Proceedings of the Australasian Computer Science Week Multiconference最新文献_第2页

FIMIL : A high-throughput deep learning model for abnormality detection with weak annotation in microscopy images filil:一种用于显微镜图像弱注释异常检测的高通量深度学习模型

Proceedings of the Australasian Computer Science Week Multiconference Pub Date : 2020-02-04 DOI: 10.1145/3373017.3373051

Jing Ke, Changchang Liu, Yizhou Lu, Naifeng Jing, Xiaoyao Liang, Fusong Jiang

{"title":"FIMIL : A high-throughput deep learning model for abnormality detection with weak annotation in microscopy images","authors":"Jing Ke, Changchang Liu, Yizhou Lu, Naifeng Jing, Xiaoyao Liang, Fusong Jiang","doi":"10.1145/3373017.3373051","DOIUrl":"https://doi.org/10.1145/3373017.3373051","url":null,"abstract":"Automatic computer-aided detection plays an important role in biomedical image analysis. Many studies have focused on weak supervised learning as annotation tasks are time-consuming and tedious. Compared with pixel-wise annotation by particular software on the scanned digital high-resolution images, an alternative method of marking out of suspicious regions on microscopy slides is significantly more convenient for pathologists. Additionally, with a focus on dysplasias in the central area, there is a high likelihood of the similar tissues to be found around in clusters. In this paper, for weak annotation on microscopy images, we propose an efficient Foveated Imaging based Multiple Instance Learning (FIMIL) framework to classify weakly-labeled microscopy images. The model also provides multi-scale algorithm for arbitrary image size, in which the patches with highest possibility to contain dysplasia are considered as ”fixation points” in the image. The developed model combines deep convolutional neural networks (CNNs) with multiple instance learning (MIL) for dysplasias detection with only image-level labeling. The benchmark tests are carried out on the marked regions of 40x magnified whole-slide cytology images and the normal/abnormal label and their corresponding possibilities are predicted. Evaluated on the real-life clinical data, our proposed model shows high accuracy and efficiency by weakly-supervised learning. 1","PeriodicalId":297760,"journal":{"name":"Proceedings of the Australasian Computer Science Week Multiconference","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134499208","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}

引用次数: 2

PPM: A Provenance-Provided Data Sharing Model for Open Banking via Blockchain PPM:通过区块链为开放银行提供来源的数据共享模型

Proceedings of the Australasian Computer Science Week Multiconference Pub Date : 2020-02-04 DOI: 10.1145/3373017.3373022

Zhiyu Xu, Qin Wang, Ziyaun Wang, Donghai Liu, Yang Xiang, S. Wen

引用次数: 10

Poisonous Spider Recognition through Deep Learning 通过深度学习识别毒蜘蛛

Proceedings of the Australasian Computer Science Week Multiconference Pub Date : 2020-02-04 DOI: 10.1145/3373017.3373031

R. Sinnott, Donghan Yang, Xueyang Ding, Zhenyuan Ye

引用次数: 4

A Syndicated Adaptive News-feed: The Energy Hub 联合自适应新闻提要:能源中心

Proceedings of the Australasian Computer Science Week Multiconference Pub Date : 2020-02-04 DOI: 10.1145/3373017.3373036

D. Nagumothu, Peter W. Eklund

引用次数: 0

Security Analysis of Fountain V1 Fountain V1的安全性分析

Proceedings of the Australasian Computer Science Week Multiconference Pub Date : 2020-02-04 DOI: 10.1145/3373017.3373023

Matthew Beighton, Harry Bartlett, L. Simpson

引用次数: 0

Epileptic Seizure Detection Using Convolutional Neural Network: A Multi-Biosignal study 用卷积神经网络检测癫痫发作:多生物信号的研究

Proceedings of the Australasian Computer Science Week Multiconference Pub Date : 2020-02-04 DOI: 10.1145/3373017.3373055

