To see the other types of publications on this topic, follow the link: Field transfer trailer.
Journal articles on the topic 'Field transfer trailer'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Field transfer trailer.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Shaffer, Robert M., and James M. Keesee. "Keeping Mud Off the Highway During Wet-Weather Logging." Southern Journal of Applied Forestry 15, no. 1 (February 1, 1991): 50–53. http://dx.doi.org/10.1093/sjaf/15.1.50.
Full textAbstract:
Abstract Mud transfer from soil-based logging roads to paved public highways by log trucks operating during muddy conditions is a major problem for southern logging contractors. Mud transfer can result in fines, traffic accidents, lawsuits, and loss of production. Four devices that could be attached to a log trailer to remove mud from the trailer's dual tires were designed, constructed, and field tested. A simple and inexpensive "bar and scraper" was found to be particularly effective, removing 85% of the mud accumulated during the control phase of the study. South J. Appl. For. 15(1):50-53.
2
Sarwary, A. M. E., D. F. Stegeman, L. P. J. Selen, and W. P. Medendorp. "Generalization and transfer of contextual cues in motor learning." Journal of Neurophysiology 114, no. 3 (September 2015): 1565–76. http://dx.doi.org/10.1152/jn.00217.2015.
Full textAbstract:
We continuously adapt our movements in daily life, forming new internal models whenever necessary and updating existing ones. Recent work has suggested that this flexibility is enabled via sensorimotor cues, serving to access the correct internal model whenever necessary and keeping new models apart from previous ones. While research to date has mainly focused on identifying the nature of such cue representations, here we investigated whether and how these cue representations generalize, interfere, and transfer within and across effector systems. Subjects were trained to make two-stage reaching movements: a premovement that served as a cue, followed by a targeted movement that was perturbed by one of two opposite curl force fields. The direction of the premovement was uniquely coupled to the direction of the ensuing force field, enabling simultaneous learning of the two respective internal models. After training, generalization of the two premovement cues' representations was tested at untrained premovement directions, within both the trained and untrained hand. We show that the individual premovement representations generalize in a Gaussian-like pattern around the trained premovement direction. When the force fields are of unequal strengths, the cue-dependent generalization skews toward the strongest field. Furthermore, generalization patterns transfer to the nontrained hand, in an extrinsic reference frame. We conclude that contextual cues do not serve as discrete switches between multiple internal models. Instead, their generalization suggests a weighted contribution of the associated internal models based on the angular separation from the trained cues to the net motor output.
3
Sheppard, Daniel J., Sherrie A. Jones, Daniel P. Westra, and Joyce J. Madden. "Simulator Evaluation of Instructional and Design Features for Training Helicopter Shipboard Landing." Proceedings of the Human Factors Society Annual Meeting 32, no. 18 (October 1988): 1261–65. http://dx.doi.org/10.1177/154193128803201815.
Full textAbstract:
The effects of four instructional issues and one simulator design feature for training helicopter shipboard landing on small ships were tested in the Vertical Take-off and Landing Simulator (VTOL) at the Visual Technology Research Simulator (VTRS), Naval Training Systems Center. They were: (1) field of view (VTRS versus a test field of view), (2) task chaining (segmented backward chaining versus whole task training), (3) augmented cueing (augmented cueing versus no augmented cueing), (4) length of training (18, 27, and 36 trials), and (5) the timing of seastate introduction (early versus late). The experiment utilized an in-simulator transfer-of-training paradigm in which pilots who were not proficient in the helicopter shipboard landing task were trained under one of several experimental conditions, then tested on the transfer condition (that represented maximum realism) in the simulator. Thirty-two pilots each completed a total of 54 trials (36 training, 18 transfer). Pilots were tested in the transfer condition (six trials) after their 18th, 27th, and 36th training trial. Of the experimental instructional issues, task chaining had the largest effect, with better performance in all segments of the task for pilots who were trained with the backward-chaining sequence, than for pilots who received whole task training. Augmented cueing did not yield the transfer performance anticipated. Seastate introduction had no effect on performance. Field of view had some marginal effects on vertical performance in the hover, with better performance for pilots who were trained with the combination VTRS field-of-view and backward-chaining. Results suggest a diminished rate of learning after 33 simulator trials (includes 27 training trials and six transfer trials of the first probe).
4
Nguyen, Minh Ngoc, Nha Thanh Nguyen, and Thien Tich Truong. "Estimation of heat transfer parameters by using trained POD-RBF and Grey Wolf Optimizer." Vietnam Journal of Mechanics 42, no. 4 (December 27, 2020): 401–14. http://dx.doi.org/10.15625/0866-7136/15015.
Full textAbstract:
The article presents a numerical model for estimation of heat transfer parameters, e.g. thermal conductivity and convective coefficient, in two-dimensional solid bodies under steady-state conduction. This inverse problem is stated as an optimization problem, in which input is reference temperature data and the output is the design variables, i.e. the thermal properties to be identified. The search for optimum design variables is conducted by using a recent heuristic method, namely Grey Wolf Optimizer. During the heuristic search, direct heat conduction problem has to be solved several times. The set of heat transfer parameters that lead to smallest error rate between computed temperature field and reference one is the optimum output of the inverse problem. In order to accelerate the process, the model order reduction technique Proper-Orthogonal-Decomposition (POD) is used. The idea is to express the direct solution (temperature field) as a linear combination of orthogonal basis vectors. Practically, a majority of the basis vectors can be truncated, without losing much accuracy. The amplitude of this reduced-order approximation is then further interpolated by Radial Basis Functions (RBF). The whole scheme, named as trained POD-RBF, is then used as a surrogate model to retrieve the heat transfer parameters.
5
Subedi, Bhawani Shankar. "Assessing the Effectiveness of Teacher Training Programs to Improve the Quality of School Education in Nepal." Journal of Training and Development 1 (July 31, 2015): 9–14. http://dx.doi.org/10.3126/jtd.v1i0.13084.
Full textAbstract:
Inadequate transfer of knowledge, skills, attitudes and behaviours from the training environment to the workplace environment has emerged as a global issue. Teachers’ training has not been an exception. Available literature on teacher training indicates that the contribution of training can be assessed at least on six dimensions- quality, access, equity, efficiency, teacher development and overall school development. Studies conducted in the area of teacher training or teacher professional development in the context of Nepal are also evident of lack of sufficient transfer of knowledge and skills from training to workplace. There are several factors facilitating or inhibiting the extent of such transfer. Research shows that the training of teachers has contributed and can positively influence quality of education if stakeholders are made aware of and well informed about the quality and relevance of training and development interventions carefully designed and implemented for the capacity development of teachers, teacher educators or trainers. This article has been derived from the synopsis of a comprehensive study conducted in Nepal and concluded in March 2010. Data bases of 4033 trained teachers of 45 schools from 25 sample districts were studied. This study was a blending of quantitative as well as qualitative approaches. Nine education experts and 22 field researchers were involved. The author was the team leader of the study. The only academic purpose of this article is to inspire excellence in teaching, learning and performance by means of professionalism and capacity building of teachers, teacher trainers and their employers. DOI: http://dx.doi.org/10.3126/jtd.v1i0.13084 Journal of Training and Development Vol.1 2015: 9-14
6
Houldin, Adina, Romeo Chua, Mark G. Carpenter, and Tania Lam. "Limited interlimb transfer of locomotor adaptations to a velocity-dependent force field during unipedal walking." Journal of Neurophysiology 108, no. 3 (August 1, 2012): 943–52. http://dx.doi.org/10.1152/jn.00670.2011.
Full textAbstract:
Several studies have demonstrated that motor adaptations to a novel task environment can be transferred between limbs. Such interlimb transfer of motor commands is consistent with the notion of centrally driven strategies that can be generalized across different frames of reference. So far, studies of interlimb transfer of locomotor adaptations have yielded disparate results. Here we sought to determine whether locomotor adaptations in one (trained) leg show transfer to the other (test) leg during a unipedal walking task. We hypothesized that adaptation in the test leg to a velocity-dependent force field previously experienced by the trained leg will be faster, as revealed by faster recovery of kinematic errors and earlier onset of aftereffects. Twenty able-bodied adults walked unipedally in the Lokomat robotic gait orthosis, which applied velocity-dependent resistance to the legs. The amount of resistance was scaled to 10% of each individual's maximum voluntary contraction of the hip flexors. Electromyography and kinematics of the lower limb were recorded. All subjects were right-leg dominant and were tested for transfer of motor adaptations from the right leg to the left leg. Catch trials, consisting of unexpected removal of resistance, were presented after the first step with resistance and after a period of adaptation to test for aftereffects. We found no significant differences in the sizes of the aftereffects between the two legs, except for peak hip flexion during swing, or in the rate at which peak hip flexion adapted during steps against resistance between the two legs. Our results indicate that interlimb transfer of these types of locomotor adaptation is not a robust phenomenon. These findings add to our current understanding of motor adaptations and provide further evidence that generalization of adaptations may be dependent on the movement task.
