检索结果-内蒙古大学图书馆

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Gupta, Kavya Tayal, Devendra Kumar Jain, Aarti Indira Gandhi Delhi Technical University for Women Department of Computer Science and Engineering Delhi India Netaji Subhas University of Technology Department of Electronics and Communication Engineering Delhi India

ISBN: (纸本)9798350371055

As the Internet of Things (IoT) continues to revolutionize data acquisition and dissemination, integrating monotonicity principles into data fusion (DF) processes emerges as a pivotal avenue for enhancing decision support systems (DSS). This paper explores the impact of monotonicity in DF, specifically focusing on its potential applications within the IoT landscape. The significance of DF in IoT is discussed, and the research delves into the concepts of monotonicity, elucidating its mathematical formulation, types, and integration into IoT DF algorithms. The review examines existing literature, identifying gaps and laying the groundwork for further exploration. Challenges and opportunities associated with implementing monotonicity in DF in IoT are scrutinized, providing insights into technical considerations and practical implications. The paper also explores monotonic fuzzy sets and their applications to DF. The paper concludes with reflections on key findings, contributions to the field, and recommendations for future research, establishing monotonicity as a promising avenue for unlocking the potential of DF in IoT applications. © 2024 IEEE.

关键词： Data Fusion Fuzzy Set Theory Internet of Things (IoT) Monotonic Fuzzy Sets Monotonicity

来源：评论

学校读者我要写书评

暂无评论

Depression Detection by Using Wearable Sensors

Depression Detection by Using Wearable Sensors

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Shrivastav, Vishal Giriraj Tiwari, Sudhanshu Singal, Gaurav Kushwaha, Riti Tewari, Tulika Gupta, Ankur Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India School of Computer Science and Technology Bennett University Greater Noida India Rishihood University Newton School of Technology Department of Computer Science Sonipat India

ISBN: (纸本)9798350364866

This research introduces an innovative approach to depression detection utilizing wearable health sensor systems integrated with machine learning models. By integrating self-reported PHQ-9 results and physiological measurements from wearable sensors, a comprehensive dataset was assembled. Evaluation of supervised and semi-supervised ML techniques displayed notable success, with Hybrid Supervised and Semi-Supervised Approach achieving a remarkable 98% accuracy in detecting Major Depressive Disorder (MDD), marking significant advancement in mental health technology. The study highlights the potential of wearable devices in proactive mental health monitoring and intervention. Insights from exploratory data analysis (EDA) informed algorithmic development, enhancing accuracy and robustness in depression detection. This research aims to make mental health support more accessible and helpful. Our results show that this wearable system could be useful in real-life situations for detecting depression. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Energy efficient random forest classifier-based secure routing for opportunistic internet of things

引用

International Journal of Ad Hoc and Ubiquitous Computing 2024年第2期46卷 80-89页

作者： Dhurandher, Anjay K. Kandhoul, Nisha Woungang, Isaac Chao, Han-Chieh Department of Information Technology Netaji Subhas University of Technology New Delhi India National Institute of Electronics and Information Technology New Delhi India Department of Computer Science Toronto Metropolitan University Toronto Canada Department of Artificial Intelligence Tamkang University Tamsui New Taipei Taiwan Department of Electrical Engineering National Dong Hwa University Hualien Taiwan Institute of Computer Science and Innovation UCSI University Kuala Lumpur Malaysia

Opportunistic internet of things (OppIoT) is a class of opportunistic networks, where the data are transmitted in a broadcast manner and shared among the nodes (i.e., IoT devices and human communities' devices) through opportunistic contact. In such networks, taking into consideration the energy level of each node while performing the routing of data is of utmost importance. This paper proposes an energy-efficient secure routing protocol that uses a random forest classifier (called ESRFCSec) for device behaviour predictions and for protecting the OppIoT network against packet collusion attacks. Through simulations, ESRFCSec is shown to achieve a prediction accuracy of 97.97%. It is also shown to be superior to three benchmark routing schemes in terms of node's residual energy, delivery probability, average latency, number of dead nodes, and number of dropped packets. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Framework for Domain Independent Hybrid Recommender Systems: Addressing Challenges of Imperfect Data

Framework for Domain Independent Hybrid Recommender Systems:...

