Search

Big data and intelligence artificial have greatly broadened the channels for people to acquire knowledge. The practical application of artificial intelligence technology in college English classrooms can not only help teachers prepare more scientific and advanced teaching plans, and also effectively improve the quality of college English teaching. In this paper, we employ deep neural networks to design a big data-driven English teaching improvement scheme. The proposed method can help teachers and students improve teaching strategies and assist students to learn more accurately and efficiently. First, we analyze the current deficiencies and reasons in English teaching. Second, we analyze the application of artificial intelligence in text corpus construction. Third, we use neural networks to design an intelligent face recognition system for teachers to improve the attendance rate. Forth, by analyzing the students' writing, we design a writing scoring method based on the neural network model, which can evaluate students' writing content. Finally, we experimentally evaluate and verify the effectiveness of the proposed method in this paper. [ABSTRACT FROM AUTHOR]

Hand gesture recognition system helps in development of interface system for entering text in human computer interaction. In this paper, we have presented a hand gesture recognition system designed for dataset consisting of numerals and alphabets in lower case. The proposed system detects the hand with the help of skin color and motion information. Hand tracking is done with the help of two-level tracking system using modified Kanade–Lucas–Tomasi (KLT) tracking algorithm. The existing KLT was not able to track the gesture trajectory once the skin detected becomes less in area resulting in decreased number of points. In this paper, traditional KLT has been modified with a new additional feature to overcome this difficulty. In feature extraction process, a feature matrix consisting of 30 features have been created. Among these 30 features, few features like density-1, density-2, and perimeter efficiency have been introduced and are used for calculating efficiency along with some existing features. Inclusion of new features helps in improving the performance and accuracy of the system. Recognition is done using six classifiers including SVM (Support Vector machine), Decision Tree, Naïve Bayes, k-NN (K nearest neighbor), ANN (Artificial neural Network) and ELM (Extreme learning Machine). The experimental results prove that 89.67% of accuracy is achieved for the recognition of dataset containing both numerals and alphabets. Our proposed system is also compared with two existing literatures and it has been observed that better accuracy is exhibited by the proposed system. [ABSTRACT FROM AUTHOR]

Inter-specific variation in the occurrence of individual recognition (IR) has mostly been examined in species that differ with respect to two critical conditions necessary for such ability: presence of complex social behaviours and sender's distinctiveness. However, variation in IR when species share such conditions is lesser known. We tested for IR in the paper wasp Polistes versicolor and compared the results with published information on IR in Polistes fuscatus. Both species have a flexible nest-founding behaviour and form dominance hierarchies. Additionally, both have individually distinctive facial patterns. P. versicolor faces are highly variable, and they do not appear to be associated with individual quality, consistent with the role as cues in IR. However, the wasps did not discriminate between nestmates with familiar and unfamiliar faces. Besides, wasps did not discriminate between familiar and unfamiliar social partners. Familiar discrimination (discrimination of individuals based on prior social interactions) is considered the first stage toward IR; therefore, P. versicolor wasps, unlike P. fuscatus, lack the ability for IR. Our results suggest that the high variation in colour pattern may not be a good proxy for the occurrence of IR in paper wasps and that neutral variation may be an underestimated factor promoting phenotypic variability. Significance statement: High inter-individual phenotypic variability in primitively eusocial paper wasps has sometimes been considered to be a result of selection for efficient individual identity signalling, especially because senders may benefit from being individually recognised. P. versicolor paper wasp females have highly variable inter-individual facial patterns. However, we demonstrated that they lack individual recognition. After excluding some potentially confounding hypothesis, we conclude that selection for efficient individual identity signalling is not the only factor promoting phenotypic variability in paper wasps and that at least in some species, neutral variation may play a role. [ABSTRACT FROM AUTHOR]

This paper presents spatiotemporal hybrid features, human tracking, and activity recognition into a single framework from video sequences captured by a RGB-D sensor. Initially, we received a sequence of depth maps to extract human silhouettes from the noisy background and track them using temporal human motion information from each frame. Then, hybrid features as optical flow motion features and distance parameters features are extracted from the depth silhouette region and used in an augmented form to work as patiotemporal features. In order to represent each activity in a better way, the augmented features are being clustered and symbolized by self-organization maps. Finally, these features are then processed by hidden Markov models to train and recognize human activities based on transition and emission probabilities values. The experimental results show the superiority of the proposed method over the state-of-the-art methods using two challenging depth images datasets. [ABSTRACT FROM AUTHOR]

