检索结果-内蒙古大学图书馆

Utilizing Different Edge Detection and Preprocessing Techniques to Improve the Accuracy of Durian Cultivar Detection using Convolutional Neural Networks 9

Utilizing Different Edge Detection and Preprocessing Techniq...

引用

9th IEEE International Conference on Computing, Engineering and Design, ICCED 2023

作者： Hussin, Amir Laalieff Bin Amir Muzammil, Harith Syazwan Bin Haril Shaharuddin, Muhammad Afiq A. Bin Ismail, Amelia Ritahani Binti Zainuddin, Ahmad Anwar Bin Kulliyyah of Information and Communication Technology Department of Computer Science Gombak Malaysia

ISBN: (纸本)9798350370126

Using machine learning to recognize images of fruits or plants is a very practical and focused application. When using machine learning principles to classify specific fruit varieties, as opposed to traditional approaches, a higher level of accuracy is promised but also requiring more training data. Particularly in situations where different cultivars of the same fruit family are valued differently, the capacity to recognize and classify diverse cultivars of a fruit family is crucial. The objective of this study is to develop a practical method for classifying the many cultivars of Durio zibethinus, also known as Durian, based on the visual traits of the crop using Convolution Neural Networks (CNNs) to improve the accuracy and speed of cultivar recognition. Utilizing a database of images with tagged Durian cultivars. Images from two high-value classes of Durian cultivars are utilized to train the neural network. The first phases in the research project involve pre-processing and converting the images using Canny, Laplacian, Sobel on X-axis, and image binarization. Next up are model training, model validation, and network architecture development. Finally, they were combined as an ensemble machine learning method using majority voting to examine the potential for enhancing prediction performance. Laplacian edge detection was found to yield the best results of the four studied approaches, while ensemble methods gave more accurate results than a single method. © 2023 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Medical Image Denoising using Convolutional Autoencoders 3

Performance Evaluation of Medical Image Denoising using Conv...

引用

3rd International Conference on Creative Communication and Innovative technology, ICCIT 2024

作者： Ismail, Amelia Ritahani Zulhazmi Rafiqi Azhary, Muhammad Zaharin Noor Azwan, Nor Aiman Ismail, Ahsiah Alsaiari, Nisrin Amer International Islamic University Malaysia Kulliyyah of Information Communication Technology Department of Computer Science Kuala Lumpur Malaysia International Islamic University Malaysia Kulliyyah of Information and Communication Technology Department of Computer Science Kuala Lumpur Malaysia Arab Open University Faculty of Computer Studies Saudi Arabia

ISBN: (纸本)9798350367492

Convolutional Autoencoders (CAEs) are neural network architectures specifically designed for image-processing tasks. CAEs also show a great performance in image denoising as it has the capability to efficiently eliminate noise from images while retaining crucial features and structural integrity. However, the effectiveness of CAEs in denoising tasks can be limited by the specific characteristics and complexities present in the images;for example, different intensities and distribution of noise will lead to challenges in achieving consistent and highquality denoising results across diverse datasets like medical images. This paper, therefore, explores the capabilities of CAEs in effectively denoising images corrupted by varying levels of Gaussian noise. The CAE's performance is evaluated under different levels of noise severity using two datasets: PathMNIST and Brain MRI Scan images. Findings indicate that at a low noise level, CAEs achieve impressive results with PathMNIST images, demonstrating high image fidelity. However, Brain MRI Scan images show moderate denoising suggesting opportunities for improvement. As noise severity increases, both datasets experience reduced denoising performance, highlighting the need for enhanced CAE configurations to maintain image quality in critical applications like medical diagnosis. © 2024 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Hybrid Agile Model, the Synergy of Waterfall Model and Scrum in a Software Project 9

Hybrid Agile Model, the Synergy of Waterfall Model and Scrum...

