检索结果-内蒙古大学图书馆

Artificial Intelligence Robotics, Signal and Image Processing (AIRoSIP), International Conference on

作者： Rissa Rahmania Yaya Heryadi Lukas Lukas Wayan Suparta Ilvico Sonata Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Group (CEG) Faculty of Engineering Universitas Katolik Atma Jaya Jakarta Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia

ISBN: (数字)9798350327472

ISBN: (纸本)9798350327489

The existence of fine-grained image classification supporting smart retail provides effectiveness in recognizing products with high similarity. However, the generic classification method performs poorly in identifying products from a subordinate category. This paper aims to identify augmentation techniques to leverage the Vision Transformer (ViT) model to classify the fine-grained grocery product, which involves embedding patches and transformer encoders to extract the main features. First, we develop a fine-grained image dataset with ColorJitter, CutOut, and combining both augmentations. Secondly, we perform experiments and analysis of ViT size, embedded patch size and image size in the patch embedding process. Lastly, the ViT model are evaluated according to the image sizes 224, 384, and 512 in accuracy, loss, and confusion matrix. The highest accuracy was obtained at 0.9922. The ColorJitter and CutOut improved the confusion matrix in ViT-B/16 and ViT-L/16 with an image size of 384 and 512. The results show that both augmentations in the ViT model are able to distinguish fine-grained grocery products.

关键词： Surveys Computer vision Accuracy Image recognition Transformers Feature extraction Data augmentation Artificial intelligence Image classification

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

Digital Forensics Investigation and Incident Response in Internet of Things (IoT-DFIR): Challenges and Models

Digital Forensics Investigation and Incident Response in Int...

引用

International Conference on Wireless and Telematics (ICWT)

作者： Syaiful Ahdan Eki Ahmad Zaki Hamidi Sampurna Dadi Riskiono Ridha Muldina Negara Ratna Mayasari Suci Ramadona Ade Nurhayati Adi Sucipto Jupriyadi Galih Nugraha Nurkahfi Dzata Farahiyah Muchammad Naseer Faculty of Engineering & Computer Science Universitas Teknokrat Indonesia Lampung Indonesia Electrical Engineering Department UIN Sunan Gunung Djati Bandung Bandung Indonesia School of Electrical Engineering Telkom University Bandung Indonesia Elearical Engineering Study Program Politeknik Caltex Riau Riau Indonesia Faculty of Engineering Institut Teknologi Telkom Jakarta Jakarta Indonesia National Research and Innovation Agency (BRIN) Bandung Indonesia Faculty of Industrial Technology Universitas Islam Indonesia Yogyakarta Yogyakarta Indonesia Informatics Department Sekolah Tinggi Teknologi Bandung Bandung Indonesia

Many different industries are currently making substantial use of the Internet of Things (IoT). IoT is the process through which electronic devices communicate with their surrounding virtual environment by continuously exchanging data via sensors. Due to increased IoT security concerns, digital forensic investigators now possess greater knowledge and abilities to investigate IoT devices. IoT-DigFor are required in terms of cybercrime due to the rapid growth in the number of electronic devices and the collection and consumption of enormous amounts of data. IoT systems with billions of devices have produced a significant amount of evidence, which presents a significant challenge to digital investigators and practitioners who must connect with IoT devices to conduct fast and thorough investigations into cybercrimes. This article presents detailed information about forensics in the IoT environment. The IoT forensic paradigm and the challenges that design-based security requirements and IoT system security offer for IoT-DigFor are covered in great detail at the beginning of the article.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electrodermal Activity-Based Stress Measurement Using Continuous Deconvolution Analysis Method 1

引用

1st International Conference on Electronics, Biomedical engineering, and Health Informatics, ICEBEHI 2020

作者： Putri, Yang Sa’ada Kamila Ariyansah Rahma, Osmalina Nur Fajriaty, Nuzula Dwi Putra, Alfian Pramudita Rahmatillah, Akif Ain, Khusnul Biomedical Engineering Study Program Department of Physics Faculty of Science and Technology Universitas Airlangga Surabaya60115 Indonesia Biomedical Signals and Systems Research Group Faculty of Science and Technology Universitas Airlangga Surabaya60115 Indonesia

ISBN: (数字)9789813369269

ISBN: (纸本)9789813369252

Stress is a psychological response that must be handled properly, or it can affect psychology and trigger other complicated diseases. Nowadays, stress measured by filling out stress-related forms or interviews with a psychologist. This method still requires a willingness from the patient to consult their condition, which is often not giving the best result due to late treatment. Therefore, we need a system to monitor a person’s stress level conditions independently so they could be threatened quickly if their state gets worsen. One of the non-invasive methods that can be used to measure stress is an Electrodermal Activity (EDA) sensor. EDA is known to be associated with sweat gland activity regulated by SudoMotor Nerve Activity (SMNA), which response to a stressor. However, the SMNA need to decompose into the Skin Conductance Response (SCR) before it could represent stress condition. Hence, the decomposition stage is essential in measuring the quality of the stress condition. In this study, the EDA sensor placed in the palm to obtain the skin conductivity signal. Then, the skin conductivity signals were deconvolved using the Continuous Deconvolution Analysis (CDA) method to capture the SCR. CDA was chosen because it could produce a zero-based line SCR driver and could separate two overlapping peaks in SCR. The result, CDA is adequate to extract SCR, which is shown by the zero baseline of the SCR driver line with a clear peak. The clear SCR peaks are essential for identifying the responses related to the stimulus (stressor). © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Noninvasive medical procedures

