检索结果-内蒙古大学图书馆

1st International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2022

作者： Lal, Utkarsh Kamath, Priya Applied Intelligence Accenture NCR Delhi India Manipal Institute of Technology Department of Computer Science and Engineering Karnataka Manipal India

ISBN: (纸本)9781665436472

Good quality of data preprocessing will have a greater impact on improving the performance of the classification models. Negation is one of the most important features in textual data. Only one negation word can change the polarity of the whole sentence. It is often seen that words like 'not', 'non' or suffixes like 'n't' are removed during noise removal thereby leading to blunders in Sentiment Classification. Effective Feature extraction is the cornerstone of effective Sentiment Analysis and Negation handling is simply essential for this purpose. In this paper, an effective function for handling negations based on First Sentiment Word (FSW) antonymy in the WordNet has been implemented on a set of IMDB movie reviews. The function for Negation Handling created for this paper increased the accuracy of Sentiment Classification by 4-8%. Experiments done in this paper show that improving the quality of the data gives higher results than implementing different state-of-the-art methods like n-grams and even deep learning methods like Word Embeddings, especially when used in an industry setting, where there is a need of quick deployments and changes with cost effectiveness and resource management. © 2022 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Real-Time Violent Action Recognition Using Key Frames Extraction and Deep Learning

引用

computers, Materials & Continua 2021年第11期69卷 2217-2230页

作者： Muzamil Ahmed Muhammad Ramzan Hikmat Ullah Khan Saqib Iqbal Muhammad Attique Khan Jung-In Choi Yunyoung Nam Seifedine Kadry Deparment of Computer Science and Information Technology The University of LahoreSargodha CampusSargodha40100Pakistan Department of Computer Science COMSATS University IslamabadWah CampusWah Cantt47040Pakistan School of System and Technology University of Management and TechnologyLahore54782Pakistan Department of Computer Science and Information Technology University of SargodhaSargodha40100Pakistan College of Engineering Al Ain UniversityAl AinUnited Arab Emirates Department of Computer Science HITEC University TaxilaTaxilaPakistan Applied Artificial Intelligence Ajou UniversitySuwonKorea Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea Department of Mathematics and Computer Science Faculty of ScienceBeirut Arab UniversityLebanon

Violence recognition is crucial because of its applications in activities related to security and law *** semi-automated systems have issues such as tedious manual surveillances,which causes human errors and makes these systems less *** approaches have been proposed using trajectory-based,non-object-centric,and deep-learning-based *** studies have shown that deep learning techniques attain higher accuracy and lower error rates than those of other ***,the their performance must be *** study explores the state-of-the-art deep learning architecture of convolutional neural networks(CNNs)and inception V4 to detect and recognize violence using video *** the proposed framework,the keyframe extraction technique eliminates duplicate consecutive *** keyframing phase reduces the training data size and hence decreases the computational cost by avoiding duplicate *** feature selection and classification tasks,the applied sequential CNN uses one kernel size,whereas the inception v4 CNN uses multiple kernels for different layers of the *** empirical analysis,four widely used standard datasets are used with diverse *** results confirm that the proposed approach attains 98%accuracy,reduces the computational cost,and outperforms the existing techniques of violence detection and recognition.

关键词： Violence detection violence recognition deep learning convolutional neural network inception v4 keyframe extraction

来源：评论

学校读者我要写书评

暂无评论

Cumulants from fluctuating width of rapidity distribution

引用

Physical Review C 2023年第1期108卷 014907-014907页

作者： Michał Barej Adam Bzdak AGH University of Science and Technology Faculty of Physics and Applied Computer Science 30-059 Kraków Poland

In relativistic heavy-ion collisions, the longitudinal fluctuations of the fireball density caused, e.g., by fluctuations in the number of stopped baryons result in event-by-event modifications of the shape of the proton rapidity density distribution. The multiparticle rapidity correlation functions due to the varying distribution width of the proton rapidity density in central Au+Au collisions at low energies are derived. The cumulant ratios are calculated and discussed in the context of the recent STAR Collaboration results. We find that for small fluctuations in the width of the proton rapidity distribution, the cumulant ratios are independent of the underlying width distribution. It is also emphasized that the cumulant ratios strongly depend on the size of the rapidity interval.

