检索结果-内蒙古大学图书馆

IEEE Transactions on Computational Biology and Bioinformatics 2025年第3期22卷 997-1008页

作者： Rupali Patua Anup Kumar Halder Soma Dasgupta Piyali Chatterjee Mita Nasipuri Subhadip Basu Department of Computer Science and Engineering Maulana Abul Kalam Azad University of Technology Haringhata India Department of Computer Science and Engineering Indian Institute of Information Technology Raichur India Department of Computer Science and Engineering Jadavpur University Kolkata India Department of Computer Science and Engineering Netaji Subhash Engineering College Kolkata India

Proteins interact with other proteins and bio-molecules to form a complex and execute key biological functions in a living organism, and respond to several environmental signals. Designing efficient predictive models for protein complexes is a challenging task with limited coverage in the contemporary literature. With this motivation, we have developed a novel method, PCPredG, for 3-node protein complex prediction from PPI networks using 5-node graphlet features. CORUM protein complex repository has been used to curate positive and negative data samples with the help of MCODE and MCL clustering algorithms. During experiments, Random Forest(RF) and SVM classifiers are trained with 1000 positive 3-node complexes in 10-fold cross-validation setup and with 1:1 to 1:10 positive-negative proportions. In parallel, we have implemented the state-of-the-art GCN with polarised message-passing, GAT and an ensemble of GCN and GAT in both balanced and imbalanced setups. We also introduced a 10-fold quality consensus on the hold-out set across all the experiments. We have achieved the best performances with the RF classifier in both balanced and imbalanced experiments.

关键词： Proteins Orbits Databases Clustering algorithms Vectors Predictive models Feature extraction Prediction algorithms Electronic mail computer science

来源：评论

学校读者我要写书评

暂无评论

Drought prediction using artificial neural network 2

Drought prediction using artificial neural network

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Metta, Pardha Saradhi Chintamaneni, Anish Kumar, Ashish Yadav, Jatin Kumar, Vishesh Bhaskar, Bharath Vellore Institute of Technology Department of Computer Science and Engineering Tamil Nadu Vellore India Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Tamil Nadu Coimbatore India Netaji Subhas University of Technology Dwarka Department of Information Technology Delhi India Karunya Institute of Technology and Sciences Department of Instrumentation and Technology Tamil Nadu Coimbatore India SRM Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Kattankulathur India Pes University Department of Electronics and Communications Karnataka Bangalore India

ISBN: (纸本)9781665437899

Drought has been one of the most frightening natural calamity that is being faced by the humans., and it is generally faced by the farmers all around the world. It can occur anywhere in the world and is also known as one of the slow disaster as it stays for a very longer time period and maybe even more if it wants to be harsher. Drought not only impacts the human life but also the agriculture, world economies and energy that had been infiltrated by the farmers. Everything goes on stakes during this calamity and the basic needs such as food are not easy to get during these times and the inflammation is at peak due to supply and demand instability. There are many ways which can be done to avoid the drought, which include drip irrigation to save water during the times of drought, rainwater harvesting can also be a saviour, crop engineering, desalination of water and many more things. The main solution for this would be to analyse the weather and the future outcomes of it which would help in preparing for the worse situation and also the soil prediction can help a lot when it comes to predicting this situation. The paper aims to take the data of weather and soil together to predict how droughts can be avoided. Deep learning techniques will help to get a great idea if the drought is going to happen or not. © 2022 IEEE.

关键词： Drought

来源：评论

学校读者我要写书评

暂无评论

Ontology-driven sentiment analysis in indian healthcare sector 8th

Ontology-driven sentiment analysis in indian healthcare sect...

引用

8th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2020

作者： Sharma, Abhilasha Chandra Singh, Anmol Pandey, Harsh Srivastava, Milind Department of Computer Science & Engineering Delhi Technological University Delhi42 India Netaji Subhas Institute Of Technology Delhi78 India

ISBN: (纸本)9789811556784

In today’s world, social media platforms have emerged as one of the most prominent media for expressing opinions. Sentiment analysis for utilizing the big data socially available over the web has become one of the most researched areas. Sentimental analysis is used to get the public perception over any event, topic or subject matter by classifying data into various polarity categories like positive, neutral, negative, etc. Various computational techniques such as machine learning and deep learning are used to perform polarity analysis and to find the best classifiers. Traditional techniques tend to create feature vectors in order to quantify the data, but these feature vectors are often very large for tweets collected over a particular domain and that leads to a performance reduction. This paper proposes a combined approach which utilizes domain ontology with machine learning methods in order to reduce the size of feature vector to increase the performance for all machine learning models. The observations state that our technique provides a significant advantage over the traditional methods. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.

