Neural Organization Research Articles

Detecting Credit Card Fraud using Machine Learning

Credit card is getting increasingly more famous in budgetary exchanges, simultaneously frauds are likewise expanding. Customary techniques use rule-based master frameworks to identify fraud practices, ignoring assorted circumstances, the outrageous lopsidedness of positive and negative examples. In this paper, we propose a CNN-based fraud detection system, to catch the natural examples of fraud practices gained from named information. Bountiful exchange information is spoken to by an element lattice, on which a convolutional neural organization is applied to recognize a bunch of idle examples for each example. Trials on true monstrous exchanges of a significant business bank show its boss presentation contrasted and some best-in-class strategies. The aim of this paper is to merge between Convolutional Neural Network (CNN), Long-Short Term Memory (LSTM), and Auto-encoder (AE) to increase credit card fraud detection and enhance the performance of the previous models. By using these four models; CNN, AE, LSTM, and AE&LSTM. each of these models is trained by different parameter values highest accuracy has been achieved where the AE model has accuracy =0.99, the CNN model has accuracy =0.85, the accuracy of the LSTM model is 0.85, and finally, the AE&LSTM model obtained an accuracy of 0.32 by 400 epoch. It is concluded that the AE classifies the best result between these models.

Whole-Brain Reconstruction of Neurons in the Ventral Pallidum Reveals Diverse Projection Patterns.

The ventral pallidum (VP) integrates reward signals to regulate cognitive, emotional, and motor processes associated with motivational salience. Previous studies have revealed that the VP projects axons to many cortical and subcortical structures. However, descriptions of the neuronal morphologies and projection patterns of the VP neurons at the single neuron level are lacking, thus hindering the understanding of the wiring diagram of the VP. In this study, we used recently developed progress in robust sparse labeling and fluorescence micro-optical sectioning tomography imaging system (fMOST) to label mediodorsal thalamus-projecting neurons in the VP and obtain high-resolution whole-brain imaging data. Based on these data, we reconstructed VP neurons and classified them into three types according to their fiber projection patterns. We systematically compared the axonal density in various downstream centers and analyzed the soma distribution and dendritic morphologies of the various subtypes at the single neuron level. Our study thus provides a detailed characterization of the morphological features of VP neurons, laying a foundation for exploring the neural circuit organization underlying the important behavioral functions of VP.

Intelligent system for leaf disease detection using capsule networks for horticulture

Horticulture crops take a crucial part of the Indian economy by creating employment, supplying raw materials to different food processing industries. Mangoes are one of the major crops in horticulture. General Infections in Mango trees are common by various climatic and fungal infections, which became a cause for reducing the quality and quantity of the mangos. The most common diseases with bacterial infection are anthracnose and Powdery Mildew. In recent years, it has been perceived that different variants of deep learning architectures are proposed for detecting and classifying the problems in the agricultural domain. The Convolutional Neural Network (CNN) based architectures have performed amazingly well for disease detection in plants but at the same time lacks rotational or spatial invariance. A relatively new neural organization called Capsule Network (CapsNet) addresses these limitations of CNN architectures. Hence, in this work, a variant of CapsNet called Multilevel CapsNet is introduced to characterize the mango leaves tainted by the anthracnose and powdery mildew diseases. The proposed architecture of this work is validated on a dataset of mango leaves collected in the natural environment. The dataset comprises both healthy and contaminated leaf pictures. The test results approved the undeniable level of exactness of the proposed framework for the characterization of mango leaf diseases with an accuracy of 98.5%. The outcomes conceive the higher-order precision of the proposed Multi-level CapsNet model when contrasted with the other classification algorithms such as Support Vector Machine (SVM) and CNNs.

Music Genre Classification and Recommendation

There are various sorts to group the music. Classes are for the most part various classifications wherein music is partitioned. In this day and age as music industry develops quickly, there are various kinds of music sorts made. It is essential to classify the music into these classifications, yet it is mind boggling task. In past times this is done physically and prerequisite for programmed framework for type grouping emerges. As a rule, AI techniques are utilized to group music types and profound learning strategy is utilized to prepare the model yet in this undertaking, we will utilize neural organization strategies for the characterization.

