检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Kumar, Deepak Dhamdhere, Piyush Raman, Balasubramanian Department of Computer Science and Engineering Indian Institute of Technology Roorkee Roorkee247667 India

ISBN: (纸本)9783031783043

Recognizing social cues and emotions is vital for navigating daily interactions, understanding emotions in conversations, interpreting body language in meetings, and supporting friends in difficult situations. This work focuses on analyzing group-level emotions in videos captured in natural settings, marking an attempt at multimodal group-level emotion analysis. Automatic group emotion recognition is pivotal for understanding complex human-human interactions. Group emotion recognition in videos presents several challenges because existing work predominantly focuses either on individual emotion recognition or group emotion analysis in static images. To address this challenge, we introduce a deep-learning-based multimodal fusion model that integrates diverse modalities, including audio, video, and scene. Feature extraction employs advanced models like TimeSformer for video description and wav2vec2.0 for audio analysis. All the experiments are conducted on the VGAF dataset. Our key findings include: (1) Multimodal approaches outperform their unimodal counterparts, (2) Experimental results confirm the superior performance of proposed approach compared to benchmark methods on the given dataset, and (3) There is a strong correlation between modalities and respective emotions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Maximizing Weighted Dominance in the Plane 21st

Maximizing Weighted Dominance in the Plane

引用

21st International Colloquium on Theoretical Aspects of Computing, ICTAC 2024

作者： Akram, Waseem Saxena, Sanjeev Department of Computer Science and Engineering Indian Institute of Technology Kanpur Kanpur208016 India

ISBN: (纸本)9783031770180

Let P be a set of n weighted points, Q be a set of m unweighted points in the plane, and k a non-negative integer. We study the k-maxDominance problem, where the objective is to find a subset Q′⊆Q with size at most k such that the sum of the weights of the points in P dominated by at least one point in Q′ is maximized. A point q in the plane dominates another point p if and only if x(q)≥x(p) and y(q)≥y(p), and at least one inequality is strict. An algorithm for the k-maxDominance problem can be used to solve problems previously examined in scheduling, graph optimization, and database systems. We present a simple algorithm solving the problem in O(km2+nlogm) time and O(n+m) space. The algorithm is faster than the existing one when m=o(n). Additionally, we provide another solution to the problem with O(kmin{n+m,nk+m2}logm) time and O(n+m) space. These bounds are the same or better than those of the existing solution (the bounds are better when m=o(n)). The expected number of skyline points is θ(logn), a term much less than n. To obtain the second solution, we design a general technique that can be used to reduce the number of points n in P to min{n,m2} in any algorithm for the k-maxDominance problem. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Attack Classification using Machine Learning on UNSW-NB 15 dataset using XGBoost Feature Selection & Ablation Analysis 9

Attack Classification using Machine Learning on UNSW-NB 15 d...

引用

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

作者： Pansari, Nikunj Srivastava, Shourya Raghavendra, R.H. Agarwal, Mayank Indian Institute of Technology Patna Department of Computer Science And Engineering Patna India

ISBN: (纸本)9798350394474

The surge in network intrusions is a pressing concern for industry and government in cybersecurity. To counter this, network intrusion detection systems (NIDS) discern normal and abnormal network traffic effectively. Accurate anomaly identification depends on NIDS precision and performance metrics. Diverse feature selection methods, including standard, ensemble, and hybrid strategies, have been adopted to bolster intrusion detection datasets. In this study, we explore the application of the XGBoost feature selection technique on the UNSW-NB15 dataset. The core objective of our feature selection approach is to identify the optimal number of features conducive to the analysis of attacks, catering to both binary and multi-class classification scenarios. Subsequently, we meticulously assess the performance of diverse machine learning algorithms. This comprehensive evaluation includes well-known methods such as logistic regression, KNN, random forest, Decision Tree, AdaBoost, Bagging, and J48. Our scrutiny extends to another facet, wherein we conduct an ablation study. Specifically, we systematically eliminate the minority attack classes, namely Worms and Shellcode, separately from the training and test sets. The results with the reduced feature set provided better accuracy, precision, recall, and F1-Score compared to preceding rudimentary implementations. More specifically the training and testing time showed an improvement of over 50% in most cases under ablation with a reduced feature set using XGBoost (N =19) features while still retaining a higher accuracy score obtained with all features under consideration (N = 41). © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Automatic emotion recognition using deep neural network

引用

Multimedia Tools and Applications 2025年 1-30页

作者： Sujatha, R. Chatterjee, Jyotir Moy Pathy, Baibhav Hu, Yu-Chen School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India Department of CSE Graphic Era University Dehradun India School of Electrical Engineering Vellore Institute of Technology Vellore India Department of Computer Science Tunghai University Taichung City Taiwan

