发布求助
文献互助 智能选刊 最新文献

2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)最新文献

筛选
英文 中文
Brain Tumor Diagnosis with Transfer Learning and Data Augmentation 基于迁移学习和数据增强的脑肿瘤诊断
2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2021-11-26 DOI: 10.1109/ISCMI53840.2021.9654939
Deniz Kavi
{"title":"Brain Tumor Diagnosis with Transfer Learning and Data Augmentation","authors":"Deniz Kavi","doi":"10.1109/ISCMI53840.2021.9654939","DOIUrl":"https://doi.org/10.1109/ISCMI53840.2021.9654939","url":null,"abstract":"Brain tumors are masses of abnormal cells in the brain. These masses can be lethal. As there are various types of brain tumors, the treatment of each type is different. As such, the diagnosis of the type of brain tumor is vital for patients’ treatment. Since the procedure of brain tumor diagnosis requires the expertise and knowledge of doctors, and not everyone may have access to expert doctors, the automation of this process would be beneficial. Currently, one of the most common methods for brain tumor diagnosis is using Magnetic Resonance Imaging (MIR) scans. As deep learning architectures such as Convolutional Neural Networks (CNNs) have reached human-level performance in detecting patterns in images, they may be used to classify between MRI scans. The proposed method reaches an accuracy of 99.26% when classifying between meningiomas, gliomas, and pituitary tumors. The same model is used to reach an accuracy of 99.00% between scans of healthy brains and brains with tumors. The model takes Magnetic Resonance Imaging (MRI) scans as input, then classifies whether the model is healthy or not, afterwards, if a tumor is detected, the model predicts the type of brain tumor. Transfer learning, progressive resizing, cyclical learning rates and MixUp data augmentation are used to reach an accuracy of 99.26%.","PeriodicalId":260519,"journal":{"name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131113170","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
[ISCMI 2021 Front cover] [ISCMI 2021封面]
2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2021-11-26 DOI: 10.1109/iscmi53840.2021.9654810
{"title":"[ISCMI 2021 Front cover]","authors":"","doi":"10.1109/iscmi53840.2021.9654810","DOIUrl":"https://doi.org/10.1109/iscmi53840.2021.9654810","url":null,"abstract":"","PeriodicalId":260519,"journal":{"name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114488265","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: 0
[Title page] (标题页)
2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2021-11-26 DOI: 10.1109/iscmi53840.2021.9654967
{"title":"[Title page]","authors":"","doi":"10.1109/iscmi53840.2021.9654967","DOIUrl":"https://doi.org/10.1109/iscmi53840.2021.9654967","url":null,"abstract":"","PeriodicalId":260519,"journal":{"name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114732839","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: 0
Development of an Accurate Cheque Reader Based on a Comparative Study of Various Methods of Digit Recognition 基于各种数字识别方法比较研究的精确支票阅读器的研制
2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2021-11-26 DOI: 10.1109/ISCMI53840.2021.9654800
Ankit Kumar, Kunal Jani, Visaj Nirav Shah, Divyansh Khatri, Nabin Kumar Sahu, M. Khare
{"title":"Development of an Accurate Cheque Reader Based on a Comparative Study of Various Methods of Digit Recognition","authors":"Ankit Kumar, Kunal Jani, Visaj Nirav Shah, Divyansh Khatri, Nabin Kumar Sahu, M. Khare","doi":"10.1109/ISCMI53840.2021.9654800","DOIUrl":"https://doi.org/10.1109/ISCMI53840.2021.9654800","url":null,"abstract":"Digit recognition is essential in developing machines in the future that can automatically read digits written on cheques. Since the number of applications involving image processing and accurate image classification is increasing, it has become necessary to find a model for a cheque reading system that can read handwritten digits accurately. In this paper, we show how various images of digits can be classified using multiple machine learning models and make a comparison between different models. Five different machine learning algorithms have been used to implement this problem. For each method, the testing handwritten number images are classified, and the variation of the accuracy with the number of principal components considered for our machine learning classifier is reported. It is also possible to figure out the optimal number of principal components for each model. We propose an automated cheque reader based on the comparison of the most accurate model and the optimal principal components. Finally, brief discussions mention using human feedback to improve its performance further.","PeriodicalId":260519,"journal":{"name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124797465","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: 0
Scheduling with Restricted Machine Availability Using Cloud Computing 使用云计算限制机器可用性的调度
2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2021-11-26 DOI: 10.1109/ISCMI53840.2021.9654825
Araby I. Mahdy, Abdullah A. Elfar
