Ransomware is one of the most advanced malware which uses high computer resources and services to encrypt system data once it infects a system and causes large financial data losses to the organization and individuals...
详细信息
Interoperability is a crucial aspect of the effective functioning of Internet of Things (IoT) devices, particularly in the healthcare industry. Although the use of IoT devices in healthcare has brought numerous benefi...
详细信息
App reviews are crucial in influencing user decisions and providing essential feedback for developers to improve their *** the analysis of these reviews is vital for efficient review *** traditional machine learning(M...
详细信息
App reviews are crucial in influencing user decisions and providing essential feedback for developers to improve their *** the analysis of these reviews is vital for efficient review *** traditional machine learning(ML)models rely on basic word-based feature extraction,deep learning(DL)methods,enhanced with advanced word embeddings,have shown superior *** research introduces a novel aspectbased sentiment analysis(ABSA)framework to classify app reviews based on key non-functional requirements,focusing on usability factors:effectiveness,efficiency,and *** propose a hybrid DL model,combining BERT(Bidirectional Encoder Representations from Transformers)with BiLSTM(Bidirectional Long Short-Term Memory)and CNN(Convolutional Neural Networks)layers,to enhance classification *** analysis against state-of-the-art models demonstrates that our BERT-BiLSTM-CNN model achieves exceptional performance,with precision,recall,F1-score,and accuracy of 96%,87%,91%,and 94%,*** contributions of this work include a refined ABSA-based relabeling framework,the development of a highperformance classifier,and the comprehensive relabeling of the Instagram App Reviews *** advancements provide valuable insights for software developers to enhance usability and drive user-centric application development.
Even though every individual is entitled to freedom of speech, some limitations exist when this freedom is used to target and harm another individual or a group of people, as it translates to hate speech. In this stud...
详细信息
Diffusion models have become a prevalent framework in deep generative modeling across various modalities. However, despite producing high quality results, these models are computationally expensive and suffer from slo...
详细信息
Diffusion models have become a prevalent framework in deep generative modeling across various modalities. However, despite producing high quality results, these models are computationally expensive and suffer from slow convergence. In this work, we address these challenges in image generation by leveraging the wavelet domain, which decomposes images into low and high-frequency components, each at half the resolution of the original image in both height and width. We observe that prioritizing the learning of low-frequency components over high-frequency details and masking out unnecessary high-frequency content in wavelet space can significantly enhance training convergence and reduce computational demands. This strategy simplifies the complexity associated with high-frequency details during training, allowing the model to capture the most representative features of the data distribution while maintaining a balance in detail preservation. To facilitate controlled learning across different wavelet coefficients, we employ a multitask loss function, with each task corresponding to the learning of a distinct wavelet subband. Additionally, to ensure consistency among wavelet coefficients, which is crucial for accurate reconstruction in pixel space, we introduce a multispectral cross-attention mechanism to aid the joint generation of different wavelet coefficients. The sampling process involves jointly generating wavelet coefficients, followed by an inverse wavelet transform to convert them back to pixel space. Our approach not only improves the training efficiency for unconditional image generation compared with the standard denoising diffusion probabilistic model (vanilla DDPM) but also uniquely supports the generation of high-frequency content conditioned on a low-resolution image, enabling both image generation and upsampling within a single model. To our knowledge, this capability is novel. Our model demonstrates superior performance in image generation compared with b
Free speech is essential, but it can conflict with protecting marginalized groups from harm caused by hate speech. Social media platforms have become breeding grounds for this harmful content. While studies exist to d...
