检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Huang, Zhixing Mei, Yi Zhang, Fangfang Zhang, Mengjie Banzhaf, Wolfgang Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Victoria University of Wellington Wellington6140 New Zealand Department of Computer Science and Engineering BEACON Center for the Study of Evolution in Action and Ecology Evolution and Behavior Program Michigan State University East LansingMI48864 United States

Existing genetic programming (GP) methods are typically designed based on a certain representation, such as tree-based or linear representations. These representations show various pros and cons in different domains. However, due to the complicated relationships among representation and fitness landscapes of GP, it is hard to intuitively determine which GP representation is the most suitable for solving a certain problem. Evolving programs (or models) with multiple representations simultaneously can alternatively search on different fitness landscapes since representations are highly related to the search space that essentially defines the fitness landscape. Fully using the latent synergies among different GP individual representations might be helpful for GP to search for better solutions. However, existing GP literature rarely investigates the simultaneous effective use of evolving multiple representations. To fill this gap, this paper proposes a multi-representation GP algorithm based on tree-based and linear representations, which are two commonly used GP representations. In addition, we develop a new cross-representation crossover operator to harness the interplay between tree-based and linear representations. Empirical results show that navigating the learned knowledge between basic tree-based and linear representations successfully improves the effectiveness of GP with solely tree-based or linear representation in solving symbolic regression and dynamic job shop scheduling problems. © 2024, CC BY.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Image Processing Implementation to Classify Coffee Fruit Ripeness Using K-Nearest Neighbor (KNN) Algorithm 8

Image Processing Implementation to Classify Coffee Fruit Rip...

引用

8th International Conference on Information Management and Technology, ICIMTech 2023

作者： Hussaini Dermawan, M. Farhan Witarsyah, Deden Syamsuar, Dedy Fakhrurroja, Hanif Luthfi, Ahmad Herdiansyah, Muhammad Izman Telkom University Faculty of Industrial Engineering Bandung Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Islamic University of Indonesia Faculty of Industrial Technology Department of Informatics Jogjakarta Indonesia Universitas Bina Darma Informatics Study Program Faculty of Science and Technology Palembang Indonesia

ISBN: (纸本)9798350326093

Coffee is one of the plantation crops that has long been a cultivated plant in Indonesia. The classification of coffee fruit maturity manually still has several weaknesses and requires a long process, has low accuracy and is inconsistent, this is because the determination is made subjectively by coffee farmers. As for the classification of coffee fruit maturity levels automatically, it can be faster with objective determination, therefore the use of image processing is relatively easier, faster, and based on a quantified descriptive assessment to determine coffee maturity. Image Processing is a method used to process or manipulate images in 2-dimensional form. In the classification process, there are many methods used to obtain classification of objects based on training data. One of the algorithms used for the classification process is K-Nearest Neighbor (KNN). KNN is a classification technique for objects based on training data that is the closest or has similar characteristics to the object. KNN includes supervised learning algorithms, where the results of the new query instance are classified based on the majority of the categories in K-Nearest Neighbors (K-NN). The finding indicated that class classification of ripe and unripe were 88,24 % and 100% respectively with 93,33% accuracy level. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Measuring the Complexity of EMG Signal by Using Fuzzy Approximate Entropy in Post-Stroke Patients Rehabilitation

引用

Journal of engineering science and Technology Review 2021年第3期14卷 85-90页

作者： Rulaningtyas, Riries Prasetyo, Angga Bagus Rahmatillah, Akif Putra, Alfian Pramudita Rahma, Osmalina Nur Ain, Khusnul Pawana, I Putu Alit Biomedical Engineering Study Program Department of Physics Faculty of Science and Technology Universitas Airlangga Surabaya Indonesia Department of Physical Medicine and Rehabilitation School of Medicine Universitas Airlangga Dr. Soetomo General Academic Hospital Surabaya Indonesia

