检索结果-内蒙古大学图书馆

3D-SCUMamba: An Abdominal Tumor Segmentation model

IEEE Access 2025年 13卷 98362-98373页

作者： Juwita Hassan, Ghulam Mubashar Datta, Amitava Departement of Computer Science and Software Engineering The University of Western Australia Australia Departemet of Informatics University of Syiah Kuala Indonesia

Identification and segmentation of tumors from CT scans are essential for early detection and effective treatment but they remain challenging due to imaging artifacts and significant variability in tumor location, size, and morphology. Existing deep learning models typically adopt encoder-decoder architectures integrating convolutional layers with global dependency modeling to capture broader contextual information around tumors. Capturing global dependencies is critical, as local information alone often inadequately distinguishes tumors, especially given their diverse sizes, complex shapes, and interference from imaging artifacts. Recent advancements observe the emergence of the convolution-transformer architecture, which improves segmentation performance on the cost of substantial computational resources. In this article, we propose 3D-SCUMamba, an innovative architecture strategically integrating State Space Modeling- Based deep learning (Mamba) within the bottleneck of the encoder-decoder structure to overcome the limitations of existing segmentation networks. The proposed model efficiently models global dependencies while maintaining stable training dynamics and efficient inference. Additionally, we introduce a novel Spatio-Context (SC) module utilizing 3D convolutions without pooling to enhance feature representations and reduce information loss commonly associated with pooling operations. The SC module effectively prepares summarized features for robust global dependency processing by the Mamba component. 3D-SCUMamba explicitly addresses the prevalent limitations in current deep learning methods by prioritizing robust feature representation, training stability, and substantial accuracy *** evaluations conducted on three medical imaging datasets: MSD Pancreas Tumor, MSD Colon Tumor, and Synapse BTCV, demonstrate that computationally efficient 3D-SCUMamba consistently outperforms state-of-the-art methods with segmentation accuracy improve

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Obstacle Detection and Tracking System for Robot Soccer ERSOW based on Centroid Tracking Method 25

Obstacle Detection and Tracking System for Robot Soccer ERSO...

引用

25th International Electronics Symposium, IES 2023

作者： Wardhana, Vega Kurnia Garindra Wibowo, Iwan Kurnianto Bachtiar, Mochamad Mobed Politeknik Elektronika Negeri Surabaya Departement of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

EEPIS Robot Soccer on Wheeled (ERSOW) is a wheeled soccer robot developed by Politeknik Elektronika Negeri Surabaya and participated in the national robot competition, Indonesian Robot Contest in KRSBI Wheeled division. ERSOW team has striker robot, striker robot was used in attack strategy for scoring goals. The ability to tracking the obstacle is one of main abilities that striker robot must has. Obstacle tracking plays a crucial role in robot soccer on wheels due to the dynamic and unpredictable nature of the game. As robots navigate the field, they encounter various obstacles such as opponents, teammates, and static objects (obstacle). Accurate and real-time tracking of these obstacles enables robots to make informed decisions, adapt their strategies, and effectively interact with the environment. Obstacle tracking enhances situational awareness. By continuously monitoring the positions and movements of obstacles, robots gain valuable information about the current game state. Tracking system on this research works with centroid tracking algorithm. The fundamental concept of the centroid tracking algorithm revolves around assigning a distinct identification (ID) to every tracked object by taking their centroids, this algorithm takes the center of obstacle bounding box as an input, to generated bounding box this system used thresholding detection method based on HSV color space. The center of bounding box (in pixel coordinate) converted into world coordinate by using Ab-exponential regression and Linear regression. The testing results of tracking system could estimate obstacle from 50cm-250cm from the robot with 0,967 cm error average, the system also could track the obstacle with 86% accuracy when the robot moved 330 cm ahead. © 2023 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Smart Paddy Rice Plant Monitoring System Based on Soil and Leaf Quality Integrated with PadiSense Mobile Apps 11

Smart Paddy Rice Plant Monitoring System Based on Soil and L...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Rahmadewi, Reni Latifa, Ulinnuha Padilah, Tesa Nur Sutiyana, Agus Husna, Fitria Nurul Sandi Syafri, Edi College of Singaperbangsa Karawang Departement of Electrical Engineering Karawang Indonesia College of Singaperbangsa Karawang Departement of Informatics Engineering Karawang Indonesia College of Pertanian Negeri Payakumbuh Departement of Agricultural and Computer Science Lima Puluh Kota Indonesia

