检索结果-南通市图书馆

Optimal Deep Belief Network Enabled Cybersecurity Phishing Email Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第3期44卷 2701-2713页

作者： Ashit Kumar Dutta T.Meyyappan Basit Qureshi Majed Alsanea anas waleed abulfaraj Manal M.Al Faraj Abdul Rahaman Wahab Sait Department of Computer Science and Information Systems College of Applied SciencesAlMaarefa UniversityAd DiriyahRiyadh13713Kingdom of Saudi Arabia Department of Computer Science Alagappa UniversityKaraikudi630003India Department of Computer Science Prince Sultan UniversityRiyadh11586Kingdom of Saudi Arabia Department of Computing Arabeast CollegesRiyadh11583Kingdom of Saudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah23613Kingdom of Saudi Arabia Department of Archives and Communication King Faisal UniversityAl AhsaHofuf31982Kingdom of Saudi Arabia

Recently,developments of Internet and cloud technologies have resulted in a considerable rise in utilization of online media for day to day *** results in illegal access to users’private data and compromises *** is a popular attack which tricked the user into accessing malicious data and gaining the *** identification of phishing emails can be treated as an essential process in the domain of *** article focuses on the design of bio-geography based optimization with deep learning for Phishing Email detection and classification(BBODL-PEDC)*** major intention of the BBODL-PEDC model is to distinguish emails between legitimate and *** BBODL-PEDC model initially performs data pre-processing in three levels namely email cleaning,tokenization,and stop word ***,TF-IDF model is applied for the extraction of useful feature ***,optimal deep belief network(DBN)model is used for the email classification and its efficacy can be boosted by the BBO based hyperparameter tuning *** performance validation of the BBODL-PEDC model can be performed using benchmark dataset and the results are assessed under several *** comparative studies reported the superior outcomes of the BBODL-PEDC model over the recent approaches.

关键词： Cybersecurity phishing email data classification deep learning biogeography based optimization hyperparameter tuning

DLBT:Deep Learning-Based Transformer to Generate Pseudo-Code from Source Code

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第2期70卷 3117-3132页

作者： Walaa Gad anas Alokla waleed Nazih Mustafa Aref Abdel-badeeh Salem Faculty of Computers and Information Sciences Ain Shams UniversityAbassiaCairo11566Egypt College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl Kharj11942Saudi Arabia

Understanding the content of the source code and its regular expression is very difficult when they are written in an unfamiliar ***-code explains and describes the content of the code without using syntax or programming language ***,writing Pseudo-code to each code instruction is ***,neural machine translation is used to generate textual descriptions for the source *** this paper,a novel deep learning-based transformer(DLBT)model is proposed for automatic Pseudo-code generation from the source *** proposed model uses deep learning which is based on Neural Machine Translation(NMT)to work as a language *** DLBT is based on the transformer which is an encoder-decoder *** are three major components:tokenizer and embeddings,transformer,and *** code line is tokenized to dense *** transformer captures the relatedness between the source code and the matching Pseudo-code without the need of Recurrent Neural Network(RNN).At the post-processing step,the generated Pseudo-code is *** proposed model is assessed using a real Python dataset,which contains more than 18,800 lines of a source code written in *** experiments show promising performance results compared with other machine translation methods such as Recurrent Neural Network(RNN).The proposed DLBT records 47.32,68.49 accuracy and BLEU performance measures,respectively.

关键词： Natural language processing long short-term memory neural machine translation pseudo-code generation deep learning-based transformer

Pathological Role of Fungal Biofilms in Fungal Rhinosinusitis: A Case-Control Study

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Otolaryngology and Head & Neck Surgery 2021年第2期10卷 75-84页

作者： waleed F. Ezzat anas Askoura Hesham Falah Ahmed Negm Department of Otolaryngology/Head and Neck Surgery Faculty of Medicine Ain Shams University Cairo Egypt Department of Otolaryngology/Head and Neck Surgery Misr University for Science and Technology Cairo Egypt

Objective: This case-control study aimed to detect the presence of fungal biofilms in cases of fungal sinusitis, trying to find its role in recurrence of fungal sinus infection and resistance to medical treatment. Patients and Methods: This study was conducted at Ain-Shams University from June-2017 to June-2018 upon 20 patients as the fungal cases are not much in Egypt. All patients were subjected to functional endoscopic sinus surgery and taking specimens. Examination of specimens by scanning electron microscope was made. Results: The prevalence of fungal biofilms was 7 (70%) in cases and 0 (0%) in controls (p-value = 0.001). There is higher risk of fungal biofilms in cases of fungal sinusitis, the odds of biofilms is higher in the study group 2.33 than in the control group 0. The lower is the invasiveness, the higher is the fungal biofilms (OR = 0.94, 95% CI 0.46 - 4.05). Also, the analysis showed that the lower is the recurrence the lower is the fungal biofilms (OR = 2.25, 95% CI 0.15 - 7.93). Conclusion: This study showed the presence of fungal biofilms in different cases of fungal sinusitis whether primary or recurrent, also whether invasive or non-invasive. Studies with large sample size are recommended to get a strong evidence.

关键词： Fungal Biofilms Rhinosinusitis Recurrence Invasiveness

Survival and Prognostic Factors in Patients with Carcinoma of Cervical Stump

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Cancer Therapy 2015年第11期6卷 1008-1012页

作者： Hanan Ahmed Wahba Hend Ahmed El-Hadaad waleed Nabeel Abozeed waleed Elnahas Sameh Roshdy anas Gamal Clinical Oncology and Nuclear Medicine Mansoura University Mansoura Egypt Surgical Oncology Unit Mansoura Oncology Center Mansoura University Mansoura Egypt Obstetrics and Gynecology Mansoura University Mansoura Egypt

Purpose: To evaluate patients with carcinoma of cervical stump (CCS) and analyse different clinico-pathologic factors affect prognosis. Patients and Methods: This study was carried out through review of clinical records of patients. Recorded data included information on age, tumor stage, presenting symptoms, size of tumor, histopathology, grade, type, cause of subtotal hysterectomy (STH), treatment and follow-up results. Staging according to International Federation of Gynecology and Obstetrics (FIGO) staging system was done through: PHYSICAL examination, pelvic examination under anaesthesia, chest X-ray, magnetic resonance imaging (MRI) of the abdomen and pelvis, cystoscopy, rectosigmoidoscopy and intravenous pyelography. Prognostic factors as age, size of tumor, stage, lymph node (LN) involvement, pathological type, grade and type of CCS either true or coincidental were analysed through multivariate analysis. Results: 62% of patients are above 50 years with stage II in 48.7%. Squamous cell carcinoma was more common but 54% are of GIII. 89% were true CCS. Positive lymph nodes were reported in 27%. The predominant reason for STH was abnormal bleeding (73%). In about 95% of cases, women seeked medical attention because of symptoms and the most common presenting symptom was bleeding (54%). According to the stage and performance status of patients, treatment consisted of radiotherapy either external or interstitial, chemotherapy and chemoradiotherapy. Through multivariate analysis, the following was found to have adverse impact on survival: Coincidental type (P = 0.04), high grade (P = 0.03), advanced stage (P = 0.01), larger tumor size (P = 0.02), lymph node involvement (P = 0.029) and older age (P = 0.035). While pathological type was not (P = 0.52). After median follow-up of 52 months;5-year overall survival was 65%. Conclusion: CCS has a low morbidity. Adverse survival outcomes can be anticipated in those patients with: high grade lesions, advanced stages, large tu

关键词： Carcinoma of Cervical Stump Chemo-Radiotherapy Radiotherapy Survival and Prognostic Factors