Stroke is one of world’s highest medical cases that cause physical or mental problem, even death. The treatment for overcoming stroke so far was by conducting rehabilitation or therapy. The therapy progress could be seen over the improvement indicated by stroke patients after participation in rehabilitation program. So far, the assessment of the level of development exhibited by stroke patients are still subjective. Meanwhile, Electromyograph (EMG) can be used as a quantitative method to evaluate the patient's improvement. The complexity of the EMG signal could define the progress of a rehabilitation process related to muscle function. One of the methods to calculate the complexity is fuzzy approximate entropy (fApEn). This study aims to propose fApEn as a quantitative method to evaluate the condition of stroke patients by comparing the complexity of the normal EMG, affected, and unaffected side limb of the patient's EMG signal. The value of fApEn on Subject 1 showed that the affected side obtained the complexity of 0.18141 and on the unaffected side of 0.80740. Subject 2 showed the complexity on the affected side of 0.58597 and the unaffected side of 1.02787, whereas the healthy subjects showed the complexity of 2.07856. The statistical results showed that the data were homogeneous and normally distributed. There was a significant difference between the results of fApEn on the affected side and the unaffected side. Thus, fApEn could be used as a quantitative method to determine the condition of muscle activity. © 2021 School of science, IHU. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Implementation of AI-Based Support Vector Machine Algorithm for Fraud Detection in Digital Payment Systems

Implementation of AI-Based Support Vector Machine Algorithm ...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Edy Prayitno Rikie Kartadie Uning Lestari Munengsih Sari Bunga Accounting Information Systems Faculty of Information Technology Universitas Teknologi Digital Indonesia Yogyakarta Indonesia Computer Engineering Study Program Faculty of Information Technology Universitas Teknologi Digital Indonesia Yogyakarta Indonesia Informatics Study Program Faculty of Science and Information Technology Universitas Akprind Indonesia Yogyakarta Indonesia Department of Computer Engineering Smart City Information Systems Politeknik Negeri Indramayu Indramayu Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

The increasing use of digital payment systems has led to a rise in fraudulent activities, presenting a significant challenge in ensuring secure transactions. This research focuses on implementing the Support Vector Machine (SVM) algorithm with a Radial Basis Function (RBF) kernel to detect fraud in digital payment systems. One of the main challenges addressed in this study is the severe class imbalance in the dataset, where fraudulent transactions account for only 0.17% of total transactions. To overcome this, the SMOTE (Synthetic Minority Over-sampling Technique) method was applied to balance the dataset, allowing the model to better recognize fraudulent patterns. The results indicate that the SVM model achieved an accuracy of 99.93%, with a precision of 86.23% and a recall of 75.51%. These results demonstrate that SVM, combined with SMOTE and RBF kernel, is highly effective in detecting fraudulent transactions while minimizing false positives. This research provides a strong foundation for improving fraud detection models in the context of digital payment systems, offering enhanced security and trust for users. Further research could explore hybrid models and real-time data analysis to improve performance.

关键词： Support vector machines Seminars Adaptation models Accuracy Data models Real-time systems Fraud Security Kernel Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Implementation of Malaria Detection Using MobileNetV2 Pretrained Model for Improved Deep Learning Based Diagnostics

Implementation of Malaria Detection Using MobileNetV2 Pretra...

引用

International Conference on Computing, engineering, and Design (ICCED)

作者： Rahmat Hidayat Achmad Solichin Adhitia Erfina Sudin Saepudin Muhamad Muslih Mohd Zainuri Saringat Master of Computer Science Budi Luhur University Jakarta Indonesia Information Systems Study Program Nusa Putra University Sukabumi Indonesia Department of Software Engineering Faculty of Computer Science and Information Technology Tun Hussein Onn Malaysia University