7
Myers, Carole. "Core skills and transfer in the youth training schemes: A field study of trainee motor mechanics." Journal of Organizational Behavior 13, no. 6 (November 1992): 625–32. http://dx.doi.org/10.1002/job.4030130608.
Full text
8
Arnold, Gabriel, and Malika Auvray. "Perceptual Learning: Tactile Letter Recognition Transfers Across Body Surfaces." Multisensory Research 27, no. 1 (2014): 71–90. http://dx.doi.org/10.1163/22134808-00002443.
Full textAbstract:
Visual-to-tactile sensory substitution devices are designed to assist visually impaired people by converting visual stimuli into tactile stimuli. The important claim has been made that, after training with these devices, the tactile stimuli can be moved from one body surface to another without any decrease in performance. This claim, although recurrent, has never been empirically investigated. Moreover, studies in the field of tactile perceptual learning suggest that performance improvement transfers only to body surfaces that are closely represented in the somatosensory cortex, i.e. adjacent or homologous contralateral body surfaces. These studies have however mainly used discrimination tasks of stimuli varying along only one feature (e.g., orientation of gratings) whereas, in sensory substitution, tactile information consists of more complex stimuli. The present study investigated the extent to which there is a transfer of tactile letter learning. Participants first underwent a baseline session in which the letters were presented on their belly, thigh, and shin. They were subsequently trained on only one of these body surfaces, and then re-tested on all of them, as a post-training session. The results revealed that performance improvement was the same for both the trained and the untrained surfaces. Moreover, this transfer of perceptual learning was equivalent for adjacent and non-adjacent body surfaces, suggesting that tactile learning transfer occurs independently of the distance on the body. A control study consisting of the same baseline and post-training sessions, without training in between, revealed weaker improvement between the two sessions. The obtained results support the claim that training with sensory substitution devices results in a relative independence from the stimulated body surface.
9
Zheng, Zhong, Jinfei Wang, Bo Shan, Yongjun He, Chunhua Liao, Yanghua Gao, and Shiqi Yang. "A New Model for Transfer Learning-Based Mapping of Burn Severity." Remote Sensing 12, no. 4 (February 21, 2020): 708. http://dx.doi.org/10.3390/rs12040708.
Full textAbstract:
In recent years, global forest fires have occurred more frequently, seriously destroying the structural functions of forest ecosystem. Mapping the burn severity after forest fires is of great significance for quantifying fire’s effects on landscapes and establishing restoration measures. Generally, intensive field surveys across burned areas are required for the effective application of traditional methods. Unfortunately, this requirement could not be satisfied in most cases, since the field work demands a lot of personnel and funding. For mapping severity levels across burned areas without field survey data, a semi-supervised transfer component analysis-based support vector regression model (SSTCA-SVR) was proposed in this study to transfer knowledge trained from other burned areas with field survey data. Its performance was further evaluated in various eco-type regions of southwestern United States. Results show that SSTCA-SVR which was trained on source domain areas could effectively be transferred to a target domain area. Meanwhile, the SSTCA-SVR could maintain as much spectral information as possible to map burn severity. Its mapped results are more accurate (RMSE values were between 0.4833 and 0.6659) and finer, compared to those mapped by ∆NDVI-, ∆LST-, ∆NBR- (RMSE values ranged from 0.7362 to 1.1187) and SVR-based models (RMSE values varied from 1.7658 to 2.0055). This study has introduced a potentially efficient mechanism to map burn severity, which will speed up the response of post-fire management.
10
Gupta, Keshav, Rajneesh Rani, and Nimratveer Kaur Bahia. "Plant-Seedling Classification Using Transfer Learning-Based Deep Convolutional Neural Networks." International Journal of Agricultural and Environmental Information Systems 11, no. 4 (October 2020): 25–40. http://dx.doi.org/10.4018/ijaeis.2020100102.
Full textAbstract:
The ever-growing population of this world needs more food production every year. The loss caused in crops due to weeds is a major issue for the upcoming years. This issue has attracted the attention of many researchers working in the field of agriculture. There have been many attempts to solve the problem by using image classification techniques. These techniques are attracting researchers because they can prevent the use of herbicides in the fields for controlling weed invasion, reducing the amount of time required for weed control methods. This article presents use of images and deep learning-based approach for classifying weeds and crops into their respective classes. In this paper, five pre-trained convolution neural networks (CNN), namely ResNet50, VGG16, VGG19, Xception, and MobileNetV2, have been used to classify weed and crop into their respective classes. The experiments have been done on V2 plant seedling classification dataset. Amongst these five models, ResNet50 gave the best results with 95.23% testing accuracy.
11
Kandel, Ibrahem, Mauro Castelli, and Aleš Popovič. "Musculoskeletal Images Classification for Detection of Fractures Using Transfer Learning." Journal of Imaging 6, no. 11 (November 23, 2020): 127. http://dx.doi.org/10.3390/jimaging6110127.
Full textAbstract:
The classification of the musculoskeletal images can be very challenging, mostly when it is being done in the emergency room, where a decision must be made rapidly. The computer vision domain has gained increasing attention in recent years, due to its achievements in image classification. The convolutional neural network (CNN) is one of the latest computer vision algorithms that achieved state-of-the-art results. A CNN requires an enormous number of images to be adequately trained, and these are always scarce in the medical field. Transfer learning is a technique that is being used to train the CNN by using fewer images. In this paper, we study the appropriate method to classify musculoskeletal images by transfer learning and by training from scratch. We applied six state-of-the-art architectures and compared their performance with transfer learning and with a network trained from scratch. From our results, transfer learning did increase the model performance significantly, and, additionally, it made the model less prone to overfitting.
12
Sabarre, A. L., A. S. Navidad, D. S. Torbela, and J. J. Adtoon. "Development of durian leaf disease detection on Android device." International Journal of Electrical and Computer Engineering (IJECE) 11, no. 6 (December 1, 2021): 4962. http://dx.doi.org/10.11591/ijece.v11i6.pp4962-4971.
Full textAbstract:
<span lang="EN-US">Durian is exceedingly abundant in the Philippines, providing incomes for smallholder farmers. But amidst these things, durian is still vulnerable to different plant diseases that can cause significant economic loss in the agricultural industry. The conventional way of dealing plant disease detection is through naked-eye observation done by experts. To control such diseases using the old method is extensively laborious, time-consuming and costly especially in dealing with large fields. Hence, the proponent’s objective of this study is to create a standalone mobile app for durian leaf disease detection using the transfer learning approach. In this approach, the chosen network MobileNets, is pre-trained with a large scale of general datasets namely ImageNet to effective function as a generic template for visual processing. The pre-trained network transfers all the learned parameters and set as a feature extractor for the target task to be executed. Four health conditions are addressed in this study, 10 per classification with a total of 40 samples tested to evaluate the accuracy of the system. The result showed 90% in overall accuracy for detecting algalspot, cercospora, leaf discoloration and healthy leaf.</span>
13
Dempsey-Jones, Harriet, Vanessa Harrar, Jonathan Oliver, Heidi Johansen-Berg, Charles Spence, and Tamar R. Makin. "Transfer of tactile perceptual learning to untrained neighboring fingers reflects natural use relationships." Journal of Neurophysiology 115, no. 3 (March 1, 2016): 1088–97. http://dx.doi.org/10.1152/jn.00181.2015.
Full textAbstract:
Tactile learning transfers from trained to untrained fingers in a pattern that reflects overlap between the representations of fingers in the somatosensory system (e.g., neurons with multifinger receptive fields). While physical proximity on the body is known to determine the topography of somatosensory representations, tactile coactivation is also an established organizing principle of somatosensory topography. In this study we investigated whether tactile coactivation, induced by habitual inter-finger cooperative use (use pattern), shapes inter-finger overlap. To this end, we used psychophysics to compare the transfer of tactile learning from the middle finger to its adjacent fingers. This allowed us to compare transfer to two fingers that are both physically and cortically adjacent to the middle finger but have differing use patterns. Specifically, the middle finger is used more frequently with the ring than with the index finger. We predicted this should lead to greater representational overlap between the former than the latter pair. Furthermore, this difference in overlap should be reflected in differential learning transfer from the middle to index vs. ring fingers. Subsequently, we predicted temporary learning-related changes in the middle finger's representation (e.g., cortical magnification) would cause transient interference in perceptual thresholds of the ring, but not the index, finger. Supporting this, longitudinal analysis revealed a divergence where learning transfer was fast to the index finger but relatively delayed to the ring finger. Our results support the theory that tactile coactivation patterns between digits affect their topographic relationships. Our findings emphasize how action shapes perception and somatosensory organization.