ISBN: (纸本)9798350389654

Indonesia is well known as a country that relies on agricultural sector as the main source of livelihood. Over time, the management of agricultural products has evolved towards more advanced conventional practices, incorporating new technologies. Therefore, this research examined the measurement process of soil pH, soil moisture, and identification of fertilizer requirements through a scanning system equipped with color sensors integrated into the PadiSense mobile applications. The purposive sampling method with a pH sensor and instrument measurement of 6.4 percent and 7.5 percent were used to conduct this research. The pH sensor-based measurement yielded an average pH of 7.6 percent and within the Neutral scale, meeting the criteria for optimal rice growth and development. The results obtained from measuring soil moisture proved optimal for the growth of rice stems, with an average of 71.7 percent to 74.1 percent at a minimal measurement error of 0.047 percent. In conclusion, the requirements for nitrogen were identified using color sensors, which showed the BWD scale, with an average measurement corresponding to BWD 4. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

SUPPORTING FARMING SMART DOCUMENTATION SYSTEM by MODULAR BLOCKCHAIN SOLUTIONS

Decision Making: Applications in Management and Engineering

引用

Decision Making: Applications in Management and engineering 2022年第1期5卷 1-26页

作者： Arsyad, Andi Arniaty Widayat, Irawan Widi Köppen, Mario Departement of Computer Science and Systems Engineering Graduate School of Creative Informatics Kyushu Institute of Technology Japan

For more than a decade, various farm-specific models have been developed by collaborating and integrating sensing technologies as a step toward successful data-farm documentation and effective decision-making. However, the stored and gathered data continues to rely on cloud infrastructure or centralized platform control, which is particularly vulnerable to threats such as data tampering, data distortion, confidentiality, and manipulation, which caused the farm product data difficult to trace to its provenance. The objective study in this paper proposes a farm transaction model by demonstrating a flow of farm transaction simulation implicated by Modular Block Chain(MBC) sensing instrument with an array of sensors, controllers, networking hardware, computing equipment, and internal memory functions to enhance data integrity and security farm object. Based on the proposed model, a proof-of-concept experimental system called Encapsulating Block Mesh (EBM) integrates blockchain technology with the specific application case of cocoa production has been implemented. Results have shown that farm objects represented by MBC take turn recording information on the process of generating, transacting, and consuming a farm product and encrypting it into a block was validated and linked in the EBM with the hash of transaction data that connected to each cocoa farm object in a simulation environment. The findings from this study are twofold: the approach has been shown to be feasible and effective, but also capable to be expanded to other stages of the food supply chain, such as manufacturing, supermarkets, food consumption (consumers), and recycling in real-world environments. © 2018 by the authors.

关键词： Food supply

来源：评论

学校读者我要写书评

暂无评论

Optimizing Item-based Collaborative Filtering for Course Recommendation: A Case Study with Coursera Data

Optimizing Item-based Collaborative Filtering for Course Rec...

引用

2024 International Conference on Information Technology Systems and Innovation, ICITSI 2024

作者： Suryani, Mira Pangestu, Risyad Pradana, Aditya Universitas Padjadjaran Departement of Computer Science Sumedang Indonesia Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798331511470

In e-learning environments, the sheer volume of available courses often overwhelms users, leading to decision fatigue and disengagement Learners vary widely in their preferences, learning styles, and goals, yet generic recommendations fail to account for these differences, resulting in suboptimal learning experiences. Therefore, personalized recommendations which are generally found in recommendation systems are needed especially in e-learning systems. Collaborative filtering is a popular method in recommendation systems, generating predictions by analyzing user ratings to forecast items of interest. This study implements an item-based collaborative filtering approach, calculating item similarity to recommend courses effectively. The study involves developing a web-based recommendation system utilizing a dataset of 623 Coursera courses and 1,454,711 course review entries. Prediction accuracy is enhanced through weighted sum and adjusted weighted sum calculations, employing cosine similarity and adjusted cosine similarity to refine similarity scores. Prediction errors are evaluated using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) metrics. Testing various K-nearest neighbor values reveals that an optimal K value of 150 yields an MAE of 0.4791 and an RMSE of 0.7882 for weighted sum predictions. For adjusted weighted sum predictions, an optimal K value of 160 produces an MAE of 0.4792 and an RMSE of 0.7638. These results highlight the effectiveness of item-based collaborative filtering in delivering accurate course recommendations and showcase the impact of similarity measures on predictive accuracy. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive IoT Home Medical Check-up Programming to Monitor Blood Sugar, Cholesterol, Uric Acid, and Body Temperature 5

Non-Invasive IoT Home Medical Check-up Programming to Monito...

