检索结果-内蒙古大学图书馆

24th International Seminar on Intelligent technology and Its Applications, ISITIA 2023

作者： Sunaryono, Dwi Siswantoro, Joko Sarno, Riyanarto Susilo, Rahardian Indarto Sabilla, Shoffi Izza ITS Department of Informatics Engineering Surabaya Indonesia Universitas Surabaya Department of Informatics Engineering Surabaya Indonesia Universitas Airlangga Department of Neurosurgery Surabaya Indonesia ITS Department of Medical Technology Surabaya Indonesia

ISBN: (纸本)9798350313956

At the present day, smart technology has made life simpler for people in all spheres of life, including medical. It is necessary to have technology that can identify diseases or physical defects in humans since this will influence the course of therapy. One of the cutting-edge technologies used to identify epilepsy is the electroencephalogram (EEG). The signal was obtained by observed brain's electrical activity for a period of time to get these signals. Medical professionals need to be very accurate and confident in their ability to categorize EEG patterns in order to diagnose epilepsy. This study suggested using Zero Crossing Frequency and Mean Crossing Frequency features extracted from transformed singnal using Discrete Wavelet Transform. EEG signals were classified into three categories: ictal, pre-ictal, and normal using Convolutional Neural Network. According to the study's findings, the suggested approach can accurately categorize three categories with a confidence interval (CI) of 0.0013 and an accuracy of 98.09%. © 2023 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Comparison of Classical and Deep Learning-Based Feature Representations for Age-Related Macular Degeneration 5th

Comparison of Classical and Deep Learning-Based Feature Re...

引用

5th International Conference on Medical Imaging and Computer Aided Diagnosis, MICAD 2024

作者： Sinichi, Parsa Bernabeu, Miguel O. Javidi, Malihe Department of Computer Engineering Faculty of Electronic and Computer Engineering Quchan University of Technology Quchan Iran Centre for Medical Informatics University of Edinburgh Edinburgh United Kingdom

ISBN: (纸本)9789819638628

Age-related Macular Degeneration (AMD) is a leading cause of visual impairment among the elderly worldwide. This study compares deep learning-based and classical feature extraction methods for AMD classification using colour fundus images, a cost-effective imaging modality. This comparative approach aims to evaluate the performance of advanced deep learning methods against traditional computer vision approaches in generating effective feature representation. To achieve this, we compared various classical feature extraction methods alongside deep learning-based approaches, specifically VGG16 pre-trained on ImageNet, RETFound and RETFound-Green, which are foundation models pre-trained on a significant number of retinal images. The results demonstrate that combinations of classical features still obtained notable performance and even outperformed the VGG16 model pre-trained on ImageNet. These results also highlight the need for deep learning models to be trained on domain-specific data to surpass classical approaches. In this regard, the pre-trained RETFound and RETFound-Green models yielded promising outcomes for AMD classification, and the highest performance was achieved using a fine-tuned RETFound model. Furthermore, the best proposed method was compared with the state-of-the-art methods. This approach achieved competitive results on the ADAM dataset, demonstrating its robustness and effectiveness in AMD classification while utilising a significantly simpler architecture. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Video Frame Sequence using Face Mesh and Pre-Trained Models of Convolutional Neural Network 24

Emotion Recognition from Video Frame Sequence using Face Mes...

引用

24th International Seminar on Intelligent technology and Its Applications, ISITIA 2023

作者： Adi, Derry Pramono Yuniarno, Eko Mulyanto Wulandari, Diah Puspito Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Dept. of Electrical Engineering Surabaya Indonesia Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Dept. of Electrical Engineering Dept. of Computer Engineering Surabaya Indonesia Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Dept. of Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350313956

