Neural Base Research Articles

Algorithm for detecting abnormal electricity usage by customers based on electricity big data and deep learning

Abstract In order to optimize the effect of individuals’ aberrant power utilization detection and reinforce the recognition rate and accuracy of abnormal power consumption detection of electricity use, an aberrant power utilization identification algorithm based on electric power big data and deep learning is proposed. Taking the two-way dialogue between power users and the power company as the basic perspective, real-time monitoring and collection of power consumption dynamics of users is carried out, and the power big data collection framework is designed. The retrieval of aberrant power utilization detection indexes is completed. Based on the deep learning algorithm, the artificial neural network base operation medium is combined to quantitatively solve the aberrant power utilization indexes, completing the design of a user aberrant power utilization detection algorithm. Experimental results show that the accuracy of the designed algorithm is 0.963, the F1 value is 0.985, and the AUC value is 0.942, which can effectively identify the aberrant power utilization and has a better performance of abnormal power consumption identification and detection.

Let’s Discover More API Relations: A Large Language Model-based AI Chain for Unsupervised API Relation Inference

APIs have intricate relations that can be described in text and represented as knowledge graphs to aid software engineering tasks. Existing relation extraction methods have limitations, such as limited API text corpus and affected by the characteristics of the input text. To address these limitations, we propose utilizing large language models (LLMs) (e.g., gpt-3.5) as a neural knowledge base for API relation inference. This approach leverages the entire Web used to pre-train LLMs as a knowledge base and is insensitive to the context and complexity of input texts. To ensure accurate inference, we design an AI chain consisting of three AI modules: API Fully Qualified Name (FQN) Parser, API Knowledge Extractor, and API Relation Decider. The accuracy of the API FQN Parser and API Relation Decider is 0.81 and 0.83, respectively. Using the generative capacity of the LLM and our approach’s inference capability, we achieve an average F1 value of 0.76 under the three datasets, significantly higher than the state-of-the-art method’s average F1 value of 0.40. Compared to the original CoT and modularized CoT methods, our AI chain design has improved the performance of API relation inference by 71% and 49%, respectively. Meanwhile, the prompt ensembling strategy enhances the performance of our approach by 32%. The API relations inferred by our method can be further organized into structured forms to provide support for other software engineering tasks.

The Exploring Mechanisms of the Formation of Altruistic Behaviors

Altruism is essential to the world. If people do something on account of caring for others more, it is altruistic. Evolution motivates kin altruism. Reciprocal altruism is essential to human society. There also exists altruism that has nothing to do with gene correlation, like vernacular altruism. Different kinds of altruism have different motivations. The glow effect exists because people want to experience again the warm glow they feel when being altruistic, though the neural base needs to be studied. A costly long-term investment is a more complex altruistic behavior in the real world. It can be explained by selective investment theory, which discusses the importance of relationships. What’s more, altruism has its neurological base. The amygdala volume of people with altruistic trait may be more significant. They may also have more excellent neural activity in regions concerning caring and empathy, like midbrain periaqueductal gray and anterior insular. These neurological findings also lay the foundation for some people to be more altruistic than others. Future research can enlarge the investigation on the practical use of altruism, like discovering how to activate people’s altruistic behaviors and what people can do to cultivate and preserve altruism.

FQN Inference in Partial Code by Prompt-tuned Language Model of Code

Partial code usually involves non-fully-qualified type names (non-FQNs) and undeclared receiving objects. Resolving the FQNs of these non-FQN types and undeclared receiving objects (referred to as type inference) is the prerequisite to effective search and reuse of partial code. Existing dictionary-lookup based methods build a symbolic knowledge base of API names and code contexts, which involve significant compilation overhead and are sensitive to unseen API names and code context variations. In this article, we propose using a p rompt-tuned c o de m asked language mod e l (MLM) as a neural knowledge base for type inference, called POME, which is lightweight and has minimal requirements on code compilation. Unlike the existing symbol name and context matching for type inference, POME infers the FQNs syntax and usage knowledge encapsulated in prompt-tuned code MLM through a colze-style fill-in-blank strategy. POME is integrated as a plug-in into web and integrated development environments (IDE) to assist developers in inferring FQNs in the real world. We systematically evaluate POME on a large amount of source code from GitHub and Stack Overflow, and explore its generalization and hybrid capability. The results validate the effectiveness of the POME design and its applicability for partial code type inference, and they can be easily extended to different programming languages (PL). POME can also be used to generate a PL-hybrid type inference model for providing a one-for-all solution. As the first of its kind, our neural type inference method opens the door to many innovative ways of using partial code.

