Conference Paper

An Analysis of a Large Scale Wireless Image Distribution System Deployment

150 150 MIMOS Berhad

Authors:

Gin Xian Kok ; Khong Neng Choong ; Chrishanton Vethanayagam ; Yasunori Owada ; and Goshi Sato

 

Abstract:

In this paper, we describe twosetupsof a wireless image distribution system using different network architectures.In the first setup, commercialgrade network equipmentwasused inthe network infrastructure ofthe system. In the other setup, the network infrastructure consists of a wireless mesh of NICT NerveNet nodes.For the first setup, results showed that the choice ofhardware and network equipmentused were sufficient to support the load of the system in an auditorium with a capacity ofabout 160 people.For the NerveNet setup,it superseded the first setup in terms of quick and clean setup, leaving the performance aspect to be further improved.

 

Source:

IEEE 9th Symposium on Computer Applications & Industrial Electronics (ISCAIE), Kota Kinabalu, Malaysia

Advanced resource allocation and Service level monitoring for container orchestration platform

150 150 MIMOS Berhad

Authors:

Rajendar Kandan, Mohammad Fairus Khalid, Bukhary Ikhwan Ismail, and Ong Hong Hoe

 

Abstract:

Containerization becomes the first choice for faster deployment of application. Lightweight and instant start of containers find its place across various domains including big data and cloud. Due to this wide range in heterogeneity of resources, the orchestration framework is required for the management of containers. Resource selection becomes one of the major challenges in such environment. Although various open-source orchestration available in market for addressing the management of containers across varied platform, they provide only a basic scheduling scheme. In this paper, we highlighted various factors affecting the resource selection and proposed an architecture of resource-aware placement and SLA (Service Level Agreement) based monitoring which provides advanced scheduling and minimizes container migration.

 

Source:

International Conference on Sensors and Nanotechnology (SENSORS AND NANO 2019), Penang

Absorption Spectrum Analysis of Dentine Sialophosphoprotein (DSPP) in Orthodoctic Patient

150 150 MIMOS Berhad

Authors:

Mohd Norzaliman Mohd Zain, Zalhan Md Yusof, Farinawati Y. , Asma A., Ken, WSH, Lee, WJ , Tan, KF, Shahrul , HA and Rohaya

 

Abstract:

Aforce applied during the orthodontic treatment induces inflammation which is essential for tooth movement, can leadtoroot resorption. Previous research works haveproved aprotein biomarker which can monitorthe root resorption during orthodontic tooth movement. Dentine sialophosphoprotein (DSPP) is one of most abundant non-collagenous protein in dentine. DSPP is released into Gingival crevicular fluid (GCF)during external root resorption. In this work, we investigate and analysis the absorbance spectrum of human DSPP by using spectroscopyand a qualitative model using Soft Independent Modelling Class Analogies (SIMCA). The absorption spectrum data will be used asan indicatorfor clinical examination of root resorption in orthodontic treatment. The subjects for this study consisted of non-orthodonticand orthodontic patientsbased on different clinical treatment period. GCF samples collected from both non-orthodontic and orthodontic groups showed ultra-violet spectrum range from 244.11 to 259.86 nm. The spectrum data model accuracy for non-orthodontic and orthodontic patient obtained at 0.91. The result indicates that GCFabsorption spectrumsobtained correlated with the duration of orthodontic treatmentafter the occurrence of Orthodontic-induced inflammatory root resorption(OIIRR). The qualitative spectrum data model developed is capable to classify samples into non-orthodontic and orthodontic groups.

 

Source:

2nd International Conference on Applied Photonics and Electronics (InCAPE 2019), Putrajaya

Benchmarking Supervived Learning Models For Emotion Analysis

150 150 MIMOS Berhad

Authors:

Ang Jia Pheng, Duc Nghia Pham, and Ong Hong Hoe

 

Abstract:

Emotion is the most genuine reaction of a person towards a circumstance or an object that are usually hidden between lines in their speech, text and actions. While emotion is more sophisticated and complicated to process and analyze, emotion provides more detailed and valuable insights for organizations to re-evaluate/fine-tunetheir actions and make informed decisions. This paper benchmarkedsupervised learning models for emotion analysis using sentence-level documents with six categories: anger, sadness, joy, love, surprise, and fear. We evaluatedone deep learning model: Bidirectional Long-Short Term Memory (BiLSTM), and one machinelearning model: FastText. Since FastText does not support GPU, both BiLSTM and FastText were ranon CPU for a fair time comparison. The results showed that while sacrificing speed that tookat least 9000% longer to train and validate, BiLSTM consistentlyoutperformedFastText.We also found that text pre-processing helped boost the performance of supervised learning models in emotion analysis.

 

Source:

6th International Conference on Artificial Intelligence and Computer Science (AICS2019), Wuhan, Hubei, China

Evaluating The Impact of Removing Less Important Terms on Sentiment Analysis

150 150 MIMOS Berhad

Authors:

Salhana Amad Darwis, Duc Nghia Pham, Ang Jia Pheng, and Ong Hong Hoe

 

Abstract:

Sentiment analysis is an important taskin Natural Language Processing (NLP) that analyses and predicts people¶s opinion from te[tualdata. It is a complex process due to the interactions with computer science, linguistics, psychology and social science disciplines. There is no straight forward rule to analyse and predict sentiment. Supervised learning methods, which adopt learning models from human, are being widely used by NLP researchers and experts to predict sentiment. However, this approach is tricky due to the challenges in ensuring the quality of the manually labelled training dataset. In this study, we investigated the use of lingXistic factors to improYe the model¶s accuracy. We gathered two datasets: (i) 125,000 annotated sentences from Amazon product reviews, and (ii) 11,250 annotated sentences from financial news articles. We then pre-processed the data, identified the less importantterms that exist in the dataset, the linguistic featuresand their effect towards the correctness of predictedsentiment. Our experimental results showed thatpunctuation separationand removal ofsupporting POS words improves precisionaccuracyin larger-generic dataset rather than in smaller-context sensitive dataset.

 

Source:

6th International Conference on Artificial Intelligence and Computer Science (AICS2019), Wuhan, Hubei, China