2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)最新文献

{"title":"FPGA Implementation of Support Vector Machine Using Ising Model for AI on Things","authors":"Yudai Taguchi, Ryoma Iimura, Takayuki Kawahara","doi":"10.1109/CIVEMSA52099.2021.9493676","DOIUrl":"https://doi.org/10.1109/CIVEMSA52099.2021.9493676","url":null,"abstract":"In this study, we classified three datasets by using a support vector machine (SVM) implemented in an Ising model. In the previous research, the Ising SVM system succeeded in linearly classifying plotted points on a secondary plane into two classes in a simulation. For this study, we improved the system in two ways: we applied a nonlinear transformation by a Gaussian, and we enabled the system to handle feature vectors of three dimensions or more. The performance of the improved Ising-SVM system was evaluated by simulation with MATLAB and actual machine verification with a field-programmable gate array (FPGA). The performance was evaluated on three datasets assuming real-world applications. In the MATLAB simulation, the identification rates of the Ising-SVM system were almost the same as those of a conventional SVM. Furthermore, the calculation time of the proposed system was reduced to an average of 18.0% of that of the standard SVM. Finally, almost the same identification rates were obtained in the actual FPGA verification as in the MATLAB simulation.","PeriodicalId":248405,"journal":{"name":"2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129465947","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":"Noise Characterization and Modelling for Powerline Communications in Nigeria","authors":"O. Oyeleke, Olabode Idowu-Bismark, A. Andrew, Charles Bala Dyaji, Idris Muhammad, Talatu Adamu","doi":"10.1109/CIVEMSA52099.2021.9493668","DOIUrl":"https://doi.org/10.1109/CIVEMSA52099.2021.9493668","url":null,"abstract":"Powerline Communication (PLC) where electricity infrastructure is been used for data transmission is finding usage in many domain including smart grid, IoT, Data backhaul and for advanced metering. PLC is also combining with visible light communication (VLC) to provide broadband access for home networking. One major impediment to achieving the above is powerline communication noise. Various types of noises are present in power-line communication. New approaches are required to mitigate these noises. These mitigation methods entail noise modeling and designing receivers using these models. In developing such noise models, statistical knowledge of noise parameters are essential which can accurately describe noise present in PLC communication. These noise parameters can be obtained from the experimental measurement. In this paper, therefore, we characterize the various noises in PLC communication at domestic and office scenario; identify the type of noise, their sources and potential impact in PLC data transmission.","PeriodicalId":248405,"journal":{"name":"2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122586227","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":"Data Acquisition and Monitoring System for Legacy Injection Machines","authors":"Bruno Silva, João Sousa, G. Alenyà","doi":"10.1109/CIVEMSA52099.2021.9493675","DOIUrl":"https://doi.org/10.1109/CIVEMSA52099.2021.9493675","url":null,"abstract":"Nowadays, companies must embrace the concept of Digitalization and Industry 4.0 to remain competitive in the market. The reality is that most of them do not have their industrial devices prepared to access their data on a real-time basis. As most companies do not have the possibility to renew all their legacy devices and because these devices are still very productive, a retrofit solution is of high interest. In this work, we propose an affordable procedure that allows data collection and monitoring of older injection machines, as a contribution towards legacy devices integration. The developed system neither requires additional proprietary modules, nor contractual annual fees for different devices, sharing the same interface across different machine manufacturers and also contributing to uniform data collection. Evaluation was carried out in a real shop floor, monitoring the injection parameters for different machine models, validating the effectiveness of the developed system.","PeriodicalId":248405,"journal":{"name":"2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"189 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133807420","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":"Process Capability Indices Based on Skewed Possibility Distributions for Drilling Operations","authors":"L. Foulloy, G. Mauris","doi":"10.1109/CIVEMSA52099.2021.9493671","DOIUrl":"https://doi.org/10.1109/CIVEMSA52099.2021.9493671","url":null,"abstract":"Process capability indices play an important role in the process control since they help determine if a manufacturing process is suitable. They are unitless and defined as the ratio of specification conformance to the natural variability of a process. This variability is generally determined by using a normal probability distribution or in a few cases by Pearson or Burr systems of distribution. This paper investigates the use of skewed possibility distributions to model data variability. Bridges with existing approaches and new results are presented and illustrated on drilling operations.","PeriodicalId":248405,"journal":{"name":"2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124227943","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":"Emotion Specific Network with Multi-dimension Features in Emotion Recognition","authors":"Gufeng