检索结果-内蒙古大学图书馆

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

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

Digital forensics for the socio-cyber world (DF-SCW): A novel framework for deepfake multimedia investigation on social media platforms

引用

Egyptian Informatics Journal 2024年 27卷

作者： Ayub Khan, Abdullah Chen, Yen-Lin Hajjej, Fahima Ahmed Shaikh, Aftab Yang, Jing Soon Ku, Chin Yee Por, Lip Department of Computer Science and Information Technology Benazir Bhutto Shaheed University Lyari Sindh Karachi75660 Pakistan Department of Computer Science Sindh Madressatul Islam University Sindh Karachi74000 Pakistan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei106344 Taiwan Department of Software Engineering College of Computer and Inf. Sci. Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur50603 Malaysia Department of Computer Science Universiti Tunku Abdul Rahman Kampar31900 Malaysia

Owing to the major development of social media platforms, the usage of technological adaptation increases by means of editing software tools. Posting media in social communication environments has become one of our common daily routines. Before posting, various editing generators are used to manipulate pixel values, such as for enhancing brightness and contrast. Undoubtedly, this software helps bring posting media from ordinary to outstanding. But such a type of editing crosses the line in terms of creating fakes—anything that comes from anywhere and does not retain its originality anyway. It poses a series of issues in the process of multimedia forensics investigation and chain of custody. In order to restrict the attempts at deep faking and make the investigation hierarchy more effective, efficient, and reliable in the socio-cyber space (SCS), this paper presents a novel framework called DF-SCW. A digital forensics-enabled socio-cyber world with artificial intelligence (AI), especially deep neural networks (DNNs), for detecting and analyzing deep fake media investigations on social media platforms. It compares pixels with their neighboring values in the same media (such as images and videos) to identify information about the original one. There is a media flag designed to filter out malicious and dangerous attempts, like a powerful leader declaring war. Putting flags on such fakes helps digital investigators resist sharing the posts. In addition, the other prospect of this research is to make the digital forensics ecosystem more appropriate to take qualitative judgments in real-time while media is uploaded on social media platforms. The simulation of the proposed DF-SCW is tested on three different platforms, such as Instagram, Facebook, and Twitter. Through the experiment, the DF-SCW outperformed in terms of detection, identification, and analysis of deepfake media by an increased rate of 3.77%. © 2024

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Indonesian Police in the Twitterverse: A Sentiment Analysis Perspectives

Indonesian Police in the Twitterverse: A Sentiment Analysis ...

引用

International Conference on information Technology, information systems and Electrical Engineering (ICITISEE)

作者： Pungkas Subarkah Primandani Arsi Dhanar Intan Surya Saputra Afrig Aminuddin Berlilana Nandang Hermanto Department of Informatics Faculty of Computer Science Universitas Amikom Purwokerto Banyumas Jawa Tengah Indonesia Faculty of Computer Science Universitas Amikom Yogyakarta Sleman Indonesia Department of Information System Faculty of Computer Science Universitas Amikom Purwokerto Banyumas Jawa Tengah Indonesia

Sentiment analysis is extracting information in the form of emotional tendencies based on a series of data. One data source that can be used is tweets from users on Twitter social media. The biggest challenge of text-based sentiment analysis is the Text's multiple representations or meanings. In addition, the rules for writing non-standard texts require special handling. This study analyzes public sentiment towards the police by crawling Twitter tweets with the hashtag #percumaLaporPolisi. Process stages in this study include data collection, pre-processing, feature engineering, Naive Bayes classification, and evaluation. In the data collection process, manual labelling was carried out into three classes: positive, neutral, and negative, resulting in 633 data. At the pre-processing stage, the dataset will be normalized by Text, namely changing the words of slang and typos to synonyms of more understandable words. For feature engineering, researchers use TF-IDF for feature extraction algorithms and chi-square for feature selection. This study uses Naive Bayes as a classification algorithm because of its ability to classify documents by paying attention to the number of word occurrences. The study results show that people tend to be negative toward the police. Meanwhile, the naive Bayes classification model developed produces an accuracy of 74.8%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SNPE-SRGAN: Lightweight Generative Adversarial Networks for Single-Image Super-Resolution on Mobile Using SNPE Framework 5

SNPE-SRGAN: Lightweight Generative Adversarial Networks for ...

