检索结果-内蒙古大学图书馆

An Experimental Study on Dynamic Lifelong Learning with GPT for Mitigating Catastrophic Forgetting in Aspect-Based Sentiment Analysis

引用

IEEE Access 2025年 13卷 90316-90332页

作者： Huang, Huang Mustafa, Mumtaz Begum Asemi, Adeleh University of Malaya Faculty of Computer Science and Information Technology Department of Software Engineering Kuala Lumpur50603 Malaysia Branch Faculty of Engineering Department of Computer Engineering Isfahan81551-39998 Iran

GPT is widely recognized as one of the most versatile and powerful large language models, excelling across diverse domains. However, its significant computational demands often render it economically unfeasible for individuals and small businesses, underscoring the need for efficient, domain-specific alternatives. In Aspect-Based Sentiment Analysis (ABSA), existing models are typically optimized for single domains, facing challenges in performing effectively across multiple domains. A key issue, known as "catastrophic forgetting,"arises when models trained on one domain lose previously learned knowledge upon exposure to new domain data. This leads to two significant problems: limited cross-domain generalization and difficulty in retaining prior knowledge while learning domain-specific information. To address these challenges, we introduce the Dynamic Lifelong Learning Aspect-Based Sentiment Analysis GPT (DllaGPT), a model designed to handle multiple domains while mitigating catastrophic forgetting. Leveraging datasets from four ABSA domains - Laptops, Restaurants, Tweets, and Finance - this study fine-tunes a pretrained GPT model from HuggingFace sequentially across domains. DllaGPT employs a mechanism to retain real data from earlier domains during new domain training, effectively preserving prior knowledge. Experimental results highlight that DllaGPT achieves an average accuracy of 0.85 and a Backward Transfer (BWT) score of -0.09 across the four domains, showcasing its high accuracy and robust lifelong learning capabilities. © 2013 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Framework for Classification and Detection of Android Malware

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第21期18卷 59-73页

作者： Al Sharah, Ashraf Alrub, Yousef Abu Owida, Hamza Abu Elsoud, Esraa Abu Alshdaifat, Nawaf Khtatnaha, Hamzah Department of Electrical Engineering College of Engineering Technology Al-Balqa Applied University Amman Jordan Department of Computer Information Systems Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University Zarqa Jordan Department of Medical Engineering Faculty of Engineering Al-Ahliyya Amman University Amman Jordan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan Faculty of Information Technology Applied Science Private University Amman Jordan

The hardware and software of a computer are controlled by its operating system (OS), which performs essential tasks such as input and output processing, file and memory management, and the management of peripheral devices such as disk drives and printers. Application software refers to programs designed for specific purposes, these applications, often freely available and open source, contribute to the rising number of downloads. In the third quarter of 2022, combined downloads from the Apple App Store and Google Play Reached an estimated 35.3 billion. However, the prevalence of insecurity in these applications and technologies heightens the potential for cybercrimes. Protection against unauthorized intruders is crucial in identifying malicious applications. Machine learning (ML) serves as a promising avenue for detecting malware attacks, offering potential solutions to bolster cybersecurity measures. We propose a novel approach utilizing ML to enhance malware detection accuracy by segmenting datasets into distinct groups. Our research employs supervised ML techniques on the CICMaldroid2020 dataset, which includes comprehensive information such as intent actions, permissions, and sensitive APIs. The dataset was partitioned into four groups, each containing 150 features, and analyzed across four experiments to distinguish between attack and benign classes. Our proposed model demonstrated exceptional performance, with the random forest algorithm achieving an accuracy of 98.6% and a precision of 98.75%. These results highlight the effectiveness of our segmentation approach and its significant contribution to advancing malware detection in Android applications, offering a promising direction for future cybersecurity solutions. © 2024 by the authors of this article.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

On Reliability of the Extrema Propagation Technique in Random Environment 28

On Reliability of the Extrema Propagation Technique in Rando...

