Abstract:
:In today's society, image resources are everywhere, and the number of available images can be overwhelming. Determining how to rapidly and effectively query, retrieve, and organize image information has become a popular research topic, and automatic image annotation is the key to text-based image retrieval. If the semantic images with annotations are not balanced among the training samples, the low-frequency labeling accuracy can be poor. In this study, a dual-channel convolution neural network (DCCNN) was designed to improve the accuracy of automatic labeling. The model integrates two convolutional neural network (CNN) channels with different structures. One channel is used for training based on the low-frequency samples and increases the proportion of low-frequency samples in the model, and the other is used for training based on all training sets. In the labeling process, the outputs of the two channels are fused to obtain a labeling decision. We verified the proposed model on the Caltech-256, Pascal VOC 2007, and Pascal VOC 2012 standard datasets. On the Pascal VOC 2012 dataset, the proposed DCCNN model achieves an overall labeling accuracy of up to 93.4% after 100 training iterations: 8.9% higher than the CNN and 15% higher than the traditional method. A similar accuracy can be achieved by the CNN only after 2,500 training iterations. On the 50,000-image dataset from Caltech-256 and Pascal VOC 2012, the performance of the DCCNN is relatively stable; it achieves an average labeling accuracy above 93%. In contrast, the CNN reaches an accuracy of only 91% even after extended training. Furthermore, the proposed DCCNN achieves a labeling accuracy for low-frequency words approximately 10% higher than that of the CNN, which further verifies the reliability of the proposed model in this study.
journal_name
Comput Intell Neuroscijournal_title
Computational intelligence and neuroscienceauthors
Cao J,Wu C,Chen L,Cui H,Feng Gdoi
10.1155/2019/2060796subject
Has Abstractpub_date
2019-07-04 00:00:00pages
2060796eissn
1687-5265issn
1687-5273journal_volume
2019pub_type
杂志文章abstract::An effective hybrid cuckoo search algorithm (CS) with improved shuffled frog-leaping algorithm (ISFLA) is put forward for solving 0-1 knapsack problem. First of all, with the framework of SFLA, an improved frog-leap operator is designed with the effect of the global optimal information on the frog leaping and informat...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2014/857254
更新日期:2014-01-01 00:00:00
abstract::Stress is categorized as a condition of mental strain or pressure approaches because of upsetting or requesting conditions. There are various sources of stress initiation. Researchers consider human cerebrum as the primary wellspring of stress. To study how each individual encounters stress in different forms, researc...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2020/8860841
更新日期:2020-08-01 00:00:00
abstract::We report on tests with a mind typing paradigm based on a P300 brain-computer interface (BCI) on a group of amyotrophic lateral sclerosis (ALS), middle cerebral artery (MCA) stroke, and subarachnoid hemorrhage (SAH) patients, suffering from motor and speech disabilities. We investigate the achieved typing accuracy giv...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2011/519868
更新日期:2011-01-01 00:00:00
abstract::Critical gap is an important parameter used to calculate the capacity and delay of minor road in gap acceptance theory of unsignalized intersections. At an unsignalized intersection with two one-way traffic flows, it is assumed that two events are independent between vehicles' arrival of major stream and vehicles' arr...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2014/236072
更新日期:2014-01-01 00:00:00
abstract::Traffic congestion at bus bays has decreased the service efficiency of public transit seriously in China, so it is crucial to systematically study its theory and methods. However, the existing studies lack theoretical model on computing efficiency. Therefore, the calculation models of bus delay at bays are studied. Fi...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2015/750304
更新日期:2015-01-01 00:00:00
abstract::This paper investigated the interregional correlation changed by sport training through electroencephalography (EEG) signals using the techniques of classification and feature selection. The EEG data are obtained from students with long-time professional sport training and normal students without sport training as bas...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2016/6184823
更新日期:2016-01-01 00:00:00
abstract::This paper presents a grammatical evolution (GE)-based methodology to automatically design third generation artificial neural networks (ANNs), also known as spiking neural networks (SNNs), for solving supervised classification problems. The proposal performs the SNN design by exploring the search space of three-layere...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2019/4182639
更新日期:2019-03-28 00:00:00
abstract::Cat Swarm Optimization (CSO) algorithm was put forward in 2006. Despite a faster convergence speed compared with Particle Swarm Optimization (PSO) algorithm, the application of CSO is greatly limited by the drawback of "premature convergence," that is, the possibility of trapping in local optimum when dealing with non...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2017/1583847
更新日期:2017-01-01 00:00:00
abstract::It is well known that the evaluation of a product from the shelf considers the simultaneous cerebral and emotional evaluation of the different qualities of the product such as its colour, the eventual images shown, and the envelope's texture (hereafter all included in the term "product experience"). However, the measu...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2018/9616301
更新日期:2018-09-24 00:00:00
abstract::This article is devoted to statistical modeling and analysis of electrocorticogram (ECoG) signals induced by painful cutaneous laser stimuli, which were recorded from implanted electrodes in awake humans. Specifically, with statistical tools of factor analysis and independent component analysis, the pain-induced laser...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2007/10479
更新日期:2007-01-01 00:00:00
abstract::The design and application of Serious Games (SG) based on the Leap Motion sensor are presented as a tool to support the rehabilitation therapies for upper limbs. Initially, the design principles and their implementation are described, focusing on improving both unilateral and bilateral manual dexterity and coordinatio...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2018/7148427
更新日期:2018-04-11 00:00:00
abstract::Ways to estimate the time-to-collision are explored. In the context of traffic simulation models, classical lane-based notions of vehicle location are relaxed and new, fast, and efficient algorithms are examined. With trajectory conflicts being the main focus, computational procedures are explored which use a two-dime...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2014/761047
更新日期:2014-01-01 00:00:00