ISBN: (数字)9798331529376

ISBN: (纸本)9798331529383

The Plasmodium parasite, which causes malaria, is an acute fever illness that infects people when a female Anopheles mosquito bites them. It is predicted that malaria would claim 619,000 lives in 2021, with 96% of those deaths occurring in the African continent. We can achieve this by using a microscope to examine thick and thin blood smears. The proficiency of a microscope examiner is crucial for doing microscopic examinations. Consider how time-consuming, ineffective, and costly it would be to examine thousands of malaria cases. Consequently, Creating an automated method for detecting malaria parasites is the aim of this study. We employ a MobileNetV2 pretrained model with CNN technology. Because it has been trained on dozens or even millions of data points, this pretrained model is incredibly light but dependable. There are two main benefits of automatic malaria parasite detection: firstly, it can offer a more accurate diagnosis, particularly in locations with limited resources; secondly, it lowers diagnostic expenses. The optimizer utilizes Adam Weight, the criteria uses NLLLoss, and the model is trained using 32 for batch_size. In the fourteenth epoch, we obtained the maximum accuracy score of 96.26% based on the training data. The outcomes of the predictions demonstrate how excellent this score is. EfficienceNet, DenseNet, AlexNet, and other pretrained models are among the alternatives that scientists are advised to try training with.

关键词： Training Adaptation models Accuracy Costs Malaria Microscopy Data visualization Training data Cost function Data models

来源：评论

学校读者我要写书评

暂无评论

IoT System for Floating Raft Hydroponics: Nutrient Monitoring and Automation 13

IoT System for Floating Raft Hydroponics: Nutrient Monitorin...

引用

13th International Physics Seminar 2024, IPS 2024

作者： Purwalaksana, A.Z. Wahyu, S. Ndari, W.E.W. Syah, S.A. Rismawati, E. Kusumadjati, A. Suharmanto, P. Department of Physics Universitas Negeri Jakarta Jl. Rawamangun Muka Jakarta13220 Indonesia Department of Physics Education Universitas Negeri Jakarta Jl. Rawamangun Muka Jakarta13220 Indonesia Physics Study Program Indonesia Defense University IPSC Sentul Area West Java16810 Indonesia Department of Industrial Engineering Faculty of Engineering and Computer Science Universitas Indraprasta PGRI Jl. Nangka Raya No.58 C Jakarta12530 Indonesia

The utilization of hydroponic cultivation in agriculture is increasing due to its high productivity even in limited spaces. However, in practice, monitoring and controlling nutrients in hydroponic systems often require intensive human supervision and intervention. This issue can be addressed through technological advancements, particularly with the adoption of microcontrollers, sensors, and the Internet of Things (IoT). Previous research has developed IoT-based monitoring and control systems for DFT hydroponics using the Blynk platform. This study aims to develop an IoT-based nutrient monitoring and automation system for floating raft hydroponics. Floating raft hydroponics was chosen for its simplicity, lower installation costs, and space optimization. The system developed in this study uses the HC-SR04 ultrasonic sensor with an average error of 1.229%, the DS18B20 water temperature sensor with an error of 0.415%, and the TDS sensor with an error of 2.055%. The sensor and actuator measurement data are presented via the Antares Web. This research has the potential to minimize the necessity for manual intervention in hydroponic systems, thereby enhancing both efficiency and consistency in nutrient delivery. © Published under licence by IOP Publishing Ltd.

关键词： Hydroponics

来源：评论

学校读者我要写书评

暂无评论

Smart Home Gas Sensor Optimization Using Kalman Filter for Data Processing

Smart Home Gas Sensor Optimization Using Kalman Filter for D...

引用

International Conference on Informatics and Computing (ICIC)

作者： Somantri Muhamad Ikhsan Thohir Alun Sujjada Deni Setiawan Ilham Komara Fikri Ardiansyah Efendi Muhamad Muslih Zubaile Bin Abdullah Mohd Zainuri Saringat Department of Software Engineering University Tun Hussein Onn Malaysia Informatics Engineering Study Program Nusa Putra University Sukabumi Indonesia Informatics Engineering Study Program Nusa Putra University Sukabumi Indonesia Department of Software Engineering University Tun Hussein Onn Malaysia Sukabumi Indonesia Department of Information System Nusa Putra University Sukabumi Indonesia Department of Software Engineering Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Johor Bahru Malaysia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

