检索结果-内蒙古大学图书馆

Improving Fall Classification Accuracy of multi-input models Using Three-Axis Accelerometer and Heart Rate Variability Data

引用

SENSORS 2025年第4期25卷 1180-1180页

作者： Kim, Seunghui Ko, Jae Eun Baek, Seungbin Kim, Daechang Kim, Sungmin Dongguk Univ Dept Regulatory Sci Med Device Seoul 04620 South Korea Dongguk Univ Dept Med Device Business Seoul 04620 South Korea Dongguk Univ Dept Biomed Engn Goyang Si 10326 South Korea

Reduced body movement and weakened musculoskeletal function as a result of aging increase the risk of falls and serious physical injuries requiring medical attention. To solve this problem, a fall prevention algorithm using an acceleration sensor has been developed, and research is being conducted to enable continuous monitoring using a Holter electrocardiograph. In this study, we implemented a multi-input model that can detect and classify movements, including falls, utilizing the baroreflex characteristics of the heart's potential energy changes due to movement, measured with an electrocardiogram with a three-axis acceleration sensor and a Holter electrocardiograph. Patterns were identified from the various movement characteristics of acceleration sensor data using a deep learning model consisting of CNN-LSTM, and heart rate variability (HRV) data were analyzed using a wide learning model to provide additional weight values for fall classification. Finally, a multi-input model using wide and deep learning was proposed to enhance the accuracy of fall classification. The results show that the HRV increased in fall case except in two motion types, while it decreased when standing up from a chair, indicating the application of the baroreflex characteristics reflecting the heart's potential energy. Compared to the classification model using conventional HRV and ACC, a higher accuracy was achieved in the multi-input model using ACC-HRV data, and a precision, recall, and F1 score of 0.91 was measured, indicating improved performance. This is expected to have a positive impact on fall prevention by improving the accuracy of fall classification in the elderly for 15 different movements.

关键词： three-axis acceleration sensor Holter electrocardiograph multi-input model fall classification heart rate variability (HRV)

来源：评论

学校读者我要写书评

暂无评论

ATSDetector: An Android Trojan spyware detection approach with multi-features

引用

COMPUTERS & SECURITY 2025年 150卷

作者： Wang, Siyu Wu, Haiyong Lu, Ning Shi, Wenbo Liu, Zhiquan Northeastern Univ Coll Comp Sci & Engn Shenyang Peoples R China Xidian Univ Sch Comp Sci & Technol Xian Peoples R China Jinan Univ Coll Cyber Secur Guangzhou Peoples R China

With the widespread popularity of Android Trojan spyware, detection technology for Android Trojan spyware is very necessary to prevent financial loss. However, when considering the comprehensive behaviors of Android Trojan spyware, the existing approaches based on a single feature (static information, internal behavior, and external behavior) have low accuracy and even errors. In this paper, we propose a multi-features-based Android Trojan spyware detection approach (hereafter referred to as ATSDetector). Specifically, we first define a multichannel detection algorithm supported by heterogeneous information. And then, devise a weight-size sharing mechanism to establish the correlation between different behavioral features. At last, we then conduct real- world experiments to prove the effectiveness and stability of ATSDetector. The results show that the assessment accuracy can achieve almost 96.81%, and its kappa coefficient is about 93.62%.

关键词： Software detection Android Trojan spyware Behavioral features multi-input model Weight-size sharing

来源：评论

学校读者我要写书评

暂无评论

A multi-input Residual Network for Non-Destructive Prediction of Wood Mechanical Properties

引用

FORESTS 2025年第2期16卷 355-355页

作者： Ma, Jingchao Kuang, Zhufang Fang, Yixuan Huang, Jiahui Cent South Univ Forestry & Technol Sch Comp & Math Changsha 410004 Peoples R China Cent South Univ Forestry & Technol Sch Mat Sci & Engn Changsha 410004 Peoples R China

Modulus of elasticity (MOE) and modulus of rupture (MOR) are crucial indicators for assessing the application value of wood. However, traditional physical testing methods for the mechanical properties of wood are typically destructive, costly, and time-consuming. To efficiently assess these properties, this study proposes a multi-input residual network (MIRN) model, which integrates microscopic images of wood with physical density data and leverages deep learning technology for rapid and accurate predictions. By using larger convolution kernels to enhance the receptive field, the model captures fine microstructural features in the images. Batch normalization layers were removed from the ResNet architecture to reduce the number of parameters and improve training stability. Shortcut connections were utilized to enable deeper network architectures and address the vanishing gradient problem. Two types of residual blocks, convolutional block and identity block, were defined based on input dimensional changes. The MIRN method, based on multi-input residual networks, is proposed for non-destructive testing of wood mechanical properties. The experimental results show that MIRN outperforms convolutional neural networks (CNNs) and ResNet-50 in predicting MOE and MOR, with an R2 of 0.95 for MOE and RMSE reduced to 46.88, as well as an R2 of 0.85 for MOR and an RMSE of 0.44. Thus, this method offers an efficient and cost-effective tool for wood processing and quality control.

