检索结果-内蒙古大学图书馆

Classification of Cacao Pods Ripeness Using Convolutional Neural Networks

Procedia Computer Science 2025年 257卷 1197-1204页

作者： Karl O. Borromeo Melbert R. Bonotan Archie P. Llagas Joana Marie O. Juan Philip Donald C. Sanchez Nathan Kit A. Berro Department of Computer Science College of Computing and Information Sciences Caraga State University Butuan City Philippines Department of Information Technology College of Computing and Information Sciences Caraga State University Butuan City Philippines Center for Resource Assessment Analytics and Emerging Technologies College of Engineering and Geo-Sciences Caraga State University Butuan City Philippines Department of Information Systems College of Computing and Information Sciences Caraga State University Butuan City Philippines

This paper presents methods for the development of Ripeness Identification of Cacao Pods using Convolutional Neural Network (CNN) and precision agriculture employed in a Mobile Application. This research explores if there is a correlation between the color dynamics of cacao pods and its physiological characteristics, and the possibility of using this correlation to develop Artificial Intelligence (AI) model for ripeness and variety identification, which conventional eye estimation resulted to unripe and overripe harvesting of Cacao Pods. Data analysis and correlation was developed, integrating detection and classification models based on the Single Shot Detection (SSD) MobileNet and Visual geometry Group (VGG) 16 or VGG16 layers network architectures, respectively. The mobile application utilizes the TensorFlow template for object detection and incorporates image preprocessing techniques for enhanced accuracy. The successful integration of the model into a mobile application demonstrates its potential for practical applications in the cacao industry.

关键词： Cacao Physiological Properties Convolutional Neural Network CNN Deep Learning Ripeness Identification Precision Agriculture

来源：评论

学校读者我要写书评

暂无评论

VI-SLAM2tag: Low-Effort Labeled Dataset Collection for Fingerprinting-Based Indoor Localization

arXiv

引用

arXiv 2022年

作者： Laska, Marius Schulz, Till Grottke, Jan Blut, Christoph Blankenbach, Jörg Geodetic Institute and Chair for Computing in Civil Engineering & Geo Information Systems RWTH Aachen University Aachen Germany

Fingerprinting-based approaches are particularly suitable for deploying indoor positioning systems for pedestrians with minimal infrastructure costs. The accuracy of the method, however, strongly depends on the quality of collected labeled fingerprints within the calibration phase, which is a tedious process when done manually in a static fashion. We present VI-SLAM2tag, a system for auto-labeling of dynamically collected fingerprints using the visual-inertial simultaneous localization and mapping (VI-SLAM) module of ARCore. ARCore occasionally updates its internal coordinate system. Mapping the entire trajectory to a target coordinate system via a single transformation thus results in large drift effects. To solve this, we propose a strategy for determining locally optimal sub-trajectory transformations. Our system is evaluated with respect to the accuracy of the generated position labels using a geodetic tracking system. We achieve an average labeling error of roughly 50 cm for trajectories of up to 15 minutes, which is sufficient for fingerprinting-based localization. We demonstrate this by collecting a multi-floor dataset including WLAN and IMU data and show how it can be used to train neural network based models that achieve a positioning accuracy of roughly 2 m. VI-SLAM2tag and the dataset are made publicly available. © 2022, CC BY.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dynamic Dipper Throated Optimization for Feature Selection in Medical Data

引用

Computers, Materials & Continua 2023年第4期75卷 1883-1900页

作者： Ghada Atteia El-Sayed M.El-kenawy Nagwan Abdel Samee Mona M.Jamjoom Abdelhameed Ibrahim Abdelaziz A.Abdelhamid Ahmad Taher Azar Nima Khodadadi Reham A.Ghanem Mahmoud Y.Shams Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Faculty of Computers and Artificial Intelligence Benha UniversityBenha13518Egypt College of Computer and Information Sciences Prince Sultan UniversityRiyadh11586Saudi Arabia Department of Civil Engineering University of Science and TechnologyMiami33101USA Department of Civil and Environmental Engineering Florida International UniversityMiamiUSA Oral Biology Department Faculty of Oral and Dental MedicineDelta University for Science and TechnologyGamasaEgypt Faculty of Artificial Intelligence Kafrelsheikh UniversityKafrelsheikh33511Egypt

