High Learning Ability Research Articles

Generation and Characterization of Three Novel Mouse Mutant Strains Susceptible to Audiogenic Seizures

The mechanisms of epileptogenesis after brain injury, ischemic stroke, or brain tumors have been extensively studied. As a result, many effective antiseizure drugs have been developed. However, there are still many patients who are resistant to therapy. The molecular and genetic bases regarding such drug-resistant seizures have been poorly elucidated. In many cases, heavy seizures are instigated by brain development malformations and often caused by gene mutations. Such malformations can be demonstrated in mouse models by generating mutant strains. One of the most potent mutagens is ENU (N-ethyl-N-nitrosourea). In the present study, we describe three novel mutant strains generated by ENU-directed mutagenesis. Two of these strains present a very strong epileptic phenotype triggered by audiogenic stimuli (G9-1 and S5-1 strains). The third mouse strain is characterized by behavioral disorders and hyperexcitation of neuronal networks. We identified changes in the expression of those genes encoding neurotransmission proteins in the cerebral cortexes of these mice. It turned out that the G9-1 strain demonstrated the strongest disruptions in the expression of those genes encoding plasma membrane channels, excitatory glutamate receptors, and protein kinases. On the other hand, the number of GABAergic neurons was also affected by the mutation. All three lines are characterized by increased anxiety, excitability, and suppressed motor and orientational–exploratory activities. On the other hand, the strains with an epileptic phenotype—G9-1 and S5-1ave reduced learning ability, and the A9-2 mice line retains high learning ability.

On the application of hybrid deep 3D convolutional neural network algorithms for predicting the micromechanics of brain white matter

Background:Material characterization of brain white matter (BWM) is difficult due to the anisotropy inherent to the three-dimensional microstructure and the various interactions between heterogeneous brain-tissue (axon, myelin, and glia). Developing full scale finite element models that accurately represent the relationship between the micro and macroscale BWM is however extremely challenging and computationally expensive. The anisotropic properties of the microstructure of BWM computed by building unit cells under frequency domain viscoelasticity comprises of 36 individual constants each, for the loss and storage moduli. Furthermore, the architecture of each unit cell is arbitrary in an infinite dataset. Methods:In this study, we extend our previous work on developing representative volume elements (RVE) of the microstructure of the BWM in the frequency domain to develop 3D deep learning algorithms that can predict the anisotropic composite properties. The deep 3D convolutional neural network (CNN) algorithms utilizes a voxelization method to obtain geometry information from 3D RVEs. The architecture information encoded in the voxelized location is employed as input data while cross-referencing the RVEs’ material properties (output data). We further develop methods by incorporating parallel pathways, Residual Neural Networks and inception modulus that improve the efficiency of deep learning algorithms. Results:This paper presents different CNN algorithms in predicting the anisotropic composite properties of BWM. A quantitative analysis of the individual algorithms is presented with the view of identifying optimal strategies to interpret the combined measurements of brain MRE and DTI. Significance:The proposed Multiscale 3D ResNet (M3DR) algorithm demonstrates high learning ability and performance over baseline CNN algorithms in predicting BWM tissue properties. The hybrid M3DR framework also overcomes the significant limitations encountered in modeling brain tissue using finite elements alone including those such as high computational cost, mesh and simulation failure. The proposed framework also provides an efficient and streamlined platform for implementing complex boundary conditions, modeling intrinsic material properties and imparting interfacial architecture information.

Connotation and Analysis of English Self-Study Ability in High School Students Under Deep Learning Theory

It advocates deepening the teaching classroom s engagement, encouraging students to transition from a passive to an active learning mindset, enhancing their participation, and enabling them to understand and actively construct knowledge, thereby achieving a unified learning experience.[1].Current high school students English learning ability in classroom inside and outside, classroom teaching fragmentation and surface problems and classroom independent learning consciousness weak problems still exist, how to cultivate high school students critical thinking, problem solving ability and help high school students improve autonomous learning ability, become the current in the process of deepening the reform of high school English curriculum need to focus on areas[2].Under the guidance of deep learning theory, it is particularly necessary to explore the connotation and causes of the English self-study ability of senior high school students.

