Rock Segmentation in the Navigation Vision of the Planetary Rovers

Visual navigation is an essential part of planetary rover autonomy. Rock segmentation emerged as an important interdisciplinary topic among image processing, robotics, and mathematical modeling. Rock segmentation is a challenging topic for rover autonomy because of the high computational consumption, real-time requirement, and annotation difficulty. This research proposes a rock segmentation framework and a rock segmentation network (NI-U-Net++) to aid with the visual navigation of rovers. The framework consists of two stages: the pre-training process and the transfer-training process. The pre-training process applies the synthetic algorithm to generate the synthetic images; then, it uses the generated images to pre-train NI-U-Net++. The synthetic algorithm increases the size of the image dataset and provides pixel-level masks—both of which are challenges with machine learning tasks. The pre-training process accomplishes the state-of-the-art compared with the related studies, which achieved an accuracy, intersection over union (IoU), Dice score, and root mean squared error (RMSE) of 99.41%, 0.8991, 0.9459, and 0.0775, respectively. The transfer-training process fine-tunes the pre-trained NI-U-Net++ using the real-life images, which achieved an accuracy, IoU, Dice score, and RMSE of 99.58%, 0.7476, 0.8556, and 0.0557, respectively. Finally, the transfer-trained NI-U-Net++ is integrated into a planetary rover navigation vision and achieves a real-time performance of 32.57 frames per second (or the inference time is 0.0307 s per frame). The framework only manually annotates about 8% (183 images) of the 2250 images in the navigation vision, which is a labor-saving solution for rock segmentation tasks. The proposed rock segmentation framework and NI-U-Net++ improve the performance of the state-of-the-art models. The synthetic algorithm improves the process of creating valid data for the challenge of rock segmentation. All source codes, datasets, and trained models of this research are openly available in Cranfield Online Research Data (CORD).

Evaluating Construct Validity and Reliability of Intention to Transfer Training Conduct Instrument Using Rasch Model Analysis

The impact of the Industry Revolution 4.0 (IR4.0) in the workplace requires organisations to ensure clerical employees can effectively transfer their newly acquired knowledge and skills learned in training back into the workplace. Hence, an instrument is required to identify factors influencing the intention to transfer training conduct amongst clerical employees. Thus, this paper presents the evaluation of construct validity and reliability of the new instrument to confirm its objectivity and clarity in measuring the constructs under study as intended. This four-point Likert-type scale instrument consists of 72 self-assessment items that represent 12 constructs. The Rasch Model was then employed to analyse the construct validity and reliability by evaluating the suitability of items in the respective constructs on the instrument. The item and person reliability and strata indices, point-measure correlation, and outfit mean square values were examined. The analysis found that three constructs in the item and person reliability index and eight constructs in the item and person reliability strata index were low but adequate and met the Rasch Model measurement acceptable level. Meanwhile, point-measure correlation values for all constructs fulfilled the criteria. Finally, the outfit mean square values established that 65 items in the constructs were found to be fit, whereas seven items were misfits which require improvement. Subsequently, the seven misfit items were improved as the item and person reliability values could be increased, thus the items were retained. Thereafter, the instrument was ready to be used for data collection in the actual study.

Devising a method for recognizing the causes of deviations in the development of the plant Aloe arborescens L. using machine learning capabilities

This paper considers the process of developing a method to recognize the causes of plant growth deviations from normal using the advancements in artificial intelligence. The medicinal plant Aloe arborescens L. was chosen as the object of this research given that this plant had been for decades one of the best-selling new products in the world. Aloe arborescens L. is famous for its medicinal properties used in medicine, cosmetology, and even the food industry. Diagnosing the abnormalities in the plant development in a timely and accurate manner plays an important role in preventing the loss of crop production yields. The current study has built a method for recognizing the causes of abnormalities in the development of Aloe arborescens L. caused by a lack of watering or lighting, based on the use of transfer training of the VGG-16 convolutional neural network (United Kingdom). A given architecture is aimed at recognizing objects in images, which is the main reason for using it to achieve the goal set. The analysis of the quality metrics of the proposed image classification process by specified classes has revealed high recognition reliability (for a normally developing plant, 91 %; for a plant without proper watering, 89 %; and for a plant without proper lighting, 83 %). The analysis of the validity of test sample recognition has demonstrated a similar validity of the plant's classification to one of three classes: 92.6 %; 87.5 %; and 85.5 %, respectively. The results reported here make it possible to supplement the automated systems that control the mode parameters of hydroponic installations by the world's major producers with the main feedback on the deviation of the plant's development from the specified values