关键词： wood mechanical properties multi-input model microscopic images deep learning residual networks non-destructive testing

来源：评论

学校读者我要写书评

暂无评论

multi-Leak Deep-Learning Side-Channel Analysis

引用

IEEE ACCESS 2022年 10卷 22610-22621页

作者： Hu, Fanliang Wang, Huanyu Wang, Junnian Hunan Univ Sci & Technol Sch Phys & Elect Sci Xiangtan 411199 Hunan Peoples R China KTH Royal Inst Technol Sch EECS S-11428 Stockholm Sweden

Deep Learning Side-Channel Attacks (DLSCAs) have become a realistic threat to implementations of cryptographic algorithms, such as Advanced Encryption Standard (AES). By utilizing deep-learning models to analyze side-channel measurements, the attacker is able to derive the secret key of the cryptographic algorithm. However, when traces have multiple leakage intervals for a specific attack point, the majority of existing works train neural networks on these traces directly, without a appropriate preprocess step for each leakage interval. This degenerates the quality of profiling traces due to the noise and non-primary components. In this paper, we first divide the multi-leaky traces into leakage intervals and train models on different intervals separately. Afterwards, we concatenate these neural networks to build the final network, which is called multi-input model. We test the proposed multi-input model on traces captured from STM32F3 microcontroller implementations of AES-128 and show a 2-fold improvement over the previous single-input attacks.

关键词： Mathematical models Software Side-channel attacks Deep learning Power demand Neural networks Feature extraction AES deep learning multiple leakage multi-input model side-channel attacks

来源：评论

学校读者我要写书评

暂无评论

Moving State Estimation by CNN from Long Time Data of Smartphone Sensors Sussex-Huawei Locomotion Challenge 2023

Moving State Estimation by CNN from Long Time Data of Smartp...

引用

ACM International Joint Conference on Pervasive and Ubiquitous Computing / ACM International Symposium on Wearable Computing (UbiComp/ISWC)

作者： Kawakatsu, Masaki Hyugaji, Takumi Toyoshima, Yugo Tokyo Denki Univ Sch Syst Design & Technol Tokyo Japan

ISBN: (纸本)9798400702006

This paper presents the ideas utilized by Team Ds at the 2023 Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge. The 2023 SHL Challenge involves classifying eight modes of locomotion and transportation using data acquired by smartphone motion and GPS sensors. The data were obtained from three users, User1 provided the training set, and parts of the data acquired by User2 and User3 were used as the validation and test sets. Long-period data (up to 110 s) were used to estimate the modes of locomotion and transportation for a sample in the main processing. We have created a model to estimate the modes of locomotion and transportation using User1's accelerometer, gyro sensor, magnetic sensor, and GPS location data. The neural network model comprised four sections, i.e., two types of a one-dimensional convolutional neural networks (1D-CNNs) with different filter size using raw waveform data for nine sensors, one 2D-CNN using the spectrograms of accelerometer and gyro sensor, and two fully-connected layers of 22 statistical data computed from the sensors. In a post-processing step, a model was constructed to output the labels from the SoftMax output obtained from the previous model, and this output was used as the final estimation. The developed model was evaluated experimentally, and the F1-score obtained on the validation data was 0.952.

关键词： CNN Neural network Long-term data multi-input model

来源：评论

学校读者我要写书评

暂无评论

Intervention Prediction in MOOCs Based on Learners' Comments: A Temporal multi-input Approach Using Deep Learning and Transformer models 18th

Intervention Prediction in MOOCs Based on Learners' Comments...

引用

18th International Conference on Intelligent Tutoring Systems (ITS)

作者： Alrajhi, Laila Alamri, Ahmed Cristea, Alexandra, I Univ Durham Comp Sci Durham England

ISBN: (纸本)9783031096808;9783031096792

High learner dropout rates in MOOC-based education contexts have encouraged researchers to explore and propose different intervention models. In discussion forums, intervention is critical, not only to identify comments that require replies but also to consider learners who may require intervention in the form of staff support. There is a lack of research on the role of intervention based on learner comments to prevent learner dropout in MOOC-based settings. To fill this research gap, we propose an intervention model that detects when staff intervention is required to prevent learner dropout using a dataset from FutureLearn. Our proposed model was based on learners' comments history by integrating the most-recent sequence of comments written by learners to identify if an intervention was necessary to prevent dropout. We aimed to find both the proper classifier and the number of comments representing the appropriate most recent sequence of comments. We developed several intervention models by utilising two forms of supervised multi-input machine learning (ML) classification models (deep learning and transformer). For the transformer model, specifically, we propose the siamese and dual temporal multi-input, which we term the multi-siamese BERT and multiple BERT. We further experimented with clustering learners based on their respective number of comments to analyse if grouping as a pre-processing step improved the results. The results show that, whilst multi-input for deep learning can be useful, a better overall effect is achieved by using the transformer model, which has better performance in detecting learners who require intervention. Contrary to our expectations, however, clustering before prediction can have negative consequences on prediction outcomes, especially in the underrepresented class.