Chemical mimicry is an effective strategy when signal receivers recognize and discriminate models by relying on chemical cues. Some aphid enemies mimic the cuticular chemicals of aphids through various means thus avoiding detection and attack by aphid-tending ants. However, because ants have been reported to learn the chemical signatures of aphids in order to distinguish the aphids, the efficacy of chemical mimicry is predicted to depend on the experience of the ants that had tended aphids. The present study tested this hypothesis using two predator species: larvae of the green lacewing Mallada desjardinsi, and larvae of the ladybeetle Scymnus posticalis. Lacewing larvae carry the carcasses of aphids on which they have preyed upon their backs, and these function via chemical camouflage to reduce the aggressiveness of aphid-tending ants toward the larvae. Ladybeetle larvae reportedly produce a covering of wax structures, and their chemicals appear to attenuate ant aggression. We examined whether the behavior of the ant Tetramorium tsushimae toward these predators changed depending on their aphid-tending experience. Ants moderated their aggressiveness toward both predators when they had previously tended aphids, indicating that chemical mimicry by both aphid predators is dependent on previous experience of the ants in tending aphids. Chemical mimicry by the predators of ant-tended aphids is therefore considered to exploit learning-dependent aphid recognition systems of ants. [ABSTRACT FROM AUTHOR]

In ant-aphid associations, many aphid species provide ants with honeydew and are tended by ants, whereas others are never tended and are frequently preyed upon by ants. In these relationships, ants must have the ability to discriminate among aphid species, with mutualistic aphids being accepted as partners rather than prey. Although ants reportedly use cuticular hydrocarbons (CHCs) of aphids to differentiate between mutualistic and non-mutualistic species, it is unclear whether the ability to recognize mutualistic aphid species as partners is innate or involves learning. Therefore, we tested whether aphid recognition by ants depends on learning, and whether the learning behavior is species-specific. When workers of the ant Tetramorium tsushimae had previously tended the cowpea aphid, Aphis craccivora, they were less aggressive toward this species. In addition, ants also reduced their aggressiveness toward another mutualistic aphid species, Aphis fabae, after tending A. craccivora, whereas ants remained aggressive toward the non-mutualistic aphid, Acyrthosiphon pisum, regardless of whether or not they had previous experience in tending A. craccivora. When ants were offered glass dummies treated with CHCs of these aphid species, ants that had tended A. craccivora displayed reduced aggression toward CHCs of A. craccivora and A. fabae. Chemical analyses showed the similarity of the CHC profiles between A. craccivora and A. fabae but not with A. pisum. These results suggest that aphid recognition of ants involves learning, and that the learning behavior may not be species-specific because of the similarity of CHCs between different aphid species with which they form mutualisms. [ABSTRACT FROM AUTHOR]

All individuals in social insect colonies benefit from being informed about the presence and fertility state of reproducers. This allows the established reproductive individuals to maintain their reproductive monopoly without the need for physical control, and the non-reproductive individuals to make appropriate reproductive choices. Here, we studied whether fertility signaling is responsible for the partitioning of reproduction in the ant Neoponera apicalis. This species forms small colonies from one single-mated queen, with workers establishing reproductive hierarchies when hopelessly queenless. Previous studies identified putative fertility signals, particularly the hydrocarbon 13-methylpentacosane (13-MeC), and have shown that precise status discrimination based on these signals could be involved in the regulation of reproductive activities. Here, we extend these findings and reveal that all individuals, be they queens or workers, differ in their cuticular hydrocarbon profile according to fertility state. Proportions of 13-MeC were a strong predictor of an individual's ovarian activity, and could, thus, advertise the established reproducer(s) in both queenright and queenless conditions. Furthermore, this compound might play a key role in the establishment of the reproductive hierarchy, since workers with low fertility at the onset of hierarchy formation already have relatively high amounts of 13-MeC. Dyadic encounters showed that individuals with experimentally increased amounts of 13-MeC triggered less agonistic interactions from top rankers, in accord with them 'advertising' higher status. Thus, these bioassays supported the use of 13-MeC by competing ants. This simple recognition system potentially allows permanent regulation of partitioning of reproduction in this species. [ABSTRACT FROM AUTHOR]