关键词： Particle correlations & fluctuations Relativistic heavy-ion collisions

来源：评论

学校读者我要写书评

暂无评论

On the Feasibility of Reliable Tunneling: Modelling Delay Imposed by Re-Transmissions

On the Feasibility of Reliable Tunneling: Modelling Delay Im...

引用

International Workshop on Reliable Networks Design and Modeling (RNDM)

作者： Marcus Pieska Anna Brunstrom Andreas Kassler Computer Science Department Karlstad University Karlstad Sweden Department of Applied Computer Science Deggendorf Institute of Technology Deggendorf Germany

5G will support transparent multi-path connectivity for mobile users through the Access Traffic Steering, Switching and Splitting function. For real-time traffic, this can be implemented by a multi-path proxy that implements transport layer tunnels between users and a proxy node in the packet core network. However, the choice of transport layer protocol for such a multi-path tunnel could greatly impact the user Quality-of-Experience. For example, re-transmitting lost packets could reduce video playback artefacts, but the additional delay caused by re-transmission could lead to the video freezing. In this paper, we develop mathematical models that estimate the lower bound on the average delay imposed by a reliable or semi-reliable multi-path tunnel. We validate our model using extensive network emulations and evaluate model accuracy for different scenarios. Finally, we use the model to derive design principles for a semi-reliable multipath tunnel protocol.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Model for Detecting Emotions Through Pipeline

Deep Learning Model for Detecting Emotions Through Pipeline

引用

International Conference on Advanced Technologies for Communications, ATC

作者： Afshan Fatima Masrath Parveen Vijender Kumar Solanki Ngoc Linh Nguyen Computer Science & Engineering CMR Institute of Technology Hyderabad Telangana India Computer Science &Engineering VJ Institute of Technology Hyderabad Telangana India Computer Science & Engineering Stanley College of Engineering and Technology for women Hyderabad Telangana India Faculty of Applied Science VNU-International School Hanoi Vietnam

ISBN: (数字)9798350353983

ISBN: (纸本)9798350353990

Human emotions, a pervasive psychological phenomenon, significantly influence individuals' daily experiences and mental health. In today's society, emotional well-being has become a major focus of concern. Facial expressions convey a diverse array of emotions, including natural, joy, sorrow, revulsion, terror, rage, astonishment, and disdain. This research introduces an innovative real-time emotion detection system that analyzes facial images using a multi-kernel approach within a deep learning framework. A notable contribution is the implementation of a Support Vector Machine (SVM) classifier with multiple kernel functions, emphasizing the improved accuracy and decreased processing time achieved by the Polynomial Kernel. This model demonstrates substantial enhancements in precision and efficiency compared to existing single-kernel methods, making it ideal for real-time applications. The study explores the effectiveness of emotional indicators derived from social media platforms, such as chatbots, messages, photographs, and facial expressions. The paper proposes a deep learning-based workflow for emotion recognition through facial expressions, utilizing a multi-kernel approach. The model incorporates Linear, Radial Basis Function (RBF), and Polynomial kernels, with the Polynomial Kernel exhibiting superior performance, attaining the highest cross-validation accuracy of 77.97% on the FER-2013 dataset. This research provides a thorough assessment of the model's accuracy and computational efficiency, demonstrating its competitive edge over current emotion recognition techniques.

关键词： Support vector machines Deep learning Emotion recognition Accuracy Social networking (online) Computational modeling Face recognition Polynomials Real-time systems Kernel

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Data Analysis for Recommendation Systems Using Machine Learning 2

An Intelligent Data Analysis for Recommendation Systems Usin...

引用

2nd International Conference on Business Analytics for technology and Security, ICBATS 2023

作者： Hussain, Zahid Mago, Beenu Khadim, Assma Amjad, Kamran NCBAE Lahore Pakistan Skyline University College University City Sharjah School of Information Technology Sharjah1797 United Arab Emirates NCBA&E School of Computer Science Lahore Pakistan Applied Science Private University Applied Science Research Center Amman11937 Jordan

