Artificial Neural Networks

Identification of the safe usable road is a crucial task for autonomous vehicles and robots. It is one of the main parameters which help in elevating the level of automation. The autonomous vehicle needs to understand the difference between various types of roads present in various conditions. External factors like lighting effects, shadows, weather conditions, occlusions, and mobile passengers also need to be considered. It helps in avoiding an obstacle, path planning, and decision making. It is useful in conditions where lane markings are not visible, example-road covered by snow or due to poor lighting conditions or lane markings not present (in certain rural and urban roads). There are many different ways to overcome these difficult situations using multiple sensors like monocular camera images, stereo images, RADAR sensor, LiDAR sensor, Inertial Measurement Unit (IMU), Global Positioning System (GPS) information and pre-loaded maps. Here we have presented a survey of various road extraction techniques.

With the advancement in technology, attackers are making use of cyberspace to perform various cyber attacks. Cyber frameworks are highly sensitive to intrusion as well as many other threats. As every workplaces now a days are connected to some network in one way or another leads to heavy traffic or network congestion, more security attack attempts and security breaches. We need to have security from these attacks. The treatment of various attacks is also accessible, but the approach to find which system is being attacked is difficult. This paper provides an introduction of the Cyber Security techniques and how Artificial Intelligence (AI) could help in solving the cyber security problems. It also shows the work done in the area of Artificial Intelligence for fighting against cyber assaults.

Many years ago neural networks were subject of scientific research conducted only for curiosity. The researchers pursue to better understanding of natural brain behavior by means of forming of mathematical, electronic and simulation models. Unexpectedly as additional result of such research new computational tool occur, which very fast become huge popularity and high effectiveness. Now, when typical neural networks are used almost by everybody for almost everything – new progress in computational applications can come from new “cut end” research on neurocybernetics. The paper shows short survey of some most promising areas of current neurocybernetic research for inducting new possible technological inspirations.

This study presents a method based on an artificial neural network (ANN) for protecting voltage source converters (VSC)-high-voltage direct current (HVDC) systems. The proposed method takes advantage of ANNs' excellent capabilities in pattern recognition and classification. The solution presented here is able to detect a fault condition in the whole HVDC system based only on voltage waveforms measured at the rectifier substation, which is an important advantage over other fault detection methods. For any given fault condition, the faulty zone is identified and then the fault is classified concerning the phases or poles involved. The proposed method is shown to be both robust against false operations and very reliable with respect to fault detection and classification. A large number of simulations were performed and results show the effectiveness of the proposed scheme. Different operational conditions and fault cases were considered to evaluate the proposed algorithm, ensuring excellent performance concerning a wide range of possible situations in VSC-HVDC systems.

Artificial neural networks have been in the position of producing complex dynamics in control applications over the last decade, especially when they are linked to feedback. Although ANNs are strong for network design, the harder the design of the network, the more complex the desired dynamic is. Many researchers tried to automate the design process of ANN using computer programs. Search and optimization problems can be considered as the problem of finding the best parameter set for a network to solve a problem. Recently, the problem of optimizing ANN parameters to train different research datasets has been targeted by two commonly used stochastic genetic algorithms (GA). The process based on the neural network is optimized with GA to enable the robot to perform complex tasks. However, using such optimization algorithms to optimize the ANN training process cannot always be balanced or successful. These algorithms simultaneously aim to develop three main components of an ANN: synaptic weight, connections, architecture and transfer functions set for each neuron. Developed with the proposed approach, ANN is also compared with hand-designed Levenberg-Marquardt and Back Propagation algorithms.

The application of advanced oxidation process (AOP) in the treatment of wastewater contaminated with oil was investigated in this study. The AOP investigated is the homogeneous photo-Fenton (UV/H2O2/Fe(+2)) process. The reaction is influenced by the input concentration of hydrogen peroxide H2O2, amount of the iron catalyst Fe(+2), pH, temperature, irradiation time, and concentration of oil in the wastewater. The removal efficiency for the used system at the optimal operational parameters (H2O2 = 400 mg/L, Fe(+2) = 40 mg/L, pH = 3, irradiation time = 150 min, and temperature = 30 °C) for 1,000 mg/L oil load was found to be 72%. The study examined the implementation of artificial neural network (ANN) for the prediction and simulation of oil degradation in aqueous solution by photo-Fenton process. The multilayered feed-forward networks were trained by using a backpropagation algorithm; a three-layer network with 22 neurons in the hidden layer gave optimal results. The results show that the ANN model can predict the experimental results with high correlation coefficient (R (2) = 0.9949). The sensitivity analysis showed that all studied variables (H2O2, Fe(+2), pH, irradiation time, temperature, and oil concentration) have strong effect on the oil degradation. The pH was found to be the most influential parameter with relative importance of 20.6%.

