks to these techniques, both the time complexity and the time overhead of the USP algorithm are further reduced. The results of extensive experiments demonstrate the superior performance of the proposed work.

关键词： filtering-and-verification framework indoor uncertain semantic trajectory inverted index trajectory similarity join

来源：评论

学校读者我要写书评

暂无评论

IoT Based Systems and Services: Recent Security Concerns and Feasible Solutions 1

IoT Based Systems and Services: Recent Security Concerns and...

引用

1st IEEE Karachi Section Humanitarian Technology Conference, Khi-HTC 2024

作者： Attaullah, Hafiz Muhammad Memon, Shahzad Erkan, Ozlem Feyza Khawar, Ruba Mohammad Ali Jinnah University Department of Computer Science Karachi Pakistan Beykoz University Faculty of Engineering and Architecture Department of Computer Engineering Istanbul Turkey NED University of Engineering and Technology Faculty of Information Sciences and Humanities Karachi Pakistan

ISBN: (纸本)9798350373042

The term Internet of Things (IoT) is used to refer as embedded devices or objects with internet access, allowing them to communicate globally, interacting with people and networks. IoT security issues are directly related to the widespread use of its systems. This paper examines the security technologies employed in IoT and their respective features and applications. Additionally, it addresses the various security concerns associated with IoT-based systems and services, highlighting their occurrence within the three-layer framework of IoT. These days, as IoT introduces advanced application architectures that minimizes human intervention by integrating businesses in some way to address digital computer processes by communicating within a given network. Moreover, it will be discussed the key technologies associated with Advanced Encryption Standards (AES) and the changes brought in market value and usage of services that has been taken place b since the IoT incorporated. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Enhancing E-Learning Materials Recommendations with Contextual Awareness and Collaborative Filtering 6

Enhancing E-Learning Materials Recommendations with Contextu...

引用

6th International Conference on Computing and Informatics, ICCI 2024

作者： Anter, Ahmed Moawad, Ibrahim F. Mosaad, Sara M. Faculty of Commerce and Business Administration Helwan University Cairo Egypt Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt

ISBN: (纸本)9798350373875

The number of learners using online learning materials has significantly increased in recent years. Due to the overload of information, many learners face difficulty finding relevant and useful educational materials that meet their needs. To solve this problem, recommendation systems (RS) are widely relied upon. These systems are used to provide suitable recommendations to users based on their needs. However, traditional recommendation techniques such as collaborative filtering (CF) and content-based filtering (CB) solely rely on user ratings and content attributes. Therefore, it is imperative to incorporate the learner's context when it comes to precise and personalized recommendations in e-learning. These conventional methods often neglect the learner's context when computing similarities and making recommendations, resulting in less accurate suggestions. This paper proposes a learning materials recommendation approach by integrating context awareness with collaborative filtering (CF) algorithms. Context awareness in the proposed approach entails incorporating context-specific data, like the learner's knowledge level and preferred learning style. Collaborative filtering computes predictions and generates targeted learner recommendations based on contextualized data. Evaluating the proposed recommendation approach (CF-CA) involved experiments comparing it with traditional collaborative filtering (CF) on a dataset of 349 learners. The two-recommendation technique's performance varied with neighbors (5 to 50). The proposed method demonstrated a 0.21 MAE improvement at an optimal size of 5. Furthermore, the proposed approach (CA-CF) consistently outperforms the CF in precision and recall across varying recommendation volumes. Additionally, by utilizing the learner's contextual data, the proposed method helps alleviate the cold-start issue. © 2024 IEEE.

关键词： Recommender systems

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：