检索结果-内蒙古大学图书馆

Smart Electronics and Communication Systems (ISENSE), International Conference on

作者： Samagnya Dudipala Shalini Gangavarapu Girish K K Biswajit Bhowmik BRICS Lab Department of Computer Science and Engineering Ishwarchandra Vidyasagar AIT Lab National Institute of Technology Karnataka Surathkal Mangalore Bharat

ISBN: (数字)9798331528126

ISBN: (纸本)9798331528133

In the realm of the Internet of Things (IoT), devices continuously generate a vast and relentless stream of data, providing a real-time representation of digital landscape. The continuous and high-velocity nature of this streaming data poses significant challenges for real-time analysis. Accurate outlier detection within this data is essential, as such anomalies may indicate critical issues, attacks, or errors. Nevertheless, the dynamic and rapidly evolving characteristics of streaming data render traditional outlier detection methods inadequate. This paper investigates the application of Artificial Neural Networks (ANNs), specifically a Multi-Layer Perceptron (MLP), for outlier detection in streaming IoT data. The selection of the MLP from a range of Deep Neural Networks (DNNs) is based on its optimal balance between computational efficiency and model complexity. The model's efficacy is confirmed through rigorous experimentation, demonstrating strong performance across diverse scenarios and data classes. The MLP achieved an accuracy of 99.4%, underscoring its ability to detect even minor deviations from expected patterns. This high level of accuracy establishes the MLP as a robust tool for outlier detection in dynamic IoT environments.

关键词： Training Adaptation models Accuracy Computational modeling Artificial neural networks Real-time systems Data models Complexity theory Internet of Things Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Context-Aware Mobile Computing for Improved Academic Supervisory Processes 5th

Deep Learning and Context-Aware Mobile Computing for Improve...

引用

5th International Conference on Electrical and Electronics engineering, ICEEE 2024

作者： Ali, Nayem Shorme, Irin Hira, Md. Mahdi Hossain Munim, Md. Abdul Kohinoor, Md. Saidur Rahman Department of Computer Science and Engineering Leading University Sylhet Bangladesh Research Lab Sylhet Bangladesh Department of Information and Computer Science King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia

ISBN: (纸本)9789819791118

In academic settings, especially in densely populated areas, supervisory roles face multifaceted challenges. Managing communication, discussions, task assignments, attendance tracking, and schedule coordination across varied platforms can be particularly burdensome, also detracting from students’ experiences. Existing mobile applications generally lack the necessary integration for these settings, as they are predominantly designed with industrial project management needs in mind. Our study introduces "Supervision", a comprehensive mobile application that leverages deep learning and context-aware computing to address these challenges. Apart from integrating the latest mobile application development and intuitive UI/UX technologies, we conducted a comparative analysis of popular facial recognition models (FaceNet, OpenFace, DeepFace, and VGGFace) using the LFW dataset to deploy the most ideal model in real-time face identification on resource-limited devices. Evaluating several criteria (accuracy, inference time, and memory utilization), our findings revealed that FaceNet outperformed other models with 94.04% accuracy, the shortest inference time (0.018 sec), and the lowest memory usage. This study also enhances the efficiency of the supervisory process, promoting timely project completion and fostering robust communication between supervisors and students. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Hybrid MPI and OpenMP on Smith-Waterman Algorithm

Performance Analysis of Hybrid MPI and OpenMP on Smith-Water...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Keyur Ninama Jainamkumar Patel Girish K K Manideep Raya V S R S Reddy Biswajit Bhowmik Dept. of Computer Science and Engineering Maharshi Sushrut CAS Lab BRICS Laboratory National Institute of Technology Karnataka Mangalore Bharat Dept. of Computer Science and Engineering Ishwarchandra Vidyasagar AIT Lab BRICS Laboratory National Institute of Technology Karnataka Mangalore Bharat Dept. of Computer Science and Engineering Maharshi Kanad QC Lab BRICS Laboratory National Institute of Technology Karnataka Mangalore Bharat Dept. of Computer Science and Engineering BRICS Laboratory National Institute of Technology Karnataka Mangalore Bharat