The application of advanced oxidation process (AOP) in the treatment of wastewater contaminated with oil was investigated in this study. The AOP investigated is the homogeneous photo-Fenton (UV/H2O2/Fe(+2)) process. The reaction is influenced by the input concentration of hydrogen peroxide H2O2, amount of the iron catalyst Fe(+2), pH, temperature, irradiation time, and concentration of oil in the wastewater. The removal efficiency for the used system at the optimal operational parameters (H2O2 = 400 mg/L, Fe(+2) = 40 mg/L, pH = 3, irradiation time = 150 min, and temperature = 30 °C) for 1,000 mg/L oil load was found to be 72%. The study examined the implementation of artificial neural network (ANN) for the prediction and simulation of oil degradation in aqueous solution by photo-Fenton process. The multilayered feed-forward networks were trained by using a backpropagation algorithm; a three-layer network with 22 neurons in the hidden layer gave optimal results. The results show that the ANN model can predict the experimental results with high correlation coefficient (R (2) = 0.9949). The sensitivity analysis showed that all studied variables (H2O2, Fe(+2), pH, irradiation time, temperature, and oil concentration) have strong effect on the oil degradation. The pH was found to be the most influential parameter with relative importance of 20.6%.

El presente artículo expone una metodología utilizada para la predicción de consumo de combustible con el objetivo de realizar estrategias operativas para un abastecimiento continuo con reducción de riesgos y minimización de costos. Ello es posible si se efectúan simulaciones con los resultados predichos.

La predicción se lleva a cabo con la ayuda de Redes Neuronales Artificiales, basada en el histórico de los consumos en un periodo de dos o más años. Se aplicó la metodología en cinco industrias con diferentes productos y ciclos de producción y se obtuvieron resultados muy aceptables (error promedio inferior al 2%) si se considera que el consumo de cada industria está ligado a la demanda de su producto, mantenimientos programados y no programados, entre otros. Así, se demuestra que el uso de redes neuronales es eficiente en el reconocimiento de patrones de consumo de combustible, lo que permite su integración con otras metodologías para optimizar la logística.

Autor: Gonzalo Aragón, Neogás

Very likely, we shall eventually be able to own humanoid robots that—in professional interactions, casual conversations, and even shallow romantic relationships—will act persuasively human. In this article, I ask two questions: What is it that we will have made? And more importantly, through these artificial entities, what will we make ourselves become?

Agriculture hold an important sector in the Indian economy as it contributes around 18% of India's gross domestic product (GDP). India is an agricultural based country where more than 50% of the population depends on agricultural. Hence there is a need to provide farmers with the effective technology and knowledge to yield better crops based on the type of soil. Different types of soil are present in India. Different types of soil have different mineral contents and each crop require different mineral components for their better growth. Each soil has certain specific characteristic and is suitable to grow only certain number of crops. Hence a farmer should know about the type of soil he possesses so that he can cultivate better crops. In this paper we have described various effective algorithms and neural network techniques which have been used to classify the soil data based on the mineral contents and predict the best suitable crop for it.

Expert systems have a major role in medicine. The expert system can: Diagnose and treat diseases by building intelligent database. There are many expert systems used in the treatment of diseases. In this paper, the researcher reviews some of the expert systems used to diagnose diseases.

