检索结果-内蒙古大学图书馆

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Cristiani, Maria Department of Electrical Computer and Biomedical Engineering University of Pavia Via Ferrata 5 Pavia27100 Italy

Here we present some early experimental studies on the propagation of optical pulses in fiber cavities that provided significant insights for the comprehension of the complex dynamics underlying dissipative soliton pr... 详细信息

ISBN: (纸本)9781957171258

关键词： Solitons

来源：评论

学校读者我要写书评

暂无评论

Pulmonary Diseases Decision Support System Using Deep Learning Approach

引用

computers, Materials & Continua 2022年第10期73卷 311-326页

作者： Yazan Al-Issa Ali Mohammad Alqudah Hiam Alquran Ahmed Al Issa Department of Computer Engineering Yarmouk UniversityIrbid21163Jordan Department of Biomedical Systems and Informatics Engineering Yarmouk UniversityIrbid21163Jordan Department of Biomedical Engineering Jordan University of Science and TechnologyIrbid 22110Jordan Pediatrician Mediclinic HospitalAl Ain14444UAE

Pulmonary diseases are common throughout the world,especially in developing *** diseases include chronic obstructive pulmonary diseases,pneumonia,asthma,tuberculosis,fibrosis,and recently *** general,pulmonary diseases have a similar footprint on chest radiographs which makes them difficult to discriminate even for expert *** recent years,many image processing techniques and artificial intelligence models have been developed to quickly and accurately diagnose lung *** this paper,the performance of four popular pretrained models(namely VGG16,DenseNet201,DarkNet19,and XceptionNet)in distinguishing between different pulmonary diseases was *** the best of our knowledge,this is the first published study to ever attempt to distinguish all four cases normal,pneumonia,COVID-19 and lung opacity from ChestX-Ray(CXR)*** models were trained using Chest-X-Ray(CXR)images,and statistically tested using 5-fold cross *** individual models,XceptionNet outperformed all other models with a 94.775%accuracy and Area Under the Curve(AUC)of Receiver Operating Characteristic(ROC)of 99.84%.On the other hand,DarkNet19 represents a good compromise between accuracy,fast convergence,resource utilization,and near real time detection(0.33 s).Using a collection of models,the 97.79%accuracy achieved by Ensemble Features was the highest among all surveyed methods,but it takes the longest time to predict an image(5.68 s).An efficient effective decision support system can be developed using one of those approaches to assist radiologists in the field make the right assessment in terms of accuracy and prediction time,such a dependable system can be used in rural areas and various healthcare sectors.

关键词： Pulmonary diseases deep learning lung opacity classification majority voting ensemble features

来源：评论

学校读者我要写书评

暂无评论

HAM: Hybrid Associations Models for Sequential Recommendation (Extended abstract) 39

HAM: Hybrid Associations Models for Sequential Recommendatio...

引用

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Peng, Bo Ren, Zhiyun Parthasarathy, Srinivasan Ning, Xia The Ohio State University Department of Computer Science and Engineering United States The Ohio State University Department of Biomedical Informatics United States The Ohio State University Translational Data Analytics Institute Department of Computer Science and Engineering United States The Ohio State University Translational Data Analytics Institute Department of Biomedical Informatics Department of Computer Science and Engineering United States

ISBN: (纸本)9798350322279

Sequential recommendation aims to identify and recommend the next few items of users' interest. It becomes an effective tool to help users select their favorite items from a variety of options. A key challenge in sequential recommendation is to learn the patterns and dynamics, which are most pertinent to inform future interactions of users. With the prosperity of deep learning, many deep models, particularly based on recurrent neural networks [1] and with attention mechanisms [2] , [3] , have been developed for sequential recommendation purposes. However, our analysis demonstrates that, these deep models, particularly those with attention mechanisms, may not always learn meaningful attention weights from the extremely sparse recommendation data, and thus, could degrade the recommendation performance. Therefore, in this study, instead of deep models, we develop novel, effective and efficient hybrid associations models (HAM) to better learn from the sparse and limited recommendation data. This study has been published in IEEE Transactions on Knowledge and Data engineering. Please refer to the full manuscript [4] for more details. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Strategies for Enhancing Quality of Experience in 360° Video Streaming 58

Adaptive Strategies for Enhancing Quality of Experience in 3...

