Search

Human-wildlife conflicts in the habitats along the forest fringes are a substantial issue. An automated monitoring system that can find animal breaches and deter them from foraging fields is essential to solve this conflict. However, automatically forefending the intruding animals is a challenging task. In this paper, we propose a deep learning model for elephant identification using YOLO lite with knowledge distillation which could be easily deployed in edge devices. We also propose an elephant re-identification system using Siamese network which is helpful in tracking the number of times the elephant tries to forage the field. This re-encounter information about the same elephant can be used to decide the averting sound for the particular elephant. The proposed system is found to show an accuracy of 89%, which is provides good performance improvement when compared to the state of art models proposed for animal identification. Thus the proposed lite weight knowledge distillation based animal identification model and deep learning based animal re-identification model can be employed in edge devices for real time monitoring and animal deterring to safe guard the farm fields.

In this manuscript, a hybridizing visual cryptography with Optimal Elliptic Curve Cryptography is proposed for medical image security in Internet of Things (IoT). The visual cryptography is generally used to send the secure and confidential medical image to the receiver. Here, the medical image is transmitted as shares and all shares of the medical image are collectively loaded to retrieve the original medical image. Moreover, the multiple shares are created interms of pixel values of medical image and this share is extracted and partioned in blocks. The blocks of every share are encrypted with elliptic curve cryptography (ECC) mechanisms and encrypted image is decrypted using ECC decrypts. In hybridizing visual crypto with optimal elliptic curve crypto, the optimal key will be generated using an imperialist competitive algorithm. Finally, the decrypted output image compares to the original image. The proposed system is executed on MATLAB platform and performance is evaluated with existing method like Score-based Key Enumeration Algorithm (SKEA). The proposed ESEA approach reduces the file size as 45.76%, 24.97%, 15.86%, 33% and 33.86%.And higher PSNR as 29.08%, 25.86%, 23.98%, 25.86% and 42.75%. The proposed ESEA approach achieves 6.89% higher security than existing SKEA method. Furthermore, the simulation outcome demonstrates that the proposed technique can be able to find the optimal global solutions efficiently and accurately than the existing techniques.

Speech recognition has now become ubiquitous and plays an inevitable role in almost all sectors. Numerous works have been proposed on speech recognition; however, more accurate transcriptions are not possible. Exploration of various studies related to spell correction implies that several kinds of research have been carried out in this field but still it is a very challenging problem. This led to the need for a new spell corrector framework capable of leveraging the performance of the automatic speech recognition (ASR) system. The proposed work unveils state-of-the-art Bidirectional Encoder Representations from Transformers (BERT) based spell correction module developed on top of the deep recurrent neural network (RNN) based ASR system. The impact of BERT-based spell correction on the ASR system is evaluated on three different accent datasets in the perspective of word error rate (WER), character error rate (CER), and Bilingual evaluation understudy (BLEU) score. The experimental results inferred that the enhanced spell correction module is efficacious in detecting and correcting spell errors, by achieving the WER of 5.025% on librispeech corpus, 6.35% on voxforge, and 7.05% on NPTEL corpus.

A precise seizure detection system allows epileptic patients to receive early warnings before a seizure occurs. It is critical for people who are drug-resistant. To find the very minimal time before seizure onset, traditional seizure prediction techniques rely on variables collected from electroencephalography (EEG) recordings and classification algorithms. Such methods cannot achieve high-accuracy prediction due to the information loss of hand-crafted features and the limited classification capabilities of regression and other algorithms. Kernels are employed in the early and late stages of the CNN RNN architecture with VGG 16 in the convolution and max-pooling layers, respectively. The suggested hybrid model is tested using the CHB-MIT scalp EEG datasets. The total sensitivity, false prediction rate, and area under the receiver operating characteristic have all yielded positive results.

EVALUATING THE EFFECT OF COMBINED APPLICATION OF HYDROGEN CYANAMIDE AND ABSCISIC ACID FOR IMPROVING THE BERRY COLOUR OF ‘FLAME SEEDLESS’ GRAPEVINE (Vitis vinifera L.) Ashok Kumar Mahawer1*, Amit Kumar Kesharwani3,4, Lokesh Kumar5, Balkesh Kumari6, Tejraj Singh Hada7, Ajay Kumar Yadav8, N.K. Arora2