Jia, Xucheng Liu, Hongtao Wang, Yong Hu, Feng Wan","doi":"10.1109/CIVEMSA52099.2021.9493578","DOIUrl":"https://doi.org/10.1109/CIVEMSA52099.2021.9493578","url":null,"abstract":"Emotion recognition has been recognized as an important issue in terms of human-computer interaction. Various studies showed brain regional cooperation changed with mental state. However, the important role of specific brain channels and their topology during the emotion activity is still unclear. In this paper, we extracted the multi-dimension EEG features to achieve emotion specific network construction and emotion recognition. The dataset is from the 2020 World Robot Conference-Brain-Computer Interfaces (BCI) Contest, provided by Shanghai Jiaotong University. There are 24 sessions included in this paper. The power spectrum density (PSD), Hjorth parameter, and functional connectivity were extracted from each session. A data-driven critical channel selection strategy was performed by sorting the classification accuracy of each channel. Meanwhile, the emotion specific network was established by the top 10 channels. Finally, we mixed the features in the emotion specific network to recognize three emotion types (positive, neutral, and negative). We found the reorganization of the brain network mostly focused on the right hemisphere. Moreover, the classification accuracy (70.53% ± 4.61% (mean ± std)) showed the feasibility of emotion specific network. Our study indicated the emotion specific network is critical for emotion alteration and provides a new insight for emotion recognition.","PeriodicalId":248405,"journal":{"name":"2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116734131","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":"Histopathological Transfer Learning for Acute Lymphoblastic Leukemia Detection","authors":"A. Genovese, M. S. Hosseini, V. Piuri, K. Plataniotis, F. Scotti","doi":"10.1109/CIVEMSA52099.2021.9493677","DOIUrl":"https://doi.org/10.1109/CIVEMSA52099.2021.9493677","url":null,"abstract":"The detection of Acute Lymphoblastic (or Lymphocytic) Leukemia (ALL) is being increasingly performed with the help of Computer Aided Diagnosis (CAD) systems based on Deep Learning (DL), that support the pathologists in performing their decision by analyzing the blood samples to determine the presence of lymphoblasts. When using DL, the limited dimensionality of ALL databases favors the use of transfer learning techniques to increase the accuracy in the detection, by considering Convolutional Neural Networks (CNN) pretrained on the general purpose ImageNet database. However, no method in the literature has yet considered the use of CNNs pretrained on histopathology databases to perform transfer learning for ALL detection. In fact, the majority of histopathology databases in the literature has either a small number of samples or limited ground truth labeling possibilities (e.g., only two possible classes), which hinders the effectiveness of training CNNs from scratch. In this paper, we propose the first method based on histopathological transfer learning for ALL detection, that trains a CNN on a histopathology database to classify tissue types, then performs a fine tuning on the ALL database to detect the presence of lymphoblasts. As histopathology database, we consider a multi-label dataset with a significantly higher number of samples and classes with respect to the literature, which enables CNNs to learn general features for histopathology image processing and hence allow to perform a more effective transfer learning, with respect to CNNs pretrained on ImageNet. We evaluate the methodology on a publicly-available ALL database and considering multiple CNNs, with results confirming the validity of our approach.","PeriodicalId":248405,"journal":{"name":"2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131206224","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":"Effect of UE Height on 3D Angular Spread of Correlated MIMO Channel","authors":"Olabode Idowu-Bismark, Francis F. Idachaba, Atayero","doi":"10.1109/CIVEMSA52099.2021.9493585","DOIUrl":"https://doi.org/10.1109/CIVEMSA52099.2021.9493585","url":null,"abstract":"In the forthcoming fifth generation (5G) architecture, full dimension MIMO (FD-MIMO) for enabling high network capacity wireless cellular system is been proposed. FD-MIMO provide beam control in azimuth and elevation plane using active antenna system (AAS) to take advantage of 3D-MIMO techniques such as 3D beamforming. It is therefore necessary to characterize and model channel parameters in 3D domain rather than the current 2D domain used for today’s cellular systems. In this work, using the REMCOM Wireless Insite X3D ray tracing engine, we characterize the mmWave MIMO channel at 28 GHz center frequency and 100 MHz bandwidth in terms of the angular spread (AS) using a 4 x 4 cross-polarized uniform planar array (UPA) at the base station and 2 x 2 MIMO antenna at the small cell receivers. Two scenarios were considered which are the street canyon and the high-rise. We provide 3D models for angular spread of arrival (at the receiver) and departure (at the base station). We obtain the cross-correlation coefficients of the parameters and analyze the effect of BS-UE height on AS.","PeriodicalId":248405,"journal":{"name":"2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133173295","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":"Lucid-GAN: An Adversarial Network for Enhanced Image Inpainting","authors":"Utkarsh Maheshwari, Venkata Pavan Kumar Turlapati, Usha