1,023 Hits in 2.2 sec

2020 Index IEEE Transactions on Cognitive and Developmental Systems Vol. 12

2020 IEEE Transactions on Cognitive and Developmental Systems  
Wilaiprasitporn, T., +, TCDS Sept. 2020 486-496 An Associative-Memory-Based Reconfigurable Memristive Neuromorphic System With Synchronous Weight Training.  ...  ., +, TCDS June 2020 311-322 Memory Mechanisms for Discriminative Visual Tracking Algorithms With Deep Neural Networks.  ...  Muscle Reducing Redundancy of Musculoskeletal Robot With Convex Hull Vertexes Selection. Zhong, S., +, TCDS Sept. 2020 601-617  ... 
doi:10.1109/tcds.2020.3044690 fatcat:yfo6c366aramfdltqegqyqphbq

Brain MRI ImageClassification for Cancer Detection using Deep Wavelet Autoencoder based Deep Neural Network

Pradeep Kumar Mallick, Seuc Ho Ryu, Sandeep Kumar Satapathy, Shruti Mishra, Nhu Gia Nguyen, Prayag Tiwari
2019 IEEE Access  
Carrying this idea into consideration, in this paper, a technique for image compression using a deep wavelet autoencoder (DWA), which blends the basic feature reduction property of autoencoder along with  ...  The performance criterion for the DWA-DNN classifier was compared with other existing classifiers such as autoencoder-DNN or DNN, and it was noted that the proposed method outshines the existing methods  ...  [22] proposed a MRI fuzzy segmentation with neural network optimization for brain tumor detection.  ... 
doi:10.1109/access.2019.2902252 fatcat:7dthl7mb45h4fgsbezgsjfgxbu

Transduction Recursive Auto-Associative Memory: Learning Bilingual Compositional Distributed Vector Representations of Inversion Transduction Grammars

Karteek Addanki, Dekai Wu
2014 Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation  
We introduce TRAAM, or Transduction RAAM, a fully bilingual generalization of Pollack's (1990) monolingual Recursive Auto-Associative Memory neural network model, in which each distributed vector represents  ...  Training of TRAAM drives both the autoencoder weights and the vector representations to evolve, such that similar bilingual constituents tend to have more similar vectors.  ...  In RAAM, which stands for Recursive Auto-Associative Memory, using feature vectors to characterize constituents at every level of a parse tree has the advantages that (1) the entire context of all subtrees  ... 
doi:10.3115/v1/w14-4013 dblp:conf/ssst/AddankiW14 fatcat:3uy67qmcnneofmoroxbhxv77uq

Car-Following Modeling Incorporating Driving Memory Based on Autoencoder and Long Short-Term Memory Neural Networks

Pengcheng Fan, Jingqiu Guo, Haifeng Zhao, Jasper S. Wijnands, Yibing Wang
2019 Sustainability  
An autoencoder was used to extract the main features underlying the time-series data in historical driving memory.  ...  This paper focuses on the impact of driving memory on car-following behavior, particularly, historical driving memory represents certain types of driving regimes and drivers' maneuver in coordination with  ...  Figure 4 . 4 Schematic diagram of the long short-term memory (LSTM) cell and LSTM's mechanism.  ... 
doi:10.3390/su11236755 fatcat:2o62mksoobdr7f6sfqibr4om4m

Deep Learning Anomaly Detection for Cellular IoT with Applications in Smart Logistics

Milos Savic, Milan Lukic, Dragan Danilovic, Zarko Bodroski, Dragana Bajovic, Ivan Mezei, Dejan Vukobratovic, Srdjan Skrbic, Dusan Jakovetic
2021 IEEE Access  
v y (2k+1) TABLE 1 . 1 ADM-EDGE memory resource utilization for the ADM-EDGE autoencoder with one hidden layer.  ...  1452 TABLE 2 . 2 ADM-EDGE memory resource utilization for ADM-EDGE autoencoders with different number of hidden layers (HL).  ... 
doi:10.1109/access.2021.3072916 fatcat:xz3zhvlyzzg23eju2ppo5uiace

Special Collection of Extended Selected Papers on "Novel Research Results Presented in The 12th International Conference on Information, Intelligence, Systems and Applications (IISA2021), 12–14 July 2021, Chania, Crete, Greece"

George A. Tsihrintzis, Maria Virvou, Ioannis Hatzilygeroudis
2021 International Journal of Intelligent Decision Technologies  
Information and Multimedia Systems, with an increasing level of Intelligence, are constantly being developed that incorporate these advances.  ...  Specifically, the fourth paper, by Konstantina Chrysafiadi and Evangelia-Aikaterini Tsichrintzi, is on "An Intelligent Fuzzy-based Emergency Alert Generation for People with Episodic Memory Decline Problems  ...  Specifically, the system protects people with episodic memory decline problems or lapses of atten-tion from dangerous situations that may be due to their memory disorder and allows them to complete everyday  ... 
doi:10.3233/idt-210008 fatcat:isljnet4wje47mhxsvwvjh2nny

Segmenting and Classifiying the Brain Tumor from MRI Medical Images Based on Machine Learning Algorithms: A Review

Omar Sedqi Kareem, Ahmed Khorsheed AL-Sulaifanie, Dathar Abas Hasan, Dindar Mikaeel Ahmed
2021 Asian Journal of Research in Computer Science  
[26] used a hybrid deep autoencoder (with a Bayesian fuzzy clustering segmentation approach) to develop a brain tumor classification model.  ...  A combination of wavelet with FCNN and autoencoder was found to be more successful for better tumor segmentation.  ... 
doi:10.9734/ajrcos/2021/v10i230239 fatcat:g5v6pxw375bozfimiekxbo4aya

