Modular Neural Network Approach Research Articles

Directional ΔG Neural Network (DrΔG-Net): A Modular Neural Network Approach to Binding Free Energy Prediction.

The protein-ligand binding free energy is a central quantity in structure-based computational drug discovery efforts. Although popular alchemical methods provide sound statistical means of computing the binding free energy of a large breadth of systems, they are generally too costly to be applied at the same frequency as end point or ligand-based methods. By contrast, these data-driven approaches are typically fast enough to address thousands of systems but with reduced transferability to unseen systems. We introduce DrΔG-Net (or simply Dragnet), an equivariant graph neural network that can blend ligand-based and protein-ligand data-driven approaches. It is based on a 3D fingerprint representation of the ligand alone and in complex with the protein target. Dragnet is a global scoring function to predict the binding affinity of arbitrary protein-ligand complexes, but can be easily tuned via transfer learning to specific systems or end points, performing similarly to common 2D ligand-based approaches in these tasks. Dragnet is evaluated on a total of 28 validation proteins with a set of congeneric ligands derived from the Binding DB and one custom set extracted from the ChEMBL Database. In general, a handful of experimental binding affinities are sufficient to optimize the scoring function for a particular protein and ligand scaffold. When not available, predictions from physics-based methods such as absolute free energy perturbation can be used for the transfer learning tuning of Dragnet. Furthermore, we use our data to illustrate the present limitations of data-driven modeling of binding free energy predictions.

BDN-GWMNN: Internet of Things (IoT) Enabled Secure Smart City Applications

Nowadays, next-generation networks such as the Internet of Things (IoT) and 6G are played a vital role in providing an intelligent environment. The development of technologies helps to create smart city applications like the healthcare system, smart industry, and smart water plan, etc. Any user accesses the developed applications; at the time, security, privacy, and confidentiality arechallenging to manage. So, this paper introduces the blockchain-defined networks with a grey wolf optimized modular neural network approach for managing the smart environment security. During this process, construction, translation, and application layers are created, in which user authenticated based blocks are designed to handle the security and privacy property. Then the optimized neural network is applied to maintain the latency and computational resource utilization in IoT enabled smart applications. Then the efficiency of the system is evaluated using simulation results, in which system ensures low latency, high security (99.12%) compared to the multi-layer perceptron, and deep learning networks.

A new modular neural network approach with fuzzy response integration for lung disease classification based on multiple objective feature optimization in chest X-ray images

This paper describes a new hybrid approach, based on modular artificial neural networks with fuzzy logic integration, for the diagnosis of pulmonary diseases such as pneumonia and lung nodules. In particular, the proposed approach analyzes medical images, which are digitized chest X-rays, focusing on a classification method based on descriptors, such as grayscale histogram features, gray-level co-occurrence matrix (GLCM) texture-based features, and local binary pattern texture features. Then, to perform feature reduction, a multi-objective genetic algorithm is used to obtain an optimized neuro-fuzzy classifier, which is able to classify the pathology found in the analyzed chest X-ray. The main contribution of this paper is the proposed modular neural network approach, which divides features to achieve specialized analysis in the modules for digital image analysis and classification. The proposed approach achieves high classification accuracy after evaluating the neuro-fuzzy model with three large datasets of chest X-rays.

A new modular neural network approach for exchange rate prediction

A novel approach using modular neural networks to forecast exchange rates based on harmonic patterns in Forex market is introduced. The proposed approach employs three algorithms to predict price, validate its prediction and update the system. The model is trained by historical data using major currencies in Forex market. The proposed system's predictions were evaluated by comparing its results with a non-modular neural network. Results showed that the infrastructure market data consist of significant accurate relations that a single network cannot detect these relations and separate trained networks in specific tasks are needed. Comparison of modular and non-modular systems showed that modular neural network outperforms the other one.

Genetic Optimization of Neural Networks for Person Recognition Based on the Iris

This paper describes the application of modular neural network architectures for person recognition using the human iris image as a biometric measure. The iris database was obtained from the Institute of Automation of the Academy of Sciences China (CASIA). We show simulation results with the modular neural network approach, its optimization using genetic algorithms, and the integration with different methods, such as: the gating network method, type-1 fuzzy integration and optimized fuzzy integration using genetic algorithms. Simulation results show a good identification rate using fuzzy integrators and the best structure found by the genetic algorithm.