Progress towards brain organoid models with representative neurovascular features

Vascular dysfunction in the brain is a leading risk factor for dementia and neurodegeneration. However, brain vascular pathology is difficult to recapitulate in an animal model without influencing other aspects of disease. Thus, it remains challenging to understand how specific insults lead to brain vascular pathology and how the subsequent changes to vascular function mechanistically impact neurodegeneration. To complement animal models and help overcome these challenges, our lab develops engineered models of the vascularized human brain from combinations of human induced pluripotent stem cell (iPSC)-derived progenies and primary tissue. We specifically focus on developing models that have: (1) neural organization and architecture similar to human cortex; (2) representative neurovascular features. We previously fabricated a functionalized hydrogel (O'Grady et al, ACS Biomat Sci & Eng, 2020) that presents an extracellular peptide epitope from N-cadherin, an important cell-cell adhesion receptor that directs cortical development. This hydrogel forms the basis for our studies. (1) Brain organoids were differentiated from human induced pluripotent stem cells (iPSCs) using published methods, then embedded in the N-cadherin functionalized hydrogel and various controls. Microscopy techniques were used to assess cellular identity and organization. (2) Primary cortical tissue was isolated from euthanized mice or human autopsy and embedded in a variant of the N-cadherin functionalized hydrogel to induce vascular outgrowth. A custom microfluidic device was built to direct vascular organization using gradients of small molecules and growth factors. Microscopy and molecular biology techniques were used to assess vascular identity and function. (1) Organoids in the N-cadherin functionalized hydrogel have more representative features of the brain, including a single neuroepithelial core segregated from the outer progenitor zone and appropriate laminar patterning of cortical layers. (2) Arterioles and capillaries with biomimetic features, including proper size and multicellular organization, can be grown from primary tissue CONCLUSION: A unifying hydrogel can pattern iPSC-derived brain organoids and coax growth of blood vessels from primary brain tissue. Ongoing work is focused on integrating these platforms to generate a neurovascular organoid where the vessels can be perfused. Once completed, this model may provide an avenue for understanding how vascular dysfunction impacts neural function and subsequent degeneration.

Modeling of the processes of extracting rules from Neural Network components with Petri nets

The paper deals with the use of extended Petri nets in modeling the processes of extracting rules from neural network components. The mathematical model for extracting rules from neural network components based on a modified timed Petri net is constructed, followed by an analysis of its dynamic behavior based on a timed reachability graph, which is a set of all its states that can be reached when a finite number of transitions are fired. The proposed model allows us to move from the initial detailed structure to its simplified description, which preserves the possibility of obtaining information about the structure and dynamic behavior of the neural network system. The proposed approach can be used in the synthesis of cognitive systems with a neural network organization to provide computational support for the functions of forming, learning, and correcting cognitive networks that display neural network models.

Neural Network Modeling and Organization of a Hierarchical Associative Memory System

Neural Network Modeling and Organization of a Hierarchical Associative Memory System

Social and emotion dimensional organizations in the abstract semantic space: the neuropsychological evidence

An essential aspect of human cognition is supported by a rich reservoir of abstract concepts without tangible external referents (e.g., “honor”, “relationship”, “direction”). While decades of research showed that the neural organization of conceptual knowledge referring to concrete words respects domains of evolutionary salience and sensorimotor attributes, the organization principles of abstract word meanings are poorly understood. Here, we provide neuropsychological evidence for a domain (sociality) and attribute (emotion) structure in abstract word processing. Testing 34 brain-damaged patients on a word-semantic judgment task, we observed double dissociations between social and nonsocial words and a single dissociation of sparing of emotional (relative to non-emotional) words. The lesion profiles of patients with specific dissociations suggest potential neural correlates positively or negatively associated with each dimension. These results unravel a general domain-attribute architecture of word meanings and highlight the roles of the social domain and the emotional attribute in the non-object semantic space.

An Islanding Detection and Control Strategy to Realize the Stable and Autonomous Operation of Microgrids Using the Virtual Synchronous Generator

Abstract: An islanding detection and based control strategy is created in this exploration to accomplish the steady and independent activity of microgrids using the neural network based Virtual Synchronous Generator (VSG) idea during unplanned grid reconfigurations . Maybe of utilizing a design-orientedmethodology, this paper gives a rigorous and extensive hypothetical investigation and reaches a concise conclusion that is easy to execute and successful even in complex situations. Based on the results of the mutation sequence and voltage wavering, a neural network based islanding identification calculation is proposed, which requires less constraint strategy. The proposed neural network approach outperforms the thefrequency measured passive detection method in terms of detection speed and reliability. Broad recreations affirm the reasonableness of the proposed islanding location and control methodology. Additionally, think about the results of the reproductions for the PI regulator, fluffy organizations, and neural organizations. Keywords: Virtual Synchronous Generator, Islanding detection, Islanding operation, Droop control, Stability, Microgrids.

