检索结果-内蒙古大学图书馆

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Pallavi, Gundala Prasanna Kumar, R. Oviya, I.R. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350370249

Protein secondary structure prediction is a critical task in bioinformatics, essential for understanding protein function and aiding drug discovery. Traditional methods have achieved significant milestones, but there remains a need for further accuracy and efficiency improvements. In this paper, we propose a novel approach that combines Bidirectional Long Short-Term Memory BiLSTM networks and Transformer models to enhance prediction accuracy. Our dual-model strategy leverages the sequential processing strengths of BiLSTM and the robust attention mechanisms of Transformers, enabling a more comprehensive analysis of protein sequences. Our extensive experiments demonstrate that this hybrid approach achieves superior performance, with Q3 accuracy reaching 92.03% and Q8 accuracy at 85.26%, significantly surpassing existing methods. This enhancement is ascribed to the capacity of BiLSTM to capture long-range dependencies and the Transformer's capability to focus on relevant parts of the sequence. The integration of these models provides a powerful tool for predicting protein secondary structures with high precision. The findings suggest that our approach not only advances the current state of PSSP but also offers valuable insights that can accelerate bioinformatics research and drug discovery processes. This work underscores the potential of combining deep learning models to tackle complex biological challenges more effectively. © 2024 IEEE.

关键词： Bioinformatics Deep Learning LSTM Protein Secondary Structure Transformer Models

来源：评论

学校读者我要写书评

暂无评论

Advancing Personality Detection through Word Embedments and Deep Learning: An Examination Using the MBTI Dataset 6

Advancing Personality Detection through Word Embedments and ...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Shanmukha, Aditya G Shamyuktha, R.S. Karan, S. Gupta, Deepa Palaniswamy, Suja Amrita School of Computing Bengaluru Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9798350381689

Personality detection and classification hold significant potential for enhancing decision-making processes and optimizing outcomes across various sectors. This interdisciplinary field finds applicative relevance in numerous domains such as business, healthcare, education, and personal development. In an effort to contribute to this burgeoning area of research, this paper introduces a comprehensive model specifically designed for personality detection. The model is rigorously tested on the Myers-Briggs Type Indicator (MBTI) dataset, a widely recognized framework in personality typology. The core of this proposed model lies in its innovative integration of four advanced word embeddings: Keras, Word2Vec, Glove, and FastText. These embeddings are coupled with cutting-edge deep learning architectures, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, Bidirectional LSTM (BI-LSTM), a hybrid of CNN and LSTM, and Gated Recurrent Units (GRU). This amalgamation results in a suite of 18 distinct models, each offering unique insights into personality classification. The implementation of these models is meticulously undertaken, and the outcomes are documented in detail. The results of this research which is 82% of accuracy, not only demonstrate the efficacy of combining various word embeddings with deep learning techniques but also pave the way for future explorations in the field of personality detection and classification. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

EBSDNET - Endanger Bird Species Detection Net using ResNet50 2

EBSDNET - Endanger Bird Species Detection Net using ResNet50

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Dharshan, R Divya Diviya, M. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350372892

In India Numerous individuals enjoy bird watching, but identifying bird species often requires consulting reference books. However, many bird species are in the verge of extinction because of climatic change and environmental change. These Changes results in many problems like, forest degradation, urbanization and avian disease. It is a threat to biodiversity because the destruction of birds are happening in rapid phase so it must be safeguarded. The use of hidden camera in wildlife for monitoring these species is skyrocketed in todays world but manually examining and taking information from vast data gathered by hidden camera be tiresome and time consuming. So to overcome this we have proposed a ResNet-50 to detect and classify these endanger bird species using image processing. This model was trained using a dataset comprising 3520 images, each depicting one of 38 unique bird species. The images had a resolution of 224 by 224 pixels. The proposed model in this work attained an accuracy level of 98.64 %. Various performance measures also evaluated to test the efficacy of the proposed work. Comparison study with the existing work also reveals that the proposed methodology yields fine results. © 2024 IEEE.

关键词： Endanger Bird species Image processing pre-trained model Resnet 50

来源：评论

学校读者我要写书评

暂无评论

Consumer Behaviour Analysis for Customer Segmentation and Purchase Prediction 10

Consumer Behaviour Analysis for Customer Segmentation and Pu...