Emotions are a collection of subjective cognitive experiences and psychological and physiological characteristics that express a wide range of feelings, thoughts, and behaviors in human interaction. Emotions can be represented through several means, such as facial expressions, tone of voice, and behavior. Deep Learning (DL) research has focused on incorporating facial expressions. Images with facial expressions are commonly used as data input for the DL model. Unfortunately, most DL models in Facial Emotion Recognition (FER) use static images. This method does not take into consideration all conceivable facial expressions. The static image of facial expressions is insufficient for recognizing emotions, but a sequential image from a video is required. In this study, we extract MediaPipe's face mesh feature, the state-of-the-art multidimensional expression key points embedded in the video image sequence. Furthermore, we feed sequence image data into the pre-trained Convolutional Neural Network (CNN) model. The data we used is from The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) with the emotion classes of 'Anger,' 'Fearful,' 'Happy,' and 'Sad.' For this specific FER task, we found that the best pre-trained CNN model achieved 92.8% accuracy (using the VGG-19 model), with the fastest runtime of ∼2.3 seconds (achieved using the SqueezeNet model). © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Silent Speech Interfaces: Non-Invasive Neuromuscular Signal Processing for Assistive Communication 4

Silent Speech Interfaces: Non-Invasive Neuromuscular Signal ...

引用

4th IEEE International Conference on Artificial Intelligence in Cybersecurity, ICAIC 2025

作者： Khan, Sallar Ali, Khawaja Usman Qadri, Ali Raza Ali Rizvi, Maisam Technological University Dublin School of Informatics and Cybersecurity Dublin Ireland Sir Syed University of Engineering and Technology Department of Computer Science & Information Technology Karachi Pakistan

ISBN: (纸本)9798331518882

Our research demonstrates a discrete speech system that empowers those afflicted with speech impairments to convey ideas by internally articulating words without producing audible sound. This method harnesses the minimal movements involved in articulation, making it less arduous than conventional vocalization, especially for individuals facing communication challenges. Silent Speech Interfaces (SSIs) form the foundation of our research, enabling the decoding of neuromuscular signals associated with internal speech articulation to facilitate non-invasive and effective communication for individuals with speech impairments. This research entails the utilization of a multi-electrode configuration to capture subtle, low-voltage electrical signals positioned on the surface area of the subject's neck. These signals emerge as a consequence of neural activation within the speech articulator muscles, signifying the internal articulation of words within the oral cavity, accompanied by minimal physical movement. Subsequent to signal acquisition, a comprehensive analysis of the data is conducted using a biosensing board (Cyton), facilitated by the implementation of the OpenBCI GUI interface and visualization via Python plotting tools. © 2025 IEEE.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Analysis of Adaptive Islanding Operation in Ungaran Subsystem, Central Java 6

Analysis of Adaptive Islanding Operation in Ungaran Subsyste...

引用

6th International Conference on Power engineering and Renewable Energy, ICPERE 2024

作者： Nurzikry, Deliar Rahman, Fathin Saifur Hariyanto, Nanang Murdani, Ahmad Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia Java Bali Load Dispatch Center Depok Indonesia

ISBN: (纸本)9798331504694

Ungaran is one of the important subsystems in the Central Java system. This subsystem is the main supplier of consumers to the significantly growing industrial area in the north coast region, and also supplies the business center and the government offices in Semarang, the capital city of Central Java province. During its operation, potential interruption of Inter-Bus Transformer (IBT) 500kV/150kV supply or frequency drop exceeding certain limits can cause the Ungaran Subsystem to form Island Operation. On May 30, 2020, the Ungaran Subsystem experienced a total blackout due to N-2 IBT disturbance, the island failed to form. Thus, due to its importance, maintaining the integrity of island operation in the Ungaran Subsystem is of high priority. The installed defense scheme is still static so that it is not flexible enough to cope with change of the distribution load and changes in the operating pattern of the power plant so that the success percentage of this static defense scheme is small. To increase the success rate of the island operation in the contingency event of loss of supply from the 500 kV system (IBT 500/150 kV) and frequency drop to 48.3 Hz, an adaptive island operation scheme is proposed. The success of the island operation scheme in the Ungaran subsystem can save the Tambaklorok Power Plant to avoid startup costs and speed up the recovery process. Based on the performed simulations, the proposed scheme could maintain the generation load balance during island operation and results in successful island operation. © 2024 IEEE.