Yu Liu, Shobi Sivathamboo, P. Goodin, C. Bonnington, P. Kwan, L. Kuhlmann, T. O'Brien, P. Perucca, Z. Ge

引用次数: 16

Attentional Matrix Factorization with Document-context awareness and Implicit API Relationship for Service Recommendation 基于文档上下文感知和隐式API关系的服务推荐注意矩阵分解

Proceedings of the Australasian Computer Science Week Multiconference Pub Date : 2020-02-04 DOI: 10.1145/3373017.3373034

Mo Nguyen, Jian Yu, Quan Bai, Sira Yongchareon, Yanbo Han

{"title":"Attentional Matrix Factorization with Document-context awareness and Implicit API Relationship for Service Recommendation","authors":"Mo Nguyen, Jian Yu, Quan Bai, Sira Yongchareon, Yanbo Han","doi":"10.1145/3373017.3373034","DOIUrl":"https://doi.org/10.1145/3373017.3373034","url":null,"abstract":"The rapid development of the mashup approach significantly plays a pivot role in building Web-based and mobile applications. Easy accessibility of data and functions are the main advantages for programmers to develop mashups from abundant sources of APIs. However, it simultaneously brings more difficulties to choose suitable APIs for a mashup, especially when the historical relations between APIs and mashups are very sparse. Existing probabilistic matrix factorization (PMF) recommender systems can effectively exploit the latent features of the invocations with the same weight. However, not all features are equally significant and predictive, and the useless features may bring noises to the model. Also, many current works explored the influence of mashups’ relationships, but few of them sheds lights on the relationship between APIs and their contextual interaction, which can be mined from their content description. This paper improves the PMF model by distinguishing the importance of latent feature interactions. We present an Attentional PMF model, which leverages a neural attention network to learn the significance of feature interactions and uses Doc2Vec technique for mining the contextual information. We also exploit the relationship between APIs from both their contextual similarities and invocation history and add them to the prediction model as a regularization part. Our experiments are performed with datasets from ProgrammableWeb. The results show that our model significantly outperforms some state-of-art recommender systems in mashup service applications.","PeriodicalId":297760,"journal":{"name":"Proceedings of the Australasian Computer Science Week Multiconference","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129838601","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}

引用次数: 8

A Fog based Building Fire Evacuation Framework 基于雾的建筑火灾疏散框架

Proceedings of the Australasian Computer Science Week Multiconference Pub Date : 2020-02-04 DOI: 10.1145/3373017.3373029

A. Kaur, Nitin Auluck

{"title":"A Fog based Building Fire Evacuation Framework","authors":"A. Kaur, Nitin Auluck","doi":"10.1145/3373017.3373029","DOIUrl":"https://doi.org/10.1145/3373017.3373029","url":null,"abstract":"Fog Computing extends traditional cloud based services to the edge of the network, close to where the data is generated. This technology fills a performance void in the cloud-to-thing architecture. By leveraging Fog Computing, the computation, storage, communication and decision making can be carried out by fog nodes. Due to significant latency, the cloud is not the best option for emergency response services, such as fire-fighting. For efficient fire-fighting, decisions should be made accurately and rapidly. In this paper, we propose an algorithm called FAFCA (Fog Assisted Fire Control Algorithm). In the wake of a fire in a building , this algorithm efficiently routes the evacuees to the shortest and least congested exits in a short span of time. The crux of the algorithm is that due to the lower communication delay between the fog nodes and the evacuees, data processing is done faster, which results in making evacuation decisions rapidly. The best path for the evacuees present in the building is calculated by the algorithm after taking various parameters into account, such as exit capacity, distance to exits and distribution of evacuees. Simulation results show that our proposed algorithm FAFCA decreases the latency as well as cost significantly, when compared to a cloud based algorithm and a random path selection algorithm.","PeriodicalId":297760,"journal":{"name":"Proceedings of the Australasian Computer Science Week Multiconference","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116740531","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}

引用次数: 1

Complex Network-Based Web Service for Web-API Discovery 用于Web- api发现的基于复杂网络的Web服务

