Deep Convolutional Computation Model for Feature Learning on Big Data in Internet of Things

Li, Peng; Chen, Zhikui; Yang, Laurence T.; Zhang, Qingchen; Deen, M. Jamal

doi:10.1109/tii.2017.2739340

Cited by 174 publications

(74 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, in [8] a CNN framework is presented to convert sensor signals from manufacturing processes to 2-D images which are used to solve image classification tasks for fault diagnosis whereas in [9] a method is reported for analyzing tomography sensory data using a convolutional neural network pipeline. Moreover, in [10], a deep convolutional computation model is proposed to learn hierarchical features of big data in IoT, by using the tensor-based representation model to extend the CNN from the vector space to the tensor space. Also, a convolutional discriminative feature learning method for induction motor fault diagnosis is introduced in [11], an approach that utilizes a combination of back-propagation neural network and a feedforward convolutional pooling architecture.…”

Section: Related Workmentioning

confidence: 99%

Fault Diagnosis in Microelectronics Attachment Via Deep Learning Analysis of 3-D Laser Scans

Dimitriou¹,

Leontaris²,

Vafeiadis³

et al. 2020

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

A common source of defects in manufacturing miniature Printed Circuits Boards (PCB) is the attachment of silicon die or other wire bondable components on a Liquid Crystal Polymer (LCP) substrate. Typically, a conductive glue is dispensed prior to attachment with defects caused either by insufficient or excessive glue. The current practice in electronics industry is to examine the deposited glue by a human operator a process that is both time consuming and inefficient especially in preproduction runs where the error rate is high. In this paper we propose a system that automates fault diagnosis by accurately estimating the volume of glue deposits before and even after die attachment. Network (3DCNN). RNet outperforms other deep architectures and is able to estimate the volume either directly from the point cloud of a glue deposit or more interestingly after die attachment when only a small part of glue is visible around each die. The entire methodology is evaluated under operational conditions where the proposed system achieves accurate results without delaying the manufacturing process. To this end a modular scanning system is deployed that produces high resolution point clouds whereas the actual estimation of glue volume is performed by (R)egression-Net (RNet), a 3D Convolutional NeuralIndex Terms-3DCNN, deep learning, PCB, smart manufacturing.

show abstract

Section: Related Workmentioning

confidence: 99%

Fault Diagnosis in Microelectronics Attachment Via Deep Learning Analysis of 3-D Laser Scans

Dimitriou¹,

Leontaris²,

Vafeiadis³

et al. 2020

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

show abstract

“…A detailed discussion on different machine learning and data mining techniques used in smart home application were presented in [39,40,41]. Artificial intelligence and machine learning techniques can be used to make predictions and learning algorithms e.g.…”

Section: Pattern Recognitionmentioning

confidence: 99%

Sensors in Smart Homes for Independent Living of the Elderly

Pirzada

White

Wilde

2018

2018 5th International Multi-Topic ICT Conference (IMTIC)

View full text Add to dashboard Cite

a rapidly ageing population requires support systems which would enable them to preserve dwellers' independence without compromising on their safety or their quality of life. Smart homes for the elderly have the potential to offer unobtrusive health and wellness monitoring. The aim is to provide a safe, independent living environment which can identify and predict problems by monitoring the activities of daily living (ADLs) of the inhabitants. For this, a system able to handle continuous streams of data is required. Such a system can extract the information by using appropriate classification and learning algorithms and thus allow the remote monitoring of health and wellbeing at a high level. The implementation requires: the use of appropriate sensing technologies, identification of ADLs, data pre-processing techniques and machine learning algorithms. This is challenging due to individual differences: such a system must be able to personalize individual needs. Our contribution was the design and implementation of a platform to smartly monitor health condition of elderly using sensor data from a smart home, through an interactive user interface which is user-friendly and multiplatform. This proof-of-concept used off-line data, with the view to extend to real-time data collection in the future, which could then be used to inform support providers remotely.

show abstract

“…New promising tools provide the chance to utilize the complete potential of the IoT paradigm by expanding current wired connections with smart wireless constructions . The propagation of mobile devices, such as smartphones and IoT gadgets, results in the recent mobile big data era . Collecting mobile big data is unsuccessful unless appropriate analytics and learning approaches are exploited for extracting significant information and hidden patterns from data .…”

Section: State‐of‐the‐art Cache Replacement Algorithmsmentioning

confidence: 99%

An intelligent database proactive cache replacement policy for mobile communication system based on genetic programming

Darwish

El-Shnawy

2018

Int J Communication

View full text Add to dashboard Cite

In the mobile environment, the movement of the users, disconnected modes, many data updates, power battery consumption, limited cache size, and limited bandwidth impose significant challenges in information access. Caching is considered one of the most important concepts to deal with these challenges.There are 2 general topics related to the client cache policy: cache invalidation method keeps data in the cache up to date and cache replacement method chooses the cached element(s) that would be removed from the cache once the cache stays full. The aim of this work is to introduce a new technique for cache replacement in a mobile database that takes into consideration the impact of invalidation time for enhancing data availability in the mobile environment by using genetic programming. In this case, each client collects information for every cached item in the cache like access probability, cached document size, and validation time and uses these factors in a fitness function to determine cached items that will be removed from the cache. The experiments were carried by NS2 simulator to assess the efficiency of the proposed method, and the outcomes are judged against existing cache replacement algorithms. It is concluded that the proposed approach performs significantly better than other approaches. KEYWORDScache invalidation, cache replacement, genetic programming, mobile database | INTRODUCTIONWith the rapid changes in technology, mobile communications are the essential part of our daily life. People are using the wireless network for making phone calls, accessing the Internet to download news, the stock market, etc. Different techniques for enhancing the capability and quality of wireless environments have become a hot research area. The development of mobile information systems has met some disadvantages. Mobile machines regularly have slight storage dimension and inadequate energy. Furthermore, mobile client users in wireless environments suffer from frequent disconnections from the server, and also calling the server for information is costly. For that reason, scholars have discovered caching approaches for valuable data managing in the mobile podium. 1-3 Still, a key difficulty is how to preserve the collected items in the cache up to date with the source data at the server.

show abstract

Deep Convolutional Computation Model for Feature Learning on Big Data in Internet of Things

Cited by 174 publications

References 19 publications

Fault Diagnosis in Microelectronics Attachment Via Deep Learning Analysis of 3-D Laser Scans

Fault Diagnosis in Microelectronics Attachment Via Deep Learning Analysis of 3-D Laser Scans

Sensors in Smart Homes for Independent Living of the Elderly

An intelligent database proactive cache replacement policy for mobile communication system based on genetic programming

Contact Info

Product

Resources

About