Tuesday, June 29, 2021

Deep-learning coupled with novel classification method to classify the urban environment of the developing world

Author :  Qianwei Cheng

Affiliation :  The University of Tokyo

Country :  Japan

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  11, 01, January, 2021

Abstract :

Rapid globalization and the interdependence of the countries have engendered tremendous in-flow of human migration towards the urban spaces. With the advent of high definition satellite images, high-resolution data, computational methods such as deep neural network analysis, and hardware capable of high-speed analysis; urban planning is seeing a paradigm shift. Legacy data on urban environments are now being complemented with high-volume, high-frequency data. However, the first step of understanding the urban area lies in the useful classification of the urban environment that is usable for data collection, analysis, and visualization. In this paper, we propose a novel classification method that is readily usable for machine analysis and it shows the applicability of the methodology in a developing world setting. However, the state-of-the-art is mostly dominated by the classification of building structures, building types, etc., and largely represents the developed world. Hence, these methods and models are not sufficient for developing countries such as Bangladesh where the surrounding environment is crucial for the classification. Moreover, the traditional classifications propose small-scale classifications, which give limited information, have poor scalability and are slow to compute in real-time. We categorize the urban area in terms of informal and formal spaces and take the surrounding environment into account. 50 km × 50 km Google Earth image of Dhaka, Bangladesh was visually annotated and categorized by an expert and consequently, a map was drawn. The classification is based broadly on two dimensions the state of urbanization and the architectural form of the urban environment. Consequently, the urban space is divided into four classifications: 1) highly informal area 2) moderately informal area 3) moderately formal area and 4) highly formal area. For semantic segmentation and automatic classification, Google’s DeeplabV3+ model was used.

Keyword :  Remote Sensing, Satellite Image, Building classification, Urban Environment, Deep Learning, Semantic Segmentation, Urban Planning, Socio-economic situation, Poverty Estimation.

For More Detailshttps://aircconline.com/csit/papers/vol11/csit110103.pdf

Monday, June 28, 2021

MULTI-AGENT REINFORCEMENT LEARNING FOR OPTIMIZING TRAFFIC SIGNAL TIMING

Author :  Areej Salaymeh

Affiliation :  Wayne State University

Country :  USA

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  11, 01, January, 2021

Abstract :

Designing efficient transportation systems is crucial to save time and money for drivers and for the economy as whole. One of the most important components of traffic systems are traffic signals. Currently, most traffic signal systems are configured using fixed timing plans, which are based on limited vehicle count data. Past research has introduced and designed intelligent traffic signals; however, machine learning and deep learning have only recently been used in systems that aim to optimize the timing of traffic signals in order to reduce travel time. A very promising field in Artificial Intelligence is Reinforcement Learning. Reinforcement learning (RL) is a data driven method that has shown promising results in optimizing traffic signal timing plans to reduce traffic congestion. However, model-based and centralized methods are impractical here due to the high dimensional state-action space in complex urban traffic network.

Keyword :  Multi-agent, Deep learning, Traffic signal timing, Reinforcement learning.

For More Detailshttps://aircconline.com/csit/papers/vol11/csit110102.pdf

PREPROCESSING TECHNIQUES TO IMPROVE CNN BASED FACE RECOGNITION SYSTEM

Author :  Jayanthi Raghavan

Affiliation :  University of Windsor

Country :  Canada

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  11, 01, January, 2021

Abstract :

In this work, deep CNN based model have been suggested for face recognition. CNN is employed to extract unique facial features and softmax classifier is applied to classify facial images in a fully connected layer of CNN. The experiments conducted in Extended YALE B and FERET databases for smaller batch sizes and low value of learning rate, showed that the proposed model has improved the face recognition accuracy. Accuracy rates of up to 96.2% is achieved using the proposed model in Extended Yale B database. To improve the accuracy rate further, preprocessing techniques like SQI, HE, LTISN, GIC and DoG are applied to the CNN model. After the application of preprocessing techniques, the improved accuracy of 99.8% is achieved with deep CNN model for the YALE B Extended Database. In FERET Database with frontal face, before the application of preprocessing techniques, CNN model yields the maximum accuracy of 71.4%. After applying the above-mentioned preprocessing techniques, the accuracy is improved to 76.3%