The rapid population growth results in a crucial problem in the early detection of diseases inmedical *** all the cancers unveiled,breast cancer is considered the second most severe ***,an exponential rising in death cases incurred by breast cancer is expected due to the rapid population growth and the lack of resources required for performing medical *** recent advances in machine learning could help medical staff in diagnosing diseases as they offer effective,reliable,and rapid responses,which could help in decreasing the death *** this paper,we propose a new algorithm for feature selection based on a hybrid between powerful and recently emerged optimizers,namely,guided whale and dipper throated *** proposed algorithm is evaluated using four publicly available breast cancer *** evaluation results show the effectiveness of the proposed approach from the accuracy and speed *** prove the superiority of the proposed algorithm,a set of competing feature selection algorithms were incorporated into the conducted *** addition,a group of statistical analysis experiments was conducted to emphasize the superiority and stability of the proposed *** best-achieved breast cancer prediction average accuracy based on the proposed algorithm is 99.453%.This result is achieved in an average time of 3.6725 s,the best result among all the competing approaches utilized in the experiments.

关键词： Medical dataset breast cancer guided whale optimizer dipper throated optimizer feature selection meta-heuristics

来源：评论

学校读者我要写书评

暂无评论

Improved Level-Set Methods for Particle Reconstruction from X-Ray Computed Tomography Images

SSRN

引用

SSRN 2024年

作者： Wang, Tingxuan Fei, Wenbin Ehinger, Krista A. Drummond, Tom W. Narsilio, Guillermo A. School of Computing and Information Systems The University of Melbourne Parkville Australia College of Civil Engineering Hunan University Hunan Changsha410082 China Department of Infrastructure Engineering The University of Melbourne Parkville Australia

In granular materials, heat and fluid flow properties are largely controlled by their 3D microstructure. With recent advancements in image-based network modelling, heat transfer and fluid dynamic physics can be confidently simulated. The accuracy of network models is reliant on precise 3D reconstruction of particles from X-ray computed tomography (XRCT);however, the current workflow based on combining watershed algorithms with level set methods requires subjective manual inputs in pre-processing and controllability in optimization. To address these problems, this paper proposes an automated workflow that achieves high precision in 3D reconstruction of particles. Instances of over-segmentation in watershed algorithm were eliminated by utilising morphological dilation, providing clean inputs for a controlled level set optimisation that separately consider the parts of energy function relevant for boundary quality. The results of our proposed level set method were validated with paired multi-resolution images, exhibiting consistent and significant improvements on smooth particle boundary, correct particle volume and inter-particle contact area, compared with the current method across samples of nearly spherical Ottawa Sands and irregular Angular Sands. © 2024, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Al-Biruni Earth Radius(BER)Metaheuristic Search Optimization Algorithm

引用

Computer systems Science & engineering 2023年第5期45卷 1917-1934页

作者： El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Seyedali Mirjalili Nima Khodadad Mona A.Al duailij Amel Ali Alhussan Doaa Sami Khafaga Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Centre for Artificial Intelligence Research and Optimization Torrens University AustraliaFortitude ValleyQLD 4006Australia Yonsei Frontier Lab Yonsei UniversitySeoul03722Korea Department of Civil and Environmental Engineering Florida International UniversityMiamiUSA Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

Metaheuristic optimization algorithms present an effective method for solving several optimization problems from various types of applications and *** metaheuristics and evolutionary optimization algorithms have been emerged recently in the literature and gained widespread attention,such as particle swarm optimization(PSO),whale optimization algorithm(WOA),grey wolf optimization algorithm(GWO),genetic algorithm(GA),and gravitational search algorithm(GSA).According to the literature,no one metaheuristic optimization algorithm can handle all present optimization *** novel optimization methodologies are still *** Al-Biruni earth radius(BER)search optimization algorithm is proposed in this *** proposed algorithm was motivated by the behavior of swarm members in achieving their global *** search space around local solutions to be explored is determined by Al-Biruni earth radius calculation method.A comparative analysis with existing state-of-the-art optimization algorithms corroborated the findings of BER’s validation and testing against seven mathematical optimization *** results show that BER can both explore and avoid local *** has also been tested on an engineering design optimization *** results reveal that,in terms of performance and capability,BER outperforms the performance of state-of-the-art metaheuristic optimization algorithms.