Object Recognition in Remote Sensing Images Based on Modified Backpropagation Neural Network

In the area of remote sensing, one of the problems is how high-quality remote sensing images are automatically categorized and classified. There have been many suggestions for alternatives. Amongst these, there are drawbacks of approaches focused on low visual and intermediate visual characteristics. This article, therefore, adopts the deep learning method for classifying high-resolution remote sensing picture scenes to learn semantic knowledge. Most of the existing neural network convolution approaches are focused on the model of transfer training and there are comparatively like hidden Marco models, linear fitting methods, the creation of new neural networks based on the latest high-resolution remote sensing picture data sets. But in this paper, we used a modified backpropagation neural network is proposed to detect the objects in images. To test the performance of the proposed model we use two remote sensing data sets benchmark tests were done. The test-precision, precision, reminder, and F1 scores are all fine with the Assist data collection. The precision, precision, reminder, and F1 score are all enhanced on the SIRI-WHU dataset. The proposed system has better precision and robustness compared to the current approaches including the most conventional methods and certain profound learning methods to scene distinguish high-resolution remote sensing pictures.

Exploring readiness of learners to transfer training: an interactionist approach

Purpose Purpose of this study is to investigate the role of learner readiness in enhancing transfer of training by empirically testing a moderated mediation mechanism in which learner readiness influences transfer through motivation to transfer, and this indirect impact is moderated by supervisor support. Design/methodology/approach The perception of trainees about the constructs considered has been captured through a survey of 250 employees of a unit of a manufacturing organization in India. For hypotheses testing, PROCESS macro developed by Hayes (2013) has been used. Findings Results have confirmed the significant role played by learner readiness in predicting transfer. This apart, supervisor support has been proved to moderate the indirect impact of learner readiness on transfer. Practical implications Trainees need to have pre-requisite knowledge to learn the content of a training programme, which would enable them to grasp such content and transfer the same subsequently to work. It is also essential that trainees are willing to attend any training voluntarily. Specific interventions may be designed for supervisors to bolster their catalytic role in training transfer. Originality/value An interactionist approach has been adopted by focussing on learner readiness as a less-studied trainee characteristic and supervisor support as a situational factor of transfer. This is construed as a significant contribution of this study to training literature. The potential overlap between learner readiness and motivation to transfer as trainee characteristics is seen to be neutralized by the presence of supervisor support as a moderator. Findings help in understanding how a trainee’s readiness and motivation, together with supervisor’s positive attitude, can enhance transfer.

An approach to rapid processing of camera trap images with minimal human input

Point 1: Camera traps have become an extensively utilized tool in ecological research, but the processing of images created by a network of camera traps rapidly becomes an overwhelming task, even for small networks. Point 2: We used transfer training to create convolutional neural network (CNN) models for identification and classification. By utilizing a small dataset with less than 10,000 labeled images the model was able to distinguish between species and remove false triggers. Point 3: We trained the model to detect 17 object classes with individual species identification, reaching an accuracy of 92%. Previous studies have suggested the need for thousands of images of each object class to reach results comparable to those achieved by human observers; however, we show that such accuracy can be achieved with fewer images. Point 4: Additionally, we suggest several alternative metrics common to computer science studies to accurately evaluate the performance of such camera trap image processing models, as well as methods to adapt the model building process to two targeted purposes.