Libraries & Information Technology eJournal最新文献

{"title":"A Contemporary Study of Deep Learning in Diagnosis and Prediction of Diseases","authors":"Sayyada Hajera Beguma, Vidyullatha P","doi":"10.2139/ssrn.3734301","DOIUrl":"https://doi.org/10.2139/ssrn.3734301","url":null,"abstract":"With the introduction of big data and its incredible advancement in image procurement devices, the transformation of medical data into valuable knowledge has become an important challenge in the area of bioinformatics. The medical images procured require huge analysis and diagnosis of images which can be done using Artificial Intelligence techniques like Machine learning and Deep Learning that yields automated diagnosis solutions. Deep learning methods can provide optimized and precise solutions for medical image diagnosis and can be an important methodology for imminent health care applications. In this paper, some contemporary deep learning neural networks will be discussed and their application in detecting various diseases.","PeriodicalId":139603,"journal":{"name":"Libraries & Information Technology eJournal","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114830015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Overview on Open Source Machine Learning Platforms-TensorFlow","authors":"Muqthadar Ali Syed","doi":"10.2139/ssrn.3732837","DOIUrl":"https://doi.org/10.2139/ssrn.3732837","url":null,"abstract":"Deep learning is a part of artificial intelligence utilizing deep neural network architectures that have essentially progressed to the cutting edge in PC vision, speech recognition, characteristic language preparation, and different spaces. In November 2015, Google delivered TensorFlow, an open-source deep-learning programming library for characterizing, preparing, and conveying machine-learning models. In this paper, we audit Tensor Flow and put it in current deep learning ideas and programming. We discuss its essential computational standards and appropriated execution model, its programming interface, and visualization toolbox. We, at that point, contrast Tensor Flow with elective libraries, for example, Theano, Torch, or Caffe on a subjective just as a quantitative premise. Lastly, remark on watched use-instances of TensorFlow in the scholarly community and industry","PeriodicalId":139603,"journal":{"name":"Libraries & Information Technology eJournal","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126465789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Time Your Hedge With Deep Reinforcement Learning","authors":"E. Benhamou, D. Saltiel, Sandrine Ungari, Abhishek Mukhopadhyay","doi":"10.2139/ssrn.3693614","DOIUrl":"https://doi.org/10.2139/ssrn.3693614","url":null,"abstract":"Can an asset manager plan the optimal timing for her/his hedging strategies given market conditions? The standard approach based on Markowitz or other more or less sophisticated financial rules aims to find the best portfolio allocation thanks to forecasted expected returns and risk but fails to fully relate market conditions to hedging strategies decision. In contrast, Deep Reinforcement Learning (DRL) can tackle this challenge by creating a dynamic dependency between market information and hedging strategies allocation decisions. In this paper, we present a realistic and augmented DRL framework that: (i) uses additional contextual information to decide an action, (ii) has a one period lag between observations and actions to account for one day lag turnover of common asset managers to rebalance their hedge, (iii) is fully tested in terms of stability and robustness thanks to a repetitive train test method called anchored walk forward training, similar in spirit to k fold cross validation for time series and (iv) allows managing leverage of our hedging strategy. Our experiment for an augmented asset manager interested in sizing and timing his hedges shows that our approach achieves superior returns and lower risk.","PeriodicalId":139603,"journal":{"name":"Libraries & Information Technology eJournal","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116245257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"واقع أمن وسرية المعلومات الإلكترونية في بنك فلسطين \"دراسة حالة\" (The Reality of Electronic Information Security in Bank of Palestine \"Case Study\")","authors":"Feras Shehada, محمد بدر","doi":"10.2139/ssrn.3686554","DOIUrl":"https://doi.org/10.2139/ssrn.3686554","url":null,"abstract":"<b>Arabic Abstract:</b> هدفت هذه الدراسة إلى تقييم واقع أمن وسرية المعلومات الإلكترونية في بنك فلسطين \"دراسة حالة\" من خلال التعرف على مدى توافر مقومات حماية البنية التحتية لأمن المعلومات ، ولتحقيق هدف الدراسة تم إعداد استبانة مكونة من ثلاث محاور (الحماية المادية - الحماية البرمجية - حماية الأفراد) لقياس متغيرات الدراسة , وزعت على العاملين في أقسام تكنولوجيا المعلومات في بنك فلسطين وقد شملت عينة الدارسة على (38) وزعت عليهم الاستبانة وتم استرداد (31) استبانة حيث بلغت نسبة الاسترداد81%) )، وقد توصلت الدراسة إلى نتائج مهمة تشير إلى أنه يتوفر لدى بنك فلسطين مقومات بنية تحتية مقبولة بمحاورها الثلاثة (المادية ,البرمجية، والأفراد ) بنسب متفاوتة , حيث كان المحور الأول (الحماية المادية) في المرتبة الأولى بنسبة (%92.69), أما المحور الثاني (الحماية البرمجية ) كان في المرتبة الثانية بنسبة (%88.77) , والمحور الأخير (حماية الأفراد) احتل المرتبة الثالثة بنسبة (%80.00) مما يدل على أن الآراء كانت في المحاور الثلاثة موافقة بدرجة كبيرة جداً, وأنه لا توجد فروق ذات دلالة إحصائية في استجابات أفراد العينة حول واقع إدارة أمن المعلومات في بنك فلسطين تُعزى للمتغيرات الديموغرافية (المؤهل العلمي، المستوى الوظيفي، والخبرة) باستثناء متغير الدورات التدريبية حيث أظهرت النتائج أنه يوجد فروق ذات دلالة إحصائية في استجابات أفراد العينة حول واقع إدارة أمن المعلومات في بنك فلسطين تُعزى لمتغير الدورات التدريبية.