检索结果-内蒙古大学图书馆

4th International Conference on Electronic and Electrical Engineering and Intelligent System, ICE3IS 2024

作者： Suni, Alfa Faridh Utomo, Aryo Baskoro Fathoni, Khoiruddin Mahendra, Budiandra Yusuf Seinsiani, Izzati Gemi Hastawan, Ahmad Fashiha Universitas Negeri Semarang Computer Engineering Semarang Indonesia Universitas Negeri Semarang Electrical Engineering Semarang Indonesia Universitas Negeri Semarang Information Technology Education Semarang Indonesia Universitas Negeri Semarang English Literature Study Program Semarang Indonesia

ISBN: (纸本)9798350378368

The emergence of OpenAI's ChatGPT is paying a lot of attention to Generative AI and its impact on Academic integrity. Generative AI is a system designed to generate content or output such as text, image, audio, simulation, video and code based on their respective training data. ChatGPT itself is in the form of a chatbot where users can communicate with AI through dialogue applications via text. GPT 3 API is the technology behind the ChatGPT. However, interaction via text is not as flexible as dialogue using voice. Therefore, speech-to-text technology is needed to interface between the user and the AI. Chatbot AI powered by GPT3 with the optional voice UI powered by Google Text to Speech clearly benefits accessibility and usability. The output of dialogue between human users and AI can be done through text or sound. This research attempts to implement a Text to Speech and vice versa Speech to Text as a User Interface on a Gen-AI using the GPT 3 API so that it will be more user-friendly and accessible. This research opens many possibilities for human-AI interaction (HAX) in implementing virtual assistants. A seamless dialogue between humans and AI will be our goal in the future. © 2024 IEEE.

关键词： ChatGPT Generative AI Speech to Text Text to Speech

来源：评论

学校读者我要写书评

暂无评论

Syllables sound signal classification using multi-layer perceptron in varying number of hidden-layer and hidden-neuron 2

Syllables sound signal classification using multi-layer perc...

引用

2nd International Conference on Engineering and technology for Sustainable Development, ICET4SD 2017

作者： Kristomo, Domy Hidayat, Risanuri Soesanti, Indah Department of Electrical Engineering and Information Technology Universitas Gadjah Mada Grafika Street No. 2 Yogyakarta55281 Indonesia Study Program of Computer Engineering STMIK Akakom Yogyakarta Raya Janti Street 143 Karang Jambe Yogyakarta55198 Indonesia

The research on signal processing of syllables sound signal is still the challenging tasks, due to non-stationary, speaker-dependent, variable context, and dynamic nature factor of the signal. In the process of classification using multi-layer perceptron (MLP), the process of selecting a suitable parameter of hidden neuron and hidden layer is crucial for the optimal result of classification. This paper presents a speech signal classification method by using MLP with various numbers of hidden-layer and hidden-neuron for classifying the Indonesian Consonant-Vowel (CV) syllables signal. Five feature sets were generated by using Discrete Wavelet Transform (DWT), Renyi Entropy, Autoregressive Power Spectral Density (AR-PSD) and Statistical methods. Each syllable was segmented at a certain length to form a CV unit. The results show that the average recognition of WRPSDS with 1, 2, and 3 hidden layers were 74.17%, 69.17%, and 63.03%, respectively. © The Authors, published by EDP Sciences, 2018.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

An intelligent applied Fuzzy Logic to prediction the Parts per Million (PPM) as hydroponic nutrition on the based Internet of Things (IoT)

An intelligent applied Fuzzy Logic to prediction the Parts p...

引用

International Conference on Informatics and Computing (ICIC)

作者： Purnawarman Musa Herik Sugeru Haya Fadhila Mufza Faculty of Computer Science and Information Technology Universitas Gunadarma Indonesia Faculty of Industrial Technology Study Program of Agrotechnology Universitas Gunadarma Indonesia

Hydroponic plants require regular monitoring of plants that grow well and can even cause plants to die. Because too late in providing nutrition or getting too little or too little food or routine monitoring in the hydroponic system. The innovation proposed in the agricultural sector that we suggest is the process of monitoring hydroponic plants in real-time. This study aims to predict the excess or lack of nutrient content based on the results of routine monitoring and has the analytical ability to determine the prediction of the value of Parts per Million (PPM) to find the nutritional value of plant media. Measurement of nutritional value using Electrical Conductivity (EC) and the potential of Hydrogen (pH) in hydroponic plant media. In this research, using the NFT hydroponic system as the application of fuzzy logic with the Mamdani method to determine the predictions of PPM values in providing nutrients at plants to adjusting the nutritional at each plant (e.g., for water spinach plants are need 1050 until 1400 PPM). The implemented is method Internet of Things (IoT) to remote sensing on measure using a smartphone as the representation of the measurement results on the hydroponic system.