PDCNN-MRW: a parallel Winograd convolutional neural network algorithm base on MapReduce

PDCNN-MRW: a parallel Winograd convolutional neural network algorithm base on MapReduce

Application of Artificial Neural Network Base Enhanced MLP Model for Scattering Parameter Prediction of Dual-band Helical Antenna

Many design optimization problems have problems that seek fast, efficient and reliable based solutions. In such cases, artificial intelligence-based modeling is used to solve costly and complex problems. This study is based on the modeling of a multiband helical antenna using the Latin hypercube sampling (LHS) method using a reduced data enhanced multilayer perceptron (eMLP). The proposed helical antenna is dual-band and has resonance frequencies of 2.4 GHz and 2.75 GHz. The enhanced structure of the artificial neural network (ANN) was tested using 4 different training algorithms and a maximum of 10 different MLP architectures to determine the most suitable model in a simple and quick way. Then, performance comparison with other ANN networks was made to confirm the success of the model. Considering the high cost of antenna simulations, it is clear that the proposed model will save a lot of time. In addition, thanks to the selected sampling model, a wide range of modeling can be done with minimum data. When the target and prediction data are compared, it is seen that these data overlap to a large extent. As a result of the study, it was seen that the ANN modeling and the 125 samples used, were as accurate as an electromagnetic (EM) simulator for other input parameters in a wide range selected.

Behavioral effects of adult male mice induced by low-level acetamiprid, imidacloprid, and nicotine exposure in early-life.

Acetamiprid (ACE) and imidacloprid (IMI), the neonicotinoid chemicals, are widely used as pesticides because of their rapid insecticidal activity. Although these neonicotinoids exert very low toxicity in mammals, the effects of early, low-level, chronic exposure on the adult central nervous system are largely unclear. This study investigated the effects of low-level, chronic neonicotinoids exposure in early life on the brain functions of adult mice, using environmentally relevant concentrations. We exposed mice to an acceptable daily intake level of neonicotinoids in drinking water during the prenatal and postnatal periods. Additionally, we also exposed mice to nicotine (NIC) as a positive control. We then examined the effects on the central nervous system in adult male offspring. In the IMI and NIC exposure groups, we detected behavior that displayed impairment in learning and memory. Furthermore, immunohistochemical analysis revealed a decrease in SOX2 (as a neural stem cell marker) and GFAP (as an astrocyte marker) positive cells of the hippocampal dentate gyrus in the IMI and NIC exposure groups compared to the control group. These results suggest that exposure to neonicotinoids at low levels in early life affects neural circuit base formation and post-maturation behavior. Therefore, in the central nervous system of male mice, the effects of low-level, chronic neonicotinoids exposure during the perinatal period were different from the expected effects of neonicotinoids exposure in mature animals.

Soil-MobiNet: A Convolutional Neural Network Model Base Soil Classification to Determine Soil Morphology and Its Geospatial Location.