关键词： Frequency stability

来源：评论

学校读者我要写书评

暂无评论

Study on Potential Interferences of 5G NR-U and WiFi 6E to Fixed Service in 6 GHz

Study on Potential Interferences of 5G NR-U and WiFi 6E to F...

引用

2024 IEEE International Conference on Computing, ICOCO 2024

作者： Farahiyah, Dzata Iskandar Anwar, Khoirul Hendrawan School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia The Center of Excellence AICOMS Telkom University Bandung Indonesia

ISBN: (纸本)9798331530303

This paper studies coexistence scenarios and observed potential interferences from services using unlicensed bands, Radio Local Area Network (RLAN) and 5G New Radio unlicensed (5G NR-U), to services using licensed band, Fixed service (FS). These interferences have the potential to disrupt FS if it exceeds established thresholds for protection criteria. To assess the impact of this coexistence, we develop several scenarios that focus on FS as the primary receiver to be protected and analyze potential interferences from RLAN and 5G NR-U. We perform a series of computer simulations for scenarios with varying power levels, series of distances, and number of devices under multipath fading channels. FS parameters are set using the practical parameters of the real-field in suburban Indonesia. We evaluate Interference-to-noise power ratio (INR) and Signal-to-interference ratio (SIR) at the FS receiver. Our results show that coexistence is feasible without causing interference to FS, when minimum separation distances and maximum number of devices for each station are well managed. ©2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Subnano-Fe (Co, Ni) clusters anchored on halloysite nanotubes: an efficient Fenton-like catalyst for the degradation of tetracycline

引用

Environmental Science and Pollution Research 2024年第19期31卷 28210-28224页

作者： Sun, Qing Yu, Jiale Zhao, Youpu Liu, Hanhu Li, Chunsheng Tao, Jiajun Zhang, Jian Sheng, Jiawei College of Materials Science and Engineering Zhejiang University of Technology Zhejiang Hangzhou310014 China School of Environmental Science and Spatial Informatics China University of Mining and Technology Xuzhou221116 China Zhejiang Institute of Geosciences Hangzhou310007 China

Iron-based catalysts are environmentally friendly, and iron minerals are abundant in the earth's crust, with great potential advantages for PMS-based advanced oxidation process applications. However, homogeneous Fe2+/PMS systems suffer from side reactions and are challenging to reuse. Therefore, developing catalysts with improved stability and activity is a long-term goal for practical Fe-based catalyst applications. In this study, we prepared Fe-HNTs nanoreactors by encapsulating a nitrogen-doped carbon layer with one-dimensional halloysite nanotubes (HNTs) using the molten salt-assisted method. Subsequently, Fe (Co, Ni) nanoclusters were anchored onto the nitrogen-doped carbon layer at a relatively low temperature (550℃), resulting in stable and uniform distribution of metal nanoclusters on the surface of HNTs carriers in the form of Fe-Nx coordination. The results showed that the dissolution of the molten salt and leaching of post-treated metal oxides generated numerous mesopores within the Fe-HNTs nanoreactor, leading to a specific surface area more than 10 times that of HNTs. This enhanced mass transfer capability facilitates rapid pollutant removal while exposing more active sites. Remarkably, Fe-HNTs adsorbed up to 97% of tetracycline within 60 min. In the Fe-HNTs/PMS system, the predominant reactive oxygen species has been shown to be 1O2, and the added tetracycline was degraded by more than 98% within 5 min. The removal of tetracycline was maintained above 96% in the presence of interfering factors such as wide pH (3–11) and inorganic anions (5 mM Cl−, HCO3−, NO3−, and SO42−). The investigated mechanism suggests that efficient degradation and interference resistance of the Fe-HNTs/PMS system is attributed to the synergistic effect between the rapid adsorption of porous structure and the non-radical (1O2)-dominated degradation pathway. Graphical Abstract: (Figure presented.) © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Sp

关键词： Nanoclusters

来源：评论

学校读者我要写书评

暂无评论

Estimating Value of Lost Load for Business and Industrial Customers in Indonesia Using Stated Preferences Methods 6

Estimating Value of Lost Load for Business and Industrial Cu...

