ABSTRACT Human infant learning happens during exploration of the environment, by interaction with objects, and by listening to and repeating utterances casually, which is analogous to unsupervised learning. Only occasionally, a learning infant would receive a matching verbal description of an action it is committing, which is similar to supervised learning. Such a learning mechanism can be mimicked with deep learning. We model this weakly supervised learning paradigm using our Paired Gated Autoencoders (PGAE) model, which combines an action and a language autoencoder. After observing a performance drop when reducing the proportion of supervised training, we introduce the Paired Transformed Autoencoders (PTAE) model, using Transformer-based crossmodal attention. PTAE achieves significantly higher accuracy in language-to-action and action-to-language translations, particularly in realistic but difficult cases when only few supervised training samples are available. We also test whether the trained model behaves realistically with conflicting multimodal input. In accordance with the concept of incongruence in psychology, conflict deteriorates the model output. Conflicting action input has a more severe impact than conflicting language input, and more conflicting features lead to larger interference. PTAE can be trained on mostly unlabeled data where labeled data is scarce, and it behaves plausibly when tested with incongruent input.

ABSTRACT Reversible lanes play an important role in alleviating urban traffic congestion and improving the utilization of road resources. However, most of the reversible lanes currently implemented are timed and fixed, and there is little research on the safety of reversible lanes without isolation facilities. In view of the existing problems of reversible lanes, this paper proposed a real-time dynamic reversible lane safety control model. The influencing factors of reversible lane safety control are analyzed first, and then determine model parameters of the no-entry zone and the buffer zone in the conflict area. Moreover, model parameters of emptying, exit, and recovery zones in the operation process were determined as well. Additionally, this paper discussed the length of reversible lanes and the timing of signals. The surrogate safety assessment model (SSAM) is adopted to analyze vehicle trajectory data for traffic simulation under different traffic flows. The experiment results show that the proposed reversible lane safety control scheme can keep the vehicle’s traffic conflict rate below 5%, which can effectively ensure the safe operation of the reversible lane.

ABSTRACT Crop yield forecasting has been well studied in recent decades and is significant in protecting food security. Crop growth is a complex phenomenon that depends on various factors. Machine learning and deep learning trends have emerged as important innovations in this field. We propose to utilize crop, weather, and soil data from agricultural datasets to evaluate yield prediction behavior. Paddy being a staple food crop in India is chosen for this research. In this paper, we propose hybrid architecture for paddy yield prediction, namely, MLR-LSTM, which combines Multiple Linear Regression and Long Short-Term Memory to utilize their complementary nature. The results are compared with traditional machine learning methods such as Support vector machine, Long short-term memory and Random forest method. Evaluation metrics such as Coefficient of Determination (R2), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE), F1 score, Recall, and Precision are used to evaluate the hybrid method and traditional models. The results obtained from the proposed hybrid method indicates that the hybrid model delivers better R2, RMSE, MAE, MSE values of 0.93, 0.1549, 0.199, and 0.024 respectively.

ABSTRACT Early identification of potato diseases is of great significance for reducing yield losses. The identification of different types of diseases has achieved great success. However, for different periods of different disease, it is difficult to distinguish due to similar symptoms and fine-grained, so there are few related studies. In this study, we proposed a convolutional neural network based on contrastive learning to identify fine-grained potato diseases. Different from the previous unsupervised contrastive learning used in pre-training, the proposed model adds a projection head to the backbone network of Vgg16 to extract the contrastive representation features, and then integrates the contrastive loss with the classification loss to form a joint loss. Finally, an end-to-end supervised contrastive convolutional neural network is constructed, which is easier to train while reducing the transmission error. Experimental results show that the proposed model achieves an average recognition accuracy of 97.24%, which is higher than 90.28% of Resnet50, 90.62% of Resnet101, 93.06% of AlexNet, 94.44% of Inception V3, and 94.79% of Vgg16. It shows that the model has an obvious effect on classification task with similar features, and has practical significance for fine-grained potato disease identification.

ABSTRACT The use of natural language processing in human resource management has become of paramount importance in order to provide support for recruiting and corporate population management. This paper proposes a heuristic algorithm to solve two problems: (i) semantic matching among heterogeneous datasets storing the hard skills possessed by the company’s employees to obtain a homogeneous catalog, according to the O*NET and ESCO competence dictionaries, and (ii) inferring the employee’s soft skills with respect to his/her own declaration of interests, work experience, certifications, etc., given his/her curriculum vitae. Empirical results demonstrate that the proposed approach yields improved performance results by comparison with baseline methods available in the literature.