Scholars have classified soil to understand its complex and diverse characteristics. The current trend of precision agricultural technology demands a change in conventional soil identification methods. For example, soil color observed using Munsell color charts is subjective and lacks consistency among observers. Soil classification is essential for soil management and sustainable land utilization, thereby facilitating communication between different groups, such as farmers and pedologists. Misclassified soil can mislead processes; for example, it can hinder fertilizer delivery, affecting crop yield. On the other hand, deep learning approaches have facilitated computer vision technology, where machine-learning algorithms trained for image recognition, comparison, and pattern identification can classify soil better than or equal to human eyes. Moreover, the learning algorithm can contrast the current observation with previously examined data. In this regard, this study implements a convolutional neural network (CNN) model called Soil-MobiNet to classify soils. The Soil-MobiNet model implements the same pointwise and depthwise convolutions of the MobileNet, except the model uses the weight of the pointwise and depthwise separable convolutions plus an additional three dense layers for feature extraction. The model classified the Vellore Institute of Technology Soil (VITSoil) dataset, which is made up of 4864 soil images belonging to nine categories. The VITSoil dataset samples for Soil-MobiNet classification were collected over the Indian states and it is made up of nine major Indian soil types prepared by experts in soil science. With a training and validation accuracy of 98.47% and an average testing accuracy of 93%, Soil-MobiNet showed outstanding performance in categorizing the VITSoil dataset. In particular, the proposed Soil-MobiNet model can be used for real-time soil classification on mobile phones since the proposed system is small and portable.

Classification and detection of diabetic retinopathy based on multi-scale shallow neural network

<p class="15">The high-quality annotated training samples in medical image processing have limited the development of deep neural networks in their field. This paper designs and proposes an integrated method for classifying and detecting diabetic retinopathy based on a multi-scale shallow neural network. The method consists of multiple shallow neural network base learners, which extract pathological features under different receptive fields. The integrated learning strategy proposed is used to optimize the integration and finally realize the classification and detection of diabetic retinopathy. In addition, to verify the effectiveness of the method in this paper on a small sample data-set, based on the two-dimensional entropy of the image, multiple sub-datasets are constructed for verification. The results show that, compared with the existing methods, the integrated method for the classification and detection of diabetic retinopathy proposed in this paper has a good detection effect on a small sample data-set.</p>

Energy optimization and neural-based dynamic analysis of integrated multiple stage evaporator

Abstract Minimizing energy consumption is often a grave challenge in many industrial energy-intensive process units such as Multiple Stage Evaporator (MSE). Integration of Energy Reduction Schemes (ERSs) is a common technique to resume a countable amount of energy. Hence, the present work proposes a hybrid (h-) ERSs integrated MSE placed in the paper industry, used to increase the solid content of the black liquor. The h-ERSs Integrated MSE comprises several ERSs such as Thermo-Vapor Compressor, Steam-, Feed-split, and Feed Preheater to improve the energy efficiency significantly, and its energy performance is compared with base (b-) MSE. For this purpose, nonlinear mathematical models have been developed and transformed into a constrained optimization problem to search for the optimum energy efficiency obtained as Steam Economy (SE). A state-of-art metaheuristic approach, Equilibrium Optimizer (EO), along with some well-acquainted solution approaches (Interior Point OPTimizer, Interior Point Method, and Particle Swarm Optimization) has been simulated in different platforms to estimate the maximum SE to check their competitiveness for this industrial optimization problem. It is observed that EO outperformed all the algorithms with a 66 % higher SE for h-MSE than b-MSE. Eventually, the steady state parameters are applied as the initial conditions to analyze the nonlinear enthalpy dynamics of the b-and h-MSE. A neural base solution has been adopted to rigorously study the open-loop process dynamics that meet the desired product quality.

Comparison of RSNET model with existing models for potato leaf disease detection

Since crop diseases have a substantial impact on production, it is necessary to detect and identify them. Using deep learning and intelligent firming, diseased crops may be identified automatically. We present exceptionally efficient convolution neural network (CNN) designs for the detection of leaf diseases as part of this research plan. For the training and testing stages of this project, a potato leaf database is created. CNN was used to extract the illness's features from the input images of the provided training dataset so that the disease could be classified. 1700 photographs of potato leaf were utilised for model training, followed by 600 photographs for testing. To recognise citrus illnesses, Convolutional Neural Networks, Deep Learning, base learning, and transfer learning were used. The proposed architecture outperforms other existing ResNet models in terms of accuracy, reaching a score of 99.62%, according to training, testing, and experimentation results.