abstract::To improve the classification performance of imbalanced learning, a novel oversampling method, immune centroids oversampling technique (ICOTE) based on an immune network, is proposed. ICOTE generates a set of immune centroids to broaden the decision regions of the minority class space. The representative immune centro...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2015/109806
更新日期:2015-01-01 00:00:00
abstract::The paper addresses the context in which the construction industry is considered risky, as the intense labor and machine environment interacts with acceleration and overlapping activities. This situation results in accidents and fatalities. A high number of accidents and fatalities leads to additional costs and delays...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2020/2610306
更新日期:2020-02-25 00:00:00
abstract::To study the relationship between brain network and shooting performance during shooting aiming, we collected electroencephalogram (EEG) signals from 40 skilled shooters during rifle shooting and calculated the EEG functional coupling, functional brain network topology, and correlation coefficients between these EEG c...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2018/4097561
更新日期:2018-11-11 00:00:00
abstract::The brain-computer interface (BCI) plays an important role in assisting patients with amyotrophic lateral sclerosis (ALS) to enable them to participate in communication and entertainment. In this study, a novel channel projection-based canonical correlation analysis (CP-CCA) target identification method for steady-sta...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2019/2361282
更新日期:2019-12-16 00:00:00
abstract::This study introduces a supercapacitor hybrid energy storage system in a wind-solar hybrid power generation system, which can remarkably increase the energy storage capacity and output power of the system. In the specific solution, this study combines the distributed power generation system and the hybrid energy stora...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2020/8887227
更新日期:2020-08-28 00:00:00
abstract::This paper proposes a method to translate human EEG into music, so as to represent mental state by music. The arousal levels of the brain mental state and music emotion are implicitly used as the bridge between the mind world and the music. The arousal level of the brain is based on the EEG features extracted mainly b...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2010/267671
更新日期:2010-01-01 00:00:00
abstract::Increasing population age demands more services in healthcare domain. It has been shown that mobile robots could be a potential solution to home biomonitoring for the elderly. Through our previous studies, a mobile robot system that is able to track a subject and identify his daily living activities has been developed...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2016/9845816
更新日期:2016-01-01 00:00:00
abstract::In recent years, ensemble classification methods have been widely investigated in both industry and literature in the field of machine learning and artificial intelligence. The main advantage of this approach is to benefit from a set of classifiers instead of using a single classifier with the aim of improving the pre...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2020/8826914
更新日期:2020-12-14 00:00:00
abstract::[This corrects the article DOI: 10.1155/2019/9898251.]. ...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章,已发布勘误
doi:10.1155/2019/9095675
更新日期:2019-09-23 00:00:00
abstract::SSD (Single Shot MultiBox Detector) is one of the best object detection algorithms and is able to provide high accurate object detection performance in real time. However, SSD shows relatively poor performance on small object detection because its shallow prediction layer, which is responsible for detecting small obje...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2020/2936920
更新日期:2020-04-05 00:00:00
abstract::Rotation Forest is an ensemble learning approach achieving better performance comparing to Bagging and Boosting through building accurate and diverse classifiers using rotated feature space. However, like other conventional classifiers, Rotation Forest does not work well on the imbalanced data which are characterized ...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2018/6798042
更新日期:2018-11-01 00:00:00
abstract::Nowadays the neuroscientific community is taking more and more advantage of the continuous interaction between engineers and computational neuroscientists in order to develop neuroprostheses aimed at replacing damaged brain areas with artificial devices. To this end, a technological effort is required to develop neura...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2015/359590
更新日期:2015-01-01 00:00:00
abstract::This study aimed to determine the effect of liraglutide pretreatment and to elucidate the mechanism of nuclear factor erythroid 2-related factor (Nrf2)/heme oxygenase-1 (HO-1) signaling after focal cerebral ischemia injury in diabetic rats model. Adult male Sprague-Dawley rats were randomly divided into the sham-opera...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2018/3094504
更新日期:2018-02-12 00:00:00
abstract::We present a multistage fuzzy rule-based algorithm for epileptic seizure onset detection. Amplitude, frequency, and entropy-based features were extracted from intracranial electroencephalogram (iEEG) recordings and considered as the inputs for a fuzzy system. These features extracted from multichannel iEEG signals wer...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2012/705140
更新日期:2012-01-01 00:00:00
abstract::We propose a biologically motivated brain-inspired single neuron perceptron (SNP) with universal approximation and XOR computation properties. This computational model extends the input pattern and is based on the excitatory and inhibitory learning rules inspired from neural connections in the human brain's nervous sy...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2014/746376
更新日期:2014-01-01 00:00:00
abstract::The effect of emotion on prospective memory on those of different age groups and its neural mechanism in Chinese adults are still unclear. The present study investigated the effect of emotion on prospective memory during the encoding and retrieval phases in younger and older adults by using event-related potentials (E...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2020/8859231
更新日期:2020-09-21 00:00:00
abstract::The neural autoregressive distribution estimator(NADE) is a competitive model for the task of density estimation in the field of machine learning. While NADE mainly focuses on the problem of estimating density, the ability for dealing with other tasks remains to be improved. In this paper, we introduce a simple and ef...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2018/6401645
更新日期:2018-12-23 00:00:00
abstract::Though Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) via Convolutional Neural Networks (CNNs) has made huge progress toward deep learning, some key issues still remain unsolved due to the lack of sufficient samples and robust model. In this paper, we proposed an efficient transferred Max-Slice CNN ...
journal_title:Computational intelligence and neuroscience
pub_type: 杂志文章
doi:10.1155/2019/9140167
更新日期:2019-11-15 00:00:00