14
Peng, Cheng, Lingling Li, Qing Chen, Zhaohui Tang, Weihua Gui, and Jing He. "A Fault Diagnosis Method for Rolling Bearings Based on Parameter Transfer Learning under Imbalance Data Sets." Energies 14, no. 4 (February 11, 2021): 944. http://dx.doi.org/10.3390/en14040944.
Full textAbstract:
Fault diagnosis under the condition of data sets or samples with only a few fault labels has become a hot spot in the field of machinery fault diagnosis. To solve this problem, a fault diagnosis method based on deep transfer learning is proposed. Firstly, the discriminator of the generative adversarial network (GAN) is improved by enhancing its sparsity, and then adopts the adversarial mechanism to continuously optimize the recognition ability of the discriminator; finally, the parameter transfer learning (PTL) method is applied to transfer the trained discriminator to target domain to solve the fault diagnosis problem with only a small number of label samples. Experimental results show that this method has good fault diagnosis performance.
15
Sellier, Anne-Laure, Irene Scopelliti, and Carey K. Morewedge. "Debiasing Training Improves Decision Making in the Field." Psychological Science 30, no. 9 (July 26, 2019): 1371–79. http://dx.doi.org/10.1177/0956797619861429.
Full textAbstract:
The primary objection to debiasing-training interventions is a lack of evidence that they improve decision making in field settings, where reminders of bias are absent. We gave graduate students in three professional programs ( N = 290) a one-shot training intervention that reduces confirmation bias in laboratory experiments. Natural variance in the training schedule assigned participants to receive training before or after solving an unannounced business case modeled on the decision to launch the Space Shuttle Challenger. We used case solutions to surreptitiously measure participants’ susceptibility to confirmation bias. Trained participants were 19% less likely to choose the inferior hypothesis-confirming solution than untrained participants. Analysis of case write-ups suggests that a reduction in confirmatory hypothesis testing accounts for their improved decision making in the case. The results provide promising evidence that debiasing-training effects transfer to field settings and can improve decision making in professional and private life.
16
Salem, Milad, Aminollah Khormali, Arash Keshavarzi Arshadi, Julia Webb, and Jiann-Shiun Yuan. "TranScreen: Transfer Learning on Graph-Based Anti-Cancer Virtual Screening Model." Big Data and Cognitive Computing 4, no. 3 (June 29, 2020): 16. http://dx.doi.org/10.3390/bdcc4030016.
Full textAbstract:
Deep learning’s automatic feature extraction has proven its superior performance over traditional fingerprint-based features in the implementation of virtual screening models. However, these models face multiple challenges in the field of early drug discovery, such as over-training and generalization to unseen data, due to the inherently unbalanced and small datasets. In this work, the TranScreen pipeline is proposed, which utilizes transfer learning and a collection of weight initializations to overcome these challenges. An amount of 182 graph convolutional neural networks are trained on molecular source datasets and the learned knowledge is transferred to the target task for fine-tuning. The target task of p53-based bioactivity prediction, an important factor for anti-cancer discovery, is chosen to showcase the capability of the pipeline. Having trained a collection of source models, three different approaches are implemented to compare and rank them for a given task before fine-tuning. The results show improvement in performance of the model in multiple cases, with the best model increasing the area under receiver operating curve ROC-AUC from 0.75 to 0.91 and the recall from 0.25 to 1. This improvement is vital for practical virtual screening via lowering the false negatives and demonstrates the potential of transfer learning. The code and pre-trained models are made accessible online.
17
Maschler, Benjamin, Simon Kamm, and Michael Weyrich. "Deep industrial transfer learning at runtime for image recognition." at - Automatisierungstechnik 69, no. 3 (March 1, 2021): 211–20. http://dx.doi.org/10.1515/auto-2020-0119.
Full textAbstract:
Abstract The utilization of deep learning in the field of industrial automation is hindered by two factors: The amount and diversity of training data needed as well as the need to continuously retrain as the use case changes over time. Both problems can be addressed by industrial deep transfer learning allowing for the performant, continuous and potentially distributed training on small, dispersed datasets. As a specific example, a dual memory algorithm for computer vision problems is developed and evaluated. It shows the potential for state-of-the-art performance while being trained only on fractions of the complete ImageNet dataset at multiple locations at once.
18
Sharma, Suvash, John E. Ball, Bo Tang, Daniel W. Carruth, Matthew Doude, and Muhammad Aminul Islam. "Semantic Segmentation with Transfer Learning for Off-Road Autonomous Driving." Sensors 19, no. 11 (June 6, 2019): 2577. http://dx.doi.org/10.3390/s19112577.
Full textAbstract:
Since the state-of-the-art deep learning algorithms demand a large training dataset, which is often unavailable in some domains, the transfer of knowledge from one domain to another has been a trending technique in the computer vision field. However, this method may not be a straight-forward task considering several issues such as original network size or large differences between the source and target domain. In this paper, we perform transfer learning for semantic segmentation of off-road driving environments using a pre-trained segmentation network called DeconvNet. We explore and verify two important aspects regarding transfer learning. First, since the original network size was very large and did not perform well for our application, we proposed a smaller network, which we call the light-weight network. This light-weight network is half the size to the original DeconvNet architecture. We transferred the knowledge from the pre-trained DeconvNet to our light-weight network and fine-tuned it. Second, we used synthetic datasets as the intermediate domain before training with the real-world off-road driving data. Fine-tuning the model trained with the synthetic dataset that simulates the off-road driving environment provides more accurate results for the segmentation of real-world off-road driving environments than transfer learning without using a synthetic dataset does, as long as the synthetic dataset is generated considering real-world variations. We also explore the issue whereby the use of a too simple and/or too random synthetic dataset results in negative transfer. We consider the Freiburg Forest dataset as a real-world off-road driving dataset.
19
Harper, Sara A., Anne Z. Beethe, Christopher J. Dakin, and David A. E. Bolton. "Promoting Generalized Learning in Balance Recovery Interventions." Brain Sciences 11, no. 3 (March 22, 2021): 402. http://dx.doi.org/10.3390/brainsci11030402.
Full textAbstract:
Recent studies have shown balance recovery can be enhanced via task-specific training, referred to as perturbation-based balance training (PBT). These interventions rely on principles of motor learning where repeated exposure to task-relevant postural perturbations results in more effective compensatory balance responses. Evidence indicates that compensatory responses trained using PBT can be retained for many months and can lead to a reduction in falls in community-dwelling older adults. A notable shortcoming with PBT is that it does not transfer well to similar but contextually different scenarios (e.g., falling sideways versus a forward trip). Given that it is not feasible to train all conditions in which someone could fall, this limited transfer presents a conundrum; namely, how do we best use PBT to appropriately equip people to deal with the enormous variety of fall-inducing scenarios encountered in daily life? In this perspective article, we draw from fields of research that explore how general learning can be promoted. From this, we propose a series of methods, gleaned from parallel streams of research, to inform and hopefully optimize this emerging field where people receive training to specifically improve their balance reactions.
20
Panyshev, Andrey Lvovich, and Larisa Nikolaevna Gorina. "The system of additional education in the field of industrial safety." Samara Journal of Science 9, no. 4 (November 30, 2020): 317–20. http://dx.doi.org/10.17816/snv202094309.
Full textAbstract:
The establishment of modern enterprises and modernization of production facilities at existing production facilities create a need for trained employees in various fields of activity. Taking into account the fact that the changes in information technologies and the current digitalization of the economy that permeates everywhere leave their mark on the requirements for personnel, the process of training necessary specialists is noticeably more complicated. Therefore, the issues of training qualified specialists for various industries are constantly in the focus of attention of both representatives of the educational community and employers. Moreover, the relevance of this topic for the latter is also becoming one of the conditions for competitive confrontation in the markets of products or services. It is obvious that a well-trained staff provides exactly a competitive advantage that allows the company to survive, and employers to make profit. A created staff of highly qualified employees makes it possible to ensure the successful operation of the organization on a permanent basis. The recruitment of employees of the enterprise occurs both due to the transfer of employees from other enterprises, and at the expense of graduates of higher educational institutions. In such conditions, in the absence of high-quality training systems for students at most universities, the importance of additional professional education increases.