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

In the rapidly advancing field of bioinformatics, sequence alignment is a pivotal task for elucidating genetic statistics and evolutionary relationships. As the volume and complexity of biological data continue to grow, it becomes imperative to employ effective computational techniques to manage this expansion. The Smith-Waterman algorithm is a key tool for sequence alignment; however, its performance can be constrained by the substantial size of contemporary datasets. To overcome this limitation, this paper explores a hybrid parallelization strategy that integrates message passing interface (MPI) with open multi-processing (OpenMP). This approach aims to significantly enhance the algorithm’s efficiency by leveraging the strengths of both parallelization models. By optimizing the scalability and execution speed of the Smith-Waterman algorithm on advanced high-performance computing (HPC) systems, the hybrid technique not only improves performance but also enables more rapid and accurate biological data analysis.

关键词： Data analysis Scalability Message passing High performance computing Memory management Parallel processing Genetics Performance analysis Bioinformatics Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Synergizing Internal and External Knowledge: Prompt engineering for Efficient and Effective Large Language Model Reasoning

Synergizing Internal and External Knowledge: Prompt Engineer...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Lu, Gewei He, Chaofan Shen, Liping Shanghai Jiao Tong University X-LANCE Lab Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9781665410205

Large language models (LLMs), such as ChatGPT, have demonstrated remarkable capability in question answering but face challenges when it comes to knowledge-based rea-soning, such as limited training data and hallucination. To address these challenges, integrating LLMs with knowledge graphs (KGs) has emerged as a promising solution. However, the cost associated with training and inference of LLMs is high. Our method integrates the Retrieval-Augmented Generation (RAG) paradigm, incorporating relevant information from KGs alongside the question to enhance LLMs' reasoning process without training. Moreover, we propose a novel concept of self-knowledge motivation to reduce the overhead of inference, which prompts LLMs to integrate retrieved information with their internal knowledge for reasoning before seeking additional queries to KGs. Experimental results showcase improvements in answer accuracy and a reduction in LLMs' API calls compared to the latest published state-of-the-art (SOTA) method employing an identical paradigm, underscoring the efficiency and effectiveness of our method. © 2024 IEEE.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Leveraging Hybrid Modeling for Enhanced Runtime Prediction in Big Data Jobs

Leveraging Hybrid Modeling for Enhanced Runtime Prediction i...

引用

Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications (COSMIC), International Conference on

作者： Rahul Singh Vivek Narayan Zadokar Sunil Kumar Sachin Shivaji Doddamani Biswajit Bhowmik Department of Computer Science and Engineering Ishwarchandra Vidyasagar AIT Lab BRICS Laboratory National Institute of Technology Karnataka Mangalore India

ISBN: (数字)9798331517892

ISBN: (纸本)9798331517908

In an era of rapid data expansion, big data has significantly transformed various industries, redefining the processes of data processing, analysis, and utilization. The widespread adoption of digital technologies has driven this surge in big data, leading to an unprecedented accumulation of information from sources such as social media, sensors, and transactions. As big data evolves, it presents significant challenges and unique opportunities, necessitating innovative solutions to leverage its potential fully. One critical challenge in big data environments is accurately predicting job runtimes, essential for optimizing resource utilization and enhancing overall system performance. Current approaches, including analytical models and machine learning algorithms, often need help to manage the complexities of unstructured data and maintain interpretability effectively. This paper proposes a novel hybrid modeling approach that integrates the strengths of both techniques to improve job runtime predictions. The hybrid architecture combines an analytical model, which captures the intricate characteristics of jobs and execution environments, with a machine learning model trained to detect patterns and relationships in historical data. As demonstrated on real-world big datasets, the hybrid model achieves greater accuracy by merging these capabilities. Utilizing the flexible capabilities of PySpark and incorporating advanced feature engineering techniques, the model dynamically adapts to various dataset sizes and complexities, ensuring robust performance across different scenarios.