{"title":"Scheduling with Restricted Machine Availability Using Cloud Computing","authors":"Araby I. Mahdy, Abdullah A. Elfar","doi":"10.1109/ISCMI53840.2021.9654825","DOIUrl":"https://doi.org/10.1109/ISCMI53840.2021.9654825","url":null,"abstract":"The production scheduling with restricted machine availability problem is known to be NP-Hard problem since the time complexity increase exponentially with the required number of jobs increasing. This fact enforces researchers to find approximate solutions for these problems by heuristics and meta-heurisics. Another state-of-the-art solution methodology which may help solving the problem exactly and saves time is the cloud computing. By using parallel computing via cloud we solved larger problems exactly than those solved by total enumeration.The results showed that by using parallel computing via cloud and by adding more workers (represented here as processing cores) the problem solution speed up could be gained and problems with more number of jobs could be solved exactly by the proposed total enumeration algorithm.Cloud computing could be the next generation in the field of solving optimization techniques exactly.","PeriodicalId":260519,"journal":{"name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125032186","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: 0
Local and Global Interpretability Using Mutual Information in Explainable Artificial Intelligence 可解释人工智能中利用互信息的局部和全局可解释性
2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2021-11-26 DOI: 10.1109/ISCMI53840.2021.9654898
Mir Riyanul Islam, Mobyen Uddin Ahmed, S. Begum
{"title":"Local and Global Interpretability Using Mutual Information in Explainable Artificial Intelligence","authors":"Mir Riyanul Islam, Mobyen Uddin Ahmed, S. Begum","doi":"10.1109/ISCMI53840.2021.9654898","DOIUrl":"https://doi.org/10.1109/ISCMI53840.2021.9654898","url":null,"abstract":"Numerous studies have exploited the potential of Artificial Intelligence (AI) and Machine Learning (ML) models to develop intelligent systems in diverse domains for complex tasks, such as analysing data, extracting features, prediction, recommendation etc. However, presently these systems embrace acceptability issues from the end-users. The models deployed at the back of the systems mostly analyse the correlations or dependencies between the input and output to uncover the important characteristics of the input features, but they lack explainability and interpretability that causing the acceptability issues of intelligent systems and raising the research domain of eXplainable Artificial Intelligence (XAI). In this study, to overcome these shortcomings, a hybrid XAI approach is developed to explain an AI/ML model’s inference mechanism as well as the final outcome. The overall approach comprises of 1) a convolutional encoder that extracts deep features from the data and computes their relevancy with features extracted using domain knowledge, 2) a model for classifying data points using the features from autoencoder, and 3) a process of explaining the model’s working procedure and decisions using mutual information to provide global and local interpretability. To demonstrate and validate the proposed approach, experimentation was performed using an electroencephalography dataset from road safety to classify drivers’ in-vehicle mental workload. The outcome of the experiment was found to be promising that produced a Support Vector Machine classifier for mental workload with approximately 89% performance accuracy. Moreover, the proposed approach can also provide an explanation for the classifier model’s behaviour and decisions with the combined illustration of Shapely values and mutual information.","PeriodicalId":260519,"journal":{"name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129970897","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: 0
RestHAR: Residual Feature Learning Transformer for Human Activity Recognition from Multi-sensor Data 基于多传感器数据的人体活动识别残差特征学习转换器
2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2021-11-26 DOI: 10.1109/ISCMI53840.2021.9654816
Debaditya Shome
{"title":"RestHAR: Residual Feature Learning Transformer for Human Activity Recognition from Multi-sensor Data","authors":"Debaditya Shome","doi":"10.1109/ISCMI53840.2021.9654816","DOIUrl":"https://doi.org/10.1109/ISCMI53840.2021.9654816","url":null,"abstract":"In recent times, surge in the use of smartphones in our daily lives has created a huge opportunity for paving the road towards human-centric computing by utilizing the rich data which gets recorded by it’s multiple sensors. Sensor-based human activity recognition has a tremendous amount of real-world applications such as health monitoring, surveillance, smart homes, and ambient assisted living. This paper presents a joint residual feature extractor and a transformer-based deep neural network for end-to-end human activity recognition using raw multi-sensor data captured from smartphones or wearable devices. Unlike conventional handcrafted feature extraction, this approach outperforms all present approaches showing state-of-the-art generalizable performance over multiple benchmark datasets. It achieves a test accuracy of 95.2% on the UCI HAR dataset and 96.4% test accuracy on the WISDM dataset.","PeriodicalId":260519,"journal":{"name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127092218","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