21
Coe, Gloria A., and David Banta. "Health Care Technology Transfer in Latin America and the Caribbean." International Journal of Technology Assessment in Health Care 8, no. 02 (March 1992): 255–67. http://dx.doi.org/10.1017/s0266462300013489.
Full textAbstract:
AbstractThe greatest problem concerning health care technology for developing countries is that they are dependent upon the industrialized world for technology. The only short-term solution to this problem is to improve the choices that are available to them. This goal will require changes in the structure and processes of policy making. A particular difficulty for these countries is the lack of trained personnel in fields related to technology assessment.
22
Ahmed, Marwa, and Serestina Viriri. "Facial Age Estimation using Transfer Learning and Bayesian Optimization based on Gender Information." Signal & Image Processing : An International Journal 11, no. 6 (December 30, 2020): 53–63. http://dx.doi.org/10.5121/sipij.2020.11604.
Full textAbstract:
Age estimation of unrestricted imaging circumstances has attracted an augmented recognition as it is appropriate in several real-world applications such as surveillance, face recognition, age synthesis, access control, and electronic customer relationship management. Current deep learning-based methods have displayed encouraging performance in age estimation field. Males and Females have a variable type of appearance aging pattern; this results in age differently. This fact leads to assuming that using gender information may improve the age estimator performance. We have proposed a novel model based on Gender Classification. A Convolutional Neural Network (CNN) is used to get Gender Information, then Bayesian Optimization is applied to this pre-trained CNN when fine-tuned for age estimation task. Bayesian Optimization reduces the classification error on the validation set for the pre-trained model. Extensive experiments are done to assess our proposed model on two data sets: FERET and FG-NET. The experiments’ result indicates that using a pre-trained CNN containing Gender Information with Bayesian Optimization outperforms the state of the arts on FERET and FG-NET data sets with a Mean Absolute Error (MAE) of 1.2 and 2.67 respectively.
23
Sethy, Prabira Kumar, Santi Kumari Behera, Nithiyakanthan Kannan, Sridevi Narayanan, and Chanki Pandey. "Smart paddy field monitoring system using deep learning and IoT." Concurrent Engineering 29, no. 1 (January 28, 2021): 16–24. http://dx.doi.org/10.1177/1063293x21988944.
Full textAbstract:
Paddy is an essential nutrient worldwide. Rice gives 21% of worldwide human per capita energy and 15% of per capita protein. Asia represented 60% of the worldwide populace, about 92% of the world’s rice creation, and 90% of worldwide rice utilization. With the increase in population, the demand for rice is increased. So, the productivity of farming is needed to be enhanced by introducing new technology. Deep learning and IoT are hot topics for research in various fields. This paper suggested a setup comprising deep learning and IoT for monitoring of paddy field remotely. The vgg16 pre-trained network is considered for the identification of paddy leaf diseases and nitrogen status estimation. Here, two strategies are carried out to identify images: transfer learning and deep feature extraction. The deep feature extraction approach is combined with a support vector machine (SVM) to classify images. The transfer learning approach of vgg16 for identifying four types of leaf diseases and prediction of nitrogen status results in 79.86% and 84.88% accuracy. Again, the deep features of Vgg16 and SVM results for identifying four types of leaf diseases and prediction of nitrogen status have achieved an accuracy of 97.31% and 99.02%, respectively. Besides, a framework is suggested for monitoring of paddy field remotely based on IoT and deep learning. The suggested prototype’s superiority is that it controls temperature and humidity like the state-of-the-art and can monitor the additional two aspects, such as detecting nitrogen status and diseases.
24
Ding, Renjie, Xue Li, Lanshun Nie, Jiazhen Li, Xiandong Si, Dianhui Chu, Guozhong Liu, and Dechen Zhan. "Empirical Study and Improvement on Deep Transfer Learning for Human Activity Recognition." Sensors 19, no. 1 (December 24, 2018): 57. http://dx.doi.org/10.3390/s19010057.
Full textAbstract:
Human activity recognition (HAR) based on sensor data is a significant problem in pervasive computing. In recent years, deep learning has become the dominating approach in this field, due to its high accuracy. However, it is difficult to make accurate identification for the activities of one individual using a model trained on data from other users. The decline on the accuracy of recognition restricts activity recognition in practice. At present, there is little research on the transferring of deep learning model in this field. This is the first time as we known, an empirical study was carried out on deep transfer learning between users with unlabeled data of target. We compared several widely-used algorithms and found that Maximum Mean Discrepancy (MMD) method is most suitable for HAR. We studied the distribution of features generated from sensor data. We improved the existing method from the aspect of features distribution with center loss and get better results. The observations and insights in this study have deepened the understanding of transfer learning in the activity recognition field and provided guidance for further research.
25
Sheppard, Daniel, Daniel Westra, and Gavan Lintern. "Simulator Design and Instructional features for Air-to-Ground Attack: Transfer Study." Proceedings of the Human Factors Society Annual Meeting 30, no. 10 (September 1986): 1038–42. http://dx.doi.org/10.1177/154193128603001022.
Full textAbstract:
A transfer-of-training experiment was conducted to provide guidelines for simulator design and training procedures for air-to-ground attack. Two levels of scene detail (complex day scene versus a low detail dusk scene), three levels of field of view (160H X 80V, 135H X 60V, 103H X 60V), and three levels of simulator training trials (24, 48, 72) were tested in the experiment. Student Naval Aviators (SNAs) were trained in the Visual Technology Research Simulator (VTRS) in 30-degree bombing prior to their standard weapon training phase. Other students, not pretrained in the VTRS, were used for control comparisons. Training in the VTRS helped SNAs use their weapons flight time in the TA-4J more effectively. Forty-eight simulator trials were recommended as adequate pretraining for 30-degree bombing. There was no evidence of differential transfer for the scene detail and field-of-view factors. The least expensive field of view option tested was recommended. However, there were methodological problems with the scene type comparison and the apparent transfer equivalence of the two scenes may not fully indicate their relative training effectiveness. Data from other VTRS experiments suggest the superiority of the day scene and it was recommended.
26
Chardin, Jonathan, Grégoire Uhlrich, Dominique Aubert, Nicolas Deparis, Nicolas Gillet, Pierre Ocvirk, and Joseph Lewis. "A deep learning model to emulate simulations of cosmic reionization." Monthly Notices of the Royal Astronomical Society 490, no. 1 (September 7, 2019): 1055–65. http://dx.doi.org/10.1093/mnras/stz2605.
Full textAbstract:
ABSTRACT We present a deep learning model trained to emulate the radiative transfer during the epoch of cosmological reionization. CRADLE (Cosmological Reionization And Deep LEarning) is an auto-encoder convolutional neural network that uses 2D maps of the star number density and the gas density field at z = 6 as inputs and that predicts 3D maps of the times of reionization treion as outputs. These predicted single fields are sufficient to describe the global reionization history of the intergalactic medium in a given simulation. We trained the model on a given simulation and tested the predictions on another simulation with the same parameters but with different initial conditions. The model is successful at predicting treion maps that are in good agreement with the test simulation. We used the power spectrum of the treion field as an indicator to validate our model. We show that the network predicts large scales almost perfectly but is somewhat less accurate at smaller scales. While the current model is already well suited to get average estimates about the reionization history, we expect it can be further improved with larger samples for the training, better data pre-processing and finer tuning of hyper-parameters. Emulators of this kind could be systematically used to rapidly obtain the evolving H ii regions associated with hydro-only simulations and could be seen as precursors of fully emulated physics solvers for future generations of simulations.
27
Wang, Yingying, Benfeng Wang, Ning Tu, and Jianhua Geng. "Seismic trace interpolation for irregularly spatial sampled data using convolutional autoencoder." GEOPHYSICS 85, no. 2 (January 30, 2020): V119—V130. http://dx.doi.org/10.1190/geo2018-0699.1.