Multimodal Fusion of Face and Palm Using Local Color Binary Patterns and Haralick Features

Face recognizable proof has drawn in numerous scientists because of its novel benefit, for example, non-contact measure for include obtaining. Varieties in brightening, posture and appearance are significant difficulties of face acknowledgment particularly when pictures are taken as dim scale. To mitigate these difficulties partially many exploration works have been completed by considering shading pictures and they have yielded better face acknowledgment rate. A strategy for perceiving face utilizing shading nearby surface highlights is depicted. Test results show that Face ID approaches utilizing shading neighborhood surface highlights astonishingly yield preferred acknowledgment rates over Face acknowledgment approaches utilizing just shading or surface data. Especially, contrasted and grayscale surface highlights, the proposed shading neighborhood surface highlights can give great coordinating with rates to confront pictures taken under extreme varieties in enlightenment and furthermore for low goal face pictures. The other biometric framework utilizes palmprint as quality for the recognizable proof and validation of people. The principal point is to extract Haralick highlights and utilization of probabilistic neural organizations for confirmation utilizing palmprint biometric quality. PolyUdatabase tests are taken from around 200 clients every client's 2 examples are gained. This palm print biometric recognizes the phony (fake) palmprint made of POP (Plaster of paris) and separates among living and non-living dependent on the entropy highlight. Test results portray that the eleven Haralick feature values are acquired in execution stage and productive precision is accomplished.

Проектування системи автоматизованого генерування віршованих творів

Features of designing a system of automated generation of poetic works, which opens up new opportunities for artistic speech and show business, especially the preparation of poems and songs have been considered. Quite often lyrics without special content become successful due to the lack of complex plots, as well as due to the unobtrusiveness and ease of perception by listeners. Well-known literature sources and available software products that can generate poetic works by combining different methods and algorithms are analyzed. It has been established that none of them is able to ensure the content and uniqueness of the poetic work at the same time, especially in the Ukrainian language. The existing approaches to the generation of poetic works are analysed, among which the relevant is a method based on templates, generation and testing, evolutionary algorithms and the method based on specific cases. Peculiarities of generating poetical works, first of all rhyming rules, types of strophes, poetic rhythms and sizes have been investigated. An approach to automated generation of poetic works using evolutionary algorithms and a method based on specific cases have been developed. Their combination resembles a sequence of actions for creative personalities when creating poems or writing lyrics. Peculiarities of neural network organization for automated generation of poetic works have been considered. It is proposed to perform neural network training using the method of inverse propagation and using a genetic algorithm. The principle of operation of algorithms for finding optimal solutions which contain such consecutive stages as initialization, evaluation of solutions, population selection, evolution of solutions, is analysed. Their interaction and various opportunities for neural network learning have been investigated in detail. An algorithm has been developed according to which the software application will analyse the poetic works offered by the user and generate new variants of it on the basis received from the neural network of logically connected words or lines of the verse in the poem. The user can edit both the components of the poem and the generated poetic works, and thus can train the neural network. The specification of requirements to the software application has been developed, the basic requirements to the user interface are defined, and also potential classes of users who will use it are established. Keywords: computational linguistics; Artificial Intelligence; neural network; genetic algorithm; optimal solution.

Neural reinstatement reveals divided organization of fear and extinction memories in the human brain

Neurobiological research in rodents has revealed that competing experiences of fear and extinction are stored as distinct memory traces in the brain. This divided organization is adaptive for mitigating overgeneralization of fear to related stimuli that are learned to be safe while also maintaining threat associations for unsafe stimuli. The mechanisms involved in organizing these competing memories in the human brain remain unclear. Here, we used a hybrid form of Pavlovian conditioning with an episodic memory component to identify overlapping multivariate patterns of fMRI activity associated with the formation and retrieval of fear versus extinction. In healthy adults, distinct regions of the medial prefrontal cortex (PFC) and hippocampus showed selective reactivation of fear versus extinction memories based on the temporal context in which these memories were encoded. This dissociation was absent in participants with posttraumatic stress disorder (PTSD) symptoms. The divided neural organization of fear and extinction may support flexible retrieval of context-appropriate emotional memories, while their disorganization may promote overgeneralization and increased fear relapse in affective disorders.

Generation of Interconnected Neural Clusters in Multiscale Scaffolds from Human-Induced Pluripotent Stem Cells.