Emotions are a vital semantic part of human correspondence. Emotions are significant for human correspondence as well as basic for human–computer cooperation. Viable correspondence between people is possibly achieved when both the importance and the emotion of the correspondence are perceived by all groups included. Understanding the significance of language has generally been concentrated on in natural language processing (NLP) as a semantic examination. In NLP, the text can be handled appropriately for classification. Emotion detection from facial emotion is the subfield of social signal processing applied in a wide assortment of regions, explicitly for human and PC collaboration. Many researchers have proposed various approaches, generally utilizing machine learning concepts. Automatic emotion recognition (AER) is significant for working with consistent intuitiveness between a person and a smart device toward fully acknowledging an intelligent society. Many researchers examined cross-lingual and multilingual speech emotion as a stage toward language-free emotion acknowledgment in natural speech. In the present work, we are proposing a deep learning-based AER system using four openly accessible datasets, namely Basic Arabic Vocal Emotions Dataset (BAVED), Acted Emotional Speech Dynamic Database (AESDD), Urdu written in Latin/Roman Script (URDU), and Toronto Emotional Speech Set (TESS), by utilizing the Jupyter notebook and a Python library for music and audio synthesis named Librosa. The experimental results exhibited that the proposed approach achieves better than the existing approaches, i.e., the accuracy of the proposed system with the URDU dataset is 96.24%, the TESS dataset is 99.10%, the AESDD dataset is 65.97%, and the BAVED dataset is 73.12%. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Classifiers using Wav2Vec2.0 Layer Embeddings for Imbalanced Stuttering Datasets 1

Comparative Analysis of Classifiers using Wav2Vec2.0 Layer E...

引用

1st International Conference on Electronics, Communication and Signal Processing, ICECSP 2024

作者： Sen, Madhurima Batra, Ashita Das, Pradip K. Indian Institute of Technology Guwahati Department of Computer Science & Engineering Guwahati India

ISBN: (纸本)9798350364590

Stuttering is a speaking problem affecting normal fluency and flow of speech. Despite research done in this area, stuttering detection and identification is challenging in nature, due to the heterogeneity of audio samples which varies across people who stutter. This paper presents the application of extracting feature representations using pretrained deep learning models i.e. Wav2Vec2.0 (BASE & LARGE) and examines different data sampling methods for effective analysis. We have explored different sampling techniques i.e. oversampling and undersampling and evaluated their performance on traditional classifiers i.e. k-Nearest Neigh-bors (kNN), Support Vector Machines (SVM), Naïve Bayes' Classifier (NBC), Random Forest (RF) where SVM performed the best. With this, we performed a comprehensive layer-wise analysis of Wav2Vec2.0 feature embeddings and observed that middle layers capture more stuttering information. Our results show significant improvements in unweighted average recall (UAR) using the KSoF [1] and Sep-28k [2] datasets. Specifically, we observed a relative increase of 15.5% & 24.4% in UAR for the KSoF and Sep-28k dataset, relative to the results reported in [3] and [4] respectively. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Likelihood Ratio Test of Genetic Relationship among Languages

A Likelihood Ratio Test of Genetic Relationship among Langua...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Akavarapu, V.S.D.S. Mahesh Bhattacharya, Arnab Dept. of Computer Science and Engineering Indian Institute of Technology Kanpur India

ISBN: (纸本)9798891761148

Lexical resemblances among a group of languages indicate that the languages could be genetically related, i.e., they could have descended from a common ancestral language. However, such resemblances can arise by chance and, hence, need not always imply an underlying genetic relationship. Many tests of significance based on permutation of wordlists and word similarity measures appeared in the past to determine the statistical significance of such relationships. We demonstrate that although existing tests may work well for bilateral comparisons, i.e., on pairs of languages, they are either infeasible by design or are prone to yield false positives when applied to groups of languages or language families. To this end, inspired by molecular phylogenetics, we propose a likelihood ratio test to determine if given languages are related based on the proportion of invariant character sites in the aligned wordlists applied during tree inference. Further, we evaluate some language families and show that the proposed test solves the problem of false positives. Finally, we demonstrate that the test supports the existence of macro language families such as Nostratic and Macro-Mayan. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Robustness of Smart Contracts Through Declarations 7th

Enhancing Robustness of Smart Contracts Through Declaration...

