RESUMO
Digital forensic analysis of videoconferencing applications has received considerable attention recently, owing to the wider adoption and diffusion of such applications following the recent COVID-19 pandemic. In this contribution, we present a detailed forensic analysis of Cisco WebEx which is among the top three videoconferencing applications available today. More precisely, we present the results of the forensic investigation of Cisco WebEx desktop client, web, and Android smartphone applications. We focus on three digital forensic areas, namely memory, disk space, and network forensics. From the extracted artifacts, it is evident that valuable user data can be retrieved from different data localities. These include user credentials, emails, user IDs, profile photos, chat messages, shared media, meeting information including meeting passwords, contacts, Advanced Encryption Standard (AES) keys, keyword searches, timestamps, and call logs. We develop a memory parsing tool for Cisco WebEx based on the extracted artifacts. Additionally, we identify anti-forensic artifacts such as deleted chat messages. Although network communications are encrypted, we successfully retrieve useful artifacts such as IPs of server domains and host devices along with message/event timestamps.
RESUMO
A lot of different methods are being opted for improving the educational standards through monitoring of the classrooms. The developed world uses Smart classrooms to enhance faculty efficiency based on accumulated learning outcomes and interests. Smart classroom boards, audio-visual aids, and multimedia are directly related to the Smart classroom environment. Along with these facilities, more effort is required to monitor and analyze students' outcomes, teachers' performance, attendance records, and contents delivery in on-campus classrooms. One can achieve more improvement in quality teaching and learning outcomes by developing digital twins in on-campus classrooms. In this article, we have proposed DeepClass-Rooms, a digital twin framework for attendance and course contents monitoring for the public sector schools of Punjab, Pakistan. DeepClassRooms is cost-effective and requires RFID readers and high-edge computing devices at the Fog layer for attendance monitoring and content matching, using convolution neural network for on-campus and online classes.
RESUMO
With time, numerous online communication platforms have emerged that allow people to express themselves, increasing the dissemination of toxic languages, such as racism, sexual harassment, and other negative behaviors that are not accepted in polite society. As a result, toxic language identification in online communication has emerged as a critical application of natural language processing. Numerous academic and industrial researchers have recently researched toxic language identification using machine learning algorithms. However, Nontoxic comments, including particular identification descriptors, such as Muslim, Jewish, White, and Black, were assigned unrealistically high toxicity ratings in several machine learning models. This research analyzes and compares modern deep learning algorithms for multilabel toxic comments classification. We explore two scenarios: the first is a multilabel classification of Religious toxic comments, and the second is a multilabel classification of race or toxic ethnicity comments with various word embeddings (GloVe, Word2vec, and FastText) without word embeddings using an ordinary embedding layer. Experiments show that the CNN model produced the best results for classifying multilabel toxic comments in both scenarios. We compared the outcomes of these modern deep learning model performances in terms of multilabel evaluation metrics.
Assuntos
Aprendizado Profundo , Humanos , Processamento de Linguagem Natural , Aprendizado de Máquina , Idioma , AlgoritmosRESUMO
With time, textual data is proliferating, primarily through the publications of articles. With this rapid increase in textual data, anonymous content is also increasing. Researchers are searching for alternative strategies to identify the author of an unknown text. There is a need to develop a system to identify the actual author of unknown texts based on a given set of writing samples. This study presents a novel approach based on ensemble learning, DistilBERT, and conventional machine learning techniques for authorship identification. The proposed approach extracts the valuable characteristics of the author using a count vectorizer and bi-gram Term frequency-inverse document frequency (TF-IDF). An extensive and detailed dataset, "All the news" is used in this study for experimentation. The dataset is divided into three subsets (article1, article2, and article3). We limit the scope of the dataset and selected ten authors in the first scope and 20 authors in the second scope for experimentation. The experimental results of proposed ensemble learning and DistilBERT provide better performance for all the three subsets of the "All the news" dataset. In the first scope, the experimental results prove that the proposed ensemble learning approach from 10 authors provides a better accuracy gain of 3.14% and from DistilBERT 2.44% from the article1 dataset. Similarly, in the second scope from 20 authors, the proposed ensemble learning approach provides a better accuracy gain of 5.25% and from DistilBERT 7.17% from the article1 dataset, which is better than previous state-of-the-art studies.
Assuntos
Autoria , Aprendizado de MáquinaRESUMO
Authorship analysis (AA) is the study of unveiling the hidden properties of authors from textual data. It extracts an author's identity and sociolinguistic characteristics based on the reflected writing styles in the text. The process is essential for various areas, such as cybercrime investigation, psycholinguistics, political socialization, etc. However, most of the previous techniques critically depend on the manual feature engineering process. Consequently, the choice of feature set has been shown to be scenario- or dataset-dependent. In this paper, to mimic the human sentence composition process using a neural network approach, we propose to incorporate different categories of linguistic features into distributed representation of words in order to learn simultaneously the writing style representations based on unlabeled texts for AA. In particular, the proposed models allow topical, lexical, syntactical, and character-level feature vectors of each document to be extracted as stylometrics. We evaluate the performance of our approach on the problems of authorship characterization, authorship identification and authorship verification with the Twitter, blog, review, novel, and essay datasets. The experiments suggest that our proposed text representation outperforms the static stylometrics, dynamic n -grams, latent Dirichlet allocation, latent semantic analysis, distributed memory model of paragraph vectors, distributed bag of words version of paragraph vector, word2vec representations, and other baselines.
RESUMO
Advancements in science and technology have highlighted the importance of robust healthcare services, lifestyle services and personalized recommendations. For this purpose patient daily life activity recognition, profile information, and patient personal experience are required. In this research work we focus on the improvement in general health and life status of the elderly through the use of an innovative services to align dietary intake with daily life and health activity information. Dynamic provisioning of personalized healthcare and life-care services are based on the patient daily life activities recognized using smart phone. To achieve this, an ontology-based approach is proposed, where all the daily life activities and patient profile information are modeled in ontology. Then the semantic context is exploited with an inference mechanism that enables fine-grained situation analysis for personalized service recommendations. A generic system architecture is proposed that facilitates context information storage and exchange, profile information, and the newly recognized activities. The system exploits the patient's situation using semantic inference and provides recommendations for appropriate nutrition and activity related services. The proposed system is extensively evaluated for the claims and for its dynamic nature. The experimental results are very encouraging and have shown better accuracy than the existing system. The proposed system has also performed better in terms of the system support for a dynamic knowledge-base and the personalized recommendations.
Assuntos
Atividades Cotidianas , Técnicas Biossensoriais , Monitorização Fisiológica , Sistemas Computacionais , Atenção à Saúde/métodos , HumanosRESUMO
Few techniques for guaranteeing a network lifetime have been proposed despite its great impact on network management. Moreover, since the existing schemes are mostly dependent on the combination of disparate parameters, they do not provide additional services, such as real-time communications and balanced energy consumption among sensor nodes; thus, the adaptability problems remain unresolved among nodes in wireless sensor networks (WSNs). To solve these problems, we propose a novel fuzzy logic model to provide real-time communication in a guaranteed WSN lifetime. The proposed fuzzy logic controller accepts the input descriptors energy, time and velocity to determine each node's role for the next duration and the next hop relay node for real-time packets. Through the simulation results, we verified that both the guaranteed network's lifetime and real-time delivery are efficiently ensured by the new fuzzy logic model. In more detail, the above-mentioned two performance metrics are improved up to 8%, as compared to our previous work, and 14% compared to existing schemes, respectively.