引用

9th International Conference on information technology and Digital Applications, ICITDA 2024

作者： Yahya, Norzariyah Salam, Abdul Muizz Abdul Maidin, Siti Sarah Bakar, Normi Sham Awang Abu Kulliyyah of Information and Communication Technology International Islamic University Malaysia Department of Computer Science Kuala Lumpur Malaysia Inti International University Malaysia

ISBN: (纸本)9798331510732

Hybrid agile is one of the recent software engineering process model used by a software engineering team in a software development project. A hybrid agile model is used by software engineering team to meet the requirements of a software project. However, what does the hybrid agile model used by a software engineering team look like? A qualitative study was conducted to answer this question, and a series of interviews were chosen as a data collection instrument. The interview participants are practitioners involved in software projects using hybrid agile. The recorded interviews are transcribed and analysed using thematic analysis. The finding shows that the software engineering team uses the Waterfall model in the planning, design, deployment and maintenance phases, while scrum in the development and testing phases. The results have led to the hybrid agile model presented in this study, which leverages the strengths of each model to ensure the completion of a software project. Future iterations of this study will assess a project's software quality, comparing the proposed model with plan-driven and scrum. © 2024 IEEE.

关键词： computer aided software engineering

来源：评论

学校读者我要写书评

暂无评论

Maintain Optimal Configurations for Large Configurable Systems Using Multi-Objective Optimization

引用

computers, Materials & Continua 2022年第11期73卷 4407-4422页

作者： Muhammad Abid Jamil Deafallah Alsadie Mohamed K.Nour Normi Sham Awang Abu Bakar Department of Computer Science Umm Al-Qura UniversityMakkahSaudi Arabia Kulliyyah of Information and Communication Technology International Islamic UniversityMalaysia

To improve the maintenance and quality of software product lines,efficient configurations techniques have been ***,due to the complexity of derived and configured products in a product line,the configuration process of the software product line(SPL)becomes timeconsuming and *** product line consists of a various number of feature models that need to be *** different approaches have been presented by Search-based software engineering(SBSE)to resolve the software engineering issues into computational solutions using some metaheuristic ***,multiobjective evolutionary algorithms help to optimize the configuration process of *** this paper,different multi-objective Evolutionary Algorithms like Non-Dominated Sorting Genetic algorithms II(NSGA-II)and NSGA-III and Indicator based Evolutionary Algorithm(IBEA)are applied to different feature models to generate optimal results for large *** proposed approach is also used to generate the optimized test suites with the help of different multi-objective Evolutionary Algorithms(MOEAs).

关键词： Software product line search-based software engineering metaheuristic multiobjective evolutionary algorithms feature model

来源：评论

学校读者我要写书评

暂无评论

Deep Radiomics: A Picture's Worth a Thousand Words - A Review 1

Deep Radiomics: A Picture's Worth a Thousand Words - A Revie...

引用

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

作者： Meraj, Syeda Shah, Asadullah Ismail, Ahsiah Sembokb, Tengku Mt Shadab, Syed Aftab, Syed Nageena, Syeda Khan, Nusratullah Nusratullah, Kajal Kulliyyah of Information and Communications Technology Department of Information Systems Selangor Malaysia Kulliyyah of Information and Communications Technology Department of Computer Science Selangor Malaysia Al Musanna College of Technology City Department of Information Technology Oman Higher Colleges of Technology Department of Aeronautical Engineering Technology Al-Ain United Arab Emirates Department of Health and Family Welfare Karnataka Koppal India Yanbu Industrial College Royal Commission Computer Science and Engineering Department Yanbu Saudi Arabia

ISBN: (纸本)9798350373042

In recent decades, the prevalence of diseases has witnessed a notable surge. The increasing health challenges have led to a greater use of advanced diagnostic machines for detecting and understanding these disease conditions. The diagnostic modalities, such as X-rays, CT scans, MRI scans, and nuclear medicine imaging, generate a wealth of interpretative data through medical images. Deep Radiomics aims to improve the efficiency and accuracy of image interpretation by automating the process of feature extraction, allowing for more comprehensive insights for advancing personalized medicine and improving outcomes in medical imaging. Enhance disease detection, diagnosis, and subsequent treatment strategies. © 2024 IEEE.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Fine-Tuned Large Language Model for Domain-Specific with Reinforcement Learning 3

A Fine-Tuned Large Language Model for Domain-Specific with R...