Genetic Optimization of Neural Networks for Person Recognition based on the Iris

This paper describes the application of modular neural network architectures for person recognition using the human iris image as a biometric measure. The iris database was obtained from the Institute of Automation of the Academy of Sciences China (CASIA). We show simulation results with the modular neural network approach, its optimization using genetic algorithms, and the integration with different methods, such as: the gating network method, type-1 fuzzy integration and optimized fuzzy integration using genetic algorithms. Simulation results show a good identification rate using fuzzy integrators and the best structure found by the genetic algorithm.

Modular neural network approach for short term flood forecasting a comparative study

The artificial neural networks (ANNs) have been applied to various hydrologic problems recently. This research demonstrates static neural approach by applying Modular feedforward neural network to rainfall-runoff modeling for the upper area of Wardha River in India. The model is developed by processing online data over time using static modular neural network modeling. Methodologies and techniques for four models are presented in this paper and a comparison of the short term runoff prediction results between them is also conducted. The prediction results of the Modular feedforward neural network with model two indicate a satisfactory performance in the three hours ahead of time prediction. The conclusions also indicate that Modular feedforward neural network with model two is more versatile than other and can be considered as an alternate and practical tool for predicting short term flood flow.

تفسيرات بعض الاجسام المغناطيسية بالاسلوب التعاكسي مستعملا الشبكات العصبية

Magnetic surveys have been used for mineral exploration where different data processing techniques were used to derive the parameters of causative targets. In this respect, the neural network (NN) technique was used to estimate the magnetic causative target parameters. Examples of NN inversion have been tested on synthetic examples where the NN was trained well using forward models of the vertical magnetic effect of a vertical sheet and a horizontal circular cylinder. Specifically, modular neural network (MNN) inversion has been used for the parameter estimation of the causative targets, where the sigmoid function was used as the activation function. The effect of random noise and the error estimation of the horizontal location have been analyzed. When NN is applied to real data, it estimates successfully the parameters of the causative targets such as burial depths, magnetic constants, and angle of polarization. Hilbert transform has been used to locate the source origin, which is important for the NN inversion. This approach has more advantages than the conventional data inversions in terms of its efficiency and flexibility. It also gives fast solutions. The MNN approach has been applied to the Kursk and Manjampalli anomalies, where the results were shown to be in good agreement with the other techniques published in the literature.

Modular Neural Network-Based Directional Relay for Transmission Line Protection

This letter proposes the application of a modular neural network as a mechanism to discriminate the direction of faults for transmission line protection. The modular neural network approach solves a relatively complex problem by decomposing it into simpler subtasks that are easier to manage and then assembles the solution from the results of the subtasks. In addition to the obvious advantages of a neural network as a fault classifier, incorporation of modularity to the network structure provides more important positive attributes like model complexity reduction, better learning capability, etc. The modular neural network concept has been utilized successfully to develop a directional relay algorithm for a transmission system and subsequently implemented on a DSP TMS320F243 EVM-board.

Identification of crack location and depth in a cantilever beam using a modular neuralnetwork approach

In this paper, the flexural vibration in a cantilever beam having a transverse surface crackis considered. The modal frequency parameters are analytically computed for various cracklocations and depths using a fracture mechanics based crack model. These computed modalfrequencies are used to train a neural network to identify both the crack location anddepth. The sensitivity of the modal frequencies to a crack increases when the crack is nearthe root and decreases as the crack moves to the free end of the cantilever beam. Becauseof the sensitive nature of this problem, a modular neural network approach is used. First,the crack location is identified with computed modal frequency parameters. Next,the crack depth is identified with computed modal frequency parameters andthe identified crack location. A comparative study is made using the modularneural network architecture with two widely used neural networks, namely themulti-layer perceptron network and the radial basis function network. The proposedmodular neural network method with a radial basis function network is found toperform better than the multi-layer perceptron network. In addition, the radialbasis function network takes less computational time to train the network thanthe multi-layer perceptron network. This modular neural network architecturecan be used as a non-destructive procedure for health monitoring of structures.

Face recognition using modular neural networks and the fuzzy Sugeno integral for response integration

We describe a new approach for face recognition using modular neural networks with a fuzzy logic method for response integration. We proposed a new architecture for modular neural networks for achieving pattern recognition in the particular case of human faces. Also, the method for achieving response integration is based on the fuzzy Sugeno integral. Response integration is required to combine the outputs of all the modules in the modular network. We have applied the new approach for face recognition to a real database of faces of students at our institution. Recognition rates with the modular approach were compared against the monolithic single neural network approach to measure the improvement. The results of the new modular neural network approach were excellent overall and also in comparison to the monolithic approach. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 275–291, 2005.