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Valiandi, Ioanna Pattichis, Marios S. Kyriacou, Efthyvoulos Panayides, Andreas S. Videomics Group Cyens Centre of Excellence Nicosia Cyprus University of New Mexico Department of Electrical and Computer Engineering AlbuquerqueNM87131-0001 United States Cyprus University of Technology Department of Electrical Eng. Computer Engineering and Informatics Limassol Cyprus

ISBN: (纸本)9798350354058

The unprecedented growth of immersive virtual and mixed reality technologies is driving the increasing demand of 360° video streaming applications. Facilitating unique opportunities, but also challenges, 360° videos require substantially higher video resolutions, and hence bandwidth demands, for a better viewing experience. This study examined four tile-based Region of Interest (ROI) encoding techniques to optimize 360° video encoding and streaming. These techniques encode the user's viewport regions with higher quality compared to the background, non-ROI areas. A dataset of ten 4K omnidirectional videos at 30 frames per second was used to evaluate the performance of four distinct tile-based ROI methods using four video encoding standards, namely hevc - nvenc, x265, h264 - nvenc, and x264. Overall, the proposed tile-based ROI encoding methods achieve substantial bitrate reductions compared to the uniform full-frame encoding while maintaining adequate subjective video quality levels, demonstrating their potential for efficient and scalable 360° video streaming. The ROI-3 method, which uses a sliding window approach to encode the user's field of view based on eye gaze movement (EM) data coordinates translated to tile regions, was found to achieve the best trade-off between bitrate demands savings and perceptual quality for all investigated video compression standards. © 2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Optical Readout Techniques for Smart Detection of Fluids in the Near Infrared Wavelength Region by Means of Rectangular Glass Micro-capillaries

Optical Readout Techniques for Smart Detection of Fluids in ...

引用

Annual Italian Conference on Sensors and Microsystems, AISEM 2021

作者： Bello, Valentina Bodo, Elisabetta Merlo, Sabina Department of Electrical Computer and Biomedical Engineering University of Pavia Via Ferrata 5 Pavia27100 Italy

ISBN: (纸本)9783031081354

Three different approaches for the analytical detection of fluids by means of rectangular glass micro-capillaries working in the near infrared wavelength region are presented. At first, a non-specific refractometric measurement for the detection of glucose concentration in solutions is reported, exploiting the micro-capillaries as optical resonators: by monitoring the spectral shift of the ratio between the transmitted and reflected optical spectra (T/R) from the capillary, it is possible to extract the wavelength positions of the cavity resonances (maxima of T/R) for fluids with different refractive index. When the refractive index of the sample fluid filling the channel increases, a shift towards longer wavelengths is observed. Then, a spectral phase shift interferometric technique for the detection of the wavelength position of the resonances is proposed. When the capillary is inserted in an interferometric setup, it is possible to distinguish fluids by knowing the dependence of the wavelength positions of the steep jumps in the cosine signal on the refractive index of the filling fluid. Finally, the potentiality of micro-capillaries is investigated for specific sensing, exploiting absorption spectroscopy. All the proposed optical readout approaches are remote, contactless and non-invasive. In addition, the glass-micro-capillaries are very suitable for analytical detection of fluids: they are low-cost devices, available in several formats. Thanks to their micrometric size, they can be incorporated in micro-fluidic circuits. Borosilicate glass is a bio-compatible material, allowing the use of the micro-fluidic platforms in a wide range of applications for label-free optical sensing. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Absorption spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Towards the development of a SWIR-LEDs based optoelectronic system for urea monitoring during haemodialytic therapy

Towards the development of a SWIR-LEDs based optoelectronic ...