Full textAbstract:
Seismic trace interpolation is an important technique because irregular or insufficient sampling data along the spatial direction may lead to inevitable errors in multiple suppression, imaging, and inversion. Many interpolation methods have been studied for irregularly sampled data. Inspired by the working idea of the autoencoder and convolutional neural network, we have performed seismic trace interpolation by using the convolutional autoencoder (CAE). The irregularly sampled data are taken as corrupted data. By using a training data set including pairs of the corrupted and complete data, CAE can automatically learn to extract features from the corrupted data and reconstruct the complete data from the extracted features. It can avoid some assumptions in the traditional trace interpolation method such as the linearity of events, low-rankness, or sparsity. In addition, once the CAE network training is completed, the corrupted seismic data can be interpolated immediately with very low computational cost. A CAE network composed of three convolutional layers and three deconvolutional layers is designed to explore the capabilities of CAE-based seismic trace interpolation for an irregularly sampled data set. To solve the problem of rare complete shot gathers in field data applications, the trained network on synthetic data is used as an initialization of the network training on field data, called the transfer learning strategy. Experiments on synthetic and field data sets indicate the validity and flexibility of the trained CAE. Compared with the curvelet-transform-based method, CAE can lead to comparable or better interpolation performances efficiently. The transfer learning strategy enhances the training efficiency on field data and improves the interpolation performance of CAE with limited training data.
28
Machesa, Mosa, Lagouge Tartibu, and Modestus Okwu. "Prediction of the Oscillatory Heat Transfer Coefficient in Thermoacoustic Refrigerators." Sustainability 13, no. 17 (August 24, 2021): 9509. http://dx.doi.org/10.3390/su13179509.
Full textAbstract:
Thermoacoustic refrigerators are emerging devices that make use of meaningful high-pressure sound waves to induce cooling. Despite the accelerated progress in the field of thermoacoustics, knowledge of the heat transfer process in the heat exchange of the devices is still developing. This work applies different soft computing techniques, namely, an artificial neural network trained by particle swarm optimisation (ANN-PSO), adaptive neuro-fuzzy inference system (ANFIS), and artificial neural networks (ANNs) to predict the oscillatory heat transfer coefficient in the heat exchangers of a thermoacoustic device. This study provides the details of the parametric analysis of an artificial neural network model trained by particle swarm optimisation. The solution model considers the number of neurons, the swarm population, and the acceleration factors to develop and analyse the architecture of several models. The regression model (R2) and mean squared error (MSE) were used to evaluate the accuracy of the models. The result showed that the proposed soft computing techniques can potentially be used for the modelling and the analysis of the oscillatory heat transfer coefficient with a higher level of accuracy. The result reported in this study implies that the prediction of the OHTC can be considered for the enhancement of thermoacoustic refrigerators performances.
29
Pires de Lima, Rafael, and Kurt Marfurt. "Convolutional Neural Network for Remote-Sensing Scene Classification: Transfer Learning Analysis." Remote Sensing 12, no. 1 (December 25, 2019): 86. http://dx.doi.org/10.3390/rs12010086.
Full textAbstract:
Remote-sensing image scene classification can provide significant value, ranging from forest fire monitoring to land-use and land-cover classification. Beginning with the first aerial photographs of the early 20th century to the satellite imagery of today, the amount of remote-sensing data has increased geometrically with a higher resolution. The need to analyze these modern digital data motivated research to accelerate remote-sensing image classification. Fortunately, great advances have been made by the computer vision community to classify natural images or photographs taken with an ordinary camera. Natural image datasets can range up to millions of samples and are, therefore, amenable to deep-learning techniques. Many fields of science, remote sensing included, were able to exploit the success of natural image classification by convolutional neural network models using a technique commonly called transfer learning. We provide a systematic review of transfer learning application for scene classification using different datasets and different deep-learning models. We evaluate how the specialization of convolutional neural network models affects the transfer learning process by splitting original models in different points. As expected, we find the choice of hyperparameters used to train the model has a significant influence on the final performance of the models. Curiously, we find transfer learning from models trained on larger, more generic natural images datasets outperformed transfer learning from models trained directly on smaller remotely sensed datasets. Nonetheless, results show that transfer learning provides a powerful tool for remote-sensing scene classification.
30
Bunyamin, Hendra. "Utilizing Indonesian Universal Language Model Fine-tuning for Text Classification." Journal of Information Technology and Computer Science 5, no. 3 (January 25, 2021): 325–37. http://dx.doi.org/10.25126/jitecs.202053215.
Full textAbstract:
Inductive transfer learning technique has made a huge impact on the computer vision field. Particularly, computer vision applications including object detection, classification, and segmentation, are rarely trained from scratch; instead, they are fine-tuned from pretrained models, which are products of learning from huge datasets. In contrast to computer vision, state-of-the-art natural language processing models are still generally trained from the ground up. Accordingly, this research attempts to investigate an adoption of the transfer learning technique for natural language processing. Specifically, we utilize a transfer learning technique called Universal Language Model Fine-tuning (ULMFiT) for doing an Indonesian news text classification task. The dataset for constructing the language model is collected from several news providers from January to December 2017 whereas the dataset employed for text classification task comes from news articles provided by the Agency for the Assessment and Application of Technology (BPPT). To examine the impact of ULMFiT, we provide a baseline that is a vanilla neural network with two hidden layers. Although the performance of ULMFiT on validation set is lower than the one of our baseline, we find that the benefits of ULMFiT for the classification task significantly reduce the overfitting, that is the difference between train and validation accuracies from 4% to nearly zero.
31
Umri, Buyut Khoirul, Ema Utami, and Mei P. Kurniawan. "Tinjauan Literatur Sistematik tentang Deteksi Covid-19 menggunakan Convolutional Neural Networks." Creative Information Technology Journal 8, no. 1 (March 31, 2021): 9. http://dx.doi.org/10.24076/citec.2021v8i1.261.
Full textAbstract:
Covid-19 menyerang sel-sel epitel yang melapisi saluran pernapasan sehingga dalam kasus ini dapat memanfaatkan gambar x-ray dada untuk menganalisis kesehatan paru-paru pada pasien. Menggunakan x-ray dalam bidang medis merupakan metode yang lebih cepat, lebih mudah dan tidak berbahaya yang dapat dimanfaatkan pada banyak hal. Salah satu metode yang paling sering digunakan dalam klasifikasi gambar adalah convolutional neural networks (CNN). CNN merupahan jenis neural network yang sering digunakan dalam data gambar dan sering digunakan dalam mendeteksi dan mengenali object pada sebuah gambar. Model arsitektur pada metode CNN juga dapat dikembangkan dengan transfer learning yang merupakan proses menggunakan kembali model pre-trained yang dilatih pada dataset besar, biasanya pada tugas klasifikasi gambar berskala besar. Tinjauan literature review ini digunakan untuk menganalisis penggunaan transfer learning pada CNN sebagai metode yang dapat digunakan untuk mendeteksi covid-19 pada gambar x-ray dada. Hasil sistematis review menunjukkan bahwa algoritma CNN dapat digunakan dengan akruasi yang baik dalam mendeteksi covid-19 pada gambar x-ray dada dan dengan pengembangan model transfer learning mampu mendapatkan performa yang maksimal dengan dataset yang besar maupun kecil.Kata Kunci—CNN, transfer learning, deteksi, covid-19Covid-19 attacks the epithelial cells lining the respiratory tract so that in this case it can utilize chest x-ray images to analyze the health of the lungs in patients. Using x-rays in the medical field is a faster, easier and harmless method that can be utilized in many ways. One of the most frequently used methods in image classification is convolutional neural networks (CNN). CNN is a type of neural network that is often used in image data and is often used in detecting and recognizing objects in an image. The architectural model in the CNN method can also be developed with transfer learning which is the process of reusing pre-trained models that are trained on large datasets, usually on the task of classifying large-scale images. This literature review review is used to analyze the use of transfer learning on CNN as a method that can be used to detect covid-19 on chest x-ray images. The systematic review results show that the CNN algorithm can be used with good accuracy in detecting covid-19 on chest x-ray images and by developing transfer learning models able to get maximum performance with large and small datasets.Keywords—CNN, transfer learning, detection, covid-19
32
Singh, Achyut Man. "Irrigation Management Transfer: A New Methodology to Improve thePerformance of Agency Managed Irrigation Systems (AMISs)." Hydro Nepal: Journal of Water, Energy and Environment 3 (May 26, 2009): 29–34. http://dx.doi.org/10.3126/hn.v3i0.1916.
Full textAbstract:
This paper presents a new concept on the management of Agency Managed Irrigation Systems with the joint participation of the agency and the users, with their defined roles and responsibilities. The message of the system governance and operation methodology are disseminated to the grass root level of the users. Resource management and water charge collection are anticipated to be firmly applied in the system. The users and Water User's Association and also Department of Irrigation field staff will be well trained in the Irrigation Management Transfer process with capacity building. For sustainability, monitoring and evaluation with independent auditing are part of the process. The general Irrigation Management Transfer procedures adopted by Department of Irrigation are redefined to this new concept in the World Bank assisted Irrigation and Water Resources Management Project. Key words: Irrigation management transfer, water users, AMIS, World Bank, Nepal doi: 10.3126/hn.v3i0.1916 Hydro Nepal Journal of Water, Energy and Environment Issue No. 3, July 2008. Page: 29-34
33
Bi, Taiyong, Nihong Chen, Qiujie Weng, Dongjun He, and Fang Fang. "Learning to Discriminate Face Views." Journal of Neurophysiology 104, no. 6 (December 2010): 3305–11. http://dx.doi.org/10.1152/jn.00286.2010.