引用

5th International Conference on Computing and Applied Informatics, ICCAI 2020

作者： Tampubolon, Hendrik Setyoko, Aji Purnamasari, Fanindia Department of Information System Faculty of Engineering and Computer Science Krida Wacana Christian University Jakarta Indonesia Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan20155 Indonesia

An image resulting from a low-resolution (LR) camera on the mobile phone has lower quality than a high-resolution(HR) camera on a DSLR. Meanwhile, the HR camera is pricing if compared with the LR camera. How to achieve a single-image quality on LR camera likewise on HR camera becomes essential research in the past years. Addressing this issue can be done by upscaling a single LR image. Recently, the super-resolution generative adversarial network (SRGAN) model is one of the state-of-the-art super-resolution(SR)models employed on single-image SR. However, implementing a deep learning model like SRGAN on a mobile device is challenging in computation power and resources. This study aims to develop a smaller and lower resources model while preserving single-image SR quality on mobile devices. To meet these objectives, we convert, quantize, and compress the SRGAN model on Snapdragon Neural Processing Engine (SNPE) as an example. We then validate the SRGAN on the DIV2K dataset on which improves the model performances. Besides, we conduct experiments on GPU, DSP environment. The experimental result confirmed that SNPE-SRGAN capable of achieves not only HR images' quality but also low latency by 0.06 second and smaller model by 1.7 Mb size running on DSP. Also, the SRGAN-DLC-Quantized running on GPU has a smaller size by 1.7 Mb and lower latency by 1.151 seconds compared with Non-quantized SRGAN-TensorFlow by 9.1 Mb and 1.608 seconds latency. © Published under licence by IOP Publishing Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Reshaping Automated Writing Evaluator for English as Foreign Language Users

Reshaping Automated Writing Evaluator for English as Foreign...

引用

Social sciences and Intelligent Management (SSIM), IEEE International Conference on

作者： Maria Tamarina Prawati Muhammad Fikri Hasani Lay Christian Jane Ivana English Department Faculty of Humanities Bina Nusantara University Jakarta Indonesia Computer Science School of Computer Science Bina Nusantara University Jakarta Indonesia Information System Department School of Information System Bina Nusantara University Jakarta Indonesia

To understand the role of the human rating and automatic writing evaluator (AWE), we compared their scores. There was a notable score difference in Focus and Purposes as a metric. This result indicated the need to validate and evaluate the metrics. Regarding AWE, more data is needed to improve the inference performance. Another improvement needs to include word embedding by pre-training the evaluator with a bigger corpus to represent better results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Challenges and Recommendation of the information Technologies Application in Hazardous Medical Waste Management amidst Pandemic Covid-19 2

Challenges and Recommendation of the Information Technologie...

引用

2020 2nd International Conference on science and Technology, ICoST 2020

作者： Rahayu, P. Rohajawati, S. Fairus, S. Saragih, H. Akbar, H. Information System Computer Science Faculty Universitas Mercu Buana Jakarta Indonesia Information System Informatics and Environmental Engineering Universitas Bakrie Jakarta Indonesia Department of Informatics Computer Science Faculty Universitas Esa Unggul Jakarta Indonesia

Handling of Covid-19 patients requires more medical equipment than normal conditions, increasing the amount of hazardous medical waste. The management of hazardous medical waste has many challenges;therefore, it needed a strategy to solve it using information technology. Based on a filter of 376 articles, this review adopted a systematic Literature Review approach to evaluating the recent challenge and recommendation in the field of Hazardous Medical Waste Management amidst Covid-19. Through a four-phase workflow consisting of searching, screening, excluded, and included literature search, this study identified the most influential journals, scholars, and articles that have been influential in the domain of Hazardous Medical Waste Management. These literature review results are four challenges in Hazardous Medical Waste Management, including Regulation, Technology, Financial and Awareness. The other finding is IT application recommendations such as IoT, Big Data, DSS, AI and GIS. By providing the latest research about the challenges and recommendations in the domain of Hazardous Medical Waste Management amidst Covid-19, the paper serves as a preliminary recommendation for practitioners and researchers to link current research to future trends. © 2021 Published under licence by IOP Publishing Ltd.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Water Wave Optimization with Deep Learning Driven Smart Grid Stability Prediction