关键词： Training Semiconductor device modeling Analytical models Adaptation models Runtime Computational modeling Predictive models Big Data Data models Resource management

来源：评论

学校读者我要写书评

暂无评论

Exploring Explainable AI for Enhanced Depression Prediction in Mental Health 1

Exploring Explainable AI for Enhanced Depression Prediction ...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Jo, Ashly Ann Raj, Ebin Deni Vino, Angel Susan Menon, Parvathy V. Indian Institute of Information Technology FACTS-H Lab Department of Computer Science & Engineering Kottayam India

ISBN: (纸本)9798350376517

Depression is a prevalent mental health condition affecting millions of individuals worldwide. This paper presents a comprehensive analysis using machine learning to predict depression, a prevalent mental health issue affecting millions worldwide. The dataset employed for this study includes a range of mental health conditions such as schizophrenia, bipolar disorder, eating disorders, anxiety disorders, drug use disorders, and alcohol use disorders, investigating their correlations with depression. We explore these relationships and develop predictive models to forecast the likelihood of depression. The study evaluates the performance of various machine learning algorithms, with the Random Forest algorithm demonstrating the highest accuracy rate of 99.30%. Furthermore, we delve into model interpretability by applying techniques like LIME and SHAP to explain the predictions. Our findings contribute significantly to the understanding and prediction of depression, offering valuable insights that could assist healthcare professionals in the early detection and proactive management of this condition. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

ABSPYRAMID: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph

ABSPYRAMID: Benchmarking the Abstraction Ability of Language...

引用

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Wang, Zhaowei Shi, Haochen Wang, Weiqi Fang, Tianqing Zhang, Hongming Choi, Sehyun Liu, Xin Song, Yangqiu Department of Computer Science and Engineering HKUST Hong Kong Tencent AI Lab Bellevue United States

ISBN: (纸本)9798891761193

Cognitive research indicates that abstraction ability is essential in human intelligence, which remains under-explored in language models. In this paper, we present ABSPYRAMID, a unified entailment graph of 221K textual descriptions of abstraction knowledge. While existing resources only touch nouns or verbs within simplified events or specific domains, ABSPYRAMID collects abstract knowledge for three components of diverse events to comprehensively evaluate the abstraction ability of language models in the open domain. Experimental results demonstrate that current LLMs face challenges comprehending abstraction knowledge in zero-shot and few-shot settings. By training on our rich abstraction knowledge, we find LLMs can acquire basic abstraction abilities and generalize to unseen events. In the meantime, we empirically show that our benchmark is comprehensive to enhance LLMs across two previous abstraction tasks. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Enhancing crop yield prediction in Senegal using advanced machine learning techniques and synthetic data

引用

Artificial Intelligence in Agriculture 2024年第4期14卷 99-114页

作者： Mohammad Amin Razavi A.Pouyan Nejadhashemi Babak Majidi Hoda S.Razavi Josue Kpodo Rasu Eeswaran Ignacio Ciampitti P.V.Vara Prasad School of Electrical and Computer Engineering University of TehranTehranIran Department of Biosystems and Agricuttural Engineering Michigan State UniversityMIUSA Department of Computer Engineering Khatam UniversityTehranIran Department of Computer Science and Engineering Michigan State UniversityEast LansingMIUSA Department of Agronomy Faculty of AgricultureUniversity of JafinaKilinochchSri Lanka Department of Agronomy Kansas State UniversityManhattanKSUA Feed the Future Sustainable Intensification Innovation Lab Kansas State UniversityManhattanKSUA

