2019 Artificial Intelligence for Transforming Business and Society (AITB)最新文献

{"title":"AITB 2019 Conference Booklet","authors":"Rajen Kandel","doi":"10.1109/aitb48515.2019.8947447","DOIUrl":"https://doi.org/10.1109/aitb48515.2019.8947447","url":null,"abstract":"Low contrast images are not conducive to human perception and computer vision algorithms due to their low discernibility. In many application quality of acquired images are not suitable, so image has to be enhanced according to the need of a specific application. To solve the problems of detail loss, poor contrast and problems of noise, a new technique based on homomorphic filtering is proposed. This paper contributes to combine the filter based and Successive Mean Quantization Transform (SMQT) algorithm for better image quality of digital image by minimizing the properties such as gain and bias. First, we investigate the result for the standard images and experimental images. Second, we measure the results by using Peak Signal-toNoise Ratio (PSNR), Structural Similarity (SSIM), blind/reference less image spatial quality evaluator (BRISQUE) and Blind Image Quality Indices (BIQI). Finally, model is compared with enhancement algorithms. Simulation and experimental results demonstrates that proposed model provides better results as compared to other state-of-art contrast enhancement algorithms. The implementation is done using MATLAB. Image Enhancement using successive mean quantization transform and homomorphic filtering Paper 4 (Authors: Swarup Raj Dhungana, Pranita Upadhyaya) (Authors: Sujan Adhikari, Sanjeeb Prasad Panday) Abstract In today’s world cyber threat intelligence has been one of the major prerequisites for overall development of the country, especially for developing nations like Nepal. The main aim of the research is to identify an optimal cyber threat intelligence system framework which addresses the current issues of cyber security and ideally fits in the current context of Nepal. Using the Coburg Intrusion Detection Data Set, two machine learning models; Deep Learning and Random Forest are trained and evaluated, to choose the ideal one for the framework along with ontology mapping to introduce adaptive learning feature in the system. The proposed framework minimizes the current gap in cyber security for Nepal. Furthermore, the study can be extended to add different features such as; creating a proper user interface and implementing the alert feature for the system which can be vital for establishing Nepal Cyber Security Center. Optimal Cyber Threat Intelligent System for Nepal","PeriodicalId":296159,"journal":{"name":"2019 Artificial Intelligence for Transforming Business and Society (AITB)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115217914","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":"Smart Job Recruitment Automation: Bridging Industry and University","authors":"V. Yadav, Ujjwal Gewali, S. Khatri, Shree Ram Rauniyar, Aman Shakya","doi":"10.1109/AITB48515.2019.8947445","DOIUrl":"https://doi.org/10.1109/AITB48515.2019.8947445","url":null,"abstract":"This paper proposes and highlights the need of an online job board system for colleges and its effectiveness in bridging the gap between college students and career opportunities. Traditionally, employment websites have been used in HR management for finding candidates and in recruitment. This work is based on a job portal built for one of the leading engineering campuses of Nepal, Pulchowk Campus, which is a variation of such job boards designed specifically to serve the students of the Campus. With services like job recommendations to students based on their skills, and candidate filtering to assist companies in candidate matching, the system is expected to be of use for both students for exploring jobs, and companies to find potential candidates suited for the job.","PeriodicalId":296159,"journal":{"name":"2019 Artificial Intelligence for Transforming Business and Society (AITB)","volume":"38 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132194075","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 Series Based Pattern Recognition for Anomaly Detection from System Audit Logs","authors":"Prabhat Pokharel, Sandeep Sigdel, Roshan Pokhrel, Basanta Joshi","doi":"10.1109/AITB48515.2019.8947448","DOIUrl":"https://doi.org/10.1109/AITB48515.2019.8947448","url":null,"abstract":"Pattern recognition is very important for the identification of anomalous patterns in log messages. This paper presents pattern recognition in time series log data for anomaly detection. The proposed method uses Seasonal Auto Regression Integrated Moving Average (Seasonal ARIMA) to identify deviations between actual and predicted values. The deviations beyond a defined threshold are identified as anomalous data points. Anomalous data points for the positively correlated data points are used to calculate the composite anomalous score. Finally, the approach is compared with Seasonal Extreme Studentized Deviate (ESD). The method calculates the anomalous score in the range of 0 to 100. This can be used to understand the security risk posture and thus prioritize the incidents associated with a given user.","PeriodicalId":296159,"journal":{"name":"2019 Artificial Intelligence for Transforming Business and Society (AITB)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134350044","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":"One-Shot Template Matching for Automatic Document Data Capture","authors":"Pranjal Dhakal, Manish Munikar, B. Dahal","doi":"10.1109/AITB48515.2019.8947440","DOIUrl":"https://doi.org/10.1109/AITB48515.2019.8947440","url":null,"abstract":"In this paper, we propose a novel one-shot template-matching algorithm to automatically capture data from business documents with an aim to minimize manual data entry. Given one annotated document, our algorithm can automatically extract similar data from other documents having the same format. Based on a set of engineered visual and textual features, our method is invariant to changes in position and value. Experiments on a dataset of 595 real invoices demonstrate 86.4% accuracy.","PeriodicalId":296159,"journal":{"name":"2019 Artificial Intelligence for Transforming Business and Society (AITB)","volume":"14 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130871541","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":"A Comparison of Semantic Similarity Methods for Maximum Human Interpretability","authors":"P. Sitikhu, Kritish Pahi, Pujan Thapa, S. Shakya","doi":"10.1109/AITB48515.2019.8947433","DOIUrl":"https://doi.org/10.1109/AITB48515.2019.8947433","url":null,"abstract":"The inclusion of semantic information in any similarity measures improves the efficiency of the similarity measure and provides human interpretable results for further analysis. The similarity calculation method that focuses on features related to the text's words only, will give less accurate results. This paper presents three different methods that not only focus on the text's words but also incorporates semantic information of texts in their feature vector and computes semantic similarities. These methods are based on corpus-based and knowledge-based methods, which are: cosine similarity using tf-idf vectors, cosine similarity using word embedding and soft cosine similarity using word embedding. Among these three, cosine similarity using tf-idf vectors performed best in finding similarities between short news texts. The similar texts given by the method are easy to interpret and can be used directly in other information retrieval applications.","PeriodicalId":296159,"journal":{"name":"2019 Artificial Intelligence for Transforming Business and Society (AITB)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115543812","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":"Fine-grained Sentiment Classification using BERT","authors":"Manish Munikar, Sushil Shakya, Aakash Shrestha","doi":"10.1109/AITB48515.2019.8947435","DOIUrl":"https://doi.org/10.1109/AITB48515.2019.8947435","url":null,"abstract":"Sentiment classification is an important process in understanding people's perception towards a product, service, or topic. Many natural language processing models have been proposed to solve the sentiment classification problem. However, most of them have focused on binary sentiment classification. In this paper, we use a promising deep learning model called BERT to solve the fine-grained sentiment classification task. Experiments show that our model outperforms other popular models for this task without sophisticated architecture. We also demonstrate the effectiveness of transfer learning in natural language processing in the process.","PeriodicalId":296159,"journal":{"name":"2019 Artificial Intelligence for Transforming Business and Society (AITB)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130620186","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}