The integration of Internet of Things (IoT) technologies into modern homes has enhanced safety and comfort, particularly in detecting gas leaks, which pose serious fire hazards. Gas leaks can often be detected by smell, but this method fails when no one is present. Previous research using microcontrollers and sensors to detect gas leaks faced challenges with accuracy due to noise interference. This paper proposes the use of a Kalman filter, developed by Rudolf Emil Kalman in 1960, to improve gas leak detection accuracy by filtering out noise. The system comprises an Arduino Nano, ESP8266 WiFi module, MQ-2 gas sensor, buzzer, and ThingSpeak cloud platform. By applying the Kalman filter, noise and data oscillations are reduced, enhancing detection accuracy. Experimental results show the system effectively detects gas leaks, provides real-time data, and triggers alarms. Future improvements could include additional sensors and features to further increase the system’s reliability and functionality.

关键词： Accuracy Noise Sensor phenomena and characterization Sensor systems Real-time systems Kalman filters Internet of Things Reliability Leak detection Gas detectors

来源：评论

学校读者我要写书评

暂无评论

Propolis nanoemulsion extract from celebes stingless bee (Tetragonula biroi) phytochemistry and antibacterial analysis to periodontopathogen bacteria

引用

Journal of Oral Biology and Craniofacial Research 2025年第3期15卷 576-584页

作者： Amalia, Nadya Rafika Budhy, Theresia Indah Ridwan, Rini Devijanti Rianti, Devi Bramantoro, Taufan Luthfi, Muhammad Ramadhani, Nastiti Faradilla Pramusita, Adya Putranti, Nurul Aisyah Rizki Nugraha, Albertus Putera Situmorang, Putri Cahaya Shariff, Khairul Anuar Nugraha, Alexander Patera Dental Health Science Study Program Faculty of Dental Medicine Universitas Airlangga Surabaya Indonesia Department of Oral and Maxillofacial Pathology Faculty of Dental Medicine Universitas Airlangga Surabaya Indonesia Department of Oral Biology Faculty of Dental Medicine Universitas Airlangga Surabaya Indonesia Department of Dental Material Faculty of Dental Medicine Universitas Airlangga Surabaya Indonesia Department of Dental Public Health Faculty of Dental Medicine Universitas Airlangga Surabaya Indonesia Department of Dentomaxillofacial Radiology Faculty of Dental Medicine Universitas Airlangga Surabaya Indonesia Department of Orthodontic Faculty of Dental Medicine Universitas Airlangga Surabaya Indonesia Faculty of Medicine Universitas Airlangga Surabaya Indonesia Biology Study Program Faculty of Mathematics and Natural Sciences Universitas Sumatera Utara Medan Indonesia School of Materials and Mineral Resources Engineering Engineering Campus Universiti Sains Malaysia Penang Nibong Tebal 14300 Malaysia

Background: Propolis from Sulawesi's stingless bees (Tetragonula biroi) contains antioxidants, more flavonoids than propolis from Apis bees, and the antibacterial ability. Objective: to examine the antibacterial properties of Propolis Nanoemulsion Extract (PNE), which is extracted from the Celebes Stingless Bee (T. biroi), in relation to the periodontopathogen bacteria such as Fusobacterium nucleatum (Fn), Porphyromonas gingivalis (Pg), Aggregatibacter actinomycetemcomitans (Aa), and Provotella intermedia (Pi). This investigation also examines PNE's phytochemistry, particle size analysis (PSA), and zeta potential. Methods: The maceration process with 96 % ethanol was used to create PNE from Celebes stingless bee (T. biroi), which was then subjected to zeta potential measurement and PSA. Phytochemical analysis was used to identify phytochemical constituents in the PNE (T. biroi). Diffusion zone, minimum bactericidal concentration (MBC), and minimum inhibitory concentration (MIC) were used to assess antibacterial efficacy against Aa, Pg, Pi, and Fn. Furthermore, the statistical analysis was used to extract the data. Results: Phenols, alkaloids, and flavonoids were identified;however, triterpenoids and saponins were not. Between 151.28 and 182.2 diameter nanometers (***) was the range of the PNE's diameter. At 1.56 % propolis (T. biroi) concentration, the MIC, MBC, and diffusion zone analysis performed better than at 0.76 %, with a significant difference (p:0.01;p < 0.05) to Aa, Pg, Pi, and Fn. Conclusions: The highest antibacterial activity against Aa, Pg, Pi, and Fn as periodontopathogen bacteria is demonstrated by alkaloids, flavonoids, and phenols in PNE from Celebes (T. biroi) at a concentration of 1.56 %. © 2025 The Authors

