Proceedings of the 3rd International Conference on Advances in Artificial Intelligence最新文献

{"title":"Combining Domain Knowledge & Machine Learning: Making Predictions using Boosting Techniques","authors":"Utku Kubilay Cinar","doi":"10.1145/3369114.3369125","DOIUrl":"https://doi.org/10.1145/3369114.3369125","url":null,"abstract":"The latest hit on technology is the information and telecommunication novelties. Internet and big data are important source of information in order to understand this vast majority of the upcoming knowledge. Websites are progressively expanding and making it available to everyone who has access. Modern economic systems are built on data or knowledge. Thus, tech companies gather huge data and exercise their powers to digitalize the information to capture and utilize the knowledge within their reach. Information management enables firms to improve customer satisfaction, increase revenue, understand customer behavior, mitigate risk assessment, making a multidisciplinary approach. Another approach is to be able to identify business strategies. Information management researches (using machine learning algorithm) can help the field to discover what is significant on a customer behavior and reduce costs to its clients. Over the recent years, information management and machine learning algorithms are getting more and more close and on topic. Since, information management and machine learning intensely concerns with domain knowledge. Artificial Intelligence allows the machines to accumulate knowledge and adapts it. Information management and machine learning are affected by several factors such as business strategies, customer behavior, effectively using knowledge. Therefore, pulling only a single topic will not be enough to capture meaningful information from a huge chunk. Machine learning, and information systems also have the potential to help organizations in financial aspects. XG-Boost is one of the algorithms under the Decision-Trees equipped with boosting techniques similar to Microsoft's Light GBM algorithm. In recent years, XG-Boost algorithm has gained huge popularity due to its easy to use, speed, and performance. The aim of this paper is to show the use of the data in order to predict house prices XG-Boost algorithm and Neural Network model. The main goal here is to estimate the house prices using domain knowledge and machine learning algorithms. RMSE criteria was preferred. This paper suggests a generic way to gather knowledge on a very specific domain. Following the achieved result, the house price was estimated by processing the domain info through the machine learning algorithm here presented.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123966013","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 Negative Similarity Based Hybrid Recommender System Using Apache Spark","authors":"Mustafa Fatih Cetin, S. Ayvaz","doi":"10.1145/3369114.3369152","DOIUrl":"https://doi.org/10.1145/3369114.3369152","url":null,"abstract":"The rapid technological advances in digital business after the millennium has exponentially boosted the options of available items to the users. Customized lists of recommendations assist people by limiting the number of options to a very few items that are related to the specific user and thus supporting them to have the final decision with ease. In this study, we used Apache Spark to show an effective parallel implementation of our hybrid recommendation algorithm. Our hybrid algorithm is based on Alternating Least Squares and Negative Similarity Collaborative Filtering methods. Alternating Least Squares is a type of algorithm for matrix factorization, which can be parallelized during runtime. It performs relatively well when processing large scale datasets. Negative Similarity Collaborative Filtering (NSCF) technique exploits the tastes of people at the opposite poles. The cascade hybridization method was used in the study to create a hybrid algorithm. In the evaluations, we observed that hybridization achieved significant accuracy performance improvement when compared to the performance of NSCF algorithm alone. Moreover, our hybrid method performed slightly better than the ALS algorithm alone in the overall accuracy of recommendations.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126178902","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":"Monitoring of Residential Drinking Water Service Consumption Using Human Machine Interaction (HCI) Techniques","authors":"David Chilcanan, Cristopher Cuzco, Alvaro Uyaguari","doi":"10.1145/3369114.3369137","DOIUrl":"https://doi.org/10.1145/3369114.3369137","url":null,"abstract":"The integration of the drinking water network with information and communication technologies (ICTs) is the future of automated metering for users and service providers, the modern world cannot be conceived without water and the current infrastructure of manual metering, is poorly adapted to current needs, every day the demand for this vital liquid is greater and data collection from meters must be automated, allowing users to make queries of water consumption and tariffs to pay, however, it is necessary to create a centralized intelligent network with better adaptability to the meter; Implementing these technologies is expected to significantly reduce reading times in measurements, failure reports and changes in the drinking water network. In developing countries such as Ecuador, does not provide a metering infrastructure, however in the country, is thinking about creating Smart Grids for the adequacy of intelligent cities, a big step into the future. This article presents an implementation proposal for Smart Water Meter (SWM), by means of a virtual assistant and a metering network, allowing to consult the m3 of water consumed per day, week and month, as well as the total amount to be paid per consumption, integrating hardware and free software, for greater security in communications.