ISBN: (纸本)9798350335644

Travelers are primarily concerned with finding a good hotel and reserving a room. Because of the volume of information, online hotel searches take longer than they used to. The relevance of recommender systems (RS) in decision-making and delivering correct facts about a desired product or service is driving the expansion of the RS sector. Textual evaluations, numerical rankings, votes, ratings, and video views have complicated hotel recommendations. We proposed an intelligent technique for delivering actual recommendations by interacting with massive amounts of various data and potential consumers' wants. A typical RS approach is collaborative filtering (CF), which generates recommendations. We proposed a novel CF recommendation technique based on user sentiment analysis to construct a hotel feature matrix utilizing polarity identification. When lexical, syntactic, and semantic studies are integrated, it may be simpler to understand the strange behaviors demonstrated by hotel visitors (solo, family, couple, etc.). While determining which hotels to recommend, we evaluated the types of consumers frequently served by the hotels as well as the overall quality of the companies. The system will make hotel recommendations to the user based on their travel preferences. The information accessible on hotel websites has been used in a variety of studies. This was completed after the computations were complete. As a result, this should be the key takeaway from the description. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Developing Smart Skin: A Force Sensor-Based Touch and Pressure Detector

Developing Smart Skin: A Force Sensor-Based Touch and Pressu...

引用

International Conference of Information and Communication technology (ICoICT)

作者： Muhammad Aulia Rifqi Zain Giva Andriana Mutiara Periyadi Muhammad Rizqy Alfarisi Angelica Sitorus Raka Duta Adhira Computer Technology Applied Science School Telkom University Bandung Indonesia Multimedia Engineering Applied Science School Telkom University Bandung Indonesia

ISBN: (数字)9798350363432

ISBN: (纸本)9798350363449

This research discusses the advancements in developing smart skin by employing Force Sensitive Resistor (FSR). The objective of this research is to advance research on the fundamental concept of artificial skin that relies on the human sense of touch sensors especially in pressure to imitate the sensory capabilities of human skin, since humans are incapable of accurately quantifying the pain induced by external pressure. Therefore, by employing FSR sensors, the acquired data will be stabilized, thereby serving as a dependable reference. A prototyping method is implemented in this research to construct and observe the smart skin design. This research is utilized RP-S40-ST and FS7548 sensors for gathering data pressure and touch. The smart skin is coated with an elastomeric substance that closely resembles human skin in terms of its flexibility, softness, and mechanical properties. The FSR sensor is linked to a microcontroller board called TTGO LoRa OLED, which enables the integration of data transfer for further development through the Long Range (LoRa) protocol. The AMF-500 force gauge functions as a standard for converting data obtained from analog sensors into precise force (N) and pressure measurements (kPa). This research represents a significant step towards developing smart skin using FSR sensors that aim to mimic human touch by detecting external pressure up to a maximum of under 60 Newtons and a maximum bend of under 90 degrees.

关键词： Mechanical sensors Microcontrollers Force LoRa Tactile sensors Detectors Skin Pressure measurement Intelligent sensors Standards

来源：评论

学校读者我要写书评

暂无评论

A Hybrid SARIMAX Model in Conjunction with Neural Networks for the Forecasting of Life Insurance Industry Growth in Thailand 9

A Hybrid SARIMAX Model in Conjunction with Neural Networks f...

引用

Joint 9th International Conference on Digital Arts, Media and technology with 7th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications Engineering, ECTI DAMT and NCON 2024

作者： Huadsri, Supika Mekruksavanich, Sakorn Jitpattanakul, Anuchit Phaphan, Wikanda King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Applied Statistics Bangkok10800 Thailand University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao56000 Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Mathematics Bangkok10800 Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Thailand Research Group in Statistical Learning and Inference Thailand

ISBN: (纸本)9798350318241

This article is conducted with the primary aim of comparing various forecasting models to identify the optimal model for forecasting the growth of the life insurance industry in Thailand. The models under consideration include the SARIMAX model, the Recurrent Neural Network (RNN), and a hybrid model introduced as RNN-SARIMAX. The dataset utilized for this investigation is extensive, consisting of monthly direct premium data from the Thai life insurance sector spanning January 2003 to December 2022. The dataset is segregated into two distinct segments. Initially, data from January 2003 to December 2021 is employed for constructing the forecasting model. Subsequently, data from January 2022 to December 2022 is utilized for a comparative analysis of the forecasting models, to determine the most suitable and accurate model for predicting the growth of the life insurance industry in Thailand. The evaluation criteria for comparing models include the Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and the Coefficient of Determination (R-squared). The consistent findings from our analysis indicate that the SARIMAX model consistently outperforms both the RNN and RNN-SARIMAX models. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Psychological Stress Classification Using Extreme Gradient Boosting Algorithm 15

Psychological Stress Classification Using Extreme Gradient B...