关键词： MOOCs Intelligent intervention system multi-input model

来源：评论

学校读者我要写书评

暂无评论

Person Re-identification using soft-biometric features: body silhouette and clothing texture in a multi-camera video surveillance environment 3

Person Re-identification using soft-biometric features: body...

引用

3rd International Conference on Information Systems and Software Technologies (ICI2ST)

作者： Carrillo-Medina, Jose Chango-Caisabanda, David Cuyo-Chiluisa, Victor Galarza-Medina, Eddie Univ Fuerzas Armadas ESPE Dept Comp Sci Sangolqui Ecuador

ISBN: (纸本)9781665455176

People Re-ldentification has become a topic of interest due to the increasing use of intelligent video surveillance systems in the security industry. In this paper, we implement a people Re-Id system comprising three important modules: a) a person detection, responsible for detecting people in the image, b) preprocessing module, responsible of extracting the soft-biometric features of the detected persons, and c) an identification module, capable of identifying the detected person. For this purpose, a two branches multi-input and one output network model is built. The first one receives the body silhouette descriptor and the other the clothing texture descriptor. To train this model a dataset of 7 identities was built, with 1862 and 481 images for training and validation respectively, facing problems such as the existing bias in the public datasets. In addition, two videos and one validation image set were used to evaluate the system performance. The results of our proposal are positive, demonstrating that the combination of soft-biometrics features, body silhouette and clothing textures of the person increases the system ability to Re-Identify a person in images and videos.

关键词： people re-identification soft-biometric features video surveillance deep learning multi-input model

来源：评论

学校读者我要写书评

暂无评论

multimodal Emotion Recognition via Convolutional Neural Networks: Comparison of different strategies on two multimodal datasets

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 130卷

作者： Bilotti, U. Bisogni, C. De Marsico, M. Tramonte, S. Univ Salerno Via Giovanni Paolo II132 I-84084 Fisciano Italy Sapienza Univ Rome Via Salaria 113 I-00198 Rome Italy

The aim of this paper is to investigate emotion recognition using a multimodal approach that exploits convolutional neural networks (CNNs) with multiple input. multimodal approaches allow different modalities to cooperate in order to achieve generally better performances because different features are extracted from different pieces of information. In this work, the facial frames, the optical flow computed from consecutive facial frames, and the Mel Spectrograms (from the word melody) are extracted from videos and combined together in different ways to understand which modality combination works better. Several experiments are run on the models by first considering one modality at a time so that good accuracy results are found on each modality. Afterward, the models are concatenated to create a final model that allows multiple inputs. For the experiments the datasets used are BAUM-1 ((Bahcesehir University multimodal Affective Database -1) and RAVDESS (Ryerson Audio-Visual Database of Emotional Speech and Song), which both collect two distinguished sets of videos based on the different intensity of the expression, that is acted/strong or spontaneous/normal, providing the representations of the following emotional states that will be taken into consideration: angry, disgust, fearful, happy and sad. The performances of the proposed models are shown through accuracy results and some confusion matrices, demonstrating better accuracy than the compared proposals in the literature. The best accuracy achieved on BAUM-1 dataset is about 95%, while on RAVDESS it is about 95.5%.

关键词： Emotion recognition multimodal emotion recognition multi-input model Biometrics Deep learning

来源：评论

学校读者我要写书评

暂无评论

Improving Real Estate Rental Estimations with Visual Data

引用

BIG DATA AND COGNITIVE COMPUTING 2022年第3期6卷 96页

作者： Azizi, Ilia Rudnytskyi, Iegor Univ Lausanne Fac Business & Econ Dept Operat CH-1015 Lausanne Switzerland

multi-modal data are widely available for online real estate listings. Announcements can contain various forms of data, including visual data and unstructured textual descriptions. Nonetheless, many traditional real estate pricing models rely solely on well-structured tabular features. This work investigates whether it is possible to improve the performance of the pricing model using additional unstructured data, namely images of the property and satellite images. We compare four models based on the type of input data they use: (1) tabular data only, (2) tabular data and property images, (3) tabular data and satellite images, and (4) tabular data and a combination of property and satellite images. In a supervised context, the branches of dedicated neural networks for each data type are fused (concatenated) to predict log rental prices. The novel dataset devised for the study (SRED) consists of 11,105 flat rentals advertised over the internet in Switzerland. The results reveal that using all three sources of data generally outperforms machine learning models built on only tabular information. The findings pave the way for further research on integrating other non-structured inputs, for instance, the textual descriptions of properties.

关键词： real estate visual cues satellite images deep learning computer vision multi-modal learning multi-input model

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：