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129936592","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":"Multi Point-of-View Video Recording for Eye Surgery Setting","authors":"D. H. Hareva, Livia Andriana Lohanda, Junita","doi":"10.1145/3369114.3369158","DOIUrl":"https://doi.org/10.1145/3369114.3369158","url":null,"abstract":"Reflection of post-ophthalmic surgery is needed to evaluate the results of that intervention in case of deviation. The recording technique used is utilizing cameras in the mode of multi-focus and multi-points on the object's eyes (macro view), surgeon hands (middle view), equipment and the people involved (wide view). We found mirrorless camera can achieve great result for macro view when placed over the camera adaptor. Smartphones suited the middle view position, while action camera is best used for wide view recording, and OBS Studio can be used to record all videos simultaneously. Regarding to video transmission, HDMI interface has better speed and video quality, but USB is easier to assemble. All recorded video is saved in video server to be proceed in During reconstruction, TILUplayer fulfills all requirement for playing video during postoperative evaluation.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130441014","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":"Decision System Modelling for \"Saboteur\" using Heuristics and Means-Ends Analysis","authors":"D. Krisnadi, Samuel Lukas, Laurentius Dominick Logan, Nadya Felim Bachtiar, Livia Andriana Lohanda","doi":"10.1145/3369114.3369162","DOIUrl":"https://doi.org/10.1145/3369114.3369162","url":null,"abstract":"Saboteur is a card game played by several players. Players are divided into goldminers and saboteurs who prevents goldminers from finding gold. Each player knows his/her role, but he/she does not know who has the same role. Gold searching process starts by making a path of seven cards horizontally from a single point of reference to the gold card's position. Saboteur is classified as an incomplete information card game with mechanisms that requires complex decision making. This paper proposes an approach to model a decision system for Saboteur using Heuristics and Means-End Analysis. Implementation was purely done in Java language. To test it, we performed benchmarking for the proposed system against previous intelligent agent models. The result is much better.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129789386","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":"Bandwidth Usage Forecasting and Network Anomaly Detection Based on Neural Network Approach","authors":"Omima Mashalh, Ammar Gharaibeh, A. Khalifeh","doi":"10.1145/3369114.3369133","DOIUrl":"https://doi.org/10.1145/3369114.3369133","url":null,"abstract":"The past few years have witnessed an impressive increasing number of online applications and services that play major roles of our daily life. This have created a growing need to improve our online networks performance and their immunity to online network attacks and anomalies. One approach to improve the network's performance is to predict future bandwidth demands. With accurate forecasting and comparing the forecasted network with real time bandwidth measurement, network management techniques such as resource allocation, traffic engineering, and detection of anomalies become less complex. To this end, a two-stage network analysis model is proposed. In the first stage, an Artificial Neural Network (ANN) is used to predict future bandwidth demands. The ANN is trained using a set of data collected from a local network over the period of five months. The forecasting ANN is tested for different prediction periods. The results are compared to real-time bandwidth measurements. The comparison shows that the forecasting ANN achieves an accuracy level of at least 96.7% for normal network operation. In the second stage, another ANN is used to classify the behavior of the network as normal or anomaly. In this work, the anomalies considered are Distributed Denial of Service (DDoS) attacks and link failures. Experimental DDoS attacks and link failures were performed to measure the network's behavior. The ANN in the second stage is trained and tested using the difference between the forecasted and real time bandwidth for different periods of time. The results show that the classifier is able to detect network anomalies with an error at most 0.6%.