Full textAbstract:
Although perceptual learning of simple visual features has been studied extensively and intensively for many years, we still know little about the mechanisms of perceptual learning of complex object recognition. In a series of seven experiments, human perceptual learning in discrimination of in-depth orientation of face view was studied using psychophysical methods. We trained subjects to discriminate face orientations around a face view (i.e., 30°) over eight daily sessions, which resulted in a significant improvement in sensitivity to the face view orientation. This improved sensitivity was highly specific to the trained orientation and persisted up to 6 mo. Different from perceptual learning of simple visual features, this orientation-specific learning effect could completely transfer across changes in face size, visual field, and face identity. A complete transfer also occurred between two partial face images that were mutually exclusive but constituted a complete face. However, the transfer of the learning effect between upright and inverted faces and between a face and a paperclip object was very weak. These results shed light on the mechanisms of the perceptual learning of face view discrimination. They suggest that the visual system had learned how to compute face orientation from face configural information more accurately and that a large amount of plastic changes took place at a level of higher visual processing where size-, location-, and identity-invariant face views are represented.
34
Alzubaidi, Laith, Muthana Al-Amidie, Ahmed Al-Asadi, Amjad J. Humaidi, Omran Al-Shamma, Mohammed A. Fadhel, Jinglan Zhang, J. Santamaría, and Ye Duan. "Novel Transfer Learning Approach for Medical Imaging with Limited Labeled Data." Cancers 13, no. 7 (March 30, 2021): 1590. http://dx.doi.org/10.3390/cancers13071590.
Full textAbstract:
Deep learning requires a large amount of data to perform well. However, the field of medical image analysis suffers from a lack of sufficient data for training deep learning models. Moreover, medical images require manual labeling, usually provided by human annotators coming from various backgrounds. More importantly, the annotation process is time-consuming, expensive, and prone to errors. Transfer learning was introduced to reduce the need for the annotation process by transferring the deep learning models with knowledge from a previous task and then by fine-tuning them on a relatively small dataset of the current task. Most of the methods of medical image classification employ transfer learning from pretrained models, e.g., ImageNet, which has been proven to be ineffective. This is due to the mismatch in learned features between the natural image, e.g., ImageNet, and medical images. Additionally, it results in the utilization of deeply elaborated models. In this paper, we propose a novel transfer learning approach to overcome the previous drawbacks by means of training the deep learning model on large unlabeled medical image datasets and by next transferring the knowledge to train the deep learning model on the small amount of labeled medical images. Additionally, we propose a new deep convolutional neural network (DCNN) model that combines recent advancements in the field. We conducted several experiments on two challenging medical imaging scenarios dealing with skin and breast cancer classification tasks. According to the reported results, it has been empirically proven that the proposed approach can significantly improve the performance of both classification scenarios. In terms of skin cancer, the proposed model achieved an F1-score value of 89.09% when trained from scratch and 98.53% with the proposed approach. Secondly, it achieved an accuracy value of 85.29% and 97.51%, respectively, when trained from scratch and using the proposed approach in the case of the breast cancer scenario. Finally, we concluded that our method can possibly be applied to many medical imaging problems in which a substantial amount of unlabeled image data is available and the labeled image data is limited. Moreover, it can be utilized to improve the performance of medical imaging tasks in the same domain. To do so, we used the pretrained skin cancer model to train on feet skin to classify them into two classes—either normal or abnormal (diabetic foot ulcer (DFU)). It achieved an F1-score value of 86.0% when trained from scratch, 96.25% using transfer learning, and 99.25% using double-transfer learning.
35
Liu, Lanfa, Min Ji, and Manfred Buchroithner. "Transfer Learning for Soil Spectroscopy Based on Convolutional Neural Networks and Its Application in Soil Clay Content Mapping Using Hyperspectral Imagery." Sensors 18, no. 9 (September 19, 2018): 3169. http://dx.doi.org/10.3390/s18093169.
Full textAbstract:
Soil spectra are often measured in the laboratory, and there is an increasing number of large-scale soil spectral libraries establishing across the world. However, calibration models developed from soil libraries are difficult to apply to spectral data acquired from the field or space. Transfer learning has the potential to bridge the gap and make the calibration model transferrable from one sensor to another. The objective of this study is to explore the potential of transfer learning for soil spectroscopy and its performance on soil clay content estimation using hyperspectral data. First, a one-dimensional convolutional neural network (1D-CNN) is used on Land Use/Land Cover Area Frame Survey (LUCAS) mineral soils. To evaluate whether the pre-trained 1D-CNN model was transferrable, LUCAS organic soils were used to fine-tune and validate the model. The fine-tuned model achieved a good accuracy (coefficient of determination (R2) = 0.756, root-mean-square error (RMSE) = 7.07 and ratio of percent deviation (RPD) = 2.26) for the estimation of clay content. Spectral index, as suggested as a simple transferrable feature, was also explored on LUCAS data, but did not performed well on the estimation of clay content. Then, the pre-trained 1D-CNN model was further fine-tuned by field samples collect in the study area with spectra extracted from HyMap imagery, achieved an accuracy of R2 = 0.601, RMSE = 8.62 and RPD = 1.54. Finally, the soil clay map was generated with the fine-tuned 1D-CNN model and hyperspectral data.
36
Awang Iskandar, Dayang N. F., Albert A. Zijlstra, Iain McDonald, Rosni Abdullah, Gary A. Fuller, Ahmad H. Fauzi, and Johari Abdullah. "Classification of Planetary Nebulae through Deep Transfer Learning." Galaxies 8, no. 4 (December 11, 2020): 88. http://dx.doi.org/10.3390/galaxies8040088.
Full textAbstract:
This study investigate the effectiveness of using Deep Learning (DL) for the classification of planetary nebulae (PNe). It focusses on distinguishing PNe from other types of objects, as well as their morphological classification. We adopted the deep transfer learning approach using three ImageNet pre-trained algorithms. This study was conducted using images from the Hong Kong/Australian Astronomical Observatory/Strasbourg Observatory H-alpha Planetary Nebula research platform database (HASH DB) and the Panoramic Survey Telescope and Rapid Response System (Pan-STARRS). We found that the algorithm has high success in distinguishing True PNe from other types of objects even without any parameter tuning. The Matthews correlation coefficient is 0.9. Our analysis shows that DenseNet201 is the most effective DL algorithm. For the morphological classification, we found for three classes, Bipolar, Elliptical and Round, half of objects are correctly classified. Further improvement may require more data and/or training. We discuss the trade-offs and potential avenues for future work and conclude that deep transfer learning can be utilized to classify wide-field astronomical images.
37
Alzubaidi, Laith, Mohammed A. Fadhel, Omran Al-Shamma, Jinglan Zhang, J. Santamaría, Ye Duan, and Sameer R. Oleiwi. "Towards a Better Understanding of Transfer Learning for Medical Imaging: A Case Study." Applied Sciences 10, no. 13 (June 29, 2020): 4523. http://dx.doi.org/10.3390/app10134523.
Full textAbstract:
One of the main challenges of employing deep learning models in the field of medicine is a lack of training data due to difficulty in collecting and labeling data, which needs to be performed by experts. To overcome this drawback, transfer learning (TL) has been utilized to solve several medical imaging tasks using pre-trained state-of-the-art models from the ImageNet dataset. However, there are primary divergences in data features, sizes, and task characteristics between the natural image classification and the targeted medical imaging tasks. Therefore, TL can slightly improve performance if the source domain is completely different from the target domain. In this paper, we explore the benefit of TL from the same and different domains of the target tasks. To do so, we designed a deep convolutional neural network (DCNN) model that integrates three ideas including traditional and parallel convolutional layers and residual connections along with global average pooling. We trained the proposed model against several scenarios. We utilized the same and different domain TL with the diabetic foot ulcer (DFU) classification task and with the animal classification task. We have empirically shown that the source of TL from the same domain can significantly improve the performance considering a reduced number of images in the same domain of the target dataset. The proposed model with the DFU dataset achieved F1-score value of 86.6% when trained from scratch, 89.4% with TL from a different domain of the targeted dataset, and 97.6% with TL from the same domain of the targeted dataset.