引用

Information technology, Electronics and Intelligent Communication Systems (ICITEICS), IEEE International Conference on

作者： Amey Vibhute Department of Computer Engineering Netaji Subhas Institute of Technology Delhi India

ISBN: (数字)9798350382693

ISBN: (纸本)9798350382709

Recommender systems are an indispensable aspectof numerous contemporary online platforms, aiding users inuncovering new and pertinent content. However, both content-basedfiltering (CBF) and collaborative filtering (CF) systemsexhibit distinct strengths and limitations. CBF systems typicallyexcel at addressing cold start issues but their recommendationsmay falter when metadata is incomplete or absent. CF systems,on the other hand, can provide superior recommendationquality when ample data is accessible, but they may fail wheninsufficient data is available. To mitigate these limitations, thispaper puts forward a hybrid recommender system that harnessesthe strengths of both CBF and CF methodologies. Our systemassigns confidence scores to both models and dynamically assignsweights based on those scores to generate the most advantageousrecommendations. This approach empowers us to circumventthe drawbacks of each model and capitalize on their respectivestrengths. Our framework has been evaluated on a vast dataset ofuser ratings and movie metadata. The findings demonstrate thatour hybrid system outshines both CBF and CF systems in termsof recommendation quality, particularly for cold start users andunpopular items. Notably, our hybrid system empowers users tofine-tune the balance between the two models using a handfulof parameters which allows users to tailor the recommendationengine to their specific data and preferences.

关键词： Communication systems Collaborative filtering Metadata Motion pictures Information filters Information technology Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Improvement of Adhesive Joint Strength of Aluminium to Stainless Steel by Laser Texturing 5th

Improvement of Adhesive Joint Strength of Aluminium to Stain...

引用

5th International Conference on Emerging Trends in Mechanical and Industrial engineering, ICETMIE 2022

作者： Hassan, Mohammad Mishra, Abhishek Raghav, Manoj Pal, Monu Prakash, Shashi Kumar, Nitish Kumar, Subrata Department of Mechanical Engineering Netaji Subhas University of Technology New Delhi India Department of Mechanical Engineering Indian Institute of Technology Patna India

ISBN: (纸本)9789811969447

There has been an ever-increasing demand for safe and lightweight structures that necessitates creating strong and durable joints between dissimilar materials. The most preferred lightweight material is aluminium, and it has replaced stainless steel in various structural applications. Adhesive bonding is an emerging method that can be used for joining aluminium to stainless steel, as fusion welding of the two materials turns out to be very difficult due to their different metallurgical properties. The strength of an adhesive bond depends on the type of adhesive used, the joint design, and the kind of surface preparation method chosen. Different types of surface preparation methods exist, such as mechanical grinding, sand-blasting, anodizing, chemical etching, and laser irradiation. There are many advantages of laser texturing compared to the other methods in terms of eco-compatibility, energy efficiency, manufacturing ease, etc. With the aim of increasing the strength of the adhesive joint, the surfaces of aluminium and stainless steel 304 workpieces were prepared by laser texturing in the present work. Different types of surface textures were applied using a fibre laser. Lap-shear strength of the prepared samples was tested using a universal testing machine. Laser-textured grid pattern resulted in producing larger shear strength compared to other texture designs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Path Texture Detection for Visually Impaired using Transfer Learning 3

Path Texture Detection for Visually Impaired using Transfer ...

引用

3rd International Conference on Secure Cyber Computing and Communications, ICSCCC 2023

作者： Manjari, Kanak Animesh Verma, Madhushi Singal, Gaurav Bennett University Computer Science Engineering Gr. Noida India National Institute of Technology Computer Science & Engineering Delhi India Netaji Subhas University of Technology Computer Science Engineering India

ISBN: (纸本)9798350300710

The computer vision technique known as object detection is used to determine the location of an object in an image or video. Recent advances in a number of areas, including computer vision, speech recognition, and natural language processing have been made using deep learning approaches. Convolution neural networks (CNNs), which have several layers, are used to detect objects. A deep learning model that uses CNN to identify various surface regions has been suggested. The study of tracks, walkways, playgrounds, highways, and muddy areas is a pertinent and significant aspect of object detection for Visually Impaired (VI) individuals. In addition to adding indirect vision to the blind individual, this model recognizes surface regions and alerts them using text-to-sound conversion API. In this study, transfer learning was carried out utilizing Faster RCNN (Region Based Convolutional Neural Networks) with Inception V2 and ResNet50 model weights. The accuracy of both trained models was the same, while Faster RCNN Inception V2 had the lowest loss (0.02). © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A secure framework to preserve privacy of biometric templates on cloud using deep learning

引用

Recent Advances in computer Science and Communications 2021年第5期14卷 1412-1421页

作者： Arora, Shefali Bhatia, M.P.S. Division of Computer Engineering Netaji Subhas Institute of Technology Delhi India