The development of in vitro neural networks depends to a large extent on the scaffold properties, including the scaffold stiffness, porosity, and dimensionality. Herein, we developed a method to generate interconnected neural clusters in a multiscale scaffold consisting of a honeycomb microframe covered on both sides with a monolayer of cross-linked gelatin nanofibers. Cortical neural precursor cells were first produced from human-induced pluripotent stem cells and then loaded into the scaffold for a long period of differentiation toward cortical neural cells. As a result, neurons and astrocytes self-organized in the scaffold to form clusters in each of the honeycomb compartments with remarkable inter-cluster connections. These cells highly expressed neuron- and astrocyte-specific proteins, including NF200, tau, synapsin I, and glial fibrillary acidic protein, and showed spatially correlated neural activities. Two types of neural clusters, that is, spheroid-like and hourglass-like clusters, were found, indicating the complexity of neural-scaffold interaction and the variability of three-dimensional neural organization. Furthermore, we incorporated a reconstituted basement membrane into the scaffold and performed co-culture of the neural network with brain microvascular endothelial cells. As a proof of concept, an improved neurovascular unit model was tested, showing large astrocytic end-feet on the back side of the endothelium.

A genetically tractable jellyfish model for systems and evolutionary neuroscience

Jellyfish are radially symmetric organisms without a brain that arose more than 500 million years ago. They achieve organismal behaviors through coordinated interactions between autonomously functioning body parts. Jellyfish neurons have been studied electrophysiologically, but not at the systems level. We introduce Clytia hemisphaerica as a transparent, genetically tractable jellyfish model for systems and evolutionary neuroscience. Wegenerate stable F1 transgenic lines for cell-type-specific conditional ablation and whole-organism GCaMP imaging. Using these tools and computational analyses, we find that an apparently diffusenetwork of RFamide-expressing umbrellar neurons is functionally subdivided into a series of spatially localized subassemblies whose synchronous activation controls directional food transfer from the tentacles to the mouth. These data reveal anunanticipated degree of structured neural organization in this species. Clytia affords a platform for systems-level studies of neural function, behavior, and evolution within a clade of marine organisms with growing ecological and economic importance.

Forecasting Stock Price using LSTM-CNN Method

Foreseeing assumes an indispensable part in setting an exchanging methodology or deciding the ideal opportunity to purchase or sell stock. We propose an element combination long transient memory-convolutional neural organization (LSTM-CNN) model, which joins highlights gained from various presentations of similar information, i.e., stock timetable and stock outline pictures, to anticipate stock costs. The proposed model is created by LSTM and CNN, which extricate impermanent and picture components. We assessed the proposed single model (CNN and LSTM) utilizing SPDR S&P 500 ETF information. Our LSTM-CNN combination highlight model surpasses single models in foreseeing evaluating. Also, we track down that the candle graph is the most precise image of a stock diagram that you can use to anticipate costs. Subsequently, this examination shows that prescient mistake can be viably decreased by utilizing a blend of transitory and picture components from similar information as opposed to utilizing these provisions independently.

An extensive critique of sliding mode control and adaptive neuro‐fuzzy inference system for nonlinear system

AbstractNonlinear control hypothesis is the region of control hypothesis which manages frameworks that are nonlinear, time‐variant, or both. Nonlinear control structures have extended high prevalence fundamentally because of the wide use of hypothetical intends to deal with credible issues in different zones of engineering and medical aspects. Sliding mode control (SMC) is a nonlinear control strategy applied when the deterministic model of the nonlinear system is discrepant with actual plant in terms of plant parameters and undetermined external disturbances. SMC is a sort of nonlinear control that accentuates zero error convergence modeling error, demonstrating nonlinearities and outside aggravations. Adaptive neuro‐fuzzy inference system (ANFIS) captures neural associations and soft reason guidelines in a single framework. ANFIS causes fewer errors and is more obvious to the customer isolated from the ANN. The paper centers that neural organizations accept a critical capacity in controlling nonlinear frameworks. This review aims an overview of existing methods for nonlinear control and application of SMC for nonlinear system based on ANFIS.