引用

10th International Conference on Advanced computing and Communication Systems, ICACCS 2024

作者： Gopakumar, Amritha Shine, Aathira Ajim, Amina Anjali, T. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India

ISBN: (纸本)9798350384369

E-commerce, short for electronic commerce, is the practice of placing orders online or negotiating a sale's terms and price. Although e-commerce is often associated with selling products and services to consumers, business-to-business (B2B) transactions also make use of it. To market their goods, many smaller consumer enterprises rely only on online sales. Nowadays, people are choosing to make purchases online as online transaction mechanisms and shopping platforms develop. Nevertheless, given that both clients and Merchants are unable to interact with clients face-to-face, there is a limited understanding of consumer demands. Due to this, businesses may struggle to gauge nuanced cues such as body language and personal preferences. Limited direct engagement can hinder the ability to address specific customer needs and preferences, potentially resulting in misinterpretation or overlooking crucial details. In turn, businesses may face difficulties in tailoring their products or services to meet the nuanced expectations of their customers, emphasizing the importance of alternative strategies such as detailed customer feedback mechanisms and data analytics to bridge this gap. The online system logs user activity and gathers data on consumer behaviour, allowing for the prediction of consumer purchasing patterns. Therefore, to improve the shopping experience of people, our study aims to use historical sales data to analyze consumer behaviour and do customer segmentation using RFM (Recency, Frequency, and Monetary) based K-means clustering and purchase prediction using various ML models to improve sales, out of which the combination of Logistic Regression and XGBoost performed the best. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Smart Traffic Flow Optimization with IoT and Machine Learning 15

Smart Traffic Flow Optimization with IoT and Machine Learnin...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Poojitha, D. Darak, Tanmay Samaddar, Ushnish Khanna, Manju Amrita Vishwa Vidyapeetham Amrita School Of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Traffic signal optimization is crucial for the effective traffic management within cities with the primary goals being the reduction of bottleneck occurrences, avoidance of the extension of travelling time, and improvement of overall city street network function. Historically used approaches can hardly be adjusted to fluctuating traffic situation. Hence, a new methodology involving the use of machine learning-based traffic signal control with the assistance of the IR (Infrared) /UV (Ultraviolet) sensors for traffic flow sensing in real-Time environment is introduced in this study. The UV sensors make congestion distance measurements in real time which are assisted by IR sensors for traffic information acquisition. Historic data with data gathered from the traffic sensors are used to train the machine learning model to predict traffic. The strategy employs the use of heuristic search methodologies in the determination of signal timings with reference to congestion information that has been forecasted as well as congestion information that is being experienced. This paper discusses the fact that machine learning-based approaches, supported by sensor technology, can be used for effective traffic management systems that modify with the help of data. The success of this traffic management system is proved by its ability to minimize the MSE (Mean Squared Error) of congestion predictions to an average of 0.69. © 2024 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Implementation and Analysis of TCP CUBIC Congestion Control System in Mininet 9

Implementation and Analysis of TCP CUBIC Congestion Control ...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Sunder, S Navin Akathya, Ve Ram Seshadri, Samarth Rajagopal, Shinu M. Bhaskaran, Sreebha Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science And Engineering Bengaluru India

ISBN: (纸本)9798350394474

In the realm of data transfer dynamics, an intricate comprehension of congestion control is imperative for the seamless optimization of network performance. This study rigorously delves into the complexities, unveiling discernible disparities between sending rates and throughput. Emphasizing the critical role of congestion control, the research highlights escalating retransmissions and congestion as pronounced inefficiencies. The proposed methodology encompasses a thorough examination of packet loss, network utilization, and queuing delays, paired with the implementation of effective congestion control strategies. Post-implementation, the results demonstrate a significant enhancement in network performance, characterized by adaptive sending rates and minimized inefficiencies. This research underscores congestion control's pivotal role in optimizing performance, offering valuable insights for achieving an efficient and responsive network. © 2024 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

3D shape knowledge graph for cross-domain 3D shape retrieval

引用

CAAI Transactions on Intelligence Technology 2024年第5期9卷 1199-1216页

作者： Rihao Chang Yongtao Ma Tong Hao Weijie Wang Weizhi Nie School of Microelectronics Tianjin UniversityTianjinChina School of Life Sciences Tianjin Normal UniversityTianjinChina Department of Information Engineering and Computer Science University of TrentoTrentoItaly School of Electrical and Information Engineering Tianjin UniversityTianjinChina