关键词：

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

Online Handwritten Recognition For Alphabet Writing Practice

Online Handwritten Recognition For Alphabet Writing Practice

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Ni Putu Linda Santiari I Gede Surya Rahayuda Information System Study Program Faculty of Informatics and Computer Institute of Technology and Business STIKOM Bali Denpasar Indonesia Informatics Study Program Faculty of Math and Natural Sciences Udayana University Mangupura Indonesia

ISBN: (纸本)9781665453967

Learning to write in children requires the child's habit of using a pencil to write on paper. The manual method has drawbacks such as the use of a lot of paper when children have to study harder to keep repeating the exercises and also cannot be done online remotely. In addition to this, writing exercises on the touchscreen can also train children to be more skilled at using the touchscreen. To overcome these problems, the author will discuss the use of handwriting recognition technology to practice writing capital letters (A-H), where the technology will be built on a web-based basis. The recognition algorithm used is K-NN. Testing the use of the website was carried out at Tunas Mekar Sari Kindergarten, Denpasar. The identification number and result will be stored on the web server. Based on the experiment, it was found that from 80 image data, the K-NN algorithm succeeded in providing accurate recognition results on 60 image data, and obtained an accuracy of 78.75%.

关键词： Handwriting recognition Image recognition Manuals Writing Touch sensitive screens Animation Web servers

来源：评论

学校读者我要写书评

暂无评论

Software Development Based on Sign Language Video Integration to Increase Accessibility of Port information for the Deaf in Sanur-Bali

Software Development Based on Sign Language Video Integratio...

引用

International Conference on Smart Computing & Communications (ICSCC)

作者： Decky Cipta Indrashwara Md. Wira Putra Dananjaya I Gede Fery Surya Tapa I Nyoman Indra Kumara Dewa Ayu Trisna Adhiswari Wedagama I Komang Agus Ariana Civil Engineering Study Program Universitas Pendidikan Nasional Denpasar Indonesia Technology Information Study Program Universitas Pendidikan Nasional Denpasar Indonesia Environmental Engineering Universitas Pendidikan Nasional Denpasar Indonesia

ISBN: (数字)9798350363104

ISBN: (纸本)9798350363111

This research focuses on Sanur Harbor, an inter-island ferry port located in southern Bali. The majority of visitors to Sanur Harbor are tourists who want to travel to Nusa Penida Island. At this port, facilities are available in the form of a Public Address System (PAS) and information officers whose job is to provide information regarding the arrival and departure of ships. However, the effectiveness of this facility is limited for deaf people. Deaf people often have difficulty getting this information independently and often have to rely on manual assistance from officers. This research aims to develop software based on sign language video integration which aims to increase the accessibility of departure and arrival information at Sanur Harbor for deaf people in Bali. The software development method uses a user-centered design development approach which involves the stages of needs analysis, design, implementation, and evaluation. Sign language videos will be integrated into the software as a medium to convey important information about ship departure and arrival schedules, travel routes, pier names, fast boat names, and other important information to deaf users. Evaluation is carried out through user testing and collecting feedback from users regarding understandability, usability, and user satisfaction with the software being developed. It is hoped that the results of this research can make a positive contribution to increasing information accessibility for deaf people in Sanur Harbor and can become a basis for developing similar technology in other locations.

关键词： Sign language Schedules User centered design information services Manuals Seaports Software Usability Software development management Testing

来源：评论

学校读者我要写书评

暂无评论

YoBagi's User Experience Evaluation using User Experience Questionnaire

YoBagi's User Experience Evaluation using User Experience Qu...

引用

International Conference on Informatics and Computing (ICIC)

作者： Fransiskus Panca Juniawan Dwi Yuny Sylfania Rendy Rian Chrisna Putra Henderi Program Study of Technology Information University of Bangka Belitung Pangkalpinang Indonesia Program Study of Informatics Engineering Institut Sains dan Bisnis Atma Luhur Pangkalpinang Indonesia Informatics Engineering Faculty of Science and Technology University of Raharja Tangerang Indonesia

ISBN: (纸本)9798350345728

The pandemic has brought many negative impacts on human life. One of the negative impacts is economic downturn of Micro, Small, and Medium Enterprise (MSME) actors in Bangka Belitung Province. To solve this problem, a website-based marketplace platform called Yobagi was created. As we know, a new software product must have a good user experience. By having a good user experience means that the product has met the needs of its users. For this reason, an evaluation of the user experience is necessary. This study aims to measure the user experience of using Yobagi. The evaluation uses the User Experience Questionnaire (UEQ) tool, which consists of six scales: Attractiveness, Efficiency, Perspicuity, Dependability, Stimulation, and Novelty. There were 40 respondents who were taken from the top of MSME actors. As the UX evaluation results, it is known that the final score of the six scales is above 0.8 and at the excellent level. This means that Yobagi users have a very good user experience in using Yobagi. In addition, Yobagi has met the criteria for good software by having an excellent user experience value.