详细信息
Free speech is essential, but it can conflict with protecting marginalized groups from harm caused by hate speech. Social media platforms have become breeding grounds for this harmful content. While studies exist to detect hate speech, there are significant research gaps. First, most studies used text data instead of other modalities such as videos or audio. Second, most studies explored traditional machine learning algorithms. However, due to the increase in complexities of computational tasks, there is need to employ complex techniques and methodologies. Third, majority of the research studies have either been evaluated using very few evaluation metrics or not statistically evaluated at all. Lastly, due to the opaque, black-box nature of the complex classifiers, there is need to use explainability techniques. This research aims to address these gaps by detecting hate speech in English and Kiswahili languages using videos manually collected from YouTube. The videos were converted to text and used to train various classifiers. The performance of these classifiers was evaluated using various evaluation and statistical measurements. The experimental results suggest that the random forest classifier achieved the highest results for both languages across all evaluation measurements compared to all classifiers used. The results for English language were: accuracy 98%, AUC 96%, precision 99%, recall 97%, F1 98%, specificity 98% and MCC 96% while the results for Kiswahili language were: accuracy 90%, AUC 94%, precision 93%, recall 92%, F1 94%, specificity 87% and MCC 75%. These results suggest that the random forest classifier is robust, effective and efficient in detecting hate speech in any language. This also implies that the classifier is reliable in detecting hate speech and other related problems in social media. However, to understand the classifiers’ decision-making process, we used the Local Interpretable Model-agnostic Explanations (LIME) technique to explain the
After the global pandemic,DaaS(desktop as a service)has become the first choice of many companies’remote working *** the desktops are usually deployed in the public cloud when using DaaS,customers are more cost-sensi...
详细信息
After the global pandemic,DaaS(desktop as a service)has become the first choice of many companies’remote working *** the desktops are usually deployed in the public cloud when using DaaS,customers are more cost-sensitive which boosts the requirement of proactive power *** researches in this area focus on virtual desktop infrastructure(VDI)session logon behavior modeling,but for the remote desktop service host(RDSH)-shared desktop pools,logoff optimization is also *** systems place sessions by round-robin or in a pre-defined order without considering their logoff ***,these approaches usually suffer from the situation that few left sessions prevent RDSH servers from being powered-off which introduces cost *** this paper,we propose session placement via adaptive user logoff prediction(SODA),an innovative compound model towards proactive RDSH session ***,an ensemble machine learning model that can predict session logoff time is combined with a statistical session placement bucket model to place RDSH sessions with similar logoff time in a more centralized manner on RDSH ***,the infrastructure cost-saving can be improved by reducing the resource waste introduced by those RDSH hosts with very few hanging sessions left for a long *** on real RDSH pool data demonstrate the effectiveness of the proposed proactive session placement approach against existing static placement techniques.
Video forgery detection has been necessary with recent spurt in fake videos like Deepfakes and doctored videos from multiple video capturing devices. In this paper, we provide a novel technique of detecting fake video...
详细信息
People’s demand for vehicles has been increasing day by day over the last few decades. A survey tells us that over 50,000 vehicles run on the roads per day. Such a large number of vehicles causes traffic. A survey te...
详细信息
One of the drastically growing and emerging research areas used in most informationtechnology industries is Bigdata *** is created from social websites like Facebook,WhatsApp,Twitter,*** about products,persons,initia...
详细信息
One of the drastically growing and emerging research areas used in most informationtechnology industries is Bigdata *** is created from social websites like Facebook,WhatsApp,Twitter,*** about products,persons,initiatives,political issues,research achievements,and entertainment are discussed on social *** unique data analytics method cannot be applied to various social websites since the data formats are *** approaches,techniques,and tools have been used for big data analytics,opinion mining,or sentiment analysis,but the accuracy is yet to be *** proposed work is motivated to do sentiment analysis on Twitter data for cloth products using Simulated Annealing incorporated with the Multiclass Support Vector Machine(SA-MSVM)***-MSVM is a hybrid heuristic approach for selecting and classifying text-based sentimental words following the Natural Language Processing(NLP)process applied on tweets extracted from the Twitter dataset.A simulated annealing algorithm searches for relevant features and selects and identifies sentimental terms that customers ***-MSVM is implemented,experimented with MATLAB,and the results are *** results concluded that SA-MSVM has more potential in sentiment analysis and classification than the existing Support Vector Machine(SVM)***-MSVM has obtained 96.34%accuracy in classifying the product review compared with the existing systems.
暂无评论