Water is an essential resource for agriculture and the majority of land is irrigated through borewells or wells. The power requirement for an irrigation pump motor is fed by the on-grid power supply but the availability of electricity in rural areas is still questionable. With rising concerns about global warming and the rise in carbon footprints, it is necessary to choose clean and green energy, thereby attaining self-sustainable life. India receives yearly a mean solar irradiation of 6.5 kWh/m2day. Hence, a solar photovoltaic–water-pumping system (SPV–WPS) is a suitable alternative to grid energy; thereby, the farmers would generate electricity through the solar photovoltaic system and become self-sufficient in their energy needs. In this paper, two different agricultural fields in Tamil Nadu, India that deploy flood irrigation and drip irrigation are taken as a case study. The paper discusses the concerns on the use of grid power and their carbon footprint, design and simulation of 4- and 5.5-kW SPV–WPSs using PVsyst 7.1.1, and the advantages of using SPV–WPSs and life-cycle cost analysis on different use cases. The Government of India has introduced a special scheme to promote the installation of SPV–WPSs by offering attractive incentives through PM-Kisan Urja Suraksha evam Utthaan Mahabhiyan (KUSUM) yojana. The results of the case study show that with the use of SPV–WPSs, either with or without subsidy, the farmer could gain a minimum of 250% on the investment with a project lifetime of 25 years.

Photovoltaic (PV) cell has a characteristic of decrease in power beyond a certain temperature. This decrease in power is due to a drop in the open circuit cell voltage. This decreases the efficiency of the PV cell. The objective of this research is to increase the efficiency of PV cells by reducing the PV cell temperature and reflection loss. The cell temperature and reflection loss can be reduced by spraying water over the PV cells. On spraying water over the USP36, 24V PV module, the power is found to be increased. The test result shows a 1V to 2V increase in voltage, with an efficiency increment of 1% to 1.27%. The test results of USP37 show the voltage increase of 1.2 V to 2.1 V in the PV module voltage. Due to the increase in voltage, efficiency increment of 1.29% is observed. The efficiency of USP36 with water spraying is more than the efficiency of USP37 without water spraying. In the PV power systems, an average increase in efficiency of 0.5% is observed.

Today, brain attack disorders are one of the most life-threatening areas in the medical era, which mankind is facing nowadays. Globally, more than 10,000,000 people are subjected to brain attack disorders like hemiplegia and tremor, every year, where two-thirds of them survive. Among the survival community, more than 80 per cent of them are subjected to long-term impairment of their upper extremity. In order to treat the impairment, the survival group is subjected to medications and rehabilitation in order to improve their daily living. But the facilities are very limited in fast- developing countries like India when compared to western standards. The rehabilitation given corresponding with medications during the treatment period in hospitals does not give a complete recovery from disability. People from rural background could not meet their rehabilitation requirements even in the hospital during treatment and also when they are discharged to home after treatment from hospitals due to financial constraints and reachability. In order to motivate the survival group to fulfill their daily living and improve their lifestyle, this paper is focused on intelligent home-based rehabilitation system at low cost, reliability, and affordability. One major movement disorder namely Upper Arm Hemiplegia was taken into account and visited few major hospitals around Coimbatore and Chennai for literature and case study. The facilities available in various hospitals and their drawbacks were analyzed. Based on the studies conducted at hospitals and taking advice from therapists, an innovative low-cost home-based rehabilitation device using Electro-Hydraulic systems has been developed to support patients who were used to impaired living even after treatments. To support Upper Arm Hemiplegia patients, the devices which were developed and experimented to hold different functionalities are discussed in this paper.

Energy savings, clean energy, savings in utility and energy governance tools are buzzwords in the healthcare industry. Healthcare sectors become largest consumer of energy in the modern world. Based on data of American Society of Heating, Refrigerating, and Air-Conditioning Engineers (ASHRAE), a moderate hospital consume 2.5 times higher energy than commercial buildings. As a result, increased worries about energy costs and environmental issues, as well as the anticipation of rising energy prices in the future and the need to enhance the dependability of healthcare facilities, have led to a focus on in-house power generation systems and the importance of energy management in hospitals and their health care facilities. Solar power systems that are clean and ecologically friendly have grown in popularity as distributed power generation (DPG) systems in recent years. In this work, a Grid-tied Solar PV system incorporated with Battery energy storage technology is considered in conjunction with health informatics and the hospital Energy Management System reduces energy consumption cost and improves the reliability of the power supply to run all clinical equipment available in the hospital’s Intensive Care Unit (ICU) and other premises. In this context, the Energy management controller utilised in the hospital Energy Management System will effectively use the electricity supplied by the Solar PV system while minimising grid demand and stabilising the voltage in the DC bus, which must be inverted into AC using an inverter to feed clinical loads. Furthermore the maximum power point tracking method is adopted, which enhances the quality of DC voltage generated by solar PV panels and feed to the DC bus. Sliding mode controller (SMC) is adopted in the inverter side and the quality of the inverted voltage is optimized using artificial bee colony (ABC) method. The proposed solar PV system in conjunction with health informatics and the hospital Energy Management System is developed and simulated in the MATLAB Simulink. The response of the suggested SMC and ABC techniques are compared and their outcomes are shown to confirm the performance of hospital energy management system.