AMA-K: Aggressive Multi-temporal Allocation with K Experts for Online Portfolio Selection 基于K位专家的在线投资组合积极多时配置
2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2021-11-26 DOI: 10.1109/ISCMI53840.2021.9654826
Matthew Kruger, Terence L van Zyl, A. Paskaramoorthy
{"title":"AMA-K: Aggressive Multi-temporal Allocation with K Experts for Online Portfolio Selection","authors":"Matthew Kruger, Terence L van Zyl, A. Paskaramoorthy","doi":"10.1109/ISCMI53840.2021.9654826","DOIUrl":"https://doi.org/10.1109/ISCMI53840.2021.9654826","url":null,"abstract":"Online portfolio selection is an integral component of wealth management. The fundamental undertaking is to maximise returns while minimising risk given investor constraints. We aim to examine and improve modern strategies to generate higher returns in a variety of market conditions. By integrating simple data mining, optimisation techniques, and machine learning procedures, we are able to generate aggressive and consistent high yield portfolios. This leads to a new methodology of Pattern-Matching that may yield further advances in dynamic and competitive portfolio construction. The resulting strategies outperform a variety of benchmarks that make use of similar approaches when compared using Maximum Drawdown, Annualised Percentage Yield and Annualised Sharpe Ratio. The proposed strategy returns showcase acceptable risk with high reward that performs well in a variety of market conditions. We conclude that our algorithm provides an improvement in searching for optimal portfolios compared to existing methods.","PeriodicalId":260519,"journal":{"name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132553529","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
The Role Weights Play in Catastrophic Forgetting 权重在灾难性遗忘中的作用
2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2021-11-26 DOI: 10.1109/ISCMI53840.2021.9654815
A. Hintze
{"title":"The Role Weights Play in Catastrophic Forgetting","authors":"A. Hintze","doi":"10.1109/ISCMI53840.2021.9654815","DOIUrl":"https://doi.org/10.1109/ISCMI53840.2021.9654815","url":null,"abstract":"Catastrophic forgetting is the sudden loss of performance when a neural network is trained on a new task or when experiencing unbalanced training. It often limits the ability of neural networks to learn new tasks. Previous work focused on the training data by changing the training regime, balancing the data, or replaying previous training episodes. Other methods used selective training to either allocate portions of the network to individual tasks or otherwise preserve prior task expertise. However, those approaches assume that network attractors are finely tuned, and even small changes to the weights cause misclassification. This fine-tuning is also believed to happen during overfitting and can be addressed with regularization. This paper introduces a method that quantifies how individual weights contribute to different tasks independent of weight strengths or previous training gradients. Applying this method reveals that backpropagation recruits all weights to contribute to a new task and that single weights may be somewhat more robust to noise than previously assumed.","PeriodicalId":260519,"journal":{"name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114419307","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
Evaluation of Sparse Binary Word Vectors in Chinese-English Machine Translations 稀疏二值词向量在汉英机器翻译中的评价
2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2021-11-26 DOI: 10.1109/ISCMI53840.2021.9654808
Changyi Ma, Wenye Li
{"title":"Evaluation of Sparse Binary Word Vectors in Chinese-English Machine Translations","authors":"Changyi Ma, Wenye Li","doi":"10.1109/ISCMI53840.2021.9654808","DOIUrl":"https://doi.org/10.1109/ISCMI53840.2021.9654808","url":null,"abstract":"We study the problem of language representation for automatic processing. Based on the idea of sparse lifting, our work projects dense word vectors into a higher-dimensional space and then generates sparse binary representations for words. In this way, our model combines the benefits from both one-hot representations and the distributional word vectors and provides a general representation scheme for automatic natural language processing. In an empirical study on Chinese to English bidirectional machine translations, the proposed model clearly demonstrates its advantage in downstream applications.","PeriodicalId":260519,"journal":{"name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123252320","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: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书