Exploration of Solving Methods and Applications of Neural Network Models in Optimization Problems

With the booming growth of artificial intelligence (AI) technology, machine learning (ML) as its core component has shown enormous potential and application value in solving optimization problems. Among numerous ML algorithms, neural networks (NN) have become one of the preferred tools for handling optimization problems due to their high flexibility and powerful learning ability. This article focuses on the application of NN in the field of image recognition, exploring its solution methods and application exploration. Image recognition, as an important branch in the field of AI, aims to recognize and understand information in images through computer algorithms. NN can automatically learn features in images and construct complex classification models by simulating the connections and working modes of human brain neurons. By applying the NN model, the performance of the image recognition system has been significantly improved. NN can accurately recognize objects, scenes, and text information in images, providing strong technical support for fields such as intelligent security, autonomous driving, and medical diagnosis. With the continuous progress of technology and the expansion of application scenarios, NN will play an important role in more fields, promoting the rapid growth of AI technology.

A STUDY ON THE FACTORS INFLUENCING THE TURNOVER BEHAVIOR OF NEW GENERATION EMPLOYEES IN INSURANCE COMPANIES

Along with the rapid development of the insurance industry, the requirements for insurance practitioners are also increasing. From traditional insurance businesses to digital businesses, employees are required to maintain a high level of learning and work abilities in order to face the complex and ever-changing market environment. The advantages of the new generation of employees are their strong work ability and high learning ability, but the disadvantages are that they have distinct personalities and do not attach enough importance to the authority of their leaders. They like to act according to their own style when doing things. Using the new generation of employees properly can benefit the organization, but improper use can cause harm. With the increasing proportion of new-generation employees in the organization, how to effectively manage them, reduce their turnover rate, and ensure the stable development of the talent team is an issue that organizational management should pay attention to. Empirical analysis shows that three influencing factors, namely organizational fairness, promotion channels based on the term target responsibility system, and a highly flexible salary structure, can reduce the probability of turnover behavior among the new generation of employees in insurance companies. The highly flexible salary structure has the greatest impact on the turnover behavior of new generation employees in insurance companies, proving that addressing the material needs of new generation employees can stabilize the talent pool of new generation employees.

Symmetry and Graph Bi-Regularized Non-Negative Matrix Factorization for Precise Community Detection

Community is a fundamental and highly desired pattern in a Large-scale Undirected Network (LUN). Community detection is a vital issue when LUN representation learning is performed. Owing to its good scalability and interpretability, a Symmetric and Non-negative Matrix Factorization model is frequently utilized to tackle this issue. It adopts a unique Latent Factor (LF) matrix for precisely representing LUN’s symmetry, which, unfortunately, leads to a reduced LF space that decreases its representation learning ability to a target LUN. Motivated by this discovery, this study proposes a Symmetry and Graph Bi-regularized Non-negative Matrix Factorization (B-NMF) method that: a) leverages multiple LF matrices when representing LUN, thereby boosting the representation learning ability; b) constructs a symmetry regularization term that implies the equality constraint among its multiple LF matrices, thereby illustrating LUN’s intrinsic symmetry; and c) incorporates graph regularization into its learning objective, thereby illustrating LUN’s local geometry. A theoretical proof is given to theoretically validate B-NMF’s convergence ability. The regularization hyperparameters are selected by validating model modularity, thereby guaranteeing B-NMF’s practicability in addressing real application issues. Extensive experimental results on ten LUNs from real applications demonstrate that the proposed B-NMF-based community detector significantly outperforms several baseline and state-of-the-art models in achieving highly-accurate community detection results. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —LUNs are very-commonly seen in real applications like a social network system. Communities in LUNs are vital for various knowledge discovery-related applications. For accurately detecting them, a detector should guarantee its high representation learning ability to a target LUN. To do so, this paper presents a B-NMF model that is able to perform precise representation learning to LUNs, thereby achieving accurate community detection results. In comparison with conventional Symmetric and Non-negative Matrix Factorization-based community detectors, a B-NMF-based community detector enjoys its enlarged latent feature space, which ensures its higher representation ability to a target LUN. It depends on two regularization hyperparameters, which can be selected by performing grid-search on the target LUN via its modularity evaluation. This paper gives the empirical values of B-NMF’s regularization hyperparameters based on the parametersensitivity tests on the involved experimental datasets. The proposed B-NMF model is shown to be highly suitable for addressing community detection and clustering tasks on LUNs from real applications.