引用

computers, Materials & Continua 2022年第12期73卷 6019-6035页

作者： Anwer Mustafa Hilal Aisha Hassan Abdalla Hashim Heba G.Mohamed Mohammad Alamgeer Mohamed K.Nour Anas Abdelrahman Abdelwahed Motwakel Department of Electrical and Computer Engineering International Islamic University MalaysiaKuala Lumpur53100Malaysia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam Bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Electrical Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Computer Science and Bioinformatics Singhania UniversityPacheri BariJhnujhunuRajasthanIndia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Mechanical Engineering Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11835Egypt

Smart Grid(SG)technologies enable the acquisition of huge volumes of high dimension and multi-class data related to electric power grid operations through the integration of advanced metering infrastructures,control systems,and communication *** SGs,user demand data is gathered and examined over the present supply criteria whereas the expenses are then informed to the clients so that they can decide about electricity *** the entire procedure is valued on the basis of time,it is essential to perform adaptive estimation of the SG’s *** advancements inMachine Learning(ML)andDeep Learning(DL)models enable the designing of effective stability prediction models in *** this background,the current study introduces a novel Water Wave Optimization with Optimal Deep Learning Driven Smart Grid Stability Prediction(WWOODL-SGSP)*** aim of the presented WWOODL-SGSP model is to predict the stability level of SGs in a proficient *** attain this,the proposed WWOODL-SGSP model initially applies normalization process to scale the data to a uniform ***,WWO algorithm is applied to choose an optimal subset of features from the pre-processed ***,Deep Belief Network(DBN)model is followed to predict the stability level of ***,Slime Mold Algorithm(SMA)is exploited to fine tune the hyperparameters involved in DBN *** order to validate the enhanced performance of the proposedWWOODL-SGSP model,a wide range of experimental analyses was *** simulation results confirmthe enhanced predictive results of WWOODL-SGSP model over other recent approaches.

关键词： Smart grid stability prediction deep learning energy systems machine learning metaheursitics

来源：评论

学校读者我要写书评

暂无评论

Combination of CRITIC and PROMETHEE II Methods as An Early Detection of Potential Dropout Students

Combination of CRITIC and PROMETHEE II Methods as An Early D...

引用

International Conference on information and Communications Technology (ICOIACT)

作者： Mochammad Yusa Funny Farady Coastera Deni Rahmadani Julia Purnama Sari Kusrini Kusrini Anggit Dwi Hartanto Department of Informatics Faculty of Engineering University of Bengkulu Bengkulu Indonesia Department of Information System Faculty of Engineering University of Bengkulu Bengkulu Indonesia Magister of Informatics Engineering Faculty of Computer Science Universitas AMIKOM Yogyakarta Yogyakarta Indonesia Department of Information System Faculty of Computer Science Universitas AMIKOM Yogyakarta Yogyakarta Indonesia

Dropout (DO) has negative implications for individuals and educational institutions. The field of education data mining (EDM) offers valuable contributions to prevent dropout cases and improve student retention. This study focuses on implementing EDM to identify students at risk of dropping out by integrating academic activity criteria with real-time data sources. Previous studies have encountered limitations in classification and clustering techniques, with classification relying on labeled training data (supervised learning) and clustering constrained by attribute or criteria weight (unsupervised learning). This study aims to address these limitations by combining the PROMETHEE II ranking approach and the CRITIC weighting method, producing a list of students with dropout potential. The results can aid stakeholders in implementing preventive measures. The study involves several steps: 1) Collecting data through integration with academic portals; 2) Filtering and selecting criteria for student academic activities; 3) Transforming and normalizing the data; 4) Applying automatic weighting using CRITIC; 5) Calculating criteria rankings using the PROMETHEE II technique; and 6) Validating the ranking outcomes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A HybridManufacturing ProcessMonitoringMethod Using Stacked Gated Recurrent Unit and Random Forest