38
Ning, Liang, Michael E. Mann, Robert Crane, and Thorsten Wagener. "Probabilistic Projections of Climate Change for the Mid-Atlantic Region of the United States: Validation of Precipitation Downscaling during the Historical Era*." Journal of Climate 25, no. 2 (January 15, 2012): 509–26. http://dx.doi.org/10.1175/2011jcli4091.1.
Full textAbstract:
Abstract This study uses a statistical downscaling method based on self-organizing maps (SOMs) to produce high-resolution, downscaled precipitation estimates over the state of Pennsylvania in the mid-Atlantic region of the United States. The SOMs approach derives a transfer function between large-scale mean atmospheric states and local meteorological variables (daily point precipitation values) of interest. First, the SOM was trained using seven coarsely resolved atmospheric variables from the National Centers for Environmental Prediction (NCEP) reanalysis dataset to model observed daily precipitation data from 17 stations across Pennsylvania for the period 1979–2005. Employing the same coarsely resolved variables from nine general circulation model (GCM) simulations taken from the historical analysis of the Coupled Model Intercomparison Project, phase 3 (CMIP3), the trained SOM was subsequently applied to simulate daily precipitation at the same 17 sites for the period 1961–2000. The SOM analysis indicates that the nine model simulations exhibit similar synoptic-scale features to the (NCEP) observations over the 1979–2007 training interval. An analysis of the sea level pressure signatures and the precipitation distribution corresponding to the trained SOM shows that it is effective in differentiating characteristic synoptic circulation patterns and associated precipitation. The downscaling approach provides a faithful reproduction of the observed probability distributions and temporal characteristics of precipitation on both daily and monthly time scales. The downscaled precipitation field shows significant improvement over the raw GCM precipitation fields with regard to observed average monthly precipitation amounts, average monthly number of rainy days, and standard deviations of monthly precipitation amounts, although certain caveats are noted.
39
Shrivastava, V. K., M. K. Pradhan, S. Minz, and M. P. Thakur. "RICE PLANT DISEASE CLASSIFICATION USING TRANSFER LEARNING OF DEEP CONVOLUTION NEURAL NETWORK." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-3/W6 (July 26, 2019): 631–35. http://dx.doi.org/10.5194/isprs-archives-xlii-3-w6-631-2019.
Full textAbstract:
<p><strong>Abstract.</strong> Early and accurate diagnosis of plant diseases is a vital step in the crop protection system. In traditional practices, identification is performed either by visual observation or by testing in laboratory. The visual observation requires expertise and it may vary subject to an individual which may lead to an error while the laboratory test is time consuming and may not be able to provide the results in time. To overcome these issues, image based machine learning approach to detect and classify plant diseases has been presented in literature. We have focused specifically on rice plant (<i>Oryza sativa</i>) disease in this paper. The images of the diseased symptoms in leaves and stems have been captured from the rice field. We have collected a total of 619 rice plant diseased images from the real field condition belong to four classes:(a) Rice Blast (RB), (b) Bacterial Leaf Blight (BLB), (c) Sheat Blight (SB) and (d) Healthy Leave (HL). We have used a pre-trained deep convolutional neural network(CNN) as a feature extractor and Support Vector Machine (SVM) as a classifier. We have obtained encouraging results. The early identification of rice diseases by this approach could be used as a preventive measure well as an early warning system. Further, it could be extended to develop a rice plant disease identification system on real agriculture field.</p>
40
Gribbestad, Magnus, Muhammad Umair Hassan, and Ibrahim A. Hameed. "Transfer Learning for Prognostics and Health Management (PHM) of Marine Air Compressors." Journal of Marine Science and Engineering 9, no. 1 (January 4, 2021): 47. http://dx.doi.org/10.3390/jmse9010047.
Full textAbstract:
Prognostics is an engineering discipline focused on predicting the time at which a system or a component will no longer perform its intended function. Due to the requirements of system safety and reliability, the correct diagnosis or prognosis of abnormal condition plays a vital role in the maintenance of industrial systems. It is expected that new requirements in regard to autonomous ships will push suppliers of maritime equipment to provide more insight into the conditions of their systems. One of the stated challenges with these systems is having enough run-to-failure examples to build accurate-enough prognostic models. Due to the scarcity of enough reliable data, transfer learning is established as a successful approach to improve and reduce the need to labelled examples. Transfer learning has shown excellent capabilities in image classification problems. Little work has been done to explore and exploit the use of transfer learning in prognostics. In this paper, various deep learning models are used to predict the remaining useful life (RUL) of air compressors. Here, transfer learning is applied by building a separate prognostics model trained on turbofan engines. It has been found that several of the explored transfer learning architectures were able to improve the predictions on air compressors. The research results suggest transfer learning as a promising research field towards more accurate and reliable prognostics.
41
Tang, Chia-Pei, Kai-Hong Chen, and Tu-Liang Lin. "Computer-Aided Colon Polyp Detection on High Resolution Colonoscopy Using Transfer Learning Techniques." Sensors 21, no. 16 (August 6, 2021): 5315. http://dx.doi.org/10.3390/s21165315.
Full textAbstract:
Colonoscopies reduce the incidence of colorectal cancer through early recognition and resecting of the colon polyps. However, the colon polyp miss detection rate is as high as 26% in conventional colonoscopy. The search for methods to decrease the polyp miss rate is nowadays a paramount task. A number of algorithms or systems have been developed to enhance polyp detection, but few are suitable for real-time detection or classification due to their limited computational ability. Recent studies indicate that the automated colon polyp detection system is developing at an astonishing speed. Real-time detection with classification is still a yet to be explored field. Newer image pattern recognition algorithms with convolutional neuro-network (CNN) transfer learning has shed light on this topic. We proposed a study using real-time colonoscopies with the CNN transfer learning approach. Several multi-class classifiers were trained and mAP ranged from 38% to 49%. Based on an Inception v2 model, a detector adopting a Faster R-CNN was trained. The mAP of the detector was 77%, which was an improvement of 35% compared to the same type of multi-class classifier. Therefore, our results indicated that the polyp detection model could attain a high accuracy, but the polyp type classification still leaves room for improvement.
42
Gallwey, Eyre, Tonkins, and Coggan. "Bringing Lunar LiDAR Back Down to Earth: Mapping Our Industrial Heritage through Deep Transfer Learning." Remote Sensing 11, no. 17 (August 23, 2019): 1994. http://dx.doi.org/10.3390/rs11171994.
Full textAbstract:
This article presents a novel deep learning method for semi-automated detection of historic mining pits using aerial LiDAR data. The recent emergence of national scale remotely sensed datasets has created the potential to greatly increase the rate of analysis and recording of cultural heritage sites. However, the time and resources required to process these datasets in traditional desktop surveys presents a near insurmountable challenge. The use of artificial intelligence to carry out preliminary processing of vast areas could enable experts to prioritize their prospection focus; however, success so far has been hindered by the lack of large training datasets in this field. This study develops an innovative transfer learning approach, utilizing a deep convolutional neural network initially trained on Lunar LiDAR datasets and reapplied here in an archaeological context. Recall rates of 80% and 83% were obtained on the 0.5 m and 0.25 m resolution datasets respectively, with false positive rates maintained below 20%. These results are state of the art and demonstrate that this model is an efficient, effective tool for semi-automated object detection for this type of archaeological objects. Further tests indicated strong potential for detection of other types of archaeological objects when trained accordingly.
43
Gao, Guo Dong, Wen Xiao Zhang, Gong Zhi Yu, and Jiang Hua Sui. "Research on Dissolve Oxygen Modeling Based on Neural Network." Advanced Materials Research 287-290 (July 2011): 2640–43. http://dx.doi.org/10.4028/www.scientific.net/amr.287-290.2640.
Full textAbstract:
The structure, characteristics and principles of BP neural network model are described in this paper. First, three impact factors of the dissolved oxygen are selected as the sample input of network, and then the parameters of BP neural network are selected, such as network structure, learning algorithm, output layer transfer function, learning rate and so on. Finally, the BP neural network model is established and trained, in order to approach compensate the effects of improves non-linearity. The simulation results show that BP neural network is practical and dependable in the field of dissolved oxygen modeling and has nice applied prospect.
44
Chahla, C., H. Snoussi, F. Abdallah, and F. Dornaika. "Learned versus Handcrafted Features for Person Re-identification." International Journal of Pattern Recognition and Artificial Intelligence 34, no. 04 (August 9, 2019): 2055009. http://dx.doi.org/10.1142/s0218001420550095.