ABSTRACT Student dropout in secondary schools is a major issue in developing countries, particularly in Sub-Saharan Africa. Sub-Saharan African countries had the highest dropout rate (37.5%), followed by South Asia (15.5%), the Middle East (11%), East Asia (9.5%), Latin America (7%), and Central Asia (3.5%). Various initiatives such as the big results now initiatives, no child left behind, and secondary education development programme as well as machine learning prediction models have been used to reduce the severity of the problem in Sub-Saharan countries. The ongoing dropout problem, particularly in secondary schools is ascribed to improper root cause identification and the absence of formal procedures that can be used to estimate the severity of the issue. This study has compared the AutoML model, ensemble learning approach, and KNORA-AutoML to predict student dropout problems. The KNORA-AutoML model scored 97% of accuracy, precision = 71%, and AUC = 87% when compared to the conventional ensemble of optimized ML models with accuracy = 96%, precision = 70%, and AUC = 78%. KNORA-AutoML model performance increased by 0.6% accuracy, 0.8% precision, and 8.7% AUC. An optimized model draws a lot of attention to the findings related to student dropout rates in developing countries.

ABSTRACT In today’s world, people need sleeker devices with better functionality and longer battery life. This can be achieved by integrating more components onto smaller chips, resulting in a shift to low-geometry chip design. However, power dissipation due to dynamic and static currents is more prominent in all ICs, resulting in an increase in overall power consumption. Estimating power dissipation early will provide more accurate usage of power pads/strips and help floor plan engineers do power planning efficiently. As you provide more details about your design characteristics, the estimation of power will be accurate. The major focus of this work is to give an alternative solution to predict the power dissipation of integrated circuits using a machine learning approach in both pre and post layout. The proposed work uses supervision models and algorithms like Linear regression, KNN, SVM, and RF for power prediction and a comparative study is made between power estimates made using ML algorithms and by the Cadence EDA tool for a particular technology for various bench circuits. The average error is less than 4% when we compare the estimated power using ML and by using the Cadence EDA tool and shows that for estimation of power in integrated circuits, Random Forest is a well-suited algorithm with an error percentage varying from 2 to 4.

ABSTRACT Robot swarm can be given with different functions such as ground cruising, wall climbing, and each robot is implemented with a choice from such functions. Regarding ground mobility, findings on ant swarm in biology indicate that Temnothorax albipennis ant swarm including many immobile individuals accomplishes efficient migration. Our previous work revealed that 60% of active population is enough to achieve such goal and the conclusion is consistent with field studies of biologists. However, the impacts of active population ratio (active ratio) rather than species-specific elements have not been clear enough yet. Here, hypothesizing that efficient swarm migration could be generated by lowering active ratio, we removed species-specific elements from simulation and challenged particle swarm optimization (PSO) to emulate the migration and visualize global status of the swarm with simple parameter configurations. Our statistical analysis shows that the performance simulation outcomes of the algorithm are equivalent between each active-ratios of 60% and 100%. Heterogeneity of ground mobility of individuals has not put any negative impacts on efficient swarm migration. Statistical visualization of the outcomes provides the basis for evaluation of global status of swarm migration and it can lead to exploration of robot swarm migration involving functional heterogeneity of ground mobility.

ABSTRACT Recently, land cover and land use (LCLU) classification in remote sensing imagery has attracted research interest. The LCLU contains dynamic remote sensed images due to sensor technology ability, seasonal changes, and distance for resolution. Therefore, the deep learning-based LCLU classification system needs more investigation using deep learning techniques. Deep learning approaches have gotten more attention for their powerful performance improvements. Most recent studies have been performed on deep convolutional neural networks (CNNs) that have been trained on pre-trained networks in remote sensing classification. However, designing CNNs from scratch has not yet been widely investigated in remote sensed images as they need ample training time and a powerful processor. Therefore, we used hyperparameters and early stopping techniques to apply an end-to-end CNN feature extractor (CNN-FE) model for LCLU classification in the UC-Merced dataset. We approved the model's applicability in the domain area by retraining it on another dataset called SIRI-WHU and building the VGG19 pre-trained feature extractor model built on the same hyperparameters. The CNN-FE has outperformed the state-of-the-art baseline studies' accuracy and the VGG19 pre-trained model. Moreover, a better CNN-FE performance was achieved when trained in the UC-Merced dataset than the model performance when trained in the SIRI-WHU dataset.

ABSTRACT Inspired by classical feature descriptors in motion matching, this paper proposes a multimodal failure matching point collection method, which is defined as FMP. FMP is, in fact, a collection of unstable features with a low matching degree in the conventional matching task. Based on FMP, a novel model for the saliency detection of motion object is developed. Models are evaluated on the DAVIS and SegTrackv2 datasets and compared with recently advanced object detection algorithms. The comparison results demonstrate the availability and effectiveness of FMP in the detection of motion object saliency.