Abstract

— In this paper, we address the highly challenging problem of object goal navigation. The agent, in an unseen environment, has to perceive its surroundings to identify and navigate towards potential regions where the specified goal category can occur. Rather than developing goal driven exploration policies, we aim to adapt the existing exploration policies that maximize scene coverage to be goal-conditioned. Thus, we propose a standalone scene understanding module to identify potential regions where the goal occurs. We also propose Goal-Conditioned Exploration (GCExp), an algorithm that entails the integration of our novel scene understanding module with any existing exploration policy. We test our solution in photo-realistic simulation environments using stateof-the-art exploration policy, Active Neural Slam [1], and show improved performance over the same on every evaluation metric.

Abstract

Synthetic ion channels are a promising technology in the medical and materials sciences because of their ability to conduct ions. Channels based on cyclodextrin, a cyclic oligomer of glucose, are of particular interest because of their non-toxicity and bio-compatibility. Using molecular dynamics-based free energy calculations, this study identifies cyclodextrin channel types that are best suited to serve as synthetic ion channels. Free energy profiles show that the connectivity in the channel determines whether the channel is cation-selective or anion-selective. Furthermore, the energy barrier for ion transport is governed by the number of glucose molecules constituting the cyclodextrin units of the channel. A detailed mechanism is proposed for ion transport through these channels. Findings from this study will aid in designing cyclodextrinbased channels that could be either cation-selective or anion-selective, by modifying the linkages of the channel or the number of glucose molecules in the cyclodextrin rings.

Abstract

In this chapter, we introduce Hopfield neural networks based on the ceiling neuron model. Inspired by the binary Hopfield neural network and by the definition of ceiling neuron, we propose an extension of the Hopfield neural network from a binary set of possible states of a real-valued neuron to a multistate set. We investigate the dynamics of the proposed model in asynchronous and synchronous update modes. Computational experiments illustrate that the Hopfield neural network based on the ceiling neuron in an asynchronous update mode always settles down to a stationary state under the usual conditions on synaptic weights, that is, the synaptic weight matrix is symmetric with non-negative diagonal elements. In turn, the Hopfield neural network with ceiling neurons in the synchronous update mode can generate limit cycles, similarly to the classic Hopfield neural network.

Abstract

In this research paper storage as well as retrieval of 1-D/2-D/3-D information using Hopfield type Associative Memories (AMs) is discussed. Various Artificial Neural Networks(ANN) architectures are proposed. Also, implementational issues associated with those Associative Memories are discussed. Cascade connection of AM and Convolutional Neural Network is proposed for noise immunity. Keywords: Associative Memories, Hopfield Network, Ceiling Neuron

Abstract

Over the past two decades, a growing thrust area of research has been electrification of different mechanical and hydraulic systems in ground vehicles, which offers less environmental concerns due to the removal of hydraulic fluids and continual engine parasitic losses. The electrical equivalents for traditional mechanical linkages and hydraulic power assist systems include ‘brakeby-wire’, ‘steer-by-wire’ and ‘throttle-by-wire’ system. These equivalents, collectively known as ‘X-by-Wire’ technologies, form the fundamental structure for the Semi and Fully Autonomous Driving Systems 1 . As compared to a traditional steering system, a Steer-by-Wire (SBW) system removes the mechanical shaft that connects the steering column and steering pinion: therefore, in absence of any physical connection, the steering input is transmitted via a by-wire electronic communication module 2 (cf. Fig. 1). In order to have the SBW equipped vehicle have the similar features to that of a conventional steering system, it is important to devise a tracking control mechanism for the steering actuator such that the steering commands from hand-wheel are followed as precisely as possible. Initial attempts were made to solve such control problem employing conventional PID controller 3,4; however, in presence of inevitable modelling imprecision and parametric uncertainties, advanced control strategies are eventually

Abstract

Wireless Sensors that are small in size and limited battery capacity are widely used for several different applications. For this reason energy efficient as well as cost of the overall network are the two main factors influencing the Wireless Sensor Networks (WSN) performance. In this research paper, in Wireless Sensor Network, energy efficient placement of sensors on the uniform rectangular grid (as sensor field) is proposed. Also, distributed computation of minimum and/or maximum over such sensor field is discussed (for minimizing computations and communications delay). Index Terms—Sensor Placement, Leveling, Clustering, Energy Efficiency, Network Lifetime, Cost Minimization,

Abstract

In this paper, we quantitatively show the energy savings obtained in a heterogeneous wireless sensor network, by using Weighted Centriod algorithm. Due to the energy constraints on the sensor nodes in hierarchal networks efficient cluster head selection has become crucial factor. We propose an algorithm, in which all the nodes do not necessarily have the same initial energy. Our main contribution is to derive the location of a weighted Centroid which minimizes weights sum of squares distances from the sensor nodes to the cluster head location. Analytical results are validated through simulation in OMNET++ by using various performance metrics and compared with different cluster head selection protocols such as I-Leach, Leach-E and NR-Leach. This shows the promising potentials of our Weighted Centriod algorithm.