关键词： Sentiment analysis

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

Path Texture Detection for Visually Impaired using Transfer ...

引用

International Conference on Secure Cyber Computing and Communication (ICSCCC)

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

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).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of Parkinson's Disease using CNN and ANN with the aid of Drawing and Acoustic Feature 2

Classification of Parkinson's Disease using CNN and ANN with...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Fiza, Syed Kumar, Ashish Yadav, Jatin Reddy, Sainandan Sidda, Tej Kurma Sai, Kaarthik Dayananda Sagar College of Engineering Department of Medical Electronics Karnataka Bengaluru India Delhi Technological University Department of Information Technology Shabad Daulatpur Delhi India Netaji Subhas University of Technology Department of Instrumentation and Technology Dwarka Delhi India Indian Institute of Technology Department of Civil Engineering Hyderabad India Gandhi Institute of Technology and Management Department of Computer Science and Engineering Andhra Pradesh Vishakhapatnam India Data Analytics Vellore Institute of Technology Department of Computer Science and Engineering Andhra Pradesh Amaravati India

ISBN: (纸本)9781665437899

Parkinson's disease manifests itself in a variety of ways. slurred speech, muscle rigidity, and tremors. The condition can also affect the production of the brain's dopamine. Therapies can help treat conditions after a diagnosis, however, there is no remedy. The paper primarily analyses the many drawing evaluation methods and disease diagnoses that have been used. The AI deep learning idea was used, along with convolutional neural networks and artificial neural networks. However, this article proposes a model for detecting disease using drawings of different persons from two classes. Disease detection on photos has been accomplished using a variety of techniques such as data augmentation, sequential, and CNN. The acoustic feature data was processed using a Decision tree and ANN with GridsearchCV, and the overall accuracy on testing data was 98 percent. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Simulation-Based Analysis of AlGaN/GaN Gate All Around Field Effect Transistor (AlGaN/GaN GAA-FET)

Simulation-Based Analysis of AlGaN/GaN Gate All Around Field...

引用

International Conference on VLSI and Microwave and Wireless Technologies, ICVMWT 2021

作者： Verma, Yogesh Kumar Mishra, Varun Gurjar, Rohit Chauhan, Rajeev Kumar Gupta, Santosh Kumar School of Electronics and Electrical Engineering Lovely Professional University Punjab Jalandhar144411 India Uttarakhand Dehradun248002 India Department of Electronics and Communication Engineering Netaji Subhas Institute of Technology New Delhi110078 India Department of Electronics and Communication Engineering Madan Mohan Malaviya University of Technology UP Gorakhpur273010 India Department of Electronics and Communication Engineering Motilal Nehru National Institute of Technology UP Allahabad211004 India

ISBN: (纸本)9789811903113

The multi-gate field effect transistors (FETs) offer significant merits in comparison with conventional devices such as less switching power, compatibility with current manufacturing processes, and scalability to sub10 nanometer regime. The short channel effects (SCEs) are significantly reduced in the multi-gate FETs along with improved control of gate over the channel. In this brief, the different performance parameters of AlGaN/GaN gate all around field effect transistor (GAA-FET) are computed for different device parameters using TCAD. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Aluminum gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection: Leveraging InceptionResNetV2 and LSTM for Enhanced Accuracy

Deepfake Detection: Leveraging InceptionResNetV2 and LSTM fo...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Aradhna Saini Attiuttama Sheenam Naaz Anushka Shivhare Gaurav Dhuriya Neha Yadav Computer Science and Engineering G L Bajaj Institute of Technology and Management Greater Noida Artificial Intelligence and Machine Learning G L Bajaj Institute of Technology and Management Greater Noida Computer Science and Engineering Sharda University Greater Noida Computer Science and Engineering Netaji Subhas University of Technology Delhi

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

The antique adage "seeing is believing" is simply no longer actual, which has profound implications for a ramification of sides of our lives. Deepfakes are becoming less complicated and simpler to create as technology advances. In fact, with the right software program, you can do a part of it right out of your palm. it is challenging to pick out deepfakes. The capability of the human eye to differentiate among deepfakes has reduced. however, a few academics have tried to identify deepfake. Deepfakes are media that can be generated by synthetic intelligence (AI) using algorithms. Artificial intelligence algorithms are designed to understand the traits of both the supply and the target photo. Subsequently, the target image is positioned on the pinnacle of the supply photograph. Our goal is to pick out video deepfakes by way of utilizing deep getting-to-know neural networks which include InceptionResNetV2 and LSTM. With the usage of transfer learning and the pre-trained InceptionResNetV2 CNN for characteristic extraction and vector production, we were able to efficaciously assemble a deepfake detection version. The capabilities had been used to train the LSTM layer, and the confusion matrix that was produced offers us the accuracy of testing and validation. The corresponding version's accuracy for 20 and 40 epochs was 84.75% and 91.48%, respectively.