Characteristics of murine phenotypes with signs of epilepsy obtained through ENU mutagenesis

Epilepsy is a chronic neurological disorder marked by recurring seizures and associated dysfunctions of motor, sensory, autonomic, and mental functions resulting from excessive electrical activity of neurons. Identification and characterization of the mutations that cause this pathology are essential for understanding the mechanisms that control epileptogenesis. The aim of the study is to characterize the S8-3 mutant mice strain, which shows induced epileptiform activity in response to audiogenic stimulation. Mutant strains of mice were acquired through induced chemical mutagenesis using N-ethyl-N-nitrosourea (ENU). Twenty-nine male mice were administered three rounds of ENU injections at a dose of 90 mg/kg during the study. On day 21 after birth (P21), identification and selection of mouse mutants with an elevated inclination towards epileptic seizures were conducted using the Krushinsky scale, which considered the intensity of audiogenic seizures. Strains with a recessive mutation were created by selecting animals that exhibited the aberrant phenotype for the second time. The abnormal phenotype was confirmed in the G5 generation, and basic behavioral phenotyping was performed to characterize the resulting epileptic lines. Correct grammar, spelling, and punctuation. This included assessing memory, learning ability, motor reactions, and emotional status. In vitro experiments assessed spontaneous calcium activity with primary neuronal cultures of the cerebral cortex isolated from newborn mice. The Ca2+ indicator used was Oregon Green 488 BAPTA-1 AM. Upon screening 60 strains of mice for sensitivity to audiogenic stimulation, 12 strains exhibiting epileptiform activity were observed. Subsequently, the S8-3 group was selected for further research, as its offspring (G3) showed a higher frequency of the aberrant phenotype in comparison to the other groups. Results from behavioral studies comparing S5-1 mice to the control hybrid animal group displayed a higher intensity of the acoustic startle response. The open field tests revealed that the motor activity of S8-3 strain mice was higher than that of the control group, based on the average distance traveled, and their anxiety level was lower, as indicated by fewer rears, urinary points, and boluses. When assessing cognitive functions through the CPAR test, mutant individuals exhibited high learning ability. In vitro experiments showed an increase in the frequency of spontaneous calcium events in primary cell cultures of the cerebral cortex isolated from S8-3 mice.

Reliable Feature Matching for Spherical Images via Local Geometric Rectification and Learned Descriptor

Spherical images have the advantage of recording full scenes using only one camera exposure and have been becoming an important data source for 3D reconstruction. However, geometric distortions inevitably exist due to the spherical camera imaging model. Thus, this study proposes a reliable feature matching algorithm for spherical images via the combination of local geometric rectification and CNN (convolutional neural network) learned descriptor. First, image patches around keypoints are reprojected to their corresponding tangent planes based on a spherical camera imaging model, which uses scale and orientation data from the keypoints to achieve both rotation and scale invariance. Second, feature descriptors are then calculated from the rectified image patches by using a pre-trained separate detector and descriptor learning network, which improves the discriminability by exploiting the high representation learning ability of the CNN. Finally, after classical feature matching with the ratio test and cross check, refined matches are obtained based on an essential matrix-based epipolar geometry constraint for outlier removal. By using three real spherical images and an incremental structure from motion (SfM) engine, the proposed algorithm is verified and compared in terms of feature matching and image orientation. The experiment results demonstrate that the geometric distortions can be efficiently reduced from rectified image patches, and the increased ratio of the match numbers ranges from 26.8% to 73.9%. For SfM-based spherical image orientation, the proposed algorithm provides reliable feature matches to achieve complete reconstruction with comparative accuracy.