Abstract

: Reference Evapotranspiration (ET0) is a complex hydrological variable defined by various climatic variables affecting water and energy balances and critical factors for crop water requirements and irrigation scheduling. Conventionally ET0 is calculated by various empirical methods based on rigorous climatic data. However, there are many places where various climatic data may not available for ET0 estimation. The objective of this study is to evaluate different machine learning (ML) techniques to estimate ET0 with minimal climatic inputs. In this study, FAO56 Penman-Monteith model was considered as the standard model and different ML models based on A Long short-term memory neural networks (LSTM), Gradient Boosting Regressor (GBR), Random Forest (RF) and Support Vector Regression (SVR) were developed to estimate ET0 with climatic variables as input parameters. These models were evaluated in two different climatic regions, Hyderabad in India and Waipara in New Zealand. The results indicated that 99 % accuracy could be achieved with all climatic input, whereas accuracy drops to 86% with fewer data. LSTM model performed better than other ML models with all input combinations at both the stations, followed by SVR and RF. Both LSTM and SVR models have been noted as the most robust ML models for estimating ET0 with minimal climate data. Even though the excellent performance can be achievable when all input variables are used, the study, however, found that even a three-parameter combination (Temperature, Wind Speed and Relative Humidity values) or two-parameter combination (Temperature and Relative Humidity, Temperature and Wind Speed) can also be promising in ET0 estimation. The presented study will help to estimate ET0 for data scare regions, which is vital for agricultural water management in semi-arid climates.

Abstract

Increasing demands of wearable health monitoring seek dedicated spectrum for short range wireless communication of biosignals, for which frequency band near 400 MHz has been utilized recently. While using the dedicated spectrum, biosignal communication must not cause any out of band radiations and interference, for which there is a strong need to develop spurfree, low phase noise and energy efficient wireless transmitters (TX). In this research, for the first time we present design and implementation of a reference-spur-free, low phase noise, sub-mW dual modulation mode (frequency shift keying (FSK) and on-off keying (OOK)) 400 MHz TX for wearable health monitoring, where RF synthesis depends solely on an extremely low phase noise oscillator, which uses a 400 MHz surface acoustic wave resonator and does not include any power hungry, spurgenerating frequency multiplier or phase/frequency lock loop. The proposed TX has been designed and fabricated in 180 nm CMOS technology. Measurement results show that the energy efficiencies of the proposed TX in FSK and OOK mode are 1.8 nJ/bit at 250 kb/s and 0.23 nJ/bit at 2 Mb/s, respectively. To prove the utility of the proposed TX, biosignal communication is also demonstrated with the help of a commercial receiver in actual operating scenarios, where the measured bit error rate in FSK mode was < 10−5 for range of 2 m. Index Terms—Health-monitoring, wearable, spur-free, transmitter, FSK, OOK, 400 MHz, MedRadio

Abstract

Estimation of basic material properties of masonry and understanding its compressive behaviour is the initial crucial steps in analyzing the performance of masonry buildings. Masonry being a complex and inelastic material has a large variation in mechanical properties such as compressive strength and modulus of elasticity. The variation for Indian masonry is even higher, as most of the manufacturing and construction process is performed manually. Mechanical characterization of solid clay bricks, mortar cubes (1:4 cement-sand proportion) and masonry prisms are performed using laboratory tests to determine the compressive properties. The non-linear stress strain behaviour of masonry and its constituents is also presented. Based on the results of the present study and past literature, variation in mechanical properties of Indian masonry & its constituents is studied based on two different mortar grades (1:4 and 1:6). It is observed that these properties have a large portion of aleatory variability, due to variations in constituent materials and workmanship. The relationship between the compressive strength and elastic modulus of brick, mortar and masonry is also presented. Further, the relative performance of different empirical models in predicting the properties of masonry is compared and their efficacy is examined using the statistical and error-assessment parameters. Results showed that the compressive strength of the Indian masonry can be determined using most of the empirical relations available worldwide, with reasonable accuracy; however, the elastic modulus of masonry cannot be estimated with the same level of confidence.