关键词： Deepfakes Accuracy Neural networks Transfer learning Streaming media Vectors Artificial intelligence Long short term memory Faces Testing

来源：评论

学校读者我要写书评

暂无评论

Towards Intelligent Decision Making for Charging Scheduling in Rechargeable Wireless Sensor Networks

SSRN

引用

SSRN 2023年

作者： Tomar, Abhinav Anwit, Raj Raut, Piyush Nawnath Singal, Gaurav Department of Computer Science and Engineering Netaji Subhas University of Technology New Delhi110078 India Department of Computer Science and Engineering Bhagalpur College of Engineering Bhagalpur812001 India

Wireless energy transfer (WET) technology has proven to mitigate the energy shortage challenge faced by the Internet of Things (IoT) encompassing Sensor Networks. Exploiting Mobile Charger (MC) to energize critical sensors provides a new dimension to maintain continual network operations, but existing solutions are not robust as they suffer from high charging delays at the sensor end due to inefficient scheduling. Thus, intelligent scheduling for an MC is needed based on decision-making through multiple network performance-affecting attributes but blending multiple attributes together for wise scheduling decision-making remains challenging which is overlooked in previous research. Fortunately, Multi-Criteria Decision Making (MCDM) is best-fit herein for considering numerous attributes and picking the most suitable sensor node to charge next. To this end, we have proposed solving the scheduling problem by combining two MCDM techniques, i.e., Combinative Distance Based Assessment (CODAS) and the Best Worst Method (BWM). The attributes used for the decision are the distance to MC, energy consumption rate, the remaining energy of nodes, and neighbourhood criticality. The relative weights of all considered network attributes are calculated by BWM, which is followed by CODAS to select the most appropriate node to be charged next. To make the scheme more realistic and practical in time-critical applications, the dynamic threshold of nodes is calculated along with formulation scheduling feasibility conditions. The results of the simulations demonstrate the efficiency of the proposed scheme over the competing approaches on a variety of performance parameters. © 2023, The Authors. All rights reserved.

关键词： Energy efficiency

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

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

引用

Conference on Information and Communication technology (CICT)

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

ISBN: (数字)9798331531539

ISBN: (纸本)9798331531546

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.

关键词： Mental health Jitter Depression Feature extraction Information and communication technology Ensemble learning Decision trees Public healthcare Interviews Random forests

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Congestion Control Mechanism for Opportunistic Networks

Reinforcement Learning Based Congestion Control Mechanism fo...

引用

2022 IEEE GLOBECOM Workshops, GC Wkshps 2022

作者： Singh, Jagdeep Dhurandher, Sanjay Kumar Woungang, Isaac Chatzimisios, Periklis Rodrigues, Joel J. P. C. Sant Longowal Institute of Engineering and Technology Department of Computer Science and Engineering Punjab Longowal India Netaji Subhas University of Technology Department of Information Technology New Delhi India Ryerson University Department of Computer Science TorontoON Canada International Hellenic University Thessaloniki Greece College of Computer Science and Technology Qingdao China Instituto de Telecomunicações Covilhã6201-001 Portugal

ISBN: (纸本)9781665459754

This work proposes a Reinforcement Learning-based Congestion Control protocol (called (RLCC)) for Opportunistic Networks to find the optimal number of message counts based on the real-time density in the network. (RLCC) jointly uses Q-learning and fuzzy logic to make the routing decision based on real attributes such as social status, centrality, activeness, message lifetime, hop count, and battery status. In the proposed (RLCC) scheme, the message priority is required to maintain the optimal count of messages in the network, and the fuzzy inference rules perform well in predicting the best hop for message transmission. All network nodes get inputs from the environment and take action accordingly. If the message is transferred successfully to the intended node, then the node receives the reward for the action, otherwise, the penalty will be assigned. Based on this, network nodes only select those nodes, which are capable to transmit the message from one node to another node. Simulation results demonstrate that RLCC is superior to the MARLCC and F-GSAF routing protocols using the infocom2006 real mobility data trace, in terms of delivery probability, latency, and overhead ratio. © 2022 IEEE.

关键词： Reinforcement 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：