Full textAbstract:
Person re-identification is one of the indispensable elements for visual surveillance. It assigns consistent labeling for the same person within the field of view of the same camera or even across multiple cameras. While handcrafted feature extraction is certainly one way of approaching this problem, in many cases, these features are becoming more and more complex. Besides, training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. This paper explores the following three main strategies for solving the person re-identification problem: (i) using handcrafted features, (ii) using transfer learning based on a pre-trained deep CNN (trained for object categorization) and (iii) training a deep CNN from scratch. Our experiments consistently demonstrated that: (1) The handcrafted features may still have favorable characteristics and benefits especially in cases where the learning database is not sufficient to train a deep network. (2) A fully trained Siamese CNN outperforms handcrafted approaches and the combination of pre-trained CNN with different re-identification processes. (3) Moreover, our experiments demonstrated that pre-trained features and handcrafted features perform equally well. These experiments have also revealed the most discriminative parts in the human body.
45
Montalbo, Francis Jesmar Perez, and Alexander Arsenio Hernandez. "Classifying Barako coffee leaf diseases using deep convolutional models." International Journal of Advances in Intelligent Informatics 6, no. 2 (July 12, 2020): 197. http://dx.doi.org/10.26555/ijain.v6i2.495.
Full textAbstract:
This work presents the application of recent Deep Convolutional Models (DCM) to classify Barako leaf diseases. Several selected DCMs performed image classification tasks using Transfer Learning and Fine-Tuning, together with data preprocessing and augmentation. The collected dataset used totals to 4,667. Each labeled into four different classes, which included Coffee Leaf Rust (CLR), Cercospora Leaf Spots (CLS), Sooty Molds (SM), and Healthy Leaves (HL). The DCMs were trained using the partial 4,023 images and validated with the remaining 644. The classification results of the trained models VGG16, Xception, and ResNetV2-152 attained overall accuracies of 97%, 95%, and 91%, respectively. By comparing in terms of True Positive Rate (TPR), we found that Xception has the highest number of correct classifications of CLR, VGG16 with SM, and CLS, while ResNetV2-152 with the lowest TPR for CLR. The evaluated results indicate that the use of Deep Convolutional Models with an adequate amount of data, proper fine-tuning, preprocessing, and transfer learning can yield efficient classifiers for identifying several Barako leaf diseases. This work primarily contributes to the growing field of deep learning, specifically for helping farmers improve their diagnostic process by providing a solution that can automatically classify Barako leaf diseases.
46
Qiang, Bo, Junyong Lai, Hongwei Jin, Liangren Zhang, and Zhenming Liu. "Target Prediction Model for Natural Products Using Transfer Learning." International Journal of Molecular Sciences 22, no. 9 (April 28, 2021): 4632. http://dx.doi.org/10.3390/ijms22094632.
Full textAbstract:
A large proportion of lead compounds are derived from natural products. However, most natural products have not been fully tested for their targets. To help resolve this problem, a model using transfer learning was built to predict targets for natural products. The model was pre-trained on a processed ChEMBL dataset and then fine-tuned on a natural product dataset. Benefitting from transfer learning and the data balancing technique, the model achieved a highly promising area under the receiver operating characteristic curve (AUROC) score of 0.910, with limited task-related training samples. Since the embedding distribution difference is reduced, embedding space analysis demonstrates that the model’s outputs of natural products are reliable. Case studies have proved our model’s performance in drug datasets. The fine-tuned model can successfully output all the targets of 62 drugs. Compared with a previous study, our model achieved better results in terms of both AUROC validation and its success rate for obtaining active targets among the top ones. The target prediction model using transfer learning can be applied in the field of natural product-based drug discovery and has the potential to find more lead compounds or to assist researchers in drug repurposing.
47
Kandel, Ibrahem, and Mauro Castelli. "Transfer Learning with Convolutional Neural Networks for Diabetic Retinopathy Image Classification. A Review." Applied Sciences 10, no. 6 (March 16, 2020): 2021. http://dx.doi.org/10.3390/app10062021.
Full textAbstract:
Diabetic retinopathy (DR) is a dangerous eye condition that affects diabetic patients. Without early detection, it can affect the retina and may eventually cause permanent blindness. The early diagnosis of DR is crucial for its treatment. However, the diagnosis of DR is a very difficult process that requires an experienced ophthalmologist. A breakthrough in the field of artificial intelligence called deep learning can help in giving the ophthalmologist a second opinion regarding the classification of the DR by using an autonomous classifier. To accurately train a deep learning model to classify DR, an enormous number of images is required, and this is an important limitation in the DR domain. Transfer learning is a technique that can help in overcoming the scarcity of images. The main idea that is exploited by transfer learning is that a deep learning architecture, previously trained on non-medical images, can be fine-tuned to suit the DR dataset. This paper reviews research papers that focus on DR classification by using transfer learning to present the best existing methods to address this problem. This review can help future researchers to find out existing transfer learning methods to address the DR classification task and to show their differences in terms of performance.
48
Idrissi, Idriss, Mostafa Azizi, and Omar Moussaoui. "Accelerating the update of a DL-based IDS for IoT using deep transfer learning." Indonesian Journal of Electrical Engineering and Computer Science 23, no. 2 (August 1, 2021): 1059. http://dx.doi.org/10.11591/ijeecs.v23.i2.pp1059-1067.
Full textAbstract:
<p>Deep learning (DL) models are nowadays broadly applied and have shown outstanding performance in a variety of fields, including our focus topic of "IoTcybersecurity". Deep learning-based intrusion detection system (DL-IDS) models are more fixated and depended on the trained dataset. This poses a problem for these DL-IDS, especially with the known mutation and behavior changes of attacks, which can render them undetected. As a result, the DL-IDShas become outdated. In this work, we present a solution for updating DL-ID Semploying a transfer learning technique that allows us to retrain and fine-tune pre-trained models on small datasets with new attack behaviors. In our experiments, we built CNN-based IDS on the Bot-IoT dataset and updated it on small data from a new dataset named TON-IoT. We obtained promising results in multiple metrics regarding the detection rate and the training between the initial training for the original model and the updated one, in the matter of detecting new attacks behaviors and improving the detection rate for some classes by overcoming the lack of their labeled data.</p>
49
Al-Saegh, Ali. "Off-line Signature Recognition Using Weightless Neural Network and Feature Extraction." Iraqi Journal for Electrical and Electronic Engineering 11, no. 1 (June 1, 2015): 124–31. http://dx.doi.org/10.37917/ijeee.11.1.13.
Full textAbstract:
The problem of automatic signature recognition and verification has been extensively investigated due to the vitality of this field of research. Handwritten signatures are broadly used in daily life as a secure way for personal identification. In this paper a novel approach is proposed for handwritten signature recognition in an off-line environment based on Weightless Neural Network (WNN) and feature extraction. This type of neural networks (NN) is characterized by its simplicity in design and implementation. Whereas no weights, transfer functions and multipliers are required. Implementing the WNN needs only Random Access Memory (RAM) slices. Moreover, the whole process of training can be accomplished with few numbers of training samples and by presenting them once to the neural network. Employing the proposed approach in signature recognition area yields promising results with rates of 99.67% and 99.55% for recognition of signatures that the network has trained on and rejection of signatures that the network .has not trained on, respectively.
50
Falzon, Greg, Christopher Lawson, Ka-Wai Cheung, Karl Vernes, Guy A. Ballard, Peter J. S. Fleming, Alistair S. Glen, Heath Milne, Atalya Mather-Zardain, and Paul D. Meek. "ClassifyMe: A Field-Scouting Software for the Identification of Wildlife in Camera Trap Images." Animals 10, no. 1 (December 27, 2019): 58. http://dx.doi.org/10.3390/ani10010058.
Full textAbstract:
We present ClassifyMe a software tool for the automated identification of animal species from camera trap images. ClassifyMe is intended to be used by ecologists both in the field and in the office. Users can download a pre-trained model specific to their location of interest and then upload the images from a camera trap to a laptop or workstation. ClassifyMe will identify animals and other objects (e.g., vehicles) in images, provide a report file with the most likely species detections, and automatically sort the images into sub-folders corresponding to these species categories. False Triggers (no visible object present) will also be filtered and sorted. Importantly, the ClassifyMe software operates on the user’s local machine (own laptop or workstation)—not via internet connection. This allows users access to state-of-the-art camera trap computer vision software in situ, rather than only in the office. The software also incurs minimal cost on the end-user as there is no need for expensive data uploads to cloud services. Furthermore, processing the images locally on the users’ end-device allows them data control and resolves privacy issues surrounding transfer and third-party access to users’ datasets.