引用

28th International Conference on Principles of Distributed Systems, OPODIS 2024

作者： Cichoń, Jacek Dworzański, Dawid Gotfryd, Karol Department of Fundamentals of Computer Science Faculty of Information and Communication Technology Wroclaw University of Science and Technology Poland

ISBN: (纸本)9783959773607

We study the reliability of the following simple mechanism for spreading information in a communication network in the presence of random message loss. Initially, some nodes have information that they want to distribute throughout the network. Each node that has received the information tries to broadcast it to all its neighbors. However, due to interference or communication failures, each transmission between two nodes is broken independently with some fixed probability. This transmission mechanism is the basis for the extrema propagation technique, proposed and analyzed in [2, 3, 10]. Extrema propagation is a simple but powerful method of spreading the extreme values stored by the nodes. In a fully reliable environment, only the number of rounds equal to the network diameter is required for all nodes to be informed. It was shown empirically in [2] that it also performs well in the presence of link failures and message loss. Extrema propagation is an algorithmic framework that was adopted for designing efficient method for distributed data aggregation, such as estimation of cardinalities, sums, and averages, estimation of data distribution via histograms and random sampling (cf. [3, 19]). In this paper, we propose a formal network model in which random transmission failures occur and analyze the operation time of the extrema propagation technique for any connected network graph. We provide new general probabilistic upper bounds on the number of rounds needed to spread the extreme values that depend only on the number of nodes, the diameter of the network, and the probability of successful transmission. For some special families of graphs, we also derive specific, more accurate estimates. Our theoretical and experimental results confirm the reliability and efficiency of the extrema propagation technique in faulty or noisy environments. © Jacek Cichoń, Dawid Dworzański, and Karol Gotfryd.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Community Clustering on Fraud Transactions Applied the Louvain-Coloring Algorithm

引用

International Journal of Electronics and Telecommunications 2023年第3期69卷 593-598页

作者： Mardiansyah, Heru Suwilo, Saib Nababan, Erna Budiarti Efendi, Syahril Department Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department Mathematics Faculty of Mathematics and Natural Sciences Universitas Sumatera Utara Medan Indonesia Department Data Science and Artificial Intelligence Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

The contribution main from this research is modularity and better processing time in detecting community by using K-1 coloring. Testing performed on transaction datasets remittance on P2P platforms where the Louvain Coloring algorithm is better in comparison to Louvain Algorithm Data used is data transfer transactions made by customers on the P2P Online platform. The data is the User data that has information transfer transactions, Card data that has information card, IP data that has IP information, and Device data that has information device. Every user owns unique 128-bit identification, and other nodes representing card, device, and IP are assigned a random UUID. The Device node has the guide, and device properties. IP nodes only have property guide and node User has property fraud Money Transfer, guide, money Transfer Error Cancel Amount, first Charge back Date. Each node has a unique 128-bit guide, with the amount whole of as many as 789,856 nodes. Application technique K-1 staining on Louvain algorithm shows enhancement value modularity and better processing time for detecting community on the network large scale. Through a series of exercises and tests carried out in various scenarios, it shows that the experiments carried out in this paper, namely the Louvain Coloring algorithm, are more effective and efficient than the Louvain algorithm in scenario 1,3, and 5 meanwhile For Scenarios 2 and 4 Louvain Algorithm is better. © 2023 Polish Academy of sciences. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

MLMO-HSM: Multi-label Multi-output Hybrid Sequential Model for multi-resident smart home activity recognition

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第3期14卷 2313-2325页

作者： Ramanujam, E. Perumal, Thinagaran Department of Computer Science and Engineering National Institute of Technology Silchar Assam 788010 India Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang India

Smart home automation is protective and preventive measures that are taken to monitor elderly people in a non-intrusive manner using simple and pervasive sensors termed Ambient Assistive Living. The smart home produces a large volume of sensor activations to predict an elder’s health status to improve the quality of life and independent living. Machine learning techniques are very familiar and popular in recognizing single resident activities using such a sensor reading. However, multi-resident activities are more complex, and no correlation exists between sensor readings and activities. Recently deep learning and graphical models have been proposed to solve this problem, but it consumes more time to train the model. Moreover, models are primarily executed in parallel, or multi-resident activity recognition has been converted to single for classifying events. This paper proposes a Multi-label Multi-output Hybrid Sequential Model (MLMO-HSM), a feature engineering approach with a hybrid sequential model to recognize the multi-resident activities concurrently in the shortest time. Experimentation has been performed with various machine learning, graphical and deep learning models at the different sizes of the ARAS dataset to validate the efficiency of the proposed model in terms of activity recognition and computation time. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Efficacy of ChatGPT in Different Domains: Customer Support vs. Educational Assistance 5

Evaluating the Efficacy of ChatGPT in Different Domains: Cus...