关键词： Economics System testing Pandemics Entrepreneurship User experience Software Informatics

来源：评论

学校读者我要写书评

暂无评论

Android Based Heart-rate Monitoring System using ECG Sensor

Android Based Heart-rate Monitoring System using ECG Sensor

引用

International Conference on Sustainable Engineering and Creative Computing (ICSECC)

作者： Rosalina Grace Selina Rila Mandala Faculty of Computing Information Technology Study Program President University Bekasi Indonesia School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia

ISBN: (纸本)9781728175898

This research aims to help the user monitor their heart’s condition and notify other people in case of an emergency due to an abnormal heartbeat (normal heartbeat around 60-100 beats per minute). From the heart rate graph, the user could do a consultation with an expert in the nearest hospital using a map feature that will show the nearest hospital with a 1 KM radius from the user’s current location. The heart is undeniably an essential part of the human body system. The heart's missions are to pump blood to the lungs to expel the waste carbon dioxide that resulted from the respiration and pump blood that will deliver oxygen throughout the human body's circulation system. While the blood that carries oxygen being pumped throughout the human body, the heart will provide the oxygen to all cells. Body cells need to use oxygen to get the energy from food through a process called cellular respiration. Monitoring our heartbeat and pulse rate can increase people’s awareness about their heart’s health, motivating, and encouraging people to maintain a healthy eating plan and exercise. This research will be implemented ECG Sensor. The sensor will then send the data to the android application via HC-06 Bluetooth module. Monitoring the heart rate and analyzing the user’s heartbeat will be done in the android with a microcontroller device's help.

关键词： Bluetooth Heart beat Hospitals Microcontrollers Lung Electrocardiography Biomedical monitoring

来源：评论

学校读者我要写书评

暂无评论

Inappropriate Benefits and Identification of ChatGPT Misuse in programming Tests: A Controlled Experiment

arXiv

引用

arXiv 2023年

作者： Toba, Hapnes Karnalim, Oscar Johan, Meliana Christianti Tada, Terutoshi Djajalaksana, Yenni Merlin Vivaldy, Tristan Master of Computer Science Study Program Faculty of Information Technology Maranatha Christian University Bandung Indonesia Bachelor of Informatics Study Program Faculty of Information Technology Maranatha Christian University Bandung Indonesia Media Culture Department Faculty of Information Sciences and Arts Toyo University Kawagoe Japan EC-Council TampaFL United States

While ChatGPT may help students to learn to program, it can be misused to do plagiarism, a breach of academic integrity. Students can ask ChatGPT to complete a programming task, generating a solution from other people’s work without proper acknowledgment of the source(s). To help address this new kind of plagiarism, we performed a controlled experiment measuring the inappropriate benefits of using ChatGPT in terms of completion time and programming performance. We also reported how to manually identify programs aided with ChatGPT (via student behavior while using ChatGPT) and student perspective of ChatGPT (via a survey). Seventeen students participated in the experiment. They were asked to complete two programming tests. They were divided into two groups per the test: one group should complete the test without help while the other group should complete it with ChatGPT. Our study shows that students with ChatGPT complete programming tests two times faster than those without ChatGPT, though their programming performance is comparable. The generated code is highly efficient and uses complex data structures like lists and dictionaries. Based on the survey results, ChatGPT is recommended to be used as an assistant to complete programming tasks and other general assignments. ChatGPT will be beneficial as a reference as other search engines do. Logical and critical thinking are needed to validate the result presented by ChatGPT. © 2023, CC BY.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Advancements in Deep Learning Optimization for Post-Earthquake Building Damage Detection A Systematic Review

Advancements in Deep Learning Optimization for Post-Earthqua...

引用

Advanced information Scientific Development (ICAISD), International Conference on

作者： Sahat Sonang Y Yuhandri Muhammad Tajuddin Information Technology Study Program Universitas Putra Indonesia YPTK Padang Indonesia Department of Computer Science Universitas Bumigora Mataram Indonesia

ISBN: (数字)9798350392036

ISBN: (纸本)9798350392043

This study conducts a systematic literature review (SLR) that focuses on optimizing deep-learning techniques for post-earthquake building damage detection. By employing the PRISMA protocol, this review aimed to collect, analyze, and summarize the findings of various studies published between 2014 and 2024. This research identifies and evaluates optimization methods such as hyperparameter tuning, transfer learning, and data augmentation, highlighting their effectiveness and implementation. Challenges such as data quality, computational costs, and model interpretability were also discussed. The findings indicate that while deep learning techniques significantly enhance the accuracy and efficiency of damage detection, further research is required to address existing challenges and improve model robustness in diverse earthquake scenarios.

关键词： Deep learning Protocols Computational modeling Buildings Transfer learning Earthquakes Optimization methods Robustness Tuning Systematic literature review

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：