引用

5th IEEE International Conference on computer and informatics engineering, IC2IE 2022

作者： Darmawan, Helmy Yusuf Sanubari, Agung Saida, Nur Fauzi, Rahmat Noor Ristiani, Nadia Oktivasari, Prihatin Wardhani, Rika Novita Riandini Politeknik Negeri Jakarta Departement of Electrical Engineering Departement of Informatics and Computer Engineering Depok Indonesia

ISBN: (数字)9781665453387

ISBN: (纸本)9781665453387

Non-invasive loT home medical check-up tool is a tool to check the temperature, uric acid, cholesterol, and blood sugar levels. The tool was designed using ESP32 WEMOS LOLIN 32 Lite as the micro controller, MLX90614 as the sensor to measure the temperature, and MAX30105 as the sensor to measure the uric acid, blood sugar, and cholesterol levels. To ensure the two sensors operated as expected, value readings were tested by programming the body temperature, uric acid, blood sugar, and cholesterol sensors and sending the results of sensor reading data to a database. The ccombination of sensor programming was tested when MAX30105 sensor detected IR, RED, and GREEN values, and it was compared to the BPM, Average BPM, and SP02 values and then conjoined with the MLX90614 sensor to detect temperature values. Data transmission testing was conducted by comparing the delivery time data on the ESP32 serial monitor with a database using the internet network, and the longest time difference in delivery was 0.091 seconds. © 2022 IEEE.

关键词： Cholesterol

来源：评论

学校读者我要写书评

暂无评论

A computer Vision System to Classify the Quality of Central Sulawesi Cocoa Beans Using Convolutional Neural Networks (CNN) 3

A Computer Vision System to Classify the Quality of Central ...

引用

3rd International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2023

作者： Angreni, Dwi Shinta Anshori, Yusuf Wirdayanti Arifin, Suci Ramadhani Humaira, Fitrah Maharani Universitas Tadulako Faculty of Engineering Departement of Information Technology Palu Indonesia Universitas Dipa Makassar Departement of Informatics Engineering Makassar Indonesia Politeknik Elektronika Negeri Surabaya Departemen of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350394559

The cocoa industry serves as a vital economic pillar, holding a pivotal role in the daily lives of farmers in Central Sulawesi. However, a prevailing challenge for cocoa cultivators in this region resides in the inherently subjective nature of cocoa bean quality assessment, often necessitating the involvement of a substantial human workforce. Addressing this challenge requires the implementation of computer vision technology capable of autonomously grading cocoa bean quality. Such a system not only expedites the evaluation process but also enhances the precision and consistency in determining the quality of the beans. The study employed Convolutional Neural Networks (CNN) methodology to analyze images of cocoa beans sourced from Central Sulawesi farmers. The research demonstrated a remarkable accuracy of 94.66%, accompanied by a minimal loss of 0.1195. The model demonstrates strong performance on both training and validation sets, indicating effective learning of relevant patterns. Consistent accuracy and loss trends across epochs signify stable training without notable overfitting or underfitting. The minimal gap between training and validation metrics reflects the model's effective generalization to unseen data. This technological integration promises to revolutionize cacao quality assessment, offering a sophisticated and efficient solution for the benefit of Central Sulawesi's cacao farming community. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Clustering Approach for Modeling Course Difficulty Level in Adaptive Learning

Clustering Approach for Modeling Course Difficulty Level in ...

引用

2024 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, CIVEMSA 2024

作者： Imamah Yuhana, Umi Laili Djunaidy, Arif Pardede, Eric Purnomo, Mauridhi Hery Departement of Electrical Engineering Faculty of Intelligent Electrical Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Departement of Informatics Faculty of Intelligent Electrical Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Departement of Information Systems Faculty of Intelligent Electrical Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Departement of Computer Science Information Technology La Trobe University BundooraVIC3086 Australia

ISBN: (纸本)9798350322996

The variations in students' abilities present challenges in achieving desired learning outcomes. Students exhibit different levels of comprehension regarding the complexity of learning materials. In this study, we aim to model the difficulty levels of learning materials using a clustering approach to offer personalized learning material recommendations within an adaptive learning framework. Data were collected from student scores of Data Structure course obtained between 2020 and 2022 at the University of Trunojoyo Madura. The dataset modeling process adheres to the CRISP-DM Methodology, employing the K-Means clustering method and Euclidean Distance. We employed the Within-Cluster Sum of Squares (WCSS) metric and silhouette score to identify the optimal K-value, which resulted in a value of 5, accompanied by a silhouette score of 0.629. Our analysis pinpointed Stack and Deque as the easiest, while Linked List emerged as the most challenging course material. Accordingly, we will assign a label of 1 to the easiest materials, 2 to those of medium difficulty, and 3 to the most challenging ones. These labels will serve as criteria for recommending suitable learning materials to students based on their knowledge level. We will assess the ratio between the overall knowledge level score and the difficulty level of the material. The ratio value will serve as a reference for determining material recommendations for students. Materials categorized with the highest difficulty levels are exclusively suggested to students demonstrating faster learning abilities with a high value of ratio, and vice versa. This approach is feasible for implementation in adaptive learning. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization of V2V Communication Reactive Routing Protocol Through Simulation Analysis 11

Performance Optimization of V2V Communication Reactive Routi...