引用

5th International Conference on Advanced information Technologies, ICAIT 2024

作者： Thant, Khin Shin Mon Khaing, Myat Khaung Tin, Hlaing Htake University of Computer Studies Hinthada Faculty of Information Science Hinthada Myanmar University of Information Technology Faculty of Information Science Yangon Myanmar

ISBN: (纸本)9798331510046

ChatGPT performs with striking contrasts regarding customer service and education, lessons learned in why that is the way it is, how the study uses it, and what the study can do to improve this. ChatGPT is excellent for customer support and the response to the common questions it was built on may be fast and accurate. This is to help both users and resolve issues. Each day's work is treated as quality, however, when demonstrating more troublesome or irregular problems it comes up short. If the study were to improve this cloud function by making it better at handling complex queries and sounding a lot more human, the study chatbot could perform much better in this and many other domains. But it's usually wrong and users have reported mixed outcomes. This research proposes how challenging it can be to communicate complex concepts and relate to diverse learning styles. This research will improve ChatGPT for support and as an assistant in each context where it is used. The next target of improvement is to solve the lack of contextual helping experience for ChatGPT users. This paper is crucial in informing how the study might cautiously break conversational AI and indeed future engagements with technology beyond dominant use cases and shaped towards inclusive models that stand to have a significantly positive impact on human lives. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Automatic Task Classification of Software Projects for Planning and Simulation 25th

Automatic Task Classification of Software Projects for Pla...

引用

Topical Area: Software, System and Service Engineering, S3E 2024, Held as Part of FedCSIS 2024, and 25th Conference on Practical Aspects of and Solutions for Software Engineering, KKIO 2024, held as part of SEAA 2024

作者： Wysocki, Wlodzimierz Ochodek, Miroslaw Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin Szczecin Poland Faculty of Computer Science and Telecommunications Poznan University of Technology Poznan Poland

ISBN: (纸本)9783031849121

Background: information about project tasks stored in Issue tracking systems (ITS) can be used for project analytics or process simulation. However, such issues must be classified beforehand. Considering the number of tasks stored in ITS, this task shall be done automatically. Aims: Our research aims to build an automatic recurring Jira issue classification model based on types and textual descriptions to enable the practical application of the model for software project planning and management. Method: We study a dataset from six industrial projects containing 9.6K tasks and augment it with an additional dataset of 91K task descriptions from other industrial projects to up-sample minority classes during training. We labeled the data using a semi-manual, active-learning-based method. We perform ten runs of 10-fold cross-validation for each project and evaluate classifiers using a set of state-of-the-art prediction quality metrics, i.e., Accuracy, Precision, Recall, F1-score, and MCC. Our machine-learning pipeline includes a Transformer-based sentence embedder (‘mxbai-embed-large-v1’) and an XGBoost classifier. We also study the impact of task-classification errors on project staffing issues. Results: The model automatically classifies software process tasks into 14 classes with MCCs ranging from 0.69 to 0.88. We built a confusion matrix that showed the most frequently confused task classes. We analyzed the consequences of classification errors. Conclusions: The study’s results enable the practical application of the software process model to analyze, plan, and manage software development projects. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Gauging information Extracted from Smartphones Using Neutrosophic Logic

引用

Neutrosophic Sets and Systems 2025年 76卷 154-171页

作者： Abou Alzahab, R.M. Ismail, Amr Abd Elkhalik, S.H. Shams, M.Y. El-Bakry, H.M. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Department. of Communication and Computer Engineering Air Defense University Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Department of Information Systems. Faculty of Computer and Information Science Mansoura University Egypt