A Novel Minimal-Cost Power Allocation Strategy for Fuel Cell Hybrid Buses Based on Deep Reinforcement Learning Algorithms

Energy management strategy (EMS) is critical for improving the economy of hybrid powertrains and the durability of energy sources. In this paper, a novel EMS based on a twin delayed deep deterministic policy gradient algorithm (TD3) is proposed for a fuel cell hybrid electric bus (FCHEB) to optimize the driving cost of the vehicle. First, a TD3-based energy management strategy is established to embed the limits of battery aging and fuel cell power variation into the strategic framework to fully exploit the economic potential of FCHEB. Second, the TD3-based EMS is compared and analyzed with the deep deterministic policy gradient algorithm (DDPG)-based EMS using real-world collected driving conditions as training data. The results show that the TD3-based EMS has 54.69% higher training efficiency, 36.82% higher learning ability, and 2.45% lower overall vehicle operating cost compared to the DDPG-based EMS, validating the effectiveness of the proposed strategy.

Roles of the nuclear receptor corepressor 1 (NCoR1) and the silencing mediator of retinoid and thyroid hormone receptors (SMRT) in the developing brain

The nuclear receptor corepressor 1 (NCoR1) and the silencing mediator of retinoic acid and thyroid hormone (SMRT) are critical coregulators of the nuclear receptor (e.g., thyroid hormone receptors and retinoic acid receptors), mediating transcriptional repression via histone deacetylation. Although they are highly homologous and have similar nuclear receptor interaction domains, they have different roles in different organs. Recently, de novo genetic variants in nuclear corepressors were found in pediatric patients with neurodevelopmental disorders. Thus, we generated the mouse models to understand the role of NCOR1 and SMRT in the central nervous system. We used the mice with conditional NCoR1 or SMRT (NCoR1 lox/lox or SMRT lox/lox ) alleles in combination with the mice that express Cre recombinase in a neuronal specific fashion (Snap25-Ires2-Cre). First, we performed a battery of behavioral tests to screen behavioral phenotype of mice. We found that hypoactivity, social deficits, and mild anxiety in neuronal specific NCoR1 or SMRT KO mice. In addition, NCoR1 KO mice showed high learning abilities in pairwise visual discrimination task. Next, we performed RNA-sequencing analysis with amygdala from postnatal day 21 to investigate gene expression mediated by NCoR1 and SMRT. We found that 449 genes were upregulated by SMRT deletion, whereas only 8 genes were upregulated by NCoR1 deletion. Overall, our data demonstrate for the first time that NCoR1 and SMRT have separate functions in the central nervous system. JSPS Grant-in-Aid for Early-Career Scientists 19K16486, 21K15340 This is the full abstract presented at the American Physiology Summit 2023 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

A novel smoothing-based long short-term memory framework for short-to medium-range flood forecasting

ABSTRACT A novel smoothing-based long short-term memory (Smooth-LSTM) framework for flood forecasting up to five days ahead is proposed, and compared with the benchmark LSTM (LSTM) model, an Artificial Neural Network (ANN) model, and the conceptual Nedbør Afstrømnings Model (MIKE11 NAM)-Hydrodynamic (HD) (MIKE) hydrological model. This framework was tested in the typical middle Mahanadi River basin (India), which has a tropical monsoon-type climate. Variation of training loss indicated the LSTM network has a higher learning ability at smaller network and batch sizes. The Smooth-LSTM model could predict streamflow with higher Nash-Sutcliffe efficiency of 0.82–0.87 at up to five days lead time with a better reproduction of the observed crucial high peak floods, whereas the corresponding MIKE, ANN and LSTM model-based forecasts were acceptable only up to four-, three- and one-day lead times, respectively. Overall, the Smooth-LSTM model is found to be robust in operational flood forecasting, with lower uncertainty and the least sensitivity to redundant input information.