引用

11th International Conference on Information Technology, computer and Electrical engineering, ICITACEE 2024

作者： Yogha Bintoro, Ketut Bayu Priyambodo, Tri Kuntoro Nurul Fitria, Dina Putra, Fajar Ariya Universitas Trilogi Departement of Informatics Engineering Jakarta Indonesia Gadjah Mada University Departement of Computer Science and Electronics Yogyakarta Indonesia Universitas Trilogi Departement of Agribussiness Jakarta Indonesia Board the National Energy Council of Republic of Indonesia Jakarta Indonesia

ISBN: (纸本)9798350389289

This study was conducted to explore and find the optimum parameters related to the Quality of Service (QoS) in Vehicle-to- Vehicle (V2V) communication within Vehicular Ad Hoc Networks (VANETs) by optimizing the Learning Automata-based Ad Hoc On-Demand Distance Vector protocol (LA-AODV). The study compared three variants of LA-AODV (LA-AODV(A), LA-AODV(B), and LA-AODV(C)) with the standard AODV. The simulation result evaluated their performance based on crucial QoS metrics such as FLOD ID, Packet Loss Ratio (PLR), Packet Delivery Ratio (PDR), Average Throughput, End-to-End Delay, and End-to-End Jitter. The results indicated that LA-AODV(B) consistently outperformed the other variants, particularly in FLOD ID. The improvements of 9.14%, 40.29%, and 22.79% in 50, 100, and 200-trial scenarios compared to LA-AODV(A) were significant. However, LA-AODV(C) showed suboptimal performance in the exact scenarios. Nevertheless, practical parameter tuning of LA-AODV(C) led to a remarkable improvement in protocol performance, with a 74% reduction in FLOD ID compared to AODV in various simulation scenarios. Parameter tuning is crucial for consistent efficiency in V2V communication, as LA-AODV's adaptability under different traffic conditions provides valuable insights. Our focus is on evaluating LA-AODV's performance in realistic scenarios. While we plan to compare it with established methods in the future, our current research allows us to understand its effectiveness in real-world V2V communication compared to standard AODV. We aim to expand our scope by comparing LA-AODV with other established methods in future studies. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis on Tripadvisor Hotel Review using Named Entity Recognition 5

Sentiment Analysis on Tripadvisor Hotel Review using Named E...

引用

5th International Conference on Information and Communications Technology, ICOIACT 2022

作者： Nalawati, Rizki Elisa Liliana, Dewi Yanti Nugrahani, Fitria Abiyanka, Faldan Hendra Karrel, Rhenald State Polytechnic of Jakarta Departement of Informatics and Computer Engineering Depok Indonesia

ISBN: (数字)9781665451406

ISBN: (纸本)9781665451406

Sentiment analysis is useful for understanding and grouping emotions including positive and negative in writing using natural language processing techniques. One form of sentiment analysis can be seen from people's reviews of products or services provided by a company. Reviews are excerpts, interpretations, and comments. Review can be interpreted as a form of assessment someone to something. regular review given to a product or service. good and bad reviews, may affect the reputation of the hotel. Good review indicates that the quality of service products must be maintained by the hotel. while the reviews are bad signifies that the quality of the service product must be evaluated and repaired by the hotel. Tripadvisor is a website that focuses on in the tourism sector such as tourist attractions, hotels, and restaurants. everyone can see the service rating a tourist attraction through Tripadvisor. Data hotel visitor reviews found on Tripadvisor, only classified by rating only stars from a scale of 10 to 50. Hotel visitors also provide various reviews to share their experiences during visit the hotel. Like experience dine, stay overnight, swim in the pool, etc. To facilitate the classification process based on review of the visitor's experience, then this research was made. In this research carried out sentiment analysis to distinguish negative reviews and positive using named entity method recognition. In previous research, the accuracy generated from the named entity recognition method reach 90%. © 2022 IEEE.

关键词： Hotels

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：