Kiruthika","doi":"10.1109/CIVEMSA52099.2021.9493581","DOIUrl":"https://doi.org/10.1109/CIVEMSA52099.2021.9493581","url":null,"abstract":"Image in-painting has been a significant research area which is being explored in the past decade. It has many diversified applications such as damaged image repairing and object removal. The hallmark algorithm for this application is EdgeConnect which comprises an edge generator and an image completion network. But, EdgeConnect is used to repair only damaged images. The process of repairing damaged images also faces the pitfall of enormous quality reduction after reconstruction. This paper presents a custom Generative Adversarial Network (GAN) - named Lucid-GAN on top of EdgeConnect to upscale the quality of the image. This decreases the noise in the reconstructed image, while parallely improving the SSIM, PSNR and the MAE scores by a considerable margin.","PeriodicalId":248405,"journal":{"name":"2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124017971","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":"Unmask inflated product reviews through Machine Learning","authors":"M. Bangerter, G. Fenza, Mariacristina Gallo, Alessia Genovese, F. Nota, Claudio Stanzione, G. Zanfardino","doi":"10.1109/CIVEMSA52099.2021.9493576","DOIUrl":"https://doi.org/10.1109/CIVEMSA52099.2021.9493576","url":null,"abstract":"Product reviews play a crucial role in online customer purchase decisions. In today’s marketplaces, such as Amazon, the quantity and interest of product reviews is growing, along with fierce competition between sellers. At the same time, the phenomenon of fake reviews is ever-growing. Many proposals capable of detecting fake reviews based on Machine Learning (ML) exist in literature. Nevertheless, bad practices implemented by the sellers make genuine reviews difficult to recognize. For instance, some Telegram Channels are known for giving products for free in exchange for 5-star reviews. This work focuses on the analysis of two review data streams of Amazon products. The first one is composed of the reviews corresponding to the products in the AmazonBasics category. The latter collects reviews of the products in the Telegram channels mentioned above. The analysis reveals a substantial dissimilarity between the two sources of reviews, that conducts to the construction of a ground truth dataset employed in the classification model training. The classification activity can assist during product rating interpretation, which could be invalidated by too many fake reviews. The experimental results reveal that 1&2-star reviews are good predictors of the review’s trustworthiness and the product itself.","PeriodicalId":248405,"journal":{"name":"2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114656248","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 DWT-Based Blind Robust High Capacity and Secure Digital Watermarking and Information Hiding Scheme for Image Authentication, Tampering Localization and Automatic Self-Recovery","authors":"S. S. Chaughule, D. Megherbi","doi":"10.1109/CIVEMSA52099.2021.9493672","DOIUrl":"https://doi.org/10.1109/CIVEMSA52099.2021.9493672","url":null,"abstract":"Due to the rise in many industrial environment applications involving distributed networked collaborative intelligent measurement systems, intelligent monitoring and multi-sensor information exchange of private information, digital image information security and hidden image authentication, tampering detection, correction, and automatic intelligent self-recovery have become critical concerns. Towards that end, there is a need for more secure, efficient, and robust-to-unauthorized-tampering digital image watermarking, information hiding and authentication schemes. In our prior work, we introduced non-blind watermarking schemes where the carrier and watermark images are available at the receiver's end. We also proposed a double-blind scheme where both the carrier and the watermark images are not available at the receiver's end, but at the expense of possible lower pixel tampering, authentication and automatic intelligent self-correction ability. This paper proposes a blind wavelet-based, high capacity, secure digital watermarking and information hiding scheme with higher tampering localization and authentication that nullifies the need to have the carrier image available at the receiving end. The proposed scheme also increases robustness to image authentication and automatic self-recovery and correction compared to our prior double-blind scheme. The scheme is high capacity and sustains hiding secret hidden and watermarking images of the same full size as an arbitrary-sized carrier image. One of the benefits of the blind watermarking scheme is that it allows usage of varying and arbitrary carrier images that are unknown and unavailable anywhere, including the receiver's end. This is to prevent hackers' recognition of a familiar carrier image and their potential unauthorized tampering. Here, in this paper, two grayscale images are inserted in a colored carrier image. Here the watermark image is used for authentication and tamper localization. The second image is used as ownership or encoded secret hidden message image. The Arnolds Transform is used to introduce added security to a hidden image. The proposed scheme uses an embedded correction matrices mechanism for the extracted hidden information self-recovery from various tampering and digital attacks by unauthorized hackers.","PeriodicalId":248405,"journal":{"name":"2021 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131026839","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}