Drying of Carrots in a Fluidized Bed. II. Design of a Model Based on a Modular Neural Network Approach

The present paper deals with the design of a neural network type model for drying of carrots, which includes the associated transport mechanisms of the process. The model uses the operational variables and the time as input parameters. Two sub-layers of linear and sigmoidal nodes make up the hidden layer, to represent the external and internal resistances to the diffusion of water vapors during the drying process. The single output node weights the contribution of each mechanism of the drying process to predict the exit moisture content of the product. This model was used to predict the drying of carrot particles in a mechanically fluidized bed dryer reported in a previous paper [Reyes, A.; Alvarez, P.; Marquardt, F. Drying of carrots in a fluidized bed: I.- effects of drying conditions and modeling. Drying Technology 2002, 20 (7), 1463–1483.]. Simulated drying curves obtained with this model fits adequately the curves determined experimentally for the most operation conditions, which would indicate that this model is appropriate to be used for rough estimations in the design, the selection of optimal operational conditions, and the scaling up of dryers.

Derivation of the ionospheric structure over extended geographical regions from azimuth and elevation scan backscatter ionograms: A modular neural network approach

This paper describes a new real‐time inversion method based upon multifrequency sounding schemes and variable azimuth and elevation angle backscatter ionograms for the derivation of the three‐dimensional structure of the ionosphere. The inversion technique which has been developed for this purpose employs neural network models in a modular structure and is fully explained. Tests on simulated data demonstrate the potential accuracy of the method for reconstructing the electron density profile over remote geographical regions.

Simulation of Quantification Abilities Using a Modular Neural Network Approach

A novel modular neural network architecture and its application to the field of numerical cognition simulation are presented. Previous modular connectionist systems are typically constrained at one of two levels: at the representational level, in that the connectivity of the modules is hard-wired by the modeller; or at a local architectural level, in that the modeller explicitly allocates each module to a specific subtask, Our approach aims to minimise the constraints, thus reducing the bias possibly introduced by the modeller. The efficacy of this approach is demonstrated through the successful simulation of the development of two quantification abilities, subitising and counting, amongst children. It is concluded that such a minimally constrained modular system may contribute to both the capturing of learnt behaviour, and the allocation of modules to subtasks according to the nature of the task.

A modular neural network approach to microelectronic circuit yield optimization

The unpredictable variation in microelectronic circuits due to process tolerances increases significantly with increased levels of miniaturization. If ignored, the variation will result in poor manufacturing yield. If a worst-case approach is adopted, a loss of competitive edge results. This situation provides the motivation for efficient robust design of VLSI circuits, the subject of this paper. Given the need for efficiency of analysis without significant loss of accuracy, a method is proposed which generates a neural network for mapping process-level parameters to circuit performance. The approach uses a modular neural network—an adaptive mixture of local experts competing to learn different aspects of a problem. Once the neural network model is established and validated, it is employed in performing extremely efficient optimization of the circuit yield at minimal cost: the trained ANN acts as a cheap but accurate simulator which when supplied with a set of inputs which characterize transistors at the process and device level calculates the circuit performance with 97% accuracy at 1% of the cost of a full SPICE simulation. Even when the cost of ANN training is factored in, average cost savings of 80% are achieved during yield optimization. The neural net approach offers significant advantages including vastly reduced computational cost with little loss of accuracy and complete generality of application.

A modular neural network approach to fault diagnosis

Certain real-world applications present serious challenges to conventional neural-network design procedures. Blindly trying to train huge networks may lead to unsatisfactory results and wrong conclusions about the type of problems that can be tackled using that technology. In this paper a modular solution to power systems alarm handling and fault diagnosis is described that overcomes the limitations of "toy" alternatives constrained to small and fixed-topology electrical networks. In contrast to monolithic diagnosis systems, the neural-network-based approach presented here accomplishes the scalability and dynamic adaptability requirements of the application. Mapping the power grid onto a set of interconnected modules that model the functional behavior of electrical equipment provides the flexibility and speed demanded by the problem. After a preliminary generation of candidate fault locations, competition among hypotheses results in a fully justified diagnosis that may include simultaneous faults. The way in which the neural system is conceived allows for a natural parallel implementation.

Robust Classifiers without Robust Features

We develop a two-stage, modular neural network classifier and apply it to an automatic target recognition problem. The data are features extracted from infrared and TV images. We discuss the problem of robust classification in terms of a family of decision surfaces, the members of which are functions of a set of global variables. The global variables characterize how the feature space changes from one image to the next. We obtain rapid training times and robust classification with this modular neural network approach.