The surge in 3D modelling has led to a pronounced research emphasis on the field of 3D shape *** contemporary approaches have been put forth to tackle this intricate ***,effectively addressing the intricacies of cross-modal 3D shape retrieval remains a formidable undertaking,owing to inherent modality-based *** authors present an innovative notion—termed“geometric words”—which functions as elemental constituents for representing entities through *** establish the knowledge graph,the authors employ geometric words as nodes,connecting them via shape categories and geometry ***,a unique graph embedding method for knowledge acquisition is ***,an effective similarity measure is introduced for retrieval ***,each 3D or 2D entity can anchor its geometric terms within the knowledge graph,thereby serving as a link between cross-domain *** a result,the authors’approach facilitates multiple cross-domain 3D shape retrieval *** authors evaluate the proposed method's performance on the ModelNet40 and ShapeNetCore55 datasets,encompassing scenarios related to 3D shape retrieval and cross-domain ***,the authors employ the established cross-modal dataset(MI3DOR)to assess cross-modal 3D shape *** resulting experimental outcomes,in conjunction with comparisons against state-of-the-art techniques,clearly highlight the superiority of our approach.

关键词： 3‐D multimedia

来源：评论

学校读者我要写书评

暂无评论

Quantum computing for Climate Change: A Comprehensive Review of Current Applications, Challenges, and Future Directions 15

Quantum Computing for Climate Change: A Comprehensive Review...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Ashwani, Siddhant Tripathy, Aayushi Jeeban Karna, Siwani Reddy Jahanve, Poluru Rajagopal, Shinu M. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

The need for creative ideas to address the growing challenges posed by climate change has become critical. This paper explores the various uses of quantum computing for mitigating climate change, with an emphasis on energy optimization, improved climate modeling, and weather forecasting. Environmental modeling, chemistry, material science, carbon capture techniques, and other significant applications have also been discussed. Finding important approaches, results, and associated technological constraints is the current state of study. Examining relevant case studies, the review suggests strategic directions for future research on climate change enabled by quantum computing. It serves as an essential tool for scientists, policymakers, and researchers, enabling a deeper comprehension of the potential of quantum computing in environmental science and encouraging multidisciplinary cooperation for the long-term mitigation of climate change. © 2024 IEEE.

关键词： and energy optimization carbon capture climate change climate modeling energy optimization quantum computing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Autism Detection Using Eye Tracking Scanpaths 2

Deep Learning for Autism Detection Using Eye Tracking Scanpa...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Supritha, R. Bharathi Mohan, G. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350360523

Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by difficulties in social interaction, communication, and limited repetitive behaviors, with symptoms varying significantly among individuals. Eye tracking holds promise in autism detection due to its unique ability to capture and analyze visual attention patterns, providing insights into the cognitive processes and atypical visual behaviors associated with ASD. Eye-tracking technology offers a unique perspective, allowing the observation and quantification of visual attention patterns, which may reveal distinctive features associated with ASD. These visualizations represent how individuals, particularly those with ASD, explore and engage with stimuli. In this research, we propose a novel approach using deep learning models, specifically DenseNet-201, EfficientNet B7, ResNet-50, and MobileNetV2, to analyze eye-tracking scan paths for ASD detection. The dataset focuses on visualizations of eye-tracking scan paths, primarily involving individuals with ASD. The study yielded promising results, with the deep learning models achieving accuracies of 94.97%, 94.74%, 84.21%, and 92.45%, respectively. DenseNet-201 demonstrated the highest accuracy at 94.97%. The research contributes to advancing early diagnosis and intervention strategies for individuals with ASD. © 2024 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Evolutionary Algorithm Based on Decomposition—Dynamic Resource Allocation with Mixture Model 2nd

A Multi-objective Evolutionary Algorithm Based on Decomposi...

引用

2nd International Conference on Advances in Data-driven computing and Intelligent Systems, ADCIS 2023

作者： Alagumathi, M. Thangavelu, S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9789819995301

Multi-objective evolutionary algorithm based on decomposition (MOEA/D) is the basis for studying the concept of multi-objective optimization problems on the basis of decomposition. MOEA/D has computational complexity in solving the multi-objective optimization sub-problems. To reduce computational complexity, in 2009, Zhang et al. proposed a method called MOEA/D-DRA (MOEA/D-Dynamic Resource Allocation). In MOEA/D-DRA, each sub-problem utilizes the computational resources dynamically in a different way. The construction of weight vectors is very important for the success of these algorithms. They actually define the search directions and distribution of the Pareto optimal solutions (POS). This paper proposes a weight vector generation method using uniform design and a mixture model (called MOEA/D-DRA-MM). The MOEA/D-DRA-MM builds a new weight vector generation method that makes the distribution of the weights uniform and broadens the diversity and convergence. MOEA/D-DRA-MM uses two weight vectors that are obtained by uniform design with a mixture distribution. Simulation results suggest that MOEA/D-DRA-MM may provide better convergence and diversity with respect to inverted generational distance and hypervolume metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multiobjective optimization

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：