Subtypes of Developmental Dyslexia

In light of teaching students with dyslexia and other learning difficulties (LD), neuroscientists claim that such deficiencies happen due to a neural base, depending on biological and environmental factors, and experience developing properties and improving reading skills. The research claims two types of dyslexia: developmental (or innate) and deep (or acquired due to brain traumas or diseases). This article researches developmental dyslexia (DD), which may be primary and secondary. DD is divided into two main subtypes: surface and phonological While reading; our brains must "rewire" neural circuits initially used for other tasks, such as visual and speech processing and attention and cognition. Psycholinguistics investigates the cognitive process of perception, production, and general use of language. This article revises teaching English in light of neuroscience, psycholinguistics, and appropriate methods to train working memory and other ways to overcome DD and its subtypes.

Performance evaluation of plant leaf disease detection using deep learning models

Plant diseases have a serious impact on production, and hence they must be detected and recognised at early stages. Smart firming using deep learning can automatically identify infected crops. We provide extremely effective convolution neural network (CNN) designs for the identification of leaf diseases in this research strategy. For the training and testing phases of this study, a database of potato leaves is produced. To classify the disease from the input photos of the supported training dataset, we employed CNN to extract its characteristics. 1700 photos of potato leaves were used for model training, and then about 600 images were used for testing. To identify citrus diseases, Convolutional Neural Networks, Deep Learning, base learning, and transfer learning were applied. Results from training, testing, and experiments indicate that the suggested architecture has outperformed other current models in terms of ResNet model accuracy, achieving a score of 99.62%.

An Improved Energy Management Strategy of Diesel-Electric Hybrid Propulsion System Based on FNN-DP Strategy

Diesel-electric hybrid propulsion system (HPS) is widely applied for shunting locomotive due to the characteristics of flexible configuration, economic and environmental protection in the world. Energy management strategy (EMS) is an important design factor of HPS that can optimize the energy distribution of each power sources, improve system efficiency, and reduce fuel consumption. In this paper, the model of HPS for shunting locomotive and system operating profile are firstly carried out. Then the EMS consist of the conventional rule-based (RB) strategy rule, and a fuzzy neural network base on dynamic programming (FNN-DP) strategy are studied. Finally, the simulations were carried out with these EMSs in the system model at full operating conditions to derive the fuel consumption. The conclusion is that the theoretical optimal solution of DP provides reference and guidance for the fuzzy neural network strategy to improve the rules, and the fuel consumption of the FNN-DP strategy is 10.2% lower than the conventional RB strategy.

A composite learning approach for multiple fault diagnosis in gears

A major part of Prognostic and Health Management of rotating machines is dedicated to diagnosis operations. This makes early and accurate diagnosis of single and multiple faults an economically important requirement of many industries. With the well-known challenges of multiple faults, this paper proposes a new Blended Ensemble Convolutional Neural Network – Support Vector Machine (BECNN-SVM) model for multiple and single faults diagnosis of gears. The proposed approach is obtained by preprocessing the acquired signals using complementary signal processing techniques. This form inputs to 2D Convolutional Neural Network base learners which are fused through a blended ensemble model for fault detection in gears. Discriminative properties of the complementary features ensure the high capabilities of the approach to give good results under different load, speed, and fault conditions of the gear system. The experimental results show that the proposed method can accurately detect rotating machine faults. The proposed approach compared with other state-of-the-art methods indicates improved overall effectiveness for gear faults diagnosis.

Skin Cancer Diagnosis Based on Neutrosophic Features with a Deep Neural Network.

Recent years evidenced an increase in the total number of skin cancer cases, and it is projected to grow exponentially. This paper proposes a computer-aided diagnosis system for the classification of a malignant lesion, where the acquired image is primarily pre-processed using novel methods. Digital artifacts such as hair follicles and blood vessels are removed, and thereafter, the image is enhanced using a novel method of histogram equalization. Henceforth, the pre-processed image undergoes the segmentation phase, where the suspected lesion is segmented using the Neutrosophic technique. The segmentation method employs a thresholding-based method along with a pentagonal neutrosophic structure to form a segmentation mask of the suspected skin lesion. The paper proposes a deep neural network base on Inception and residual blocks with softmax block after each residual block which makes the layer wider and easier to learn the key features more quickly. The proposed classifier was trained, tested, and validated over PH2, ISIC 2017, ISIC 2018, and ISIC 2019 datasets. The proposed segmentation model yields an accuracy mark of 99.50%, 99.33%, 98.56% and 98.04% for these datasets, respectively. These datasets are augmented to form a total of 103,554 images for training, which make the classifier produce enhanced classification results. Our experimental results confirm that the proposed classifier yields an accuracy score of 99.50%, 99.33%, 98.56%, and 98.04% for PH2, ISIC 2017, 2018, and 2019, respectively, which is better than most of the pre-existing classifiers.