Российское IT-сообщество в контексте социокультурной модернизации. Результаты интервью. Часть 1

The article presents the results of interviewing Russian IT specialists, which is part of the study of the socio-cultural characteristics of the Russian community of IT specialists. The first part examines the cultural identity of the interviewees. The authors infer that the identity of Russian specialists is determined by two main value “centers of attraction”: Russian and Western cultures. At the same time, Eastern culture does not have a significant impact on the value characteristics of specialists. Thus, the basis for the cultural identity of the respondents is Russian culture with a strong value bias towards Western culture. The specialists attributed the multiculturalism of Russian society, universality, hard work, as well as enterprise to the positive qualities of Russian culture, and conservatism, patience and inertia to the negative ones. Among the main differences between a Russian IT specialist and a foreign one mentioned in the interviews were: versatility, ability to adapt, proficiency, workaholism, stubbornness, commitment to results, high learning ability and collegiality as an ability to collective action, readiness for mutual assistance, as well as the fact that Russian specialists start working earlier and therefore gain experience faster than foreign colleagues. Collegiality, in the authors' opinion, is an exceptional quality in the context of the socio-cultural potential of the studied community because it is the ability for collective values that can be considered as a modernization value and a condition for the implementation of large social projects, and can be a factor in the consolidation of various social groups. The negative differences were: lack of specialized knowledge, the stereotype of the need for vocational education, focus on quick results, problems with the balance between work and personal life. The analysis of the attitude of community members to political life indicated the presence of a request for participation in the social life of society, accompanied by distrust of existing institutions.

DAMNet: Dual Attention Mechanism Deep Neural Network for Underwater Biological Image Classification

Due to the complex background and biodiversity of underwater biological images makes the identification of marine organisms difficult. To solve these above problems, we propose a dual attention mechanism deep neural network for underwater biological image classification (DAMNet). Firstly, tthe proposed DAMNet uses multi-stage stacking to suppress the complex underwater background, and the multiple stacking can reduce the number of parameters of the model and improve the generalization ability. Secondly, the dual attention mechanism module is combined with the improved reverse residual bottleneck based on deep convolution to extract the feature information of underwater biological images from space and channel aspects to obtain better discrimination and feature extraction capability. Finally, the gravity optimizer is selected to update the model weights, and the exponential translation can improve the model’s convergence speed and learning rate. Extensive experiments on a dataset consisting of seven types of underwater biological images demonstrate that the DAMNet model has higher learning ability and robustness compared to the state-of-the-art methods. Our DAMNet model achieves 96.93% classification accuracy in all categories, which is at least a 2 percentage point improvement compared to other models.

МІЖПІВКУЛЬНА АСИМЕТРІЯ ГОЛОВНОГО МОЗКУ ТА МЕТАБОЛІЧНІ ЗМІНИ У ЩУРІВ З РІЗНОЮ АЛКОГОЛЬНОЮ МОТИВАЦІЄЮ

The analysis of motor inter hemispheric asymmetry in rats differing in the degree of alcohol motivation and learnin gability at different stages of chronic alcoholization was performed. The qualitative and quantitative composition of blood lipids was determined as an integral indicator of the degree of ethanol influence on metabolic processes at different stages of chronic alcoholization. The obtained results indicate a certain right-hemispheric character of lateralization of the "alcohol dominant", since among alcohol-dependent rats, animals with left-sided motor a symme try were more common. In chronically alcoholic animals, the effect of alcohol on individual profiles of functional a symme try and changes in hemispheric dominance was found, which was manifested in the modulation of left motor a symme try profiles and inhibition of information processing in the righ the misp here. In addition, among rats with high learnin gability, there were significantly more animals with right-sided motor asymmetry. Chronic alcoholization led to an intensification of catabolic processes in the body, as evidenced by an increase in the concentration of triglycerides and free fatty acids in the blood of rats, which correlates with the formation of alcohol dependence. The increase in lipid concentration correlated with the stage of alcohol dependence formation.