引用

2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023

作者： Bodo, Elisabetta Bello, Valentina Merlo, Sabina Department of Electrical Computer and Biomedical Engineering University of Pavia Via Ferrata 5 Pavia27100 Italy

ISBN: (纸本)9798350345995

Chronic kidney disease (CKD) has been one of the most severe public health issues in recent decades. Patients affected by CKD require a complicated and expensive treatment such as hemodialysis. The management of hemodialysis patients have been a particular challenge for nephrologists during the COVID-19 pandemic [1]. The accepted measure of dialysis dose is based on the removal of urea from the blood pool. Urea concentration is usually evaluated with the aid of blood samples that are analyzed in a clinical laboratory, but there is still the need of continuous monitoring of the dialysis efficiency to optimize clinical treatments. Hence, we have investigated and demonstrated an optofluidic sensing platform to detect urea content in water solutions by comparing light transmittance across a flat microfluidic channel with and without fluid. We considered the effect of absorption in the wavelength bands around λ = 1.45 μm and λ = 2.15 μm, where water and urea exhibit characteristic peaks of absorbance [2]. In the instrumental configuration (Fig. 1(a)), radiation provided by two LEDs crosses the microfluidic device and is finally detected in time domain with an amplified InGaAs photodiode, connected to the oscilloscope for data visualization and acquisition. The microfluidic device is a rectangular section borosilicate glass capillary (Vitrocom, NJ, USA) with two extremities provided with heat shrink tubes to facilitate injection of the fluid into the channel. Nominal channel length and depth of the channel are 50 mm and 1 mm, respectively. We vertically fixed the capillary in direct contact with the photodiode mounting, ensuring a LED-photodiode distance of just 5 mm. Transmittance measurements were carried out by filling the channel with urea-water solutions with concentrations of urea up to 0.05 g/ml. Data acquired with the oscilloscope are then analyzed in MATLAB environment, to extract the average and standard deviation of the photodetected signal amplitude in the tim

关键词： Urea

来源：评论

学校读者我要写书评

暂无评论

Thermal Noise Analysis of Accumulation-based S/H Circuit for Shunt Current Sensing 30

Thermal Noise Analysis of Accumulation-based S/H Circuit for...

引用

30th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2023

作者： Yarragunta, Jaya Satyanarayana Aprile, Antonio Fugger, Andreas Conzatti, Francesco Bonizzoni, Edoardo Malcovati, Piero University of Pavia Department of Electrical Computer and Biomedical Engineering Italy Infineon Technologies Austria Villach Austria

ISBN: (纸本)9798350326499

Shunt current measurements are widely used for monitoring and controlling the current flow in various applications, such as power converters and battery management systems (BMS). The accuracy and resolution of this kind of measurements depend on the performance of the sample-and-hold (S/H) circuit that captures the voltage across a shunt resistor. In this paper, we propose a noise analysis of a S/H circuit that operates in accumulation mode;this technique enables to lower the thermal noise by 3 dB for every doubling of the number of accumulation cycles. The proposed analysis, confirmed by extensive simulation results, demonstrates that this approach offers a lower noise power spectral density and a higher signal-to-noise ratio if compared with conventional amplification-based S/H solutions. © 2023 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Smart Optofluidic Sensing Platform Ensuring Patients' Safety during Parenteral Nutrition Administration

A Smart Optofluidic Sensing Platform Ensuring Patients' Safe...

引用

2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023

作者： Bello, Valentina Bodo, Elisabetta Merlo, Sabina Department of Electrical Computer and Biomedical Engineering University of Pavia Via Ferrata 5 Pavia27100 Italy