引用

7th International Conference on Blockchain, ICBC 2024, Held as Part of the Services Conference Federation, SCF 2024

作者： Shyamasundar, R.K. Borse, Snehal Ummair, Mohammad Department of Computer Science and Engineering Indian Institute of Technology Bombay Mumbai400076 India

ISBN: (纸本)9783031770944

Run-time monitoring has been one of the widely used techniques to realize robust smart contracts. In this paper, we show how we can abstract aspects of run-time monitoring through declarations of programming languages so that a majority of run-time monitoring code required for preserving the intended semantics of Solidity and thereby overcome vulnerabilities can be instrumented automatically at compile time itself. For illustrative purposes, we use Solidity and call the augmented Solidity language SolidityD. SolidityDsyntactically is identical to Solidity except for declarations. The declarations preserve the intended semantics of various constructs and thus overcome a large number of vulnerabilities. We illustrate how a vast variety of vulnerabilities encountered in programming smart contracts in Solidity are overcome through declarations. Declarations envisaged in SolidityDare similar to that used in classic concurrent programming languages and are easily visualizable by the programmer. Declarations lead to automatic introduction of run-time code at compilation time needed to satisfy various executional constraints needed to satisfy the semantic requirements of declarations. Further, we demonstrate that SolidityD, can be automatically transformed to pure Solidity: thus, enabling an effective debugging at source level rather than at the byte or EVM level. Another important outcome of using SolidityD, is that it can be effectively used for asserting coarse-grained properties of declarations. Such a feature leads to gaining trust in the usage of smart contracts. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Program debugging

来源：评论

学校读者我要写书评

暂无评论

VULDetect: A Lightweight Ensemble Based Framework for Automated Software System Vulnerability Detection

VULDetect: A Lightweight Ensemble Based Framework for Automa...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Ali, Irshad Subba, Basant Department of Computer Science & Engineering Indian Institute of Technology Punjab Ropar India

ISBN: (纸本)9798350350821

This paper presents VULDetect: a lightweight and highly accurate ensemble based software system vulnerability detection framework trained on a large C/C++ file corpus comprising thousands of vulnerable and non-vulnerable source code snippets. VULDetect uses a deep learning based ensemble model comprising multiple classifiers to perform a comprehensive vulnerability assessment of the software programs. Experimental results on a proprietary dataset and a benchmark DIVERSEVUL dataset show that VULDetect is capable of detecting wide range of software system vulnerabilities with high accuracy and low false positive rate. In addition, VULDetect is also highly compact and lightweight in comparison to other Large Language Model (LLM) based frameworks proposed in the literature, which makes it highly suitable for deployment on computation constrained edge devices. © 2024 IEEE.

关键词： C++ (programming language)

来源：评论

学校读者我要写书评

暂无评论

PLD-SiM: Process Line Diagram Simulator and Modeler

PLD-SiM: Process Line Diagram Simulator and Modeler

引用

2024 International Workshop on Petri Nets and Software engineering, PNSE 2024

作者： Rajput, Akshit Shivhare, Karnika Joshi, Rushikesh K. Department of Computer Science Engineering Indian Institute of Technology Bombay Mumbai India

This paper introduces a browser-based tool for modeling applications with Process Line Diagrams (PLDs)[1]. The tool aims at providing a modular and logical approach for building process architecture models to bridge the gap between high-level process notations, low-level formal process models and implementation programming languages. While high-level process models primarily rely on manual practices for architectural detailing and trace conformance checking, the paper presents a user-assisted trace simulator to visually inspect the behavior of a process. The interface enables the user to obtain pen-paper snapshots from the process through dry run in the visual simulator. The visual modeler implements the syntactic rules of the PLD primitives, including roles, events, choices, and event synchronization. The same are enforced by the simulator for active prototyping through visual traces. © 2024 Copyright for this paper by its authors.

关键词： High level languages

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient and Mobility-Aware Device Selection for Task Offloading in Blockchain-Enabled IoT

Energy-Efficient and Mobility-Aware Device Selection for Tas...

引用

2024 IEEE Middle East Conference on Communications and Networking, MECOM 2024

作者： Sanatan, Kumar Ajay, Shubham Kant Kumar, Satendra Indian Institute of Technology Department of Computer Science and Engineering Patna801106 India

ISBN: (纸本)9798350376715

Blockchain is a decentralized ledger system that securely records transactions across multiple nodes. A key challenge in blockchain networks is forking, where the transaction history diverges due to protocol changes, leading to distinct chains. In Blockchain-enabled IoT networks, forking disrupts consistency and increases latency and energy consumption. To address this issue, we propose a mobility-aware federated learning framework that optimizes the selection of IoT devices and miners to minimize forking events. Specifically, we first employed Markov Predictor to predict the future location of the devices. Further, we select the subset of devices based on their predicted locations and eliminate the devices likely to be involved in the forking event. Finally, the task of eliminating devices is reassigned to underutilized devices. Experimental results show that our Markov-based predictor achieves a 63% prediction accuracy for four to 25 devices. © 2024 IEEE.

关键词： Miners

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：