SECONDARY SCHOOL GRADUATES' LINGUISTIC AND PERSONALITY ATTRIBUTES: EFL TEACHERS' PERSPECTIVES

Secondary school graduates who pursue a university education should possess linguistic and personality attributes and other higher learning abilities. The lack of any of these traits may significantly impact students' future endeavors. This research aims to identify secondary school graduates’ attributes and their types; to discover any significant differences in English as a Foreign Language (EFL) teachers’ perceptions due to gender (male/female) years of teaching experience; to discover how linguistic and personality attributes contribute to Saudi secondary school graduates’ EFL learning success. It correlates the teachers' responses based on the type of linguistic and personality attributes, gender, and years of teaching experience. Furthermore, it reviews how linguistic and personality attributes would contribute to secondary school graduates’ EFL learning success. To achieve its objectives, the study applied a descriptive-survey approach, using a questionnaire and a semi-structured interview to collect the data from 61 EFL teachers (33 male, 28 female). The results showed that EFL teachers perceived secondary school graduates as possessing study attributes (linguistic/personality) at a medium level. Significant differences were in the responses of the study sample for the type of attributes (linguistic/personality), favoring the personality attributes and based on the respondents’ years of teaching experience in favor of those with 6-10 years of experience. However, this study did not reveal significant differences in the responses of the study sample based on the respondents' gender (male/female). Based on the findings and their implications, this work asserts that the attributes influence graduates' initiative, competency, the tendency for hard work, and, most importantly, learning success. The study, through a blend of linguistic and personality attributes, enriches EFL teachers' experience in understanding linguistic attributes like correctness, fluency, grammar, reading, writing, and oral and communication skills. This research has explored clarity regarding desirable personality traits, including motivation, interpersonal skills, and the ability to work independently and in-group. Suggestions and recommendations conclude this study.

Developing an E-Learning Platform Capable of Being Aware of Self-Regulated Learning Behaviors of Role Models

Conventional e-learning platforms require a high self-regulatory learning (SRL) ability to ensure learning effectiveness. However, because not everyone has high autonomy and a high SRL ability, many students quit during the online learning period. To enhance the SRL ability, many studies have developed e-learning platforms based on Zimmerman's SRL training model. However, these platforms still require learners to complete a series of provided learning tasks independently and autonomously. This article developed an e-learning platform based on Zimmerman's SRL training model by using role-model group awareness tools to visualize the learning context and activities of the group of role models in each SRL training phase for learners’ observation, self-reflection, and emulation. To test the model, the learning outcomes of the two groups of students enrolled in the same course were measured experimentally. The experimental class consisted of 36 students using the proposed system, whereas the control class consisted of 35 students using a traditional e-learning platform. The experimental class spent more learning time on the platform and achieved better learning results than did the control class. Moreover, the experimental class had gradually improved assessment scores and SRL-related behaviors. The final section presents explanations, discussion, and implications derived from analytical results.

STMGCN: Mobile Edge Computing-Empowered Vessel Trajectory Prediction Using Spatio-Temporal Multigraph Convolutional Network

The revolutionary advances in machine learning and data mining techniques have contributed greatly to the rapid developments of maritime Internet of Things (IoT). In maritime IoT, the spatio-temporal vessel trajectories, collected from the hybrid satellite-terrestrial automatic identification system (AIS) base stations, are of considerable importance for promoting traffic situation awareness and vessel traffic services, etc. To guarantee traffic safety and efficiency, it is essential to robustly and accurately predict the AIS-based vessel trajectories (i.e., the future positions of vessels) in maritime IoT. In this work, we propose a spatio-temporal multigraph convolutional network (STMGCN)-based trajectory prediction framework using the mobile edge computing (MEC) paradigm. Our STMGCN is mainly composed of three different graphs, which are, respectively, reconstructed according to the social force, the time to closest point of approach, and the size of surrounding vessels. These three graphs are then jointly embedded into the prediction framework by introducing the spatio-temporal multigraph convolutional layer. To further enhance the prediction performance, the self-attention temporal convolutional layer is proposed to further optimize STMGCN with fewer parameters. Owing to the high interpretability and powerful learning ability, STMGCN is able to achieve superior prediction performance in terms of both accuracy and robustness. The reliable prediction results are potentially beneficial for traffic safety management and intelligent vehicle navigation in MEC-enabled maritime IoT.