Smartphones contain a vast amount of information about their users, which can be used as evidence in criminal cases. However, the sheer volume of data can make it challenging for forensic investigators to identify and use the most relevant information. Neutrosophic logic is a generalization of fuzzy logic that allows for uncertainty and vagueness, making it a more potent tool for dealing with the ambiguity of real-world data. The proposed framework aims to identify and utilize the most relevant information for forensic investigators, making it easier to solve criminal cases using Neutrosophic logic. This novel approach provides a more powerful tool for dealing with the ambiguity of smartphone data, ultimately improving the accuracy and effectiveness of forensic investigations. Our research has utilized Neutrosophic logic to evaluate the degree of truth, falsity, or Indeterminacy of this information. Additionally, this study analyzes conversations between individuals using Excel’s fuzzy lookup add-in to determine the percentage of truth and false in each conversation. The results were compiled into a dataset and utilized a Neutrosophic Python code to evaluate the information. The results indicate the percentage of truth, false, and Indeterminacy in each conversation and which can be used to determine its admissibility as evidence and which not. © 2025, University of New Mexico. All rights reserved.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Based Attack Detection for Imbalanced Data Classification

引用

Intelligent Automation & Soft Computing 2023年第1期35卷 297-320页

作者： Rasha Almarshdi Laila Nassef Etimad Fadel Nahed Alowidi Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Computer Science Faculty of Computer Science and EngineeringUniversity of HailHailSaudi Arabia

Internet of Things(IoT)is the most widespread and fastest growing technology *** to the increasing of IoT devices connected to the Internet,the IoT is the most technology under security *** IoT devices are not designed with security because they are resource constrained ***,having an accurate IoT security system to detect security attacks is *** Detection Systems(IDSs)using machine learning and deep learning techniques can detect security attacks *** paper develops an IDS architecture based on Convolutional Neural Network(CNN)and Long Short-Term Memory(LSTM)deep learning *** implement our model on the UNSW-NB15 dataset which is a new network intrusion dataset that cate-gorizes the network traffic into normal and attacks *** this work,interpolation data preprocessing is used to compute the missing ***,the imbalanced data problem is solved using a synthetic data generation *** experiments have been implemented to compare the performance results of the proposed model(CNN+LSTM)with a basic model(CNN only)using both balanced and imbalanced ***,with some state-of-the-art machine learning classifiers(Decision Tree(DT)and Random Forest(RF))using both balanced and imbalanced *** results proved the impact of the balancing *** proposed hybrid model with the balance technique can classify the traffic into normal class and attack class with reasonable accuracy(92.10%)compared with the basic CNN model(89.90%)and the machine learning(DT 88.57%and RF 90.85%)***,comparing the proposed model results with the most related works shows that the proposed model gives good results compared with the related works that used the balance techniques.

关键词： IoT IDS deep learning machine learning CNN LSTM

来源：评论

学校读者我要写书评

暂无评论

An Investigation on Open-RAN Specifications:Use Cases,Security Threats,Requirements,Discussions

引用

computer Modeling in Engineering & sciences 2024年第10期141卷 13-41页

作者： Heejae Park Tri-HaiNguyen Laihyuk Park Department of Computer Science and Engineering Seoul National University of Science and TechnologySeoul01811Republic of Korea Faculty of Information Technology School of TechnologyVan Lang UniversityHo Chi Minh City70000Vietnam

The emergence of various technologies such as terahertz communications,Reconfigurable Intelligent Surfaces(RIS),and AI-powered communication services will burden network operators with rising infrastructure ***,the Open Radio Access Network(O-RAN)has been introduced as a solution for growing financial and operational burdens in Beyond 5G(B5G)and 6G networks.O-RAN promotes openness and intelligence to overcome the limitations of traditional *** disaggregating conventional Base Band Units(BBUs)into O-RAN Distributed Units(O-DU)and O-RAN Centralized Units(O-CU),O-RAN offers greater flexibility for upgrades and network ***,this openness introduces new security challenges compared to traditional *** existing studies overlook these security requirements of the O-RAN *** gain deeper insights into the O-RAN system and security,this paper first provides an overview of the general O-RAN architecture and its diverse use cases relevant to B5G and 6G *** then delve into specifications of O-RAN security threats and requirements,aiming to mitigate security vulnerabilities *** providing a comprehensive understanding of O-RAN architecture,use cases,and security considerations,thisworkserves as a valuable resource for future research in O-RAN and its security.

关键词： O-RAN architecture use cases security issues security requirements security discussions

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：