引用

15th International Conference on Information and Communication technology Convergence, ICTC 2024

作者： Sakanti, Maria Mahardini Siniaev, Viacheslav Amaris, Aurelia Luo, Win-Jet Suhartono Kuncoro, C. Bambang Dwi Graduate Institute of Precision Manufacturing National Chin-Yi University of Technology Taichung41170 Taiwan Institute of Applied Computer Science Itmo University St. Petersburg19710 Russia Universitas Brawijaya Faculty of Computer Science Department of Informatics Engineering Malang65145 Indonesia National Chin-Yi University of Technology Taichung41170 Taiwan National Chin-Yi University of Technology Department of Refrigeration Air Conditioning and Energy Engineering Taichung41170 Taiwan

ISBN: (纸本)9798350364637

Stress, as a reaction to threatening situations, can raise heart rate and result in serious conditions that might cause significant damage or even be life-threatening. Traditional methods for evaluating stress, which rely on subjective self-reporting and clinical assessments, often suffer from biases and inconsistencies. Artificial intelligence models have been explored to predict stress levels more accurately. This paper investigates the application of Extreme Gradient Boosting in classifying psychological stress using the WESAD dataset, which includes parameters such as acceleration, electrocardiogram, electromyography, electrodermal activity, temperature, and respiration. The dataset was balanced and sampled to create a manageable subset for experimental. Extreme Gradient Boosting was chosen for its efficiency and scalability in handling complex datasets. The model was trained and validated, achieving a 95% accuracy in predicting stress levels. This study highlights the potential of integrating Extreme Gradient Boosting models into wearable devices for real-time stress monitoring. Future work involves optimizing the model to utilize fewer sensors without decreasing accuracy, ensuring it can be integrated into portable/wearable systems using tiny microcontrollers. © 2024 IEEE.

关键词： Electromyography

来源：评论

学校读者我要写书评

暂无评论

Adaptive Trust-Based Optimal Route Selection Algorithm in MANET Using Sooty Tern Optimization Algorithm 7

Adaptive Trust-Based Optimal Route Selection Algorithm in MA...

引用

7th International Conference on Electronics, Communication and Aerospace technology, ICECA 2023

作者： Goswami, Subhrananda Johardar, Subhankar Mondal, Sukumar Das, Chandan Bikash Raja Narendra Lal Khan Women's College Research Centre of Natural and Applied Sciences Department of Computer Science India Haldia Institute of Technology Department of Computer Science India Raja Narendra Lal Khan Women's College Department of Mathematics India Tamralipta Mahavidyalaya Department of Mathematics India

ISBN: (纸本)9798350340600

An infrastructure-free, a self-configuring network of mobile nodes, known as a Mobile Ad hoc Network (MANET), has recently gained popularity due to its simple setup. MANET has become widely applicable in various fields. In recent years, diverse research works have been explored to provide strategies for attaining the optimal path for energy routing in MANET. Thus, it faces several challenges which could not be more effective in the existing approaches. Here, the route maintenance, route setup time, and routing overhead problems become serious consideration issues in the MANET. An energy-efficient routing protocol might perform substantially worse than a standard routing protocol if it is not designed properly. MANET faces several issues that are related to security design, such as restricted resources, shared wireless media, dynamic network topology and open end-to-end networks. Due to the dynamic nature of nodes, it could be difficult to establish a Quality of Service (QoS) while the routing occurs in the MANET. To solve these issues, a trust-based optimal path selection in MANET is designed using the Sooty Tern Optimization Algorithm (STOA). Here, the different multi-objective functions like throughput, path loss, the energy that is still available in the battery, link cost, packet energy cost, end-to-delay, routing overhead ratio, energy consumption, packet delivery ratio and security which help to provide an effective data communication in MANET. In the developed model, security is the main constraint to be considered for the optimal routing scheme in the MANET. The implementation results are validated with the traditional optimal routing schemes in MANET to ensure the effectiveness of the suggested routing approach. © 2023 IEEE.

关键词： Mobile ad hoc networks

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：