An entropic associative memory

Luis A. Pineda, Gibrán Fuentes, Rafael Morales
2021 Scientific Reports  
The system has been tested with a set of memory recognition and retrieval experiments with complete and severely occluded images.  ...  AbstractNatural memories are associative, declarative and distributed, and memory retrieval is a constructive operation.  ...  Further work by Ritter and collaborators on Morphological Associative Memory 15, 16 and Implicative Fuzzy Associative Memories 17, 18 provided the basis for practical applications.  ... 
doi:10.1038/s41598-021-86270-7 pmid:33767252 fatcat:mhebiwhstvahfklqpv6w32f2la

Deep Semisupervised Learning-Based Network Anomaly Detection in Heterogeneous Information Systems

Nazarii Lutsiv, Taras Maksymyuk, Mykola Beshley, Orest Lavriv, Volodymyr Andrushchak, Anatoliy Sachenko, Liberios Vokorokos, Juraj Gazda
2022 Computers Materials & Continua  
The proposed approach is based on a deep recurrent autoencoder that learns time series of normal network behavior and detects notable network anomalies.  ...  With the massive number of connected devices, opportunities for potential network attacks are nearly unlimited.  ...  In [36] , the integration of fuzzy logic with cross-correlation was proposed to improve the detection precision.  ... 
doi:10.32604/cmc.2022.018773 fatcat:itxfgifm5rgrhiqpqqjc5ckfmu

Driving Maneuver Classification Using Domain Specific Knowledge and Transfer Learning

Supriya Sarker, Md. Mokammel Haque, M. Ali Akber Dewan
2021 IEEE Access  
Hence, it is unable to measure the driving risk associated with a particular maneuver.  ...  Besides, we have a plan to add a neural attention mechanism with the proposed model to focus on a subset of features of the time series dataset.  ... 
doi:10.1109/access.2021.3089660 fatcat:6lkr7bg5lfdnlfcxzl2aya5egu

Autoencoder-based Unsupervised Intrusion Detection using Multi-Scale Convolutional Recurrent Networks [article]

Amardeep Singh, Julian Jang-Jaccard
2022 arXiv   pre-print
Short-Term Memory (LSTM) based Autoencoder Network to process the temporal features.  ...  To address this, we propose a unified Autoencoder based on combining multi-scale convolutional neural network and long short-term memory (MSCNN-LSTM-AE) for anomaly detection in network traffic.  ...  Our IDS uses a novel Autoencoder combining multiscale Convolutional Neural Network with Long Short-Term Memory (MSCNN-LSTM) in the Autoencoder architecture to capture spatial-temporal dependencies in traffic  ... 
arXiv:2204.03779v1 fatcat:rvxxtx5mmjdhvifwojwbqojhkm

Fundamentals of Neural Networks

Amey Thakur
2021 International Journal for Research in Applied Science and Engineering Technology  
A brief introduction to Neuro-Fuzzy and its applications with a comprehensive review of NN technological advances is provided.  ...  The purpose of this study is to familiarise the reader with the foundations of neural networks.  ...  Neuro-fuzzy systems are systems that combine fuzzy logic with neural networks. To perform better, these hybrid systems might combine the benefits of neural networks with fuzzy logic.  ... 
doi:10.22214/ijraset.2021.37362 fatcat:2ebyvnxsj5djbewbd4ii4ubl4y

Deep Learning Anomaly Detection for Cellular IoT with Applications in Smart Logistics [article]

Milos Savic, Milan Lukic, Dragan Danilovic, Zarko Bodroski, Dragana Bajovic, Ivan Mezei, Dejan Vukobratovic, Srdjan Skrbic, Dusan Jakovetic
2021 arXiv   pre-print
Among several approaches to cope with these challenges, data-based methods rooted in deep learning (DL) are receiving an increased interest.  ...  The proposed architecture embeds autoencoder based anomaly detection modules both at the IoT devices (ADM-EDGE) and in the mobile core network (ADM-FOG), thereby balancing between the system responsiveness  ...  TABLE I I ADM-EDGE MEMORY RESOURCE UTILIZATION FOR THE ADM-EDGE AUTOENCODER WITH ONE HIDDEN LAYER.  ... 
arXiv:2102.08936v2 fatcat:sqxdaz2dujbvvohxqgj4aqpdfi

Single-Cell Transcriptome Data Clustering via Multinomial Modeling and Adaptive Fuzzy K-Means Algorithm

Liang Chen, Weinan Wang, Yuyao Zhai, Minghua Deng
2020 Frontiers in Genetics  
In the learned low-dimensional latent space, we proposed an adaptive fuzzy k-means algorithm with entropy regularization to perform soft clustering.  ...  In this paper, we combined the deep autoencoder technique with statistical modeling and developed a novel and effective clustering method, scDMFK, for single-cell transcriptome UMI count data.  ...  Therefore, instead of designing a specific non-linear association expression or bayesian priors, like mixture dirichlet distribution, we utilized deep autoencoders to approximate the underlying manifold  ... 
doi:10.3389/fgene.2020.00295 pmid:32362908 pmcid:PMC7180207 fatcat:osiaxajdpzfvncckxg6x435rlq

Eye movement behavior identification for Alzheimer's disease diagnosis

2018 Journal of Integrative Neuroscience  
With this information a set of denoising sparse-autoencoders are trained and a deep neural network is built using the trained autoencoders and a softmax classifier that identifies subjects with Alzheimer's  ...  disease with 89.78% accuracy.  ...  Initially, people experience memory loss and confusion, which may be mistaken for the kinds of memory changes that are sometimes associated with normal aging [1] .  ... 
doi:10.31083/j.jin.2018.04.0416 fatcat:2rl7wpmpfffn7d7rrijr65gbuq
« Previous Showing results 1 — 15 out of 1,023 results