Keyword :  CNN, ANN, GPU

Friday, June 25, 2021

OVERSAMPLING LOG MESSAGES USING A SEQUENCE GENERATIVE ADVERSARIAL NETWORK FOR ANOMALY DETECTION AND CLASSIFICATION

Author :  Amir Farzad

Affiliation :  University of Victoria

Country :  Canada

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

Dealing with imbalanced data is one of the main challenges in machine/deep learning algorithms for classification. This issue is more important with log message data as it is typically very imbalanced and negative logs are rare. In this paper, a model is proposed to generate text log messages using a SeqGAN network. Then features are extracted using an Autoencoder and anomaly detection is done using a GRU network. The proposed model is evaluated with two imbalanced log data sets, namely BGL and Openstack. Results are presented which show that oversampling and balancing data increases the accuracy of anomaly detection and classification.

Keyword :  Deep Learning, Oversampling, Log messages, Anomaly detection, Classification

For More Details https://aircconline.com/csit/papers/vol10/csit100515.pdf

ADVANCED RATE CONTROL TECHNOLOGIES FOR MVC

 Author :  Tao Yan

Affiliation :  Putian University

Country :  China

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

After analyzing the research status and existing problems of multi-view video coding and bit rate control, we found that in addition to achieving higher coding efficiency, scalability characteristics, and quality consistency, reasonable bit rate control is urgent What needs further research. The paper proposes a multi-view video coding rate control algorithm based on the quadratic rate distortion (RD) model is presented. There are already many rate control algorithms. However, the testing work is very important, and different sequences need to be tested to effectively judge the effectiveness of the algorithm. Experimental simulation results show that the algorithm can effectively control the bit rate of multi-view video coding, while maintaining efficient coding efficiency, compared with the current MVC using JVT with fixed quantization parameters.

Keyword :  MVC(multi-view video coding), Rate control, Bit allocation, Basic unit layer

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100514.pdf

Thursday, June 24, 2021

A SEMI-SUPERVISED LEARNING APPROACH TO FORECAST CPU USAGES UNDER PEAK LOAD IN AN ENTERPRISE ENVIRONMENT

Author :  Nitin Khosla

Affiliation :  University of Canberra

Country :  Austrlia

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

The aim of a semi-supervised neural net learning approach in this paper is to apply and improve the supervised classifiers and to develop a model to predict CPU usages under unpredictable peak load (under stress conditions) in a large enterprise applications environment with several hundred applications hosted and with large number of concurrent users. This method forecasts the likelihood of extreme use of CPU because of a burst in web traffic mainly due to web-traffic from large number of concurrent users. This model predicts the CPU utilization under extreme load (stress) conditions.

Keyword :  Semi-supervised learning, Performance Engineering, Stress testing, Neural Nets, Machine learning applications.

For More Details https://aircconline.com/csit/papers/vol10/csit100513.pdf

Tuesday, June 22, 2021

A NOVEL BIT ALLOCATION ALGORITHM IN MULTI-VIEW VIDEO

Author :  Tao Yan

Affiliation :  Putian University

Country :  China

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

The difficulty of rate control for Multi-view video coding(MVC) is how to allocate bits between views. The results of our previous research including the bit allocation among viewpoints uses the correlation analysis among viewpoints to predict the weight of each viewpoint. But when the scene changes, this prediction method will produce a lot of errors. Therefore, this article avoids this situation happening through scene detection. The core of the algorithm is to first divide all images into 6 types of encoded frames according to the structural relationship between disparity prediction and motion prediction, and improve the binomial rate distortion model, and then perform inter-view, frame layer, and basic unit based on the encoded information. Layer bit allocation and code rate control. In this paper, a reasonable bit rate is allocated between viewpoints based on the encoded information, and the frame layer bit rate is allocated using frame complexity and time-domain activity. Experimental simulation results show that the algorithm can effectively control the bit rate of MVC, while maintaining efficient coding efficiency, compared with the current MVC using JVT with fixed quantization parameters.

Keyword :  MVC, Quantization parameters, Bit allocation, Rate distortion model, Basic unit layer.