引用

3rd International Conference on Creative Communication and Innovative technology, ICCIT 2024

作者： Ismail, Amelia Ritahani Aminuddin, Amira Shazleen Nurul, Afiqa Zakaria, Noor Azura Fadaaq, Wafa Haussain Nasser International Islamic University Malaysia Kulliyyah of Information and Communication Technology Department of Computer Science Kuala Lumpur Malaysia Arab Open University Faculty of Computer Studies Riyadh Saudi Arabia

ISBN: (纸本)9798350367492

Large Language Models (LLMs) like GPT-3 and BERT have significantly shown advancement in natural language processing by providing robust tools for understanding and generating human languages. However, their broad but shallow knowledge across many domains often leads to less effective performance in domain-specific tasks, where detailed and special-ized knowledge is needed. To address this limitation, this paper investigates the effectiveness of fine-tuning LLMs for specific domains. The approach incorporates reinforcement learning to integrate user feedback, allowing the model to dynamically adjust and refine its responses. This will ensure the model adapts iteratively, improving communication and interaction with users. The fine-tuned model's performance is evaluated using two domain-specific datasets - medical and dental. Evaluation metrics such as Levenshtein distance and cosine similarity are used to assess the textual accuracy and semantic relevance of the fine-tuned model. The results from the dental the medical datasets indicate a low level of textual differences and strong semantic alignment, respectively. These suggest that the fine-tuned model effectively processes and preserves the integrity of domain-specific content with the potential of fine-tuning LLMs to enhance their applicability in specific domains. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Integration and Validation of a Robust Process for Cloud Applications 8

Integration and Validation of a Robust Process for Cloud App...

引用

8th IEEE International Conference on Engineering Technologies and Applied sciences, ICETAS 2023

作者： Shahid, Sheeba Eselgrimm, Sven Shah, Asadullah Mahdi, Ghulam Kulliyyah of Computer Science and Information Technology International Islamic University Malaysia Orbit Gesellschaft für Applikations-und Informationssysteme MbH Germany Kulliyyah of Information and Communication Technology International Islamic University Malaysia Kimberly Clark Corporation RoswellGA United States

ISBN: (纸本)9798350327090

The development and administration of software applications have undergone a transformation because of the introduction of cloud computing. Flexible, scalable, and cost-effective Software-as-a-Service (SaaS) applications are hosted on scalable cloud infrastructures. However, there are additional difficulties in integrating and evaluating cloud apps, especially given the various control system features of private, public, and hybrid cloud models. The integration and validation process for cloud apps is examined in this research article along with methods for resolving related problems. The paper outlines the identification, connection, data mapping, and testing processes of integration, which is the merging of systems. It makes a distinction between integration between private and public clouds. Cloud-based apps are validated to make sure they adhere to performance, security, and reliability standards. It includes a discussion of testing techniques, including load and stress testing. Lack of control over the underlying infrastructure, changing environments, and shared infrastructure are difficulties in validation. A thorough validation strategy that includes establishing requirements, developing test plans, choosing suitable validation tools, and iterating the validation process is recommended to overcome these challenges. Organizations can profit from cloud computing by adopting a systematic and effective validation approach to ensure their applications match the essential requirements, regardless of the difficulties in integrating and validating cloud apps. © 2023 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based IoT System for Real-Time Harmful Algal Bloom Monitoring: Seamless ThingsBoard Integration via MQTT and REST API 22

Cloud-Based IoT System for Real-Time Harmful Algal Bloom Mon...

引用

22nd IEEE Student Conference on Research and Development, SCOReD 2024

作者： Annas, Ammar Haziq Zainuddin, Ahmad Anwar Hussin, Amir LAatief Amir Kamal, Nik Nor Muhammad Saifudin Nik Mohd Noor, Normawaty Mohammad Razali, Roziawati Mohd International Islamic UniversityMalaysia Kulliyyah of Information and Communication Technology Dept. of Computer Science Kuala Lumpur Malaysia Institute of Oceanography & Maritime Studies Kulliyyah of Science IIUM Jln Sultan Hj Ahmad Shah Bandar Indera Mahkota Pahang Kuantan25200 Malaysia Malaysia Bayan Lepas Malaysia