<br> وانتهت الدراسة إلى مجموعة من التوصيات من أهمها ، قيام بنك فلسطين بتطوير سياسات أمن المعلومات الخاصة به، والعمل على نشرها و تطبيقها، والقيام بمراجعتها، لما لهذه السياسات من أثر في تحسين الإجراءات الأمنية , ضرورة حث المصارف الفلسطينية على الاستمرار بالاهتمام بالبنية التحتية لأمن المعلومات وتطويرها لتجاري المستحدثات التكنولوجية السريعة.<br><br><b>English Abstract:</b> This study aims at evaluating the reality of electronic information security in Bank of Palestine\" Case Study \", through recognizing the availability of the elements to protect the infrastructure of information security. To achieve the objective of this study, a questionnaire was prepared and consisted at three axes (Physical protecting, programming protecting and protect the individuals) To measure study variables, It was distributed among the employees in the Departments of information technology in Bank of Palestine, The study sample included (38) employees, we regained( 31) questionnaire, recovery rate of (81%). <br><br>The study reached important results that there is in Bank Of Palestine the elements of accepted infrastructure in its three axes the( Physical, programming and individuals) in a different ration, and there was no significant differences related to individuals responses about the real field of information security in the Bank Of Palestine, that refers to demographic variables (Qualification, the professional level, the Experience). and there are significant differences related to individuals responses about the real field of information security in the Bank Of Palestine that refers to variable (training courses).<br><br>The study ends in some recommendations, The most important one is that Bank","PeriodicalId":139603,"journal":{"name":"Libraries & Information Technology eJournal","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132182418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Save Time or Save Face? The Stage Fright Effect in the Adoption of Facial Recognition Payment Technology","authors":"Jia Gao, Ying Rong, Xin Tian, Yuliang Yao","doi":"10.2139/ssrn.3668036","DOIUrl":"https://doi.org/10.2139/ssrn.3668036","url":null,"abstract":"Although facial recognition (FR) payment technology can be more convenient for customers and reduce their costs, it is still not used by many customers — most likely due to the stage fright effect that originates from social presence in public. Using transaction data collected from three retail chains, we develop econometric models and an estimation strategy for estimating this stage fright effect and several of its moderating factors. We find that customers are less likely to use FR payment technology when more customers are in line behind them, waiting and watching; that is, when they are experiencing the stage fright effect. We estimate that the marginal stage fright effect, with every additional customer who is waiting and watching in the line behind the paying customer, can result in a 3.72% reduction in the probability of the focal customer using FR payment technology and that the potential stage fright effect may be as high as 37.58%. We also show that there are two factors that moderate the stage fright effect: \u0000 \u00001) when a customer has more experience with FR payment technology, the stage fright effect is reduced; \u0000 \u00002) when the immediately preceding customer uses FR payment technology, the stage fright of the focal customer is increased.","PeriodicalId":139603,"journal":{"name":"Libraries & Information Technology eJournal","volume":"67 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124274279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Experimental Approach to Conceal Confidential Data using LSB Embedding Technique","authors":"Ravi Kumar, Namrata Singh","doi":"10.2139/ssrn.3593175","DOIUrl":"https://doi.org/10.2139/ssrn.3593175","url":null,"abstract":"Security of our data is very important in current time, so to provide the security of our data should be on first priority. To conceal confidential information is very important in the present era. Steganography provides the features to conceal our confidential information into the cover medium. In this paper I used the LSB embedding technique to hide the data and also try to improve the quality of stego image with increased payload capacity. Here I am trying to provide authenticity, confidentiality, and integrity.","PeriodicalId":139603,"journal":{"name":"Libraries & Information Technology eJournal","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129659578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rohanish Rover: Robotic Arm and Image Processing","authors":"Snehal J. Koparde, Omkar Chavan, Meghashyam Joshi, Sushrut Bodke","doi":"10.2139/ssrn.3645299","DOIUrl":"https://doi.org/10.2139/ssrn.3645299","url":null,"abstract":"This paper presents the design and development of a robotic arm with computer vision and machine learning algorithms to recognize and perform tasks over the object. The project comprises two modules one is the Robotic arm and the other one is Mast camera. This Project proposes a Real-time Image Processing based on the Robotic Arm Control Standalone System utilizing Microprocessor. In the current time, we made a robot equipped for observation and surveillance furthermore with a substitute application in distinguishing and following a pre-specified object. The detection and recognition are done using the Open CV library of Image Processing in python. While all the processing is done on a raspberry pi which works on Raspbian OS based on Debian-Linux