关键词： Metaheuristics evolutionary optimization exploration exploitation mutation Al-biruni earth radius

来源：评论

学校读者我要写书评

暂无评论

Optimization of Shared Autonomous Electric Vehicles Operations

SSRN

引用

SSRN 2023年

作者： Ruan, Ning Andrew, Lachlan L.H. Vu, Hai L. Institute of Transport Studies Department of Civil Engineering Monash University Melbourne Australia School of Computing and Information Systems University of Melbourne Melbourne Australia

It has been proposed in the literature that on-demand mobility serviced by autonomous electric vehicles (AEVs) would replace buses for public transportation within the foreseeable future. In order to maintain their continuous operation, it will be necessary to schedule regular charging of these AEVs. To facilitate the coordinated charging of vehicles and efficiently transport passengers to their destinations, this paper proposes a model predictive control (MPC) framework as a single optimization problem that considers grid support, multiple occupancy, and limited availability of charging bays for a fleet of AVs ferrying passengers between pick-up points and their desired destinations. Their operation is evaluated by numerical simulations with parameters based on realistic values for vehicle efficiency, battery capacity, charge rates and battery losses. The results show that a larger fleet size decreases the energy consumption due to lower empty vehicle reallocation. Whether or not this results in eventual savings depends on whether vehicles are retired due to age or to the distance travelled. Furthermore, it has been shown using traces of Australian electricity spot prices that current variations in electricity price does not induce vehicle-to-grid activity. This may change when the majority of electricity comes from intermittent source such as wind and solar. © 2023, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

An adaptive large neighborhood search for the multi-vehicle profitable tour problem with flexible compartments and mandatory customers

引用

Applied Soft computing 2024年 156卷

作者： Yu, Vincent F. Salsabila, Nabila Yuraisyah Gunawan, Aldy Handoko, Anggun Nurfitriani Department of Industrial Management National Taiwan University of Science and Technology Taipei Taiwan Department of Civil and Environmental Engineering Portland State University PortlandOR97201 United States School of Computing and Information Systems Singapore Management University Singapore

The home-refill delivery system is a business model that addresses the concerns of plastic waste and its impact on the environment. It allows customers to pick up their household goods at their doorsteps and refill them into their own containers. However, the difficulty in accessing customers’ locations and product consolidations are undeniable challenges. To overcome these issues, we introduce a new variant of the Profitable Tour Problem, named the multi-vehicle profitable tour problem with flexible compartments and mandatory customers (MVPTPFC-MC). The objective is to maximize the difference between the total collected profit and the traveling cost. We model the proposed problem as Mixed Integer Linear Programming and present an Adaptive Large Neighborhood Search (ALNS) algorithm to solve it. Our ALNS outperforms the commercial solver, Gurobi, and Large Neighborhood Search (LNS), as proven by giving better solutions within reasonable computational times. Both ALNS and LNS can obtain optimal solutions for all small instances and three better solutions than Gurobi for medium problems. Furthermore, ALNS is also robust and effective in solving large MVPTPFC-MC, as proven by resulting in better solutions within less CPU time than LNS. Finally, more analyses are conducted to justify the utilization of flexible compartment sizes by comparing it with fixed compartment sizes and to evaluate the robustness of MVPTPFC-MC. The results show that utilizing flexible compartment sizes can yield more benefits than fixed compartment sizes, particularly when the fleet size is limited, and there are fewer mandatory customers to serve. © 2024 Elsevier B.V.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Unraveling adaptive changes in electric vehicle charging behavior toward the postpandemic era by federated meta-learning

引用

The Innovation 2024年第2期5卷 21-23页

作者： Linlin You Rui Zhu Mei-Po Kwan Min Chen Fan Zhang Bisheng Yang Man Sing Wong Zheng Qin School of Intelligent Systems Engineering Sun Yat-Sen UniversityShenzhen 518107China Institute of High Performance Computing(IHPC) Agency for ScienceTechnology and Research(A*STAR)1 Fusionopolis WaySingapore 138632Republic of Singapore Institute of Space and Earth Information Science Chinese University of Hong KongHong KongChina Key Laboratory of Virtual Geographic Environment(Ministry of Education) Nanjing Normal UniversityNanjing 210023China Institute of Remote Sensing and Geographical Information System School of Earth and Space SciencesPeking UniversityBeijing 100871China State Key Laboratory of Information Engineering in Surveying Mappingand Remote SensingWuhan UniversityWuhan 430079China Department of Land Surveying and Geo-Informatics The Hong Kong Polytechnic UniversityHong KongChina

Dear Editor,Electric vehicle(EV)sales have significantly grown over the years to fulfill growing demands for economic travel and greenhouse gas mitigation.1 However,the surge in the number of EVs has led to charging anxiety as users struggle to find an available charging station before running out of electricity,resulting in longer reserve and waiting times.2 Moreover,severe mobility restrictions caused by infectious diseases,such as coronavirus disease 2019(COVID-19),have greatly affected people’s travel behavior3,4 and hindered their willingness to use EVs,given that charging in public spaces consumes time and increases the risk of contracting the virus.5 This implies that in the postpandemic era,in which individuals coexist with the virus,the interplay between the two important trends,namely vehicle electrification and mobility restrictions,can extensively affect people’s daily commuting by using EVs.