ISBN: (纸本)9798331510077

Harmful Algal Blooms (HABs) pose a severe threat to aquatic ecosystems, drinking water supplies, and public health. Existing water quality monitoring methods are often costly and complex thus limiting their accessibility and scalability for continuous monitoring. This work proposes a scalable, cloud-based IoT solution for real-time water quality monitoring, specifically targeting HAB detection using cost-effective sensors. The system architecture utilizes Microsoft Azure hosted ThingsBoard platform for data management, integrating telemetry data from sensors via MQTT and REST API protocols to enable reliable, low-latency data transmission and storage. Through a combination of numeric and graph-based dashboards, end users can monitor both real-time and historical data, supporting early anomaly detection and rapid response. This work uses a cloud-based system to manage IoT devices, ensures secure data transmission, and displays the data on ThingsBoard without needing extra cloud services. The proposed system is cost-effective, flexible, and easily extendable to different monitoring environments. In addition, it could be contributing to proactive water resource management and public health protection against HABs threats. © 2024 IEEE.

关键词： Blooms (metal)

来源：评论

学校读者我要写书评

暂无评论

IoT-based Heartbeats Monitoring System 9

IoT-based Heartbeats Monitoring System

引用

9th IEEE International Conference on Computing, Engineering and Design, ICCED 2023

作者： Tamron, Mohamad Asyraf Noorza Bin Mohd Attarbashi, Zainab S. Abuzaraida, Mustafa Ali Atitallah, Nesrine Iftikhar, Saman Handayani, Dini Oktarina Dwi Basri, Atikah Balqis Binti International Islamic University Malaysia Kulliyyah of Information & Communication Technology Selangor Malaysia International Islamic University Malaysia Faculty of Information & Communication Technology Department of Computer Science Selangor Malaysia Misurata University Faculty of Information Technology Computer Science Department Libya Arab Open University Faculty of Computer Studies Saudi Arabia International Islamic University Malaysia Faculty of Information and Communication Technology Department of Information Systems Selangor Malaysia

ISBN: (纸本)9798350370126

The advent of the Internet of Things (loT) has opened up a realm of possibilities in developing globally accessible systems and devices. With the current state of internet speeds, these systems offer real-time control, making them more powerful than ever. Simultaneously, the healthcare sector has been witnessing notable advancements, but it also grapples with an increasing number of health issues, with heart problems standing out as a prominent concern in many countries. These problems manifest in various symptoms, some of which can lead to more serious conditions, such as irregular heartbeats. In response to these challenges and leveraging cutting-edge technology, researchers have embarked on endeavors to enhance healthcare devices and render them more readily available to medical professionals. This paper explores the merging of loT technology with healthcare, specifically focusing on the development of a system designed to monitor and record a patient's heartbeat. This is achieved through the deployment of a Heartbeat/SpO2 Sensor, and the data is seamlessly transmitted to a mobile application accessible remotely. The outcomes of this study demonstrate that the heartbeat data captured by Arduino is effectively transmitted to the cloud, meeting the system's predefined objectives. This represents a significant stride in harnessing loT's potential to enhance healthcare practices and patient monitoring. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Video Summarization Method for Movie Trailer-Genre Classification Based on Emotion Analysis 9th

A Video Summarization Method for Movie Trailer-Genre Classif...

引用

9th International Conference on Computing and Informatics, ICOCI 2023

作者： Ng, Wan En Pozi, Muhammad Syafiq Mohd Omar, Mohd Hasbullah Katuk, Norliza Raziff, Abdul Rafiez Abdul Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Kuala Lumpur50603 Malaysia School of Computing Universiti Utara Malaysia Kedah Sintok06010 Malaysia Kulliyyah of Information and Communication Technology International Islamic University Malaysia Gombak Kuala Lumpur50728 Malaysia

ISBN: (纸本)9789819995882

We live in an information world where visual data undergo exponential growth within a very short time window. With diverging content diversity, we simply have no capacity to keep track of those data. While short video platforms (such as TikTok™ or YouTube Shorts™) can helped users viewing relevant videos within the shortest time possible, those videos might have misleading information, primarily if it is derived from long videos. Here, we analyzed several short videos (in terms of movie trailers) from YouTube and established a correlation between one movie trailer and the classified movie genre based on the emotion found in the trailer. This paper contributes to (1) an efficient framework to process the movie trailer and (2) a correlation analysis between the movie trailer and movie genre. We found that every movie genre can be represented by two unique emotions. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Face recognition

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：