For More Details https://aircconline.com/csit/papers/vol10/csit100512.pdf

Thursday, June 10, 2021

FREE-TEXT AND STRUCTURED CLINICAL TIME SERIES FOR PATIENT OUTCOME PREDICTIONS

Author :  Emilia Apostolova PhD

Affiliation :  Language.ai, Chicago, IL

Country :  USA

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

While there has been considerable progress in building deep learning models based on clinical time series data, overall machine learning (ML) performance remains modest. Typical ML applications struggle to combine various heterogenous sources of Electronic Medical Record (EMR) data, often recorded as a combination of free-text clinical notes and structured EMR data. The goal of this work is to develop an approach for combining such heterogenous EMR sources for time-series based patient outcome predictions. We developed a deep learning framework capable of representing free-text clinical notes in a low dimensional vector space, semantically representing the overall patient medical condition. The free-text based time-series vectors were combined with time-series of vital signs and lab results and used to predict patients at risk of developing a complex and deadly condition: acute respiratory distress syndrome. Results utilizing early data show significant performance improvement and validate the utility of the approach.

Keyword :  Natural Language Processing; Clinical NLP; Time-series data; Machine Learning; Deep Learning; Free-text and structured data; Clinical Decision Support; ARDS; COVID-19

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100511.pdf

Wednesday, June 9, 2021

VSMBM: A NEW METRIC FOR AUTOMATICALLY GENERATED TEXT SUMMARIES EVALUATION

Author :  Alaidine Ben Ayed

Affiliation :  Université du Québec à Montréal (UQAM)

Country :  Canada

Category :  Computer Science & Information Technology

Abstract :

In this paper, we present VSMbM; a new metric for automatically generated text summaries evaluation. VSMbM is based on vector space modelling. It gives insights on to which extent retention and fidelity are met in the generated summaries. Two variants of the proposed metric, namely PCA-VSMbM and ISOMAP VSMbM, are tested and compared to Recall-Oriented Understudy for Gisting Evaluation (ROUGE): a standard metric used to evaluate automatically generated summaries. Conducted experiments on the Timeline17 dataset show that VSMbM scores are highly correlated to the state-of-the-art Rouge scores.

Volume, Issue, Month, Year :  10, 05, May, 2020

Keyword :  Automatic Text Summarization, Automatic summary evaluation, Vector space modelling.

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100510.pdf

Monday, June 7, 2021

QUANTUM CRITICISM: A TAGGED NEWS CORPUS ANALYSED FOR SENTIMENT AND NAMED ENTITIES

Author :  Ashwini Badgujar

Affiliation :  University of San Francisco

Country :  USA

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

In this project, we continuously collect data from the RSS feeds of traditional news sources. We apply several pre-trained implementations of named entity recognition (NER) tools, quantifying the success of each implementation. We also perform sentiment analysis of each news article at the document, paragraph and sentence level, with the goal of creating a corpus of tagged news articles that is made available to the public through a web interface. Finally, we show how the data in this corpus could be used to identify bias in news reporting.

Keyword :  Content Analysis, Named Entity Recognition, Sentiment Analysis.

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100509.pdf

Thursday, June 3, 2021

TOPIC DETECTION FROM CONVERSATIONAL DIALOGUE CORPUS WITH PARALLEL LATENT DIRICHLET ALLOCATION MODEL AND ELBOW METHOD

Author :  Haider Khalid

Affiliation :  University of Dublin

Country :  Ireland

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  10, 05, May, 2020

Abstract :

A conversational system needs to know how to switch between topics to continue the conversation for a more extended period. For this topic detection from dialogue corpus has become an important task for a conversation and accurate prediction of conversation topics is important for creating coherent and engaging dialogue systems. In this paper, we proposed a topic detection approach with Parallel Latent Dirichlet Allocation (PLDA) Model by clustering a vocabulary of known similar words based on TF-IDF scores and Bag of Words (BOW) technique. In the experiment, we use K-mean clustering with Elbow Method for interpretation and validation of consistency within-cluster analysis to select the optimal number of clusters. We evaluate our approach by comparing it with traditional LDA and clustering technique. The experimental results show that combining PLDA with Elbow method selects the optimal number of clusters and refine the topics for the conversation.

Keyword :  Conversational dialogue, latentDirichlet allocation, topic detection, topic modelling, textclassification

For More Detailshttps://aircconline.com/csit/papers/vol10/csit100508.pdf