An unprecedented year has past with Covid-19 lockdown. It has underscored the importance of reliable and uninterrupted power supply. Microgrid ensures reliability and continuity of power supply in a local region with its own local generation and load despatch system, thereby reducing or eliminating the need of a central generator. A microgrid is capable of autonomous operation or it can be connected to a central ac grid that it separates from during disturbances. In this paper results of a microgrid simulation model is presented. Here microgrid system uses two renewable sources namely, solar PV and wind generator along with a battery feeding an inverter supplying load. The system is modeled and implemented using Matlab/simulink environment. The simulation model consists of mono-crystalline solar PV panel of 2.5 kW and a wind turbine emulator having PMDC as wind generator of 1 kW rating as micro sources. For stabilisation of the system a battery bank of 48 V, 100 Ah is also provided. The system is designed to supply a maximum load of 2.5 kW. The system autonomy is approximately two hours for rated load of 2.5 kW. Stability of the system was tested during load variations. The voltage and frequency were found to be stable during load variations. The performance of the inverter to provide constant output voltage of 400 V is good and the output frequency of the inverter is also maintained at 50 Hz. The output voltage conforms to IEC 60038 Standards. An energy management scheme is also developed and simulation results show effectiveness of the scheme.

With the proliferation of multi-sensor remote sensing images, extraction of information has progressively concerned attention in recent years. It leads to great significant improvement in remote sensing areas for change detection techniques. Due to the advent of multi-spectral images in the change detection model, a change detection model named optimized convolutional neural network (CNN) framework is designed for monitoring land cover changes. This can assist to note the changes happening in the different periods. The proposed model is designed by integrating the normalization function and detection model by applying the deep learning (DL) algorithm. The actual experiment is carried out by taking the parameters accuracy and Kappa coefficient to show the effectiveness of the proposed model. The proposed experiment out performed well when compared to the existing mainstream techniques in multi-sensor images change detection. When compared with the existing DL techniques, the proposed design attained accuracy of 98.92% by possessing less loss function.

The paper presents experimental data and results from a prediction tool for the performance of a desiccant loop cooling system. The experiments are performed under a variety of high humidity and hot ambient conditions and the system performance is described. One of the experimental conditions is typical of many Indian cities and the systems appropriate for those cities are established. A simulation program that can predict the performance of the desiccant loop is developed. The simulation results show that this system can work as effectively as vapor compression air-conditioning for certain ambient conditions whereas it can function as a pre-cooler to a vapor compression system under more severe conditions, resulting in a reduced power consumption. The results presented in the paper give a guideline to practicing engineers as to when a desiccant loop cooling system would be useful. A simple payback analysis and a lifecycle cost analysis shows that a desiccant cooling system with a waste heat recovery recuperator is an economically viable investment.

The multidimensional purposes of grid-tied hybrid renewable system such as tracking of maximum power, increasing the power conversion efficiency, reducing the harmonic distortions in the injected current and control over power injected into the grid are presented in this paper by developing a laboratory-scale setup. To ensure continuous current operation at the shoot through mode of grid connected inverter, a switched Z-source converter is utilized at the PV side. The PWM rectifier connected with the wind turbine transforms AC power into dc. Individual power converters with conventional PI controllers have been dedicated for each power source, and control strategy uses only one reference voltage so as to increase the maximum power tracking speed from both PV and wind sources. The battery energy management is performed by artificial neural network (ANN) to enhance the stable power flow and increase the lifespan of the storage system. Finally, the voltage at the point of common coupling is fed to ANN-based space vector-modulated three-phase inverter and the converted AC power is injected to the grid. The overall system performance is measured by estimating the quality of injected power. A stable operation of the proposed microgrid system is verified by varying input and load at the grid. A continuous-time simulation model is realized in MATLAB and is validated using experimental prototype. This benchmark system provides various research scopes for the future smart grids.

The use of speech processing applications, particularly speech recognition, has got a lot of attention in recent decades. In recent years, research has focused on using deep learning for speech-related applications. This new branch of machine learning has outperformed others in a range of applications, including voice, and has thus become a particularly appealing research subject. Noise, speaker variability, language variability, vocabulary size, and domain remain one of the most significant research difficulties in speech recognition. We investigated on self-supervised algorithm for the unlabelled data. In recent years, these algorithms have progressed significantly, with their efficacy approaching and supervised pre-training alternatives across a variety of data modalities such as image and video. The purpose of this research is to develop powerful models for audio speech recognition that do not require human annotation. We accomplish this by distilling information from an automatic speech recognition (ASR) model that was trained on a large audio-only corpus. We integrate Connectionist Temporal Classification (CTC) loss, KL divergence loss in distillation technique. We demonstrate that distillation significantly speeds up training. We evaluate our model with evaluation metric Word Error Rate (WER).