Search

This paper introduces an advanced meta-heuristic optimization technique, namely, Atom Search Optimization (ASO) for the synthesis of linear and planar arrays. Synthesis of array antenna is a traditional electromagnetic problem. Investigations have been made by many researchers on synthesis of various antennas by applying several algorithms. ASO is a global optimization algorithm based on atom dynamics in dealing with different challenging problems. The ASO is applied to the array synthesis of the symmetric and asymmetric linear array antennas. To verify the effectiveness of the ASO algorithm, a comparative analysis of simulation results and published results for linear arrays has been made. The ASO optimized non uniform amplitude coefficients have been applied to the ON elements of the two ring concentric circular array. A comparative analysis with Firefly algorithm (FA) and Flower Pollination Algorithm (FPA) show the proposed algorithm is a comprehensive optimization algorithm in antenna array pattern synthesis.

High-speed vehicles and reckless driving have caused quite frequent accidents by intoxicated people. Alcoholism is one of the key causes contributing to reckless driving. We used an alcohol sensor in this work to detect the driver's condition and take the appropriate action. Because the flow of information is very critical in case of incidents, the device also integrates on board pressure and MEMS sensor to identify the effects. The camera takes the pictures, and the GPS location information is sent to registered mail via the Raspberry pi3 board's TWILIO app mounted in the car, sending the alert to the registered mobile phone. In addition, FMCW radar is used for anti-collision purposes because of its precise measurements of short range.

3D Integration technology is probably the best methodologies among others which suits CMOS applications with in various layers of devices are stacked with high thickness interconnects between the layers. In 3D IC structure electrical and thermal models are introduced for the interface between Through-Silicon-Via’s (TSV’s). TSV’s can be used to enable the 3-D platform; however this TSV’s will represent additional concerns. TSV-to-substrate and TSV-to-TSV noise coupling is assessed inside the 3-D IC’s. A vertical TSV’s design is proposed to reduce the area per TSV, capacitive coupling and effective inductance as compared with the other classical design patterns. TSV’s and substrate noise coupling is one of the major drawbacks in 3D IC. Some of the researchers have tried to overcome the problems in TSV based 3D IC due to noise coupling using different models, materials and different circuit techniques. This paper shows the complete road map for the noise coupling reduction in future IC integration.

Now a day’s Artificial intelligence and deep learning techniques recommended critical E-commerce applications. The human computing, computer aided designs cannot understand the alternative offline and online products. Therefore, customers are critical to find out the products such as groceries, fashion and health. However, it is a major task to overcome this limitation for human perceptions. In this research work an advanced FCNN deep learning model is proposed with global thresholding technique. For this work selecting the digital images and online images for pre-processing and classification. At primary stage segmentation is applied then classification is performed through FCNN, at final calculating the performance measures such as accuracy 98.7%, sensitivity 98.7% and throughput 99.23% has been achieved and outcomes are challenging the present technology.

Electrocardiogram (ECG) is widely used technique in study of heart beat irregularities such as cardiac arrhythmias, sinus rhythms and heart failure. It is a significant and popular technique to classify and detect the cardiac infraction. ECG signal analyses the electric activity of heart and outputs it in the form of waveforms which help in detection of heart irregularities. The main goal of this research work is to classify the arrhythmia with more accurate results in less computational time. The research is carried in machine learning technique- SVM classifier using Discrete Wavelet Transform (DWT). In this methodology, ECG samples of three different classes-Normal Sinus Rhythm, Congestive Heart Failure and Cardiac Arrhythmia were collected from MIT-BIH and BIDMC databanks. The collected signals were prepared into training set and testing set with a ratio of 70:30 percent respectively. Total 190 features were extracted from the prepared data using Discrete Wavelet Transform. DWT was chosen as it has the ability to vary the window size depending on the frequency. The extracted features were given to SVM classifier, which is best for classification purpose. The results were evaluated using the testing set and the final results were plotted using a confusion matrix. The performance accuracy of the model is 95.92 percent.