引用

6th International Conference on Power engineering and Renewable Energy, ICPERE 2024

作者： Bahari, Rachmad Putra Banjarnahor, Kevin Marojahan Putra, I Made Agus Dwi Hariyanto, Nanang Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia Bandung Indonesia UID Jawa Timur Jakarta Indonesia

ISBN: (纸本)9798331504694

The Value of Lost Load (VoLL) quantifies the economic impact of power supply disruptions in rupiah per megawatt-hour and is crucial for justifying economic feasibility and investment decisions. This study uses the Stated Preferences (survey) method to calculate VoLL for the Jawa Madura Bali (Jamali) electricity system in Indonesia, taking into account data availability, calculation complexity, and result reliability. The findings reveal that the mean VoLL for business customers ranges from IDR 782,582 for a 5-minute outage to IDR 25,842 for a 24-hour outage, while for industrial customers, it ranges from IDR 35,340,331 for a 5-minute outage to IDR 3,060,356 for a 24-hour outage. Additionally, the analysis of Willingness to Accept (WTA) and Willingness to Pay (WTP) shows that businesses have a mean WTA of IDR 12,069 and a mean WTP of IDR 3,677, whereas industries have a mean WTA of IDR 10,737 and a mean WTP of IDR 2,355. These results highlight the substantial economic impact of power outages on different customer sectors and emphasize the need for targeted investments to enhance reliability. Integrating VoLL into policy and investment frameworks allows power companies and policymakers to make informed decisions, ultimately improving system reliability and economic efficiency. © 2024 IEEE.

关键词： Economic efficiency

来源：评论

学校读者我要写书评

暂无评论

Monopole-based Wideband Antenna with Embedded Band-notch for Applications in Upper UWB 25

Monopole-based Wideband Antenna with Embedded Band-notch for...

引用

25th International Conference on Electromagnetics in Advanced Applications, ICEAA 2024

作者： Dang, Yu Alam, Tanjir Cheffena, Michael Kjelgård, Kristian G. Faculty of Engineering Norwegian University of Science and Technology Gjøvik Norway Dept. of Informatics University of Oslo Oslo Norway

ISBN: (纸本)9798350360974

In this letter, a wideband antenna with band-notch characteristics for application at the upper part of the ultra-wideband (UWB) spectrum is presented. The proposed monopole-based wideband antenna with the in-built band-notch property has an overall dimension of 0.34λ0×0.39λ0×0.024λ0 mm3. The design incorporates a simple annular ring on the bottom layer, facilitating easier fabrication and eliminating the need for expensive microwave filters. Parameter analysis shows that adjusting the ring and patch dimensions can easily shift the stop band, effectively filtering interference in the crowded 6 GHz band. The measurement results and time domain characteristics confirm that the proposed system can be a suitable, cost-effective choice for the upper UWB application. © 2024 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

iPIC-XAI: Improving PIC-XAI for Enhanced Image Captioning Explanation 14

iPIC-XAI: Improving PIC-XAI for Enhanced Image Captioning Ex...

引用

14th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2023

作者： Al-Shouha, Modafar Szűcs, Gábor Department of Telecommunications and Media Informatics Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Műegyetem rkp. 3. BudapestH-1111 Hungary

ISBN: (纸本)9798350325652

Image captioning task with its complexity has taken advantage of the recent developments in Deep learning (DL). However, DL-models are fundamentally abstruse and explaining their behaviour is a challenge. In this paper we present an algorithm to explain an image captioning model behavior. We enhanced PIC-XAI performance by introducing various components;(1) we utilize CLIP multimodal similarity for more efficiency, (2) we consider the query dependency tag as a clue for elements with bigger size, (3) we provide an algorithm to automatically set the preprocessing blurring kernel size, and (4) we use a similarity comparison technique to get more relevant answers. Additionally, we provide an improved version of XIC metric, aiming for more consistent objective evaluation for XAI methods in image captioning field1 © 2023 IEEE.

关键词： Image segmentation

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：