OS. The functioning of the robotic arm and mast camera operations are carried out without any manual control. The robotic arm placed on the chassis is having 4 Degree of Freedom (4 DOF). The total programming model is developed in Python. The programming includes capturing the whole picture and then processing the image, identifying the object, and movement of the robotic arm by using Raspberry Pi. We wanted the developers to know the limits of what low-cost, open-source hardware can do for mankind.","PeriodicalId":139603,"journal":{"name":"Libraries & Information Technology eJournal","volume":"255 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122859263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Valuation Ratios, Surprises, Uncertainty or Sentiment: How Does Financial Machine Learning Predict Returns From Earnings Announcements?","authors":"M. Schnaubelt, Oleg Seifert","doi":"10.2139/ssrn.3577132","DOIUrl":"https://doi.org/10.2139/ssrn.3577132","url":null,"abstract":"We apply state-of-the-art financial machine learning to assess the return-predictive value of more than 45,000 earnings announcements on a majority of S&P1500 constituents. To represent the diverse information content of earnings announcements, we generate predictor variables based on various sources such as analyst forecasts, earnings press releases and analyst conference call transcripts. We sort announcements into decile portfolios based on the model’s abnormal return prediction. In comparison to three benchmark models, we find that random forests yield superior abnormal returns which tend to increase with the forecast horizon for up to 60 days after the announcement. We subject the model’s learning and out-of-sample performance to further analysis. First, we find larger abnormal returns for small-cap stocks and a delayed return drift for growth stocks. Second, while revenue and earnings surprises are the main predictors for the contemporary reaction, we find that a larger range of variables, mostly fundamental ratios and forecast errors, is used to predict post-announcement returns. Third, we analyze variable contributions and find the model to recover non-linear patterns of common capital markets effects such as the value premium. Leveraging the model’s predictions in a zero-investment trading strategy yields annualized returns of 11.63 percent at a Sharpe ratio of 1.39 after transaction costs.","PeriodicalId":139603,"journal":{"name":"Libraries & Information Technology eJournal","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129693758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative Analysis on Prediction of Software Effort Estimation Using Machine Learning Techniques","authors":"A. Singh, Mukesh Kumar","doi":"10.2139/ssrn.3565813","DOIUrl":"https://doi.org/10.2139/ssrn.3565813","url":null,"abstract":"Effort Estimation (EE) is a technique for finding the entire effort required to predict the accuracy of a model. It’s a significant chore in software application development practice. To find accurate estimation, numerous predictive models have developed in recent times. The estimate prepared during the early stage of a model expansion is inaccurate since requirements at that time are not very clear, but as the model progresses, the accuracy of the estimation increases. Therefore, accurate estimation is essential to choose for each software application model development. Here, Linear Regression (LR), Multi-layer perceptron (MLP), Random Forest (RF) algorithms are implemented using WEKA toolkit, and results shows that Linear Regression shows better estimation accuracy than Multilayer Perceptron and Random Forest.","PeriodicalId":139603,"journal":{"name":"Libraries & Information Technology eJournal","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128058717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SIP Issues and Challenges – A Scalable Three Factor Authentication Scheme","authors":"S. Jan","doi":"10.2139/ssrn.3576552","DOIUrl":"https://doi.org/10.2139/ssrn.3576552","url":null,"abstract":"The SIP (Session Initiation Protocol) is an application and presentation layer signaling protocol used for initiating, continuing and terminating multimedia session for the end user. It gains much attention of the researchers because it is exposed to several threats and noticed challenging vulnerabilities from time to time. Consequently, the security of SIP is a crucial task and many efforts have been made by different researchers and tried to divert the attention towards its solution. But still, no one claims with conviction about a foolproof secure mechanism for SIP. As users extensively use SIP services, the mutual authentication and key agreement among the participants is an important issue. So, robust authentication and key agreement scheme are mandatory for enhancing security, legitimacy and better complexities. Therefore, we present an improved three-factor authentication scheme that caters all the weakness and known attacks in Mishra et al. scheme. The proposed scheme not only guarantees for security but performance can also be made lightweight. As performance and security contradict each other, the change in one inversely affects the other. The proposed scheme has been analyzed both formally using BAN (Burrows-Abadi-Needham) logic and ProVerif1.93 software verification toolkit, and informally using assumptions which show a delicate balance of security with performance.","PeriodicalId":139603,"journal":{"name":"Libraries & Information Technology eJournal","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116101057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}