ISBN: (纸本)9798350345995

Parenteral nutrition (PN) is a lifesaving treatment for a large number of patients suffering from different pathologies, from cancer to intestinal failure, from eating disorders to inflammatory bowel disease. In PN, liquid nutritive drugs are injected into the patient's body intravenously through an infusion delivery pump. As reported in the scientific literature, among all medical treatments, PN is the most commonly prone one to human errors [1]. In particular, very often wrong PN mixtures (PNMs) are administered. The consequences can be very dangerous to the patient's health, leading to death in the most severe cases. Despite this fact, currently no standard safety protocols or control devices are implemented to prevent medication errors in PN. Hence, in the framework of the DSF (Digital Smart Fluidics - project No. 1175234, founded by POR FESR 2014-2020), we have developed an optofluidic sensing platform to distinguish different types of transparent commercial PNMs on the basis of their refractive index (RI). Indeed, each mixture contains different concentrations of glucose, amino acids, and electrolytes, determining different values of their RI. The instrumental configuration of the sensor (Fig 1(a)) features a laser diode that generates a red beam (wavelength of 670 nm) travelling obliquely through a plastic cuvette channel containing the PNM under test. Light is then back-reflected by a mirror applied to the back of the cuvette, and finally exits the channel at a position that depends on the RI of the PNM. The position of the output light spot is easily detected with a linear position sensitive detector (PSD) [2]. The two photo-currents I1 and I2 generated at the extremities of the sensitive area are given as the PSD outputs: by proper normalization, it is possible to retrieve the measured light beam position as pPSD = L/2 × (I1 - I2)/(I1 + I2), where L is the PSD length. The sensor response is then retrieved, after defining the baseline signal measured in pre

关键词： Glucose

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Game Reviews on STEAM using BERT, BiLSTM, and CRF

Sentiment Analysis of Game Reviews on STEAM using BERT, BiLS...

引用

2023 International Conference on electrical engineering and informatics, ICEEI 2023

作者： Al Mursyidy Fadhlurrahman, Jalaluddin Herawati, Neng Ayu Widya Aulya, Hayyu Rachma Puspasari, Ira Utama, Nugraha Priya School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Dinamika University Computer Engineering Department Surabaya Indonesia

ISBN: (纸本)9798350381290

The Steam platform releases thousands of games almost every week, providing customers with many options, which require various considerations to make a purchase decision. Steam has features that can help consumers consider purchasing games, such as the help dashboard that provides information on game reviews and ratings. However, based on user input reviews, game ratings are still manual, which may cause human error and inaccurate results. To help gamers get the desired game information and increase customer purchasing power towards available games, sentiment analysis is one technique for classifying opinions. This study focuses on sentiment analysis of game reviews, which will result in classification into two classes, positive and negative. It will be measured for its performance based on the f1 score evaluation results. The proposed model that we created is to compare sentiment analysis models using the baseline Bi-directional Long-short Term Memory (BiLSTM), Bidirectional Gated Recurrent Unit (BiGRU), and fine-tuning Bidirectional Encoder Representations from Transformer (BERT). We then propose another model, BiLSTM-CRF, by examining the effect of using the last four hidden states of BERT and comparing it with the last one hidden state of BERT to be used in the BiLSTM-CRF model. Based on the results of sentiment analysis models we developed for the ten most reviewed games on Steam, the BiLSTM model combined with CRF on the last four hidden states yielded the best performance, with an Fl score of 95.2 %. This score exceeds the baseline transformer-based model's Fl score of 88.0%. This is because combining BiLSTM and CRF allows the log-likelihood of the BiLSTM emission sample to be obtained more accurately so the model does not lose its context. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Big Five Personality Prediction Based on Indonesian Tweets and Personality Test

Big Five Personality Prediction Based on Indonesian Tweets a...

引用

2023 International Conference on electrical engineering and informatics, ICEEI 2023

作者： Parameswara, Made Arbi Mahendra, Farrel Satya Putra Mardika, Muhammad Randy Cahya Puspasari, Ira Utama, Nugraha Priya School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Dinamika University Computer Engineering Department Surabaya Indonesia

ISBN: (纸本)9798350381290

The integration of human resources and artificial intelligence has shown a growing interest in automatically predicting personality traits, particularly in recruitment. To contribute to this field, we propose a new method to assist human resource professionals in Indonesia to identify candidates' personality traits. Biases come from personality tests due to their question format and susceptibility to manipulation on this research, we propose an approach that combines personality tests using the BFI form, which measures OCEAN personality traits, with personality trait predictions derived from Twitter data. This research aims to create a personality prediction model and system that efficiently and effectively screens candidate personality traits in human resources. This research has developed a novel model that combines personality test results with tweets personality prediction with an impressive F1-macro performance of 98%. © 2023 IEEE.

关键词： Machine learning

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：