关键词： travel behavior charging

来源：评论

学校读者我要写书评

暂无评论

Enhancing Low-Dose CT Image Quality Through Deep Learning: A DoG-Sharpened U-Net Approach With Attention Mechanism

Enhancing Low-Dose CT Image Quality Through Deep Learning: A...

引用

Emerging Technologies for Sustainability and Intelligent systems (ICETSIS), ASU International Conference in

作者： Muhammad Zubair Helmi B Md Rais Fasee Ullah Arsalaan Khan Yousafzai Farrukh Hassan Department of Computer and Information Sciences Universiti Teknologi PETRONAS Seri Iskandar Malaysia Department of Civil and Enviromental Engineering Universiti Teknologi PETRONAS Seri Iskandar Malaysia Department of Computing and Information Systems School of Engineering and Technology Sunway University Bandar University Sunway Selangor Darul Ehsan Malaysia

Computed Tomography (CT) scans utilize electromagnetic radiation. However, the excessive exposure of a patient's body during CT acquisition poses potential health risks. Subsequently, the integration of low-dose CT scans has resulted in an escalation of noise, artifacts, and a discernible decline in the overall quality of CT imaging, significantly impacting the diagnostic capabilities of Computer-Aided Diagnosis (CAD) system. Removing these noises and artifacts while preserving critical information is a challenging task. Traditional noise reduction algorithms are expensive, produce blurry results, and rely on challenging sinogram data. As a result, deep learning-based image-denoising approaches have emerged. This study introduces a DoG-UNet+ model which incorporates a novel layer called the “Difference of Gaussians (DoG) Sharpening Layer” into the U-Net architecture. This layer utilizes two distinct convolutional kernels, termed “fat” and “skinny,” aimed to capturing diverse scales of features. To increase the clinical detection precision, an attention mechanism has been added to focus on the critical features in CT images. This model has been compared with the most recent algorithms based on the Peak Signal-to-Noise Ratio (PSNR), Root Mean Squared Error (RMSE), and Structural Similarity Index (SSIM). The outcomes showed superior performance of DoG-UNet+ model, showcasing promising and notable results compared to existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding order cancellation behavior in on-demand delivery services

引用

Transportation Research Part A: Policy and Practice 2025年 198卷

作者： Liang, Jian Zhao, Ya Wang, Hai Yang, Linchuan Ke, Jintao Department of Civil Engineering the University of Hong Kong Hong Kong Department of Urban Planning and Design the University of Hong Kong Hong Kong School of Computing and Information Systems Singapore Management University Singapore Department of Urban and Rural Planning School of Architecture Southwest Jiaotong University Chengdu China

The rise of digital platforms has transformed urban mobility by offering a wide range of on-demand transportation and delivery services, such as ride-hailing, grocery delivery, and food delivery. Consumers using these services typically experience two key waiting stages: waiting online for matching and waiting physically for driver pick-up. A common consequence of waiting is order cancellation, which not only disrupts platform operations but also generates inefficient vehicle movements and puts strain on urban road networks. This paper examines the dynamics of order cancellations in the two stages and their interactions by using a two-stage survival analysis combined with a Heckman correction model. Based on a dataset of delivered and cancelled orders from an on-demand food delivery platform in Asia, we reveal several key findings. First, we identify an asymmetric effect of accumulated waiting time on cancellations before and after the expected waiting time, which provides evidence to the existence of reference-dependence preferences in on-demand services. Second, while higher delivery fees reduce cancellations in the matching stage, they increase the risk of orders being cancelled shortly after they are matched to drivers. Third, the risk of cancellation is significantly reduced when the order is delivered by a familiar driver. Lastly, we reveal how the risk of order cancellation varies with waiting time in both the matching and pick-up stages. These findings provide valuable insights for optimizing pricing and matching strategies to mitigate order cancellations, enhance the efficiency of on-demand services, and reduce inefficient trips caused by cancellations. © 2025 Elsevier Ltd

关键词： Urban transportation

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：