This paper presents an intelligent based system for grading hulled and non-hulled pistachio nuts. The first step in the pistachio nuts preparation process is to hull and to peel the picked crops. In pistachio preparation terminals, the manual separation of hulled pistachios from those without hull, increases price and contamination and decreases the quality. The proposed research introduces an automatic system based on image processing technique to enhance the accuracy in detecting the hulled and non-hulled pistachio nuts. Three ordinary classifiers including: Multilayer Feed forward Neural Network (MFNN), Radial Basis Function Neural Network (RBFNN) and Support Vector Machine (SVM) are then applied to select the best classifier for pistachio nuts process. To evaluate the performance of the system 200 pistachio nuts from four native Iranian pistachio nuts varieties are used. Each variety consists of 100 hulled and 100 non-hulled nuts. Experimental results show an accuracy of 95% and average time period of about 0.02 second for the best selection of the system. The pistachio tree belongs to the family anacardiaceae, of which the cashew, mango, sumac and poison oak are also members. There are more than sixty species of pistachio in different regions of Iran. One of the important steps of pistachio nuts grading is to separate the non-hulled pistachio nuts from the hulled ones. Pistachios processing factories begin to hull pistachio nuts after harvesting process. In practice, non-hulled pistachio nuts might be separated manually from the hulled ones at the end of the processing line and with traditional methods. Insects, fungus and aflatoxin increasing are also observed due to the unpeeled crops. Consequently, the price and the quantity of the harvested crops would be reduced [1, 2]. At the end of the line processing, samples would be classified into five groups in order to their type of hull as shown in fig. 1. Figure 1: Types of pistachios at the end of processing line: (A) the image of cracked hulled pistachio(open), (B) non-hulled pistachio, (C) half-hulled pistachio, (D) non-cracked hulled pistachio(close), (E) cracked, hulled pistachio as wastes. In this research, a mechatronics system is proposed to select samples one by one and to separates hulled and non-hulled samples automatically by processing the images. In half-hulled type, at least %15 of the pistachio nuts is hulled. Some methods and solutions are proposed to recognize cracked and semi-cracked pistachios [3]. In order to decrease Aflatoxin (A toxin specifically to plant) and increase the quality of the exported pistachio, some works are conducted as follows: Pearson et al. proposed a sorting system which has been developed for the separation of small in-shell pistachio nuts from kernels without shells on the basis of vibration generated when moving samples strike a steel plate. Impacts between the steel plate and the hard shells are measured using an accelerometer attached to the bottom of the plate, produce higher frequency signals than impacts between the plate and the kernels. On the other hand, signal amplitudes were highly variable which made them useless for the separation of samples. They developed another system by using both amplitude and frequency information to classify the signals. The algorithm activated an air nozzle to divert in-shell nuts away from the kernel stream. A prototype sorter was tested at throughput rates of 0.33, 10, 20, and 40 nuts per second using a mix of 10% in-shell and 90% kernels at the lowest throughput rate; classification accuracies were 96% for in-shell nuts and 99% for kernels. For throughput rates between 10 and 40 nuts/s, correct classification ranged from 84 to 90% for in-shell nuts. For kernels, accuracy was 95% at 10 and 20 nuts/s and 89% at 40 nuts/s [4]. Another research is led in California to grade pistachios with shell by image processing; this research illustrates the feasibility of using color imaging

JUAL VIAGRA ASLI DI JAKARTA ® viagraaslidijakarta.online,JUAL VIAGRA,VIAGRA ASLI,AGEN VIAGRA,PUSAT VIAGRA,VIAGRA ECERAN,OBAT KUAT TAHAN LAMA,JUAL VIAGRA ASLI DI banyu wangi,JUAL VIAGRA ASLI DI balikpapan,JUAL VIAGRA ASLI DI surabaya,JUAL VIAGRA ASLI DI bandung,JUAL VIAGRA ASLI DI banjarmasi kalimantan,JUAL VIAGRA ASLI DI banda aceh,JUAL VIAGRA ASLI DI kalimantan,JUAL VIAGRA ASLI DI bandar lampung,JUAL VIAGRA ASLI DI bangka balitung,JUAL VIAGRA ASLI DI banjarmasin,JUAL VIAGRA ASLI DI batam,JUAL VIAGRA ASLI DI bekasi,JUAL VIAGRA ASLI DI bengkulu,JUAL VIAGRA ASLI DI bogor,JUAL VIAGRA ASLI DI bontang,JUAL VIAGRA ASLI DI cilacap,JUAL VIAGRA ASLI DI cilegon,JUAL VIAGRA ASLI DI cirebon,JUAL VIAGRA ASLI DI denpasar,JUAL VIAGRA ASLI DI depok,JUAL VIAGRA ASLI DI gorontalo,JUAL VIAGRA ASLI DI jepara,JUAL VIAGRA ASLI DI jambi,JUAL VIAGRA ASLI DI jayapura,JUAL VIAGRA ASLI DI jember,JUAL VIAGRA ASLI DI karawang,JUAL VIAGRA ASLI DI kediri,JUAL VIAGRA ASLI DI kendari,JUAL VIAGRA ASLI DI kupang,JUAL VIAGRA ASLI DI kudus,JUAL VIAGRA ASLI DI pati,JUAL VIAGRA ASLI DI madiun,JUAL VIAGRA ASLI DI madura,JUAL VIAGRA ASLI DI magelang,JUAL VIAGRA ASLI DI malang,JUAL VIAGRA ASLI DI manado,JUAL VIAGRA ASLI DI mataram,JUAL VIAGRA ASLI DI medan,JUAL VIAGRA ASLI DI mojokerto,JUAL VIAGRA ASLI DI padang,JUAL VIAGRA ASLI DI palangkaraya,JUAL VIAGRA ASLI DI palembang

Human activity recognition based on sensor data is a topic with great potential for customized healthcare. Here, an end-to-end deep learning architecture for human activity/transition recognition is developed, achieving an error rate of 0.82%. Various deep learning models are analyzed, and a hyperparameter search is conducted to optimize our chosen model. First, an LSTM architecture is examined, which has the advantage of allowing variable-length input sequences for both training and inference. However, our best architecture (HATRNet) is a deep convolutional neural network with late sensor fusion i.e. separate processing pipelines for subsets of the input channels. We feed in zero-padded time sequences to our network, and achieve accuracy exceeding the state-of-the-art reported in literature--all without the use of hand-extracted features.