引用

Intelligent Automation & Soft Computing 2024年第2期39卷 233-254页

作者： Chao-Lung Yang Atinkut Atinafu Yilma Bereket Haile Woldegiorgis Hendrik Tampubolon Hendri Sutrisno Department of Industrial Management National Taiwan University of Science and TechnologyTaipeiTaiwanChina Faculty of Mechanical and Industrial Engineering Bahir Dar Institute of Technology(BiT)Bahir DarUniversityBahir Dar6000Ethiopia Department of Computer Science and Information Engineering National Taiwan University of Science and TechnologyTaipeiTaiwanChina Department of Information System Faculty of Engineering and Computer ScienceKridaWacana Christian UniversityJakartaIndonesia Department of Information Management National Dong Hwa UniversityHualienTaiwanChina

This study proposed a new real-time manufacturing process monitoring method to monitor and detect process shifts in manufacturing *** real-time production process monitoring is critical in today’s smart *** more robust the monitoring model,the more reliable a process is to be under *** the past,many researchers have developed real-time monitoring methods to detect process shifts ***,thesemethods have limitations in detecting process shifts as quickly as possible and handling various data volumes and *** this paper,a robust monitoring model combining Gated Recurrent Unit(GRU)and Random Forest(RF)with Real-Time Contrast(RTC)called GRU-RF-RTC was proposed to detect process shifts *** effectiveness of the proposed GRU-RF-RTC model is first evaluated using multivariate normal and nonnormal distribution ***,to prove the applicability of the proposed model in a realmanufacturing setting,the model was evaluated using real-world normal and non-normal *** results demonstrate that the proposed GRU-RF-RTC outperforms other methods in detecting process shifts quickly with the lowest average out-of-control run length(ARL1)in all synthesis and real-world problems under normal and non-normal *** experiment results on real-world problems highlight the significance of the proposed GRU-RF-RTC model in modern manufacturing process monitoring *** result reveals that the proposed method improves the shift detection capability by 42.14%in normal and 43.64%in gamma distribution problems.

关键词： Smart manufacturing process monitoring quality control gated recurrent unit neural network random forest

来源：评论

学校读者我要写书评

暂无评论

A Novel Cyber Threat Intelligence (CTI) Framework for Detecting Android Malware: Work on Progress

A Novel Cyber Threat Intelligence (CTI) Framework for Detect...

引用

2024 International Conference on information Technology systems and Innovation, ICITSI 2024

作者： Wijaya, Andri Stiawan, Deris Abdiansah Suprapto, Bhakti Yudho Saputra, Iwan Pahendra Anto Rini, Dian Palupi Sayfudin Idris, Mohd.Yazid Budiarto, Rahmat Universitas Katolik Musi Charitas Faculty of Engineering Universitas Sriwijaya Department of Information System Indonesia Universitas Sriwijaya Faculty of Computer Science Indonesia Sriwijaya University Faculty of Engineering Electrical Engineering Dept. Palembang Indonesia Sriwijaya University Faculty of Comp.Science Informatic Engineering Dept. Palembang Indonesia Universitas Muhammadiyah Palembang Indonesia Universiti Teknologi Malaysia School of Computing Faculty of Computing Johor81310 Malaysia Al-Baha University College of Computing and Information Al Aqiq Saudi Arabia

ISBN: (纸本)9798331511470

The latest approach in cyber threat intelligence (CTI) is becoming increasingly crucial in detecting evolving cyber threats, including malware on Android devices. This problem is getting deeper when the number of Android users in Indonesia is increasing compared to other platforms. Therefore, it is necessary to develop a new method that integrates the CTI framework with the use of machine learning to improve the accuracy and speed in detecting Android malware. By utilizing intelligence data from structured threat reports, this method aims to identify suspicious patterns and abnormal behavior that may not be detected by conventional security systems so that with this updated security system it is proactive towards the development of new types of malware threats, with the hope of being able to make a significant contribution to strengthening especially mobile devices with the Android platform and being able to provide more effective solutions in reducing the risk of malware attacks on Android. © 2024 IEEE.

关键词： Cyber attacks

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：