来源：评论

学校读者我要写书评

暂无评论

Classifying Tweet Sentiment Analysis on Airlines using Random Forest Classifier, Naïve Bayes Classifier and K-Nearest Neighbors Classifier Algorithm

Classifying Tweet Sentiment Analysis on Airlines using Rando...

引用

Artificial Intelligence Robotics, Signal and Image Processing (AIRoSIP), International Conference on

作者： Ivan Alexander Yaya Heryadi Lukas Wayan Suparta Ilvico Sonata Computer Science Departement Binus Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group Faculty of Engineering Universitas Katolik Indonesia Atma Jaya Jakarta Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia

ISBN: (数字)9798350327472

ISBN: (纸本)9798350327489

Opinion has always affected businesses and individuals especially from the Public. People react through social media and spread it incompletely. The situation was then accepted as public opinion. There are three categories of opinion i.e., positive, negative, and neutral. To investigate public opinion on a particular issue of interest, sentiment analysis might be employed. By offering a solution to the text classification challenge, this experiment focuses on the perception of airline tweets among the American public. We offer a method to classify tweets as positive, negative, or neutral using three machine learning classifiers: Random Forest Classifier, Naive Bayes Classifier, and K-Nearest Neighbors Classifier. We examined the performance of three machine learning classifiers in terms of accuracy, average precision, average recall, and average f-1 score. The results demonstrate that the Random Forest Classifier, which produces 82% accuracy, 80% average precision, 82% average recall, and 80% average f1-score, performs the best among the machine learning classifiers.

关键词： Training Sentiment analysis Accuracy Social networking (online) Text categorization Nearest neighbor methods Naive Bayes methods Random forests Robots Airline industry

来源：评论

学校读者我要写书评

暂无评论

Utilization of plastic waste processing for oil fuel at Tambaan Beach, Pasuruan City

Utilization of plastic waste processing for oil fuel at Tamb...

引用

2019 International Conference on Innovation and Technology, ICIT 2019

作者： Rudianto, R. Yudaningtyas, E. Lelono, T.D. Kasitowati, R.D. Marine Science Study Program Faculty of Fisheries and Marine Science Universitas Brawijaya Malang Indonesia Department of Electrical Engineering Faculty of Engineering Universitas Brawijaya Malang Indonesia Fisheries Resource Utilization Study Program Faculty of Fisheries and Marine Science Universitas Brawijaya Malang Indonesia

The amount of waste in Indonesia is estimated to reach 68 million tons in 2019, of which 9.52 million tons is a plastic waste. With this amount, Indonesia is ranked second in the world as the largest producer of plastic waste. One area that suffers from plastic waste is the coastal area. This plastic waste is difficult to decompose and cause environmental problems. Likewise, it happened on the Tambaan coast in Tambaan sub-district, Panggungrejo subdistrict, Pasuruan city. Currently, accumulation of plastic waste is evident throughout the coastal area. The accumulation of scattered plastic waste and its proximity to the residents' settlements has become a hotbed of mosquitoes and caused a pungent smell. The Serving Doctoral program at Universitas Brawijaya offers a solution to process plastic waste into fuel oil such as diesel, kerosene, and premium. The technology used was Muryani's distillation from Wlingi, Blitar Regency. The technology can change certain types of plastic waste to produce fuel. Karang Taruna Bina Hang Tuah was acted as a reliable partner to assist the implementation of the technology on site. This study aims to strengthen the capacity of Karangtaruna in Tambaan Village to be more concerned about the environmental problems of Tambaan beach by processing waste that has been polluted by plastic waste. The results of plastic waste treatment showed that 10 kg of dried plastic waste can be transformed into diesel, premium and kerosene with the efficiency value of 60%, 35%, and 15%, respectively. © Published under licence by IOP Publishing Ltd.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Monitoring Stress Level Through EDA by Using Convex Optimization 1

引用

1st International Conference on Electronics, Biomedical engineering, and Health Informatics, ICEBEHI 2020

作者： Fajriaty, Nuzula Dwi Rahma, Osmalina Nur Putri, Yang Sa’ada Kamila Ariyansah Putra, Alfian Pramudita Rahmatillah, Akif Ain, Khusnul Biomedical Engineering Study Program Department of Physics Faculty of Science and Technology Universitas Airlangga Surabaya60115 Indonesia Biomedical Signals and Systems Research Group Faculty of Science and Technology Universitas Airlangga Surabaya60115 Indonesia