Introduction: Cloud computing involves the use of maximum remote services through a network using minimum resources via internet. There are various issues associated with cloud com-puting, such as privacy, security and reliability. Due to rapidly increasing information on the cloud, it is important to ensure security of user information. Biometric template security over cloud is one such concern. Leakage of unprotected biometric data can serve as a major risk for the privacy of in-dividuals and security of real-world applications. Methods: In this paper, we improvise a secure framework named DeepCrypt that can be applied to protect biometric templates during the authentication of biometric templates. We use deep Convolu-tional Neural Networks to extract features from these modalities. The resulting features are hashed using a secure combination of Blowcrypt (Bcrypt) and SHA-256 algorithm, which salts the templates by default before storing it on the server. Results: Experiments conducted on the CASIA-Iris-M1-S1, CMU-PIE and FVC-2006 datasets achieve around 99% Genuine accept rates, proving that this technique helps to achieve better performance along with high template security. Conclusion: The proposed method is robust and provides cancellable biometric templates, high security and better matching performance as compared to traditional techniques used to protect the biometric template. © 2021 Bentham Science Publishers.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Hybrid Perceptual Structural and Pixelwise Residual Loss Function based Image Super-Resolution 3

Hybrid Perceptual Structural and Pixelwise Residual Loss Fun...

引用

3rd International Conference for Innovation in technology, INOCON 2024

作者： Singla, Shivam Bohat, Vijay Kumar Aggarwal, Manav Mehta, Yatin Netaji Subhas University of Technology Department of Computer Science and Engineering Azad Hind Fauj Marg Dwarka Sector-3 New Delhi Dwarka110078 India

ISBN: (纸本)9798350381931

Single Image Super-Resolution (SISR) aims to generate high-resolution (HR) images from the low-resolution (LR) input images. Deep learning techniques have significantly improved the HR outputs. These techniques primarily use the Mean Squared Error (MSE) Loss function for training purposes which considers pixels and doesn't take into account the structural information, textures, luminance, and contrast. These features play a crucial role in determining the perceptual quality of the image. Structural Similarity Index Metric (SSIM) can be manipulated to be used as a loss function that gives bright and well-structured HR images. However, this technique sometimes produces blurry and noisy HR outputs. To address this, a Hybrid Perceptual Structural and Pixel-wise Residual (HyPSPR) loss function approach has been introduced. This regularisation technique balances both factors. The Perceptual Structural (PS) Factor improves the structural information, textures, luminance, and contrast, while the Pixel-wise Residual (PR) Factor improves the encoded pixel-level information. A denoising and sharpening block in the model architecture has also been added to reduce the gaussian noise in the output. © 2024 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Depression Detection from Speech Using a Voting Ensemble Approach 8

Depression Detection from Speech Using a Voting Ensemble App...

引用

8th IEEE International Conference on Information and Communication technology, CICT 2024

作者： Bhatt, Nidhi Jain, Amita Jain, Minni Bhatt, Shobha Indira Gandhi Delhi Technical University for Women Department of Computer Science and Engineering Delhi India Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India Delhi Technological University Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798331531539

Depression is a widespread mental health condition affecting millions globally, making early detection and treatment crucial for public health. This study presents a voting ensemble machine learning approach for depression detection using speech data from the Distress Analysis Interview Corpus - Wizard of Oz (DAIC-WOZ) dataset. The research methodology includes speaker diarization, data augmentation, and feature extraction using OpenSMILE's eGeMAPS v2 feature set. Synthetic Minority Over-sampling Technique (SMOTE) is applied to balance the dataset. A hard voting ensemble classifier, combining Decision Tree, Random Forest, Gradient Boosting, and K-Nearest Neigh-bor as base models, is developed and optimized through two iterations. The final model achieves competitive performance with 78.69% accuracy, 77.78% precision, 75% recall, and a 76.36% F1-score, outperforming several existing methods on the DAIC-WOZ dataset. The analysis also revealed that Shimmer (voice amplitude variation) was the most significant acoustic feature, along with spectral flux, jitter, fundamental frequency, and loudness. This automated approach contributes to early depression detection efforts to improve access to mental health care. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Quantum Field Current Modelling in a Semiconductor 3rd

Quantum Field Current Modelling in a Semiconductor

引用

3rd International Conference on Computational Electronics for Wireless Communications, ICCWC 2023

作者： Vaish, Arti Parthasarathy, Harish Department of Computer Science and Engineering School of Engineering and Technology O P Jindal University CG Raigarh Punjipathra India Electronics and Communication Division Netaji Subhas University of Technology Dwarka New Delhi India

ISBN: (纸本)9789819719426

In this paper, we model the sea of electrons and holes within a semiconductor using the second quantized electron-positron Dirac wave operator field interacting with an applied classical electromagnetic field, a quantum photon field which can be regarded as quantum fluctuations of the electromagnetic field, and a noisy quantum photon field coming from the bath outside the semiconductor. Essentially, in this model, the Dirac wave field interacts and evolves along with the quantum photon field in the given background classical electromagnetic field and the given quantum noisy operator electromagnetic field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Photons

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：