Alzheimer's is a dynamic ailment that decimates the mind's memory and its general functioning. Unfortunately till now, no single test can diagnosis this disease. Cerebrum checks alone can't be considered as a key factor to decide if the individual is experiencing it or not. As of now, the physician is in a conclusion that an individual is suffering from Alzheimer's on premise of the reports of the relations in regards to the social proclivity and checking the past clinical record. Artificial intelligence along with Machine Learning calculations perhaps in a situation to adjust this model. Big processing, in light of the fact that the data is taken through various sources with complex and creating circumstances that make certain to develop later on. Along these lines, in that, we'll take consequences of what extent level of patients get the illness as positive data and negative data. The proposed arrangement shows a big processing model, from the data mining perspective. Utilizing classifiers, this paper presents the work by preparing Alzheimer's rate and qualities are appearing as a disarray framework using different machine learning algorithms. The earlier research proved that the detection of Alzheimer’s disease using Support Vector Machine classifier and obtained very less accuracy. In view of this there is need of increasing the accuracy. So, this paper presenting different algorithms to classify the data to improve the efficiency in detecting the mentioned disease and observed that the Support Vector Machine with linear kernel model gives better accuracy than other models.

Cloud computing can carry both software and hardware applications over the internet, based on the requirement of supplies and services. Hence it acts as the next generation network and computing easy of operations. Security is the at most significant also it influence the cloud computing. Virtualization is the imperative factor through cloud computing related to speed and accuracy. This research work concentrates on the safety of simulated system in virtualized situation. The security problems in virtual machines are summarized first, as well as the safety issues which are present in a virtual network. These are discussed and evaluated depend on the platform. At last, compare the simulation results with novel virtual network model and past methods. Virtualization is planned to monitor the interactions between human computations and computer design through physical machines for increasing the security measures. The performance measures sensitivity 97.89%, efficiency 95.89%, F1 score 98.85% and accuracy 99.89% has been attained. These simulation results are outperforms the present technology compared to existed methods.

Data transmission in cryptography is held by encipher and decipher processes. Data Encryption Standard is one of the symmetric key encryption algorithms. Data Encryption Standard (DES) is one of the simplest cryptography algorithms. Modified Dual Coupled LCG (MD-CLCG) is an essential element of Pseudorandom Bit Generator (PRBG) because it requires less area and it is more secured compared to previously executed different algorithmic techniques of linear congruential generator (LCG) family and other pseudorandom bit generators. In cryptographic schemes key generation makes an important role. This paper has implemented a modified dual-CLCG for the key generation with the utilization of shift register in Data Encryption Standard cryptographic technique. Usage of Modified Dual-CLCG in Data Encryption Standard algorithm is designed and coded by the Verilog-HDL language and prototyped on FPGA device Spartan3E XC3S500E.

This concise presents a quick and power efficient level-shifter (LS) using cross coupled network. This technique will eliminate the drawbacks of conventional LS using cross coupled network in the pull up region, this will make circuit to run fast and power required is also reduced. Compared to previous LS's the proposed level-shifter consists of less number of elements and their sizes are comprised to minimum, this will decrease the area of LS. The existing LS cannot convert voltages below V TH and the voltage range offered is less and power utilization is more. In order overcome this with the use of crosscoupled network in the pull up region, the high switching speed achieved. By decreasing the transistor size, voltages are converted below V TH and energy utilization is decreased. To design a high speed and low power LS by using RCC in pull up region. It is used in low power applications such as implantable medical components. Proposed level-shifter functions effectively with less delay for inputs below the sub threshold voltages. For simulations LT spice tool of 180nm technology is used. The total delay and power utilization of the proposed voltage LS for 0.4V/1.8V and 1 MHz are 21ns and 76.34nW.

Through-silicon-via (TSV) technology has emerged as the key technology to enable 3D IC integration. 3D integration is seen as the leading candidate, which can help in sustaining Moore’s Law to future IC technology nodes. It clearly set a benchmark to the IC industry due to its tremendous benefits in performance, data bandwidth, and supports heterogeneous integration. In 3D IC structure TSV’s are used to carry the overall electrical signal between the layers. The major drawback in the TSV based 3D integration is noise coupling between aggressive (electrical signal carrying TSV; ETSV) and victim TSV’s (ground). It can be reduced by creating very good isolation between TSV’s and Si substrate by using different liner materials around TSV’s. In this work, we have addressed various TSV models to reduce noise coupling between the TSV’s. The models we have studied are single layer model and stacked layers of liner model. Apart from this we have studied how the core materials in the TSV reduces noise coupling between aggressive and victim TSV’s. Also, we have shown the high frequency study for proposed models. Finally, our work shows single layer model with Crystalline-Germanium is comparably better noise coupling reduction even at higher frequency.