Material Model Calibration Using Machine Learning: A Comparative Study

A methodology based on Machine Learning, namely Fully Connected Neural Networks, is proposed to replace traditional parameter calibration strategies. In particular, the relation between hardness, yield strength and tensile strength is explored. The proposed methodology is used to predict the yield strength and the tensile strength of a Super Duplex Stainless Steel that was not included in the neural network training data base. Moreover, it is also used to determine such material parameters for individual microstructural phases, which feed a multiscale Finite Element simulation. The methodology is experimentally validated.

Memristive technologies for the implementation of a neural network element base

Memristive technologies for the implementation of a neural network element base

Vertebral pneumaticity of the paravian theropod Unenlagia comahuensis, from the Upper Cretaceous of Patagonia, Argentina

Postcranial skeletal pneumaticity (PSP) characterizes extant birds. This feature is related to a series of air sacs connected to the lungs and prolonged in diverticula that invade bones internally. Previous works revealed that PSP was present along the line to birds, being distinctive of pterosaurs and saurischian dinosaurs. PSP is profuse in the vertebral column of sauropods and theropods and was very studied in sauropods, although scarcely in non-avian theropods. Here we analyze the vertebral pneumaticity of the unenlagiine theropod Unenlagia comahuensis, including the observation through CT scans. Unenlagiinae is a clade of southern dromaeosaurid theropods that is closely related to birds. The vertebral centra have lateral pneumatic foramina (lpf) within fossae (commonly termed ‘pleurocoels’) in middle and posterior dorsals, an unusual feature among extant birds and many non-avian theropods. Another possibly pneumatic fossa stands out at both sides of the neural spine base, which is not present in dorsals of other non-avian theropods, except the unenlagiine Unenlagia paynemili. CT scans revealed camellate tissue in the centra, consisting of small chambers separated by thin trabeculae. Camellae are also observed in the unenlagiines U. paynemili and Austroraptor cabazai, other dromaeosaurids, other coelurosaurs, and some non-coelurosaurian tetanurans. Instead, more primitive groups generally have camerae (larger chambers separated by scarce thick septa). Thus, a possible trend of the vertebral inner pneumaticity types is observed throughout non-avian theropod evolution, as indicated by previous authors. This study provides valuable information that helps to clarify this trend, not only in dromaeosaurids but also throughout theropod evolution.

Artificial neural network base on grey relational analysis estimate displacement of bridge-type amplifier

The power of complaint mechanisms is able for a dramatic reduction in the number of parts required to compass a specified task. It may reduce manufacturing and assembly time and cost. Reduce the number of joints can also increase mechanism precision. The output displacement must be larger than input displacement with lower stress. Thus, Optimize geometry-shape for besting parameter design of the structure was investigated in this paper. The part was designed by Autodesk Inventor and determined displacement amplifier and stress by FEM in ANSYS. We estimate the displacement of a bridge-type amplifier using Artificial Neural Network (ANN) and regression method (RM) base on Grey relational analysis (GRA). The variability of the thickness, the incline angle, the length and the width of the flexure hinges (FH) affects the variability of target displacement (DI) and stress (ST). The influence of the width and the area of the location force is very small and not clear. The result of the simulation is verified by ANOVA and also compared with the predicted value of ANN, GRA, and RM. The displacement of a bridge-type amplifier is reached 0.95 mm with displacement input 0.01 mm. The ratio amplifier is got 95 times.