Factors influencing the accuracy of image recognition of blast and nonblast blood cells in a decision support system (DSS) are considered. A structure is presented for the requirements for the development of shape recognition systems for the diagnostics of acute leukoses. [ABSTRACT FROM AUTHOR]

We constructed a universal system for object recognition, which uses preliminary training based on sample images of “objects” and “non-objects.” The images are represented by separate points in multi-dimensional space of features. A recognition system which uses the features space obtained on the basis of lateral-inhibition type functions is described. [ABSTRACT FROM AUTHOR]

In this paper an approach that provides an estimate of the influence of decreasing sizes of database classes on a recognition rate when the k-nearest-neighbors classifiers are in use is proposed. The approach also ensures the feasibility of identifying an optimal number k of the nearest neighbors on a given set. [ABSTRACT FROM AUTHOR]

Features that are inherent to recognition systems that lay claim to constituting an optimal design are considered. A maximal probability of correct recognition is characteristic of such systems. The degree of optimality of systems, the quality of a constructed classifier, or the dimension of the confidence interval may be established on the basis of these features. [ABSTRACT FROM AUTHOR]

Kin recognition, the biased treatment of conspecific individuals based on genetic relatedness, is a widespread phenomenon in animals. The most common mechanisms mediating kin recognition are prior association (familiarity) and phenotype matching. Recognition based on prior association allows identifying familiar individuals. Recognition based on phenotype matching is an extension of prior-association-based recognition and allows identifying familiar and unfamiliar individuals due to a shared phenotypic trait. I investigated which of the two mechanisms is used by cannibalistic juvenile predatory mites, Phytoseiulus persimilis. Protonymphs that were associated with either siblings or non-kin discriminated familiar and unfamiliar larvae and preferentially cannibalized the latter irrespective of genetic relatedness. In contrast, despite previous association with either siblings or non-kin, protonymphs did not discriminate unfamiliar sibling and unfamiliar non-kin larvae. Association in the larval stage therefore mediated kin recognition based on familiarity, but not phenotype matching in cannibalistic P. persimilis protonymphs. Furthermore, in the presence of a familiar prey individual, sibling cannibalism occurred significantly sooner than non-kin cannibalism. This quick sibling cannibalism may have been the consequence of preferential association of siblings and/or may indicate the occurrence of an alternative cannibal phenotype. I discuss the adaptive significance of prior-association-based recognition for P. persimilis juveniles and emphasize the ability of P. persimilis to use multiple recognition mechanisms in dependence of the ontogeny and the ecological context. [ABSTRACT FROM AUTHOR]

Common cuckoos ( Cuculus canorus) are obligate brood parasites, laying eggs into nests of small songbirds. The cuckoo hatchling evicts all eggs and young from a nest, eliminating hosts’ breeding success. Despite the consistently high costs of parasitism by common cuckoos, great reed warbler ( Acrocephalus arundinaceus) hosts sometime accept and other times reject parasitic eggs. To explore the cognitive basis of this seemingly maladaptive variation in host responses, we documented differences in egg rejection rates within 1-day periods just before and during the egg-laying cycle across host nests. Hosts rejected cuckoo eggs at 28% of nests during the pre-egg-laying stage, but when cuckoos exchanged the first host egg with the parasite egg, rejections increased to 75%. Even later, when several host eggs remained in a nest after parasitism, rejection rate fell to 37.5%. Experimental parasitism with conspecific eggs on the first and second day of host laying showed a similar directional change in relative rejection rates, dropping from 35 to 0%. Mistakes in egg discrimination (ejection error and ejection cost) were observed mostly in the latter part of the laying cycle, mainly when nests contained 5–6 eggs. These correlational and experimental patterns of egg rejection support a cognitive process of egg discrimination through several shifts in hosts’ optimal acceptance thresholds of foreign eggs. The results are also consistent with the evolution of foreign egg rejection in the context of nest-sanitation (i.e. the removal of foreign objects). Our results suggest that common cuckoo hosts may recognize more eggs than they reject. This implies that the experience of the host with one or more of its own eggs in the clutch is a key factor in rejecting parasite eggs by allowing inspection and learning about their own clutch. [ABSTRACT FROM AUTHOR]