In this study,we employ advanced data-driven techniques to investigate the complex relationships between the yields of five major crops and various geographical and spatiotemporal features in *** analyze how these features influence crop yields by utilizing remotely sensed *** methodology incorporates clustering algorithms and correlation matrix analysis to identify significant patterns and dependencies,offering a comprehensive understanding of the factors affecting agricultural productivity in *** optimize the model's performance and identify the optimal hyperparameters,we implemented a comprehensive grid search across four distinct machine learning regressors:Random Forest,Extreme Gradient Boosting(XGBoost),Categorical Boosting(CatBoost),and Light Gradient-Boosting Machine(LightGBM).Each regressor offers unique functionalities,enhancing our exploration of potential model *** top-performing models were selected based on evaluating multiple performance metrics,ensuring robust and accurate predictive *** results demonstrated that XGBoost and CatBoost perform better than the other *** introduce synthetic crop data generated using a Variational Auto Encoder to address the challenges posed by limited agricultural *** achieving high similarity scores with real-world data,our synthetic samples enhance model robustness,mitigate overfitting,and provide a viable solution for small dataset issues in *** approach distinguishes itself by creating a flexible model applicable to various crops *** integrating five crop datasets and generating high-quality synthetic data,we improve model performance,reduce overfitting,and enhance *** findings provide crucial insights for productivity drivers in key cropping systems,enabling robust recommendations and strengthening the decision-making capabilities of policymakers and farmers in datascarce regions.

关键词： Crop yield prediction Variational auto encoder Pattern recognition on spatiotemporal and physiographical variables Synthetic tabular data generation Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Money Laundering Detection in Banking Transactions using RNNs and Hybrid Ensemble

Money Laundering Detection in Banking Transactions using RNN...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： K K Girish Biswajit Bhowmik Department of Computer Science and Engineering Ishwarchandra Vidyasagar AIT Lab BRICS Lab National Institute of Technology Karnataka Surathkal Mangalore Bharat

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The financial sector has witnessed significant transformations due to the emergence of financial technology (FinTech), transitioning from traditional paperbased processes to a dynamic digital ecosystem. Despite the industry’s advancements driven by FinTech innovations, concerns persist, particularly regarding financial fraud, notably money laundering. Perpetrators exploit modern technologies to launder illicitly obtained funds, posing a global threat to economies. Effective detection mechanisms for money laundering are crucial. This paper introduces a novel approach utilizing a recurrent neural network (RNN) for detecting money laundering in banking transactions. The proposed framework exercises standalone RNN models such as LSTM, GRU, BiLSTM, and stacked RNN models for the detection. Additionally, the effectiveness of hybrid ensemble models combining RNNs with XGBoosts is investigated. The evaluation achieves standard performance metrics, with the stacked RNN model achieving 92% accuracy. Surpassing it, the ensemble model achieves an impressive 95%. These results underscore the superiority of hybrid ensemble models over standalone RNNs, particularly in accurately detecting money laundering activities.

关键词： Measurement Technological innovation Recurrent neural networks Biological system modeling Refining computer architecture Banking Stability analysis Security Standards

来源：评论

学校读者我要写书评

暂无评论

Sales Prediction in the Retail Industry Using Machine Learning: A Case Study of BigMart

Sales Prediction in the Retail Industry Using Machine Learni...

引用

2023 IEEE International Conference on Electrical, Electronics, Communication and computers, ELEXCOM 2023

作者： Upadhyay, Hrishabh Shekhar, Sushant Vidyarthi, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Computer Science Engineering Dehradun India Propagation Research Lab Department of Electronics & Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350305111

This research paper presents a machine learning-based approach for sales prediction in the retail industry. The study was conducted using data collected from the BigMart retail chain. The research aimed to develop an accurate predictive model to forecast different products' sales in various BigMart stores. The study involved the implementation of several machine learning algorithms, including linear regression, decision tree, random forest, gradient boosting, support vector machine, convolutional neural network, and long short-term memory. The models were trained and evaluated using a dataset comprising of over 8,000 entries of sales data from different BigMart stores. The results showed that the convolutional neural network and long short-term memory models outperformed the other algorithms in terms of accuracy, with an R-squared value of 0.68 and 0.69, respectively. The study also identified the most significant features affecting sales, including item weight, store location, and promotional activities. The findings of this research have significant implications for the retail industry, as accurate sales prediction can help businesses optimize their inventory management and marketing strategies. The study also highlights the potential of machine learning algorithms for sales forecasting in the retail sector. In conclusion, this research demonstrates the effectiveness of machine learning in predicting sales and highlights the importance of leveraging advanced analytical techniques for improving business performance in the retail industry. © 2023 IEEE.

关键词： Sales

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：