The MLF-CNN includes a proposition production phase and also a diagnosis stage. In the first stage, they develop an MLF area proposal system and also pop the question to utilize a summation fusion strategy for integration of the two convolution layers. Intelligent video-surveillance is currently an active research industry in pc sight as well as artificial intelligence techniques. It delivers helpful resources for monitoring operators and forensic video private detectives. Individual re-identification (PReID) is one with these tools. Several approaches have been proposed to raise the functionality of PReID. One of the systems, a lot of scientists, made use of deep semantic networks (DNNs) as a result of their far better efficiency and fast completion at exam opportunity. Our objective is to offer potential researchers the job being done on PReID today.

Compared to OFDM, FBMC is the modulation technique that has enhanced spectral characteristics. To support higher data rates over the time and frequency selective channels FBMC plays a crucial role compared to OFDM. Simulation results shows that over flat fading channel, there is no significant changes between OFDM and FBMC, where as in frequency selective and time selective channels. FBMC shows superior performance improvement over Conventional OFDM system.

Skin cancer is considered as one of the most dangerous types of cancers and there is a drastic increase in the rate of deaths due to lack of knowledge on the symptoms and their prevention. Thus, early detection at premature stage is necessary so that one can prevent the spreading of cancer. Skin cancer is further divided into various types out of which the most hazardous ones are Melanoma, Basal cell carcinoma and Squamous cell carcinoma. This project is about detection and classification of various types of skin cancer using machine learning and image processing tools. In the pre-processing stage, dermoscopic images are considered as input. Dull razor method is used to remove all the unwanted hair particles on the skin lesion, then Gaussian filter is used for image smoothing. For noise filtering and to preserve the edges of the lesion, Median filter is used. Since color is an important feature in analyzing the type of cancer, color-based k-means clustering is performed in segmentation phase. The statistical and texture feature extraction is implemented using Asymmetry, Border, Color, Diameter, (ABCD) and Gray Level Co-occurrence Matrix (GLCM). The experimental analysis is conduted on ISIC 2019 Challenge dataset consisting of 8 different types of dermoscopic images. For classification purpose, Multi-class Support Vector Machine (MSVM) was implemented and the accuracy obtained is about 96.25.

Industrialization and urbanization in India have caused heavy environmental pollution. Most of the surface water had been polluted due to the environmental influence. Providing better quality drinking water to public is also a challenge due to pollution in the ground water and contamination even during distribution. Thus, it is very necessary to have adequate methods and equipment for water protection and drinking water quality measurement is an important aspect for the purpose. The protection of public health is an imperative and the potential of millions of severe effects from water contamination is not unrealistic. There is a need of In-situ monitoring, instant collection and calibration of data rather than manual collection of samples and testing. Wireless Sensor Network (WSN) has paved its significance into various applications. Although manual monitoring of water quality has been done, it requires a lot of labor, time and equipment. So, there is a need to develop a robust and reliable smart system where a real time monitoring of parameters of water quality for different water distribution tanks is done all the while. In this paper, Water Quality Monitoring (WQM) in a predefined Wireless Sensor zone using Zigbee Technology is implemented. Water Quality can be accessed in practical systems through the sensors which send the water quality data to the base station. Now a days, Renewable energy power generation is playing a main role in which Solar power is widely used. Maximum Power Point Tracking (MPPT) Controller improves the efficiency of Solar Power System. In this paper, a flexible, reliable Wireless Senor Network (WSN) based method of monitoring the quality of water with maximum power point tracking controlled solar PV system is developed.

Pseudo Random Bit Generator (PRBG) is a key element to protect the data in various cryptography applications during transmission. To prove more secure among different previous pseudo random bit generator methods like Linear Feedback Shift Register (LFSR), Linear Congruential Generator (LCG), coupled LCG (CLCG), and Dual Coupled LCG (dual-CLCG) the modified Dual coupled LCG (MDCLCG) is implemented. This method used is to generate a pseudo random bit with less area occupation and with single clock delay. In this paper three different ways of adder topologies ripple carry adder (RCA), carry skip adder (CSKA) and carry increment adder (CIA) are implemented in the place of modulo carry save adder to analyze the area, power and speed performance of the modified Dual Coupled LCG design using Verilog-HDL and prototyped on FPGA device Spartan3E XC3S500E.