ISBN: (数字)9789813369269

ISBN: (纸本)9789813369252

This study designed an effective system for monitoring stress levels based on Electrodermal Activity (EDA) sensors by knowing the signal patterns and characteristics using convex optimization decomposition. The EDA sensor considered accurate and sensitive for identifying stress by analyzing the skin conductivity (SC) due to the changes in sympathetic nerve activity. However, the SC signal consists of phasic and tonic components, which needed to decompose to analyze stress levels. The SC signals also followed by the white Gaussian noise, which represents the error value. Hence, deconvolution is a crucial stage for the further process because the quality of the measurement depends on this result. This study aims to deconvolve the SC signal using the convex optimization method (cvxEDA). This model is physiology inspired by EDA based on Bayesian statistics, convex mathematical optimization, and sparsity. This research conducted with 18 subjects through three sessions of measurement. The given stimuli arise in each session to increase the level of stress. The results showed that this method could separate and identify SC. The Phasic component shows an increase in the stimulus of each session, as seen from the number of peaks. In contrast, there were no significant differences in the tonic component. This study shows that the phasic component is closely related to changes in sudomotor nerve activity (SMNA) and response to a stressor, which could be useful to classify stress levels in the future study. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

DeepCat: A Deep Learning Approach to Understand Your Cat's Body Language

DeepCat: A Deep Learning Approach to Understand Your Cat's B...

引用

Electronics, Communications, and Computations (JAC-ECC), International Japan-Africa Conference on

作者： Arwa Fawzy Ahmed Hassan Ahmed Gad Ahmed B. Zaky Haitham El-Hussieny Computer Science and Information Technology (CSIT) program Egypt-Japan University of Science and Technology Alexandria Egypt Department of Computer Science Engineering (CSE) Egypt-Japan University of Science and Technology Alexandria Egypt Electrical Engineering Department Faculty of Engineering at Shoubra Benha University Egypt Department of Mechatronics and Robotics Engineering Egypt-Japan University of Science and Technology Alexandria Egypt

Pet owners experience difficulty in understanding their pets' body language and its implications for animal welfare, given that animals cannot utilize human speech to communicate their emotions and health conditions. However, previous experiments for analyzing cat behavior have demonstrated that cats are precisely expressive. DeepCat, a deep-learning approach developed in this study, translates cats' body language signals, enabling owners to discern their feline companions' intended messages and emotional states. Our DeepCat model was trained on a dataset comprising 10,000 cat images, implementing automatic labeling to track key features, including the tail, eyes, and mouth. Presented as a Flutter application, DeepCat can function everywhere, allowing owners to easily monitor their cats and make informed decisions in situations that require caution. This paper discusses the potential benefits and limitations of DeepCat and provides suggestions for future research in this domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lighting the way: Enhancing telephone notification with DC lamps in noisy settings

引用

AIP Conference Proceedings 2024年第1期3167卷

作者： Priaji Hardimita Arief Wisaksono Syamsudduha Syarorini Jamaaluddin Jamaaluddin Shazana Dhiya Ayuni Electrical Engineering Study Program Faculty of Science and Technology Universitas Muhammadiyah Sidoarjo Sidoarjo Indonesia

This study aims to develop a device that uses DC lamps as a notification of a telephone ringing in a noisy room. The research method involves observing the Cikande electronic ambassador shop and proposing the use of a DC lamp as a replacement for the speaker output of the telephone. The device includes a PNP transistor type as an amplifier and multiple LEDs to ensure visibility in a noisy environment. The result is a functional device that uses DC lamps to notify the ringing of a telephone in a noisy room. The implication of this research is that it provides a solution for situations where conventional ringing tones from telephones are not audible due to noise pollution. The device can be useful in various settings, including busy offices, factories, and public spaces.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Protecting our little ones: A GPS-based child supervision tool with 99% accuracy rate

引用

AIP Conference Proceedings 2024年第1期3167卷

作者： Syamsudduha Syahrorini Salsabillah Jamaaluddin Jamaaluddin Arief Wisaksono Shazana Dyah Ayuni Agus Hayatal Electrical Engineering Study Program Faculty of Science and Technology Universitas Muhammadiyah Sidoarjo Sidoarjo Indonesia

This study aimed to develop a child supervision tool with a sound system to help parents quickly detect and locate danger to their children. The tool utilizes a Push Button or a microphone that, when activated by the child saying "Danger," sends the GPS coordinates to a NodeMCU ESP8266 microcontroller that sends location signals and notifications to the parent’s smartphone. The buzzer on the device also activates to alert the parent of danger. The study found that Voice Recognition as a sender of Blynk notifications and activating the buzzer function properly, and the GPS U-Blox Neo 6m accurately captured locations with an accuracy rate above 99%, with a sensor reading error rate below 0.1%. The implication is that this tool can help parents supervise their children and prevent them from becoming victims of kidnapping.

关键词：

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：