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"1128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122887468","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":"Improving Collaborative Filtering Recommender System Results using Optimization Technique","authors":"Bushra Alhijawi","doi":"10.1145/3369114.3369126","DOIUrl":"https://doi.org/10.1145/3369114.3369126","url":null,"abstract":"Nowadays, recommender systems are utilized as a suitable solution to facilitate the shopping process and make it faster. Collaborative Filtering (CF) is the most popular recommendation method which generates the recommendation for the Active User (AU) based on like-minded users. Thus, the selected neighbors have a significant impact on the accuracy and quality of recommendation. This paper presents a novel optimization-based recommender system called Opt-Nibors. OptNibors employs an optimization tool to select the best neighbors' list that improves prediction accuracy. Consequently, each individual represents a candidate neighbors list of AU. The proposed method consists of two phases, preprocessing and optimization phases. The preprocessing phase prepares the used seeds for initializing the population in the optimization phase. The executed preprocessing steps differ based on the historical recorded shopping behavior of AU. A set of experiments was conducted to compare OptNibors with alternative methods. On average, OptNibors improved the prediction accuracy and recommendation quality by 31.1% and 7.7%. The results demonstrate the superiority of OptNibors and its capability to achieve high performance regardless of the number of selected neighbors.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131811117","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":"Putting Together Wavelet-based Scaleograms and Convolutional Neural Networks for Anomaly Detection in Nuclear Reactors","authors":"Thanos Tagaris, G. Ioannou, Maria Sdraka, Georgios Alexandridis, A. Stafylopatis","doi":"10.1145/3369114.3369121","DOIUrl":"https://doi.org/10.1145/3369114.3369121","url":null,"abstract":"A critical issue for the safe operation of nuclear power plants is to quickly and accurately detect possible anomalies and perturbations in the reactor. Defects in operation are principally identified through changes in the neutron flux, as captured by detectors placed at various points inside and outside of the core. While wavelet-based analysis of the measured signals has been thoroughly used for anomaly detection, it has yet to be coupled with deep learning approaches. To this end, this work presents a novel technique for anomaly detection on nuclear reactor signals through the combined use of wavelet-based analysis and convolutional neural networks. In essence, the wavelet transform is applied to the signals and the corresponding scaleograms are produced, which are subsequently used to train a convolutional neural network that detects possible perturbations in the reactor core. The overall methodology is experimentally validated on a set of simulated nuclear reactor signals generated by a well-established relevant tool. The obtained results indicate that the trained network achieves high levels of accuracy in failure detection, while at the same time being robust to noise.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"37 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130264241","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 Closer Look at Fake News Detection: A Deep Learning Perspective","authors":"Ayat Abedalla, Aisha Al-Sadi, Malak Abdullah","doi":"10.1145/3369114.3369149","DOIUrl":"https://doi.org/10.1145/3369114.3369149","url":null,"abstract":"The increasingly rapid pace of spreading fake news is considered a problem in conjunction with the increasing number of people who are relying upon social media to get news. That earns widespread attention from research communities due to the negative impact and influence of fake news on public decisions. Consequently, the current research strives to illuminate on fake news problem and the process of detecting fake news using deep learning approaches. Using the Fake News Challenge (FNC-1) dataset, we have developed different models to detect fake news based on the relation between article headline and article body. Our models are assembled mainly from Convolutional Neural Network (CNN), Long Short-Term Memory network (LSTM) and Bidirectional LSTM (Bi-LSTM). In the contrary of other studies on the same dataset where they reported accuracy for a test data derived from the same training dataset, our experiments achieved 71.2% accuracy for the official testing dataset.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134282356","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":"Simulation of Adaptive Control for Cloud Computing as Queueing System","authors":"H. Tjahyadi, A. Aribowo, P. Yugopuspito, Irene A. Lazarusli, I. M. Murwantara","doi":"10.1145/3369114.3369155","DOIUrl":"https://doi.org/10.1145/3369114.3369155","url":null,"abstract":"Cloud computing is a complex system with high uncertainty factors. To guarantee the reliability and performance of the cloud computing despite the presence of uncertainty factors, a control system is required. In this paper simulation of control system in cloud computing is presented. The cloud computing is modeled as a queueing system with one unlimited queue and one server, and a simple adaptive control is employed to keep the achievement of the desired performance. The variation of arrival rate of clients, λ, is represent the uncertainty factor and the service rate, μ, is used as the control signal. Simulation results show that the proposed controller has a promising potential to be used in cloud computing.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115973853","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}