关键词： Antibacterial Communicable disease Infectious disease Medicine Periodontal disease

来源：评论

学校读者我要写书评

暂无评论

An Evaluation of Number of Pixels Change Rate (NPCR) in Symetric Cryptography Based on Data Encryption Standard (DES)

An Evaluation of Number of Pixels Change Rate (NPCR) in Syme...

引用

International Seminar on Application for Technology of Information and Communication (ISemantic)

作者： Muhammad Rizky Naufal Christy Atika Sari Eko Hari Rachmawanto Lekso Budi Handoko Folasade Olubusola Isinkaye Wisam Subhi Talib Al-Dayyeni Study Program in Informatics Engineering University of Dian Nuswantoro Semarang Indonesia Department of Computer Science Ekiti State University Ekiti Nigeria School of Information Technologies and Engineering ADA University Baku Azerbaijan

Data Encryption Standard (DES) is a symmetric encryption algorithm that uses a single key to encrypt and decrypt information. In addition, the cipher text will be hidden inside an image using Stepic. DES Encryption use symmetric encryption to encrypt and decryption to decrypt. It will secure the symmetric encryption and maintain the speed of the encryption and decryption. The result of this study is the lowest error that we got as the Mean Square Error (MSE) is 0.00% and is inversely proportional with the Peak Signal to Noise Ratio (PSNR) and Avalanche with 79.36% and 34.91% in order that is not stable for result of Avalanche Effect (AVA). Inversely proportional to the length of the text that is hidden in the image, the longest text that is hidden, the more changes that we get in the image with the highest Unified Average Changing Intensity (UACI) and Number of Pixels Change Rate (NPCR) with the biggest image size with 43.47% for UACI and 99.87% for the NPCR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The effect of lard concentration and ozonation on changes in polarization angle of olive oil 10

The effect of lard concentration and ozonation on changes in...

引用

10th International Seminar on New Paradigm and Innovation of Natural sciences and itsApplication, ISNPINSA 2020

作者： Saputra, F.A. Azam, M. Arianto, F. Sofjan, K.F. Sugito, H. Alkian, I. Department of Physics Faculty of Science and Mathematics Diponegoro University Semarang50275 Indonesia Study Program of Automation Engineering Technology Vocational School Diponegoro University Indonesia

This research aims to analyze the effect of ozone exposure time and lard mixture on the polarization angle of transmission of olive oil. The study uses a transmission polarization method with a laser (λ = 532 nm) as a light source. The research sample in the form of olive oil mixed with lard at a concentration of 10, 20, 40, and 80%, with an ozone exposure time of 0-30 minutes. The sample is subjected to external electric fields with variations from 0-4.5 x 102 kV/m to increase the change's polarization angle. The results showed that the change in polarization angle would change linearly with the increase in lard concentration with olive oil. Olive oil with a low concentration of lard (10%) experienced an increase in the change in polarization angle with a value of 0.31 due to the effect of 90 minutes of ozone exposure. In general, the results of the study showed that increased concentrations of lard, ozone exposure time, electric field strengths caused an increase in changes in the polarization angle in a mixture of olive oil and lard. © Published under licence by IOP Publishing Ltd.

关键词： Mixtures

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：