Influence of physical loading on behavioral reactions of rats in cerebral hypoperfusion

A number of clinical studies demonstrate that individual characteristics such as stress tolerance and cognitive ability can be considered not only as diagnostic variables but also as risk factors for severe cerebral hypoperfusion. The aim of the study was to identify the typological features of the effect of physical activity on the behavioral reactions of rats during cerebral hypoperfusion. Material and methods. Cerebral hypoperfusion was modeled by bilateral carotid artery ligation. The study involved 280 rats, divided into equal subgroups, according to sex, stress tolerance and learning capacity. Of these, 112 animals were subjected to daily short-term swimming as a rehabilitation model. Before the simulation, and at 6, 8, 14, 21, 28, 35, 60 and 90 days postoperatively, the animals were tested using a Morris water maze and an “open field” test. Results and discussion. The dynamics of stress resistance and learning ability are related to the periodicity of inflammatory, necrotic, circulatory and reparative remodeling in the model used. After 2-3 months of study, cerebral hypoperfusion causes stabilization of indices characterizing stress resistance and cognitive functions below control values. A decrease in stress resistance begins earlier from day 6 of the study, while the index characterizing cognitive functions first decreases significantly after 3 weeks of study. Factors reducing the damaging effects of cerebral hypoperfusion were female gender, high baseline stress tolerance and learning ability. When assessing learning ability under physical load, animals with high baseline cognitive development showed earlier recovery dynamics during urgent adaptation and a significant increase during long-term adaptation.

Minimum Energy Control of Quadrotor UAV: Synthesis and Performance Analysis of Control System with Neurobiologically Inspired Intelligent Controller (BELBIC)

There is a strong trend in the development of control systems for multi-rotor unmanned aerial vehicles (UAVs), where minimization of a control signal effort is conducted to extend the flight time. The aim of this article is to shed light on the problem of shaping control signals in terms of energy-optimal flights. The synthesis of a UAV autonomous control system with a brain emotional learning based intelligent controller (BELBIC) is presented. The BELBIC, based on information from the feedback loop of the reference signal tracking system, shows a high learning ability to develop an appropriate control action with low computational complexity. This extends the capabilities of commonly used fixed-value proportional–integral–derivative controllers in a simple but efficient manner. The problem of controller tuning is treated here as a problem of optimization of the cost function expressing control signal effort and maximum precision flight. The article introduces several techniques (bio-inspired metaheuristics) that allow for quick self-tuning of the controller parameters. The performance of the system is comprehensively analyzed based on results of the experiments conducted for the quadrotor model.

Online Peer-Tutoring for Programming Languages Based on Programming Ability and Teaching Skill

Web-based cooperative learning could enhance students’ learning motivation; however, learning activities in this process are rather confusing because of the lack of structured learning strategies, resulting in unfavorable learning achievements. With the peer tutoring learning environment to encourage students’ mutual learning and development, an online peer-tutoring platform for programming languages with peer mentoring is established herein for one-to-one peer tutoring activities. With students with higher learning ability as tutors and those with lower learning ability as tutees, tutors can provide online peer tutoring for programming languages via demonstrations and flowcharts to discuss the effects of using different teaching methods for learning activities on the learning achievement of tutees. Based on these teaching methods for peer learning, 52 undergraduates were divided into experimental groups A and B; each group was further divided into peer mentoring group and non-peer mentoring group based on the ability levels. The results show that learning activities with the online peer-tutoring platform for programming languages could assist both groups in enhancing their learning achievement and ensure positive attitudes toward programming languages. In the analyses, the peer mentoring group was preferable in peer tutoring for programming languages with demonstration, while the non-peer mentoring group did not appear significant.