Proceedings of the Australasian Computer Science Week Multiconference Pub Date : 2020-02-04 DOI: 10.1145/3373017.3373035

Olayinka Adeleye, Jian Yu, Sira Yongchareon, Yanbo Han, Quan.Z Sheng

{"title":"Complex Network-Based Web Service for Web-API Discovery","authors":"Olayinka Adeleye, Jian Yu, Sira Yongchareon, Yanbo Han, Quan.Z Sheng","doi":"10.1145/3373017.3373035","DOIUrl":"https://doi.org/10.1145/3373017.3373035","url":null,"abstract":"With the rapid and continual increase in the number and diversity of Web-APIs currently available on the Web, finding most appropriate Web-APIs to speed-up software development is becoming increasingly challenging. At the moment, Web-API consumers including mashup developers normally rely on Web-APIs repositories such as ProgrammableWeb and Mashapes to discover API of their interest. However, these registries are considered ineffective because: (a) Web APIs registered on these directories are in general isolated, as they are registered by diverse providers independently and progressively, without considering relevant dynamic information or continuous social interactions that exist among the services, which could influence their discovery (b) they cannot effectively respond to complex, mashup-oriented Web-API requests. In this paper, we address the above challenges from complex network perspective by constructing an evolving, complex-network-based Web service that leverages an online Google custom search service for recommending Web-APIs for mashup development. We conduct our study in three phases: First, we study the Web service ecosystem topological attributes using network analysis, and build an evolving network of Web service (Web-API) based on our findings using the theoretical procedure of the Barabási-Albert complex network model. Secondly, we dynamically grow the network and publish both nodes (Web-APIs) and edges (social connections) via an active web domain. Finally, we employ Google Page-Ranking feature to facilitate node ranking based on term frequency, functionality and node popularity information. To evaluate the performance of our framework, we create synthetic mashup requests based on original mashup profile. We validate our approach using ProgrammableWeb dataset, and experimental results show that our proposed framework is effective and outperform not only ProgrammableWeb approach but several other state-of-the-art methods.","PeriodicalId":297760,"journal":{"name":"Proceedings of the Australasian Computer Science Week Multiconference","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122457075","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}

引用次数: 1

Learning Management Models in Serious Mobile Music Games 严肃手机音乐游戏中的学习管理模式

Proceedings of the Australasian Computer Science Week Multiconference Pub Date : 2020-02-04 DOI: 10.1145/3373017.3373069

Charlotte Pierce, C. Woodward, Anthony Bartel

{"title":"Learning Management Models in Serious Mobile Music Games","authors":"Charlotte Pierce, C. Woodward, Anthony Bartel","doi":"10.1145/3373017.3373069","DOIUrl":"https://doi.org/10.1145/3373017.3373069","url":null,"abstract":"Students seeking to learn musical skills face a highly complex task with a significant cognitive load. Serious games are one method that has been proposed to help manage this complexity. They offer to present content in a fun, attractive, familiar package to increase student’s engagement and help them foster self-regulated and independent learning behaviours. In this paper, we examine the ways in which serious mobile games for music facilitate and encourage learning in their players. We call this the learning management model of a game, and it comprises three sub-models: a feedback model, an incentive and achievement model, and a progression model. By defining the models used by existing games, we can understand both how developers are approaching the task of serious game design, how effective their designs might be, and where improvements could be made in the future. We found that many of the choices made by developers indicate a tendency towards implementing functionality that minimises and simplifies the complexity of development. Players are rarely given feedback beyond whether they are correct or incorrect, they are rarely encouraged to or given the means by which to reflect on their performance over time, and they are relied upon to set their own path through content they are, by definition, unfamiliar with. Although the games already offer some educational value and provide benefits over traditional teaching materials, there remains significant scope for improvement in their learning management.","PeriodicalId":297760,"journal":{"name":"Proceedings of the Australasian Computer Science Week Multiconference","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133970358","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}

引用次数: 1