Traffic Sign Classification

Abstract: The traffic signs engraved on the streets nowadays improve traffic security by advising the driver regarding speed limits or any further potential perils like profound thrilling streets, inescapable fix street works or any common intersections. With the quick improvement of economy and innovation in the cutting edge society, vehicles have become an imperative method for transportation in the day by day travel of individuals. Albeit the fame of autos has acquainted impressive comfort with individuals, it has additionally caused a various traffic security issues that can't be overlooked, for example, gridlock and successive street mishaps. Traffic security issues are to a great extent brought about by abstract reasons identified with the driver, like obliviousness, inappropriate driving activity and resistance with traffic rules, and keen vehicles have become a compelling way to wipe out these human components. Self-driving innovation can help, or even autonomously complete the driving activity, which is vital to free the human body and extensively lessen the rate of mishaps. Traffic sign identification and acknowledgment are significant in the advancement of astute vehicles, which straightforwardly influences the execution of driving practices. Traffic sign identification and grouping is of vital significance for the fate of independent vehicle innovation. We benchmark the commented on dataset with AI baselines Convolutional Neural Organizations (CNN). Computational strategies for AI (ML) have shown their importance for the projection of possible outcomes for educated choices. AI calculations have been applied for quite a while in numerous applications. An information driven methodology with higher precision as here can be extremely valuable for a proactive reaction from the public authority and residents. At long last, we propose a bunch of exploration openings and arrangement justification for additional useful applications. Keywords: Convolutional Neural Networks, Traffic sign detection, Traffic safety, Computational Methods, machine Learning Algorithms

Nerve bundle formation during the promotion of peripheral nerve regeneration: collagen VI-neural cell adhesion molecule 1 interaction.

The formation of nerve bundles, which is partially regulated by neural cell adhesion molecule 1 (NCAM1), is important for neural network organization during peripheral nerve regeneration. However, little is known about how the extracellular matrix (ECM) microenvironment affects this process. Here, we seeded dorsal root ganglion tissue blocks on different ECM substrates of peripheral nerve ECM-derived matrix-gel, Matrigel, laminin 521, collagen I, and collagen IV, and observed well-aligned axon bundles growing in the peripheral nerve ECM-derived environment. We confirmed that NCAM1 is necessary but not sufficient to trigger this phenomenon. A protein interaction assay identified collagen VI as an extracellular partner of NCAM1 in the regulation of axonal fasciculation. Collagen VI interacted with NCAM1 by directly binding to the FNIII domain, thereby increasing the stability of NCAM1 at the axolemma. Our in vivo experiments on a rat sciatic nerve defect model also demonstrated orderly nerve bundle regeneration with improved projection accuracy and functional recovery after treatment with 10 mg/mL Matrigel and 20 μg/mL collagen VI. These findings suggest that the collagen VI-NCAM1 pathway plays a regulatory role in nerve bundle formation. This study was approved by the Animal Ethics Committee of Guangzhou Medical University (approval No. GY2019048) on April 30, 2019.

Dynamic causal modeling of the working memory system of aneurysmal subarachnoid hemorrhage patients: Searching for targets for cortical intervention

IntroductionAneurysmal subarachnoid hemorrhage (aSAH), caused by rupture of an intracranial aneurysm and bleeding into the subarachnoid space, is a life‐threatening cerebrovascular disease. Because of improvements in clinical interventions, the mortality rate of aSAH is gradually decreasing. Thus, many survivors recover from aSAH but still have sequelae. Working memory (WM) deficit is one of the most common and severe sequelae after aSAH. Interestingly, the severity of WM deficit is not identical to the extent or localization of brain damage, which implies an underlying mechanism of WM deficit other than direct hemorrhagic brain damage. Previous studies have revealed altered neural activity of several brain regions during stimulus tasks. However, the behaviors and functional organization of these corresponding areas in the resting state remain unclear. Insights into the organization of the WM network could reveal novel information about the mechanism of WM deficits, which will be of great value in developing new therapeutic strategies.MethodsIn this study, we recruited 50 aSAH patients consisting of survivors with either impaired or intact WM (two groups). Independent component analysis was performed on resting state data to extract the WM network. Dynamic causal modeling was then performed to assess the intrinsic coupling between key regions of the WM network. A model describing the neural activity and functional organization of the WM network was established, although some connections were not consistent in the resting state.ResultsWe found that effective connectivity of the precuneus (PCUN)‐middle temporal gyrus (MTG), MTG‐PCUN, and middle frontal gyrus‐inferior parietal lobule was significantly decreased in the impaired WM group, which suggests a vital and central role of affected regions or connections and provides new targets for brain stimulation.ConclusionsThe results of this study may contribute to new therapeutic or rehabilitation strategies for aSAH patients with WM deficits.

A Commentary on “Can Neuroscience Provide a New Foundation for the Rorschach Variables?” (Jimura et al., 2021)

A Commentary on “Can Neuroscience Provide a New Foundation for the Rorschach Variables?” (Jimura et al., 2021)