In this paper, a lossless bio signal compression method known as Log2 sub band compression is implemented. A xor-Log2 sub-band compression where two data samples are compared to identify differences between them. This compression technique is applied for two random 24-bit bio medical signals. One block is current data which has data to be compressed and previous data has no value initially. There are four cases where the number of bits to be compressed are 8, 14, 20 and 26 bits. Compression occurs on certain count taken as 10, 16, 22 and 28. The compressed data is transmitted serially. Simulation and synthesis are performed on Xilinx ISE. Area occupied by the compressor is 83% of the total LUT-FF pairs which is quite considerable, and power consumed is 0.014 W which can make the overall compressor optimized. The delay taken by the compressor is 3.324 ns. Lesser the delay more fast the compression takes place.

Infectious diseases like typhoides, dengues, etc. are caused by water and environmental changes. It is important to provide medications for such infection patients. Conventional approaches for the correct diagnosis of patients are not acceptable. To make an appropriate diagnosis it is important to accurately identify patient status. Although advancement in reliable diagnostics of technology remains an essential mission. This thesis suggested a classification approach for certain infectious diseases. 173 Typhoid fever patients and 119 Dengue Fever patients were collected clinically. Crafted a hybrid method using voting set technique that was constructed as base classification in machine learning techniques. The diagnostic results can be classified according to the classificator's majority of votes. Data set tests were carried out and the results were contrasted with traditional computer teaching methods, including the Group Baive Bayesian, K-Nearest Neighbor and the Decision Tree. Analysis indicates that, in the case of typhoid and dengue-fever infected patients, the suggested hybrid solution has a 97.2% precision. Focusing on infectious diseases, several traditional approaches were analysed and the proposed hybrid methodology focused on an ensemble voting strategy that showed the highest efficiency in classifying infectious diseases.

An advanced System-on-Chip (SoC) architecture is designed to identify different valuable minerals embedded in the earth’s surface in this paper. Materials such as gold, diamond, petrol, and coal generate high revenues for developing and established nations. Therefore, to identify different materials, an efficient electronic device is designed in which scanning becomes an important parameter. This investigation is performed by an SoC-based ultrasonic module designed using Xilinx Vivado and verified on the ZYNQ-7000 FPGAboard. This architecture consists of a code generation unit, modulator, delays, emitter, demodulator, correlator, detector, and receiver. These modules are developed using Verilog HDL and deliver output on high-level processing screen. The experimental results outperform the conventional methodology with respect to reduced power consumption and area, this model is compared with existing methods to identify the operational performance. This SoC based ultrasonic scanning method improves the power consumption by 73.24% and area 72.24%.

In this concise, ultra low power and high speed voltage or logic LS circuit is introduced. With the help of regulated cross coupled structure in the pull up region the power utilized by the circuit is considerably decreased and speed of the circuit is also increased. The LS can convert the input logic levels or voltages below the V TH of the transistor to the higher acceptable levels. A LS requires less area because it consists of less number of components which makes it fit for low power and high speed applications, for example implantable clinical gadgets and remote sensor organizations. Tool used for simulation is LTspice 180nm technology. The LS can shift the input voltage or logic levels as less as 80mv to higher acceptable levels. The power utilized by LS is 149.5nw and propagation delay is 23.7ns.

In comparison to the OFDM (Orthogonal Frequency Division), Filter Bank multicarrying function (FBMC) has superior spectral properties, which complicates operational multiple input and mixed outputs. By extending a symbol in time, we can totally remove the imaginary interference. This gives the ease of applying all MIMO strategies known in OFDM to FBMC. The approach itself is of little complexity since it is based on hadamard matrices. While FBMC spreading allows complicated orthogonality to be restored in one block of communication, interference may be seen from the neighbouring blocks. By inserting a time security slot, the signal-to - interference ratio can also be improved. Furthermore, we examine the effect on the propagation process of a time channel. The estimation of the potential for Bit Error in double selective channels has been improved. In doubly selective channels, that is, time selectivity and frequency selectivity, we study the degeneration of output between OFDM and FBMC. In order to do this, we derive closed-form Bit Error Probability (BEP) terminology for the arbitrary linear modulation methods dependent on one-tap equalizers, in which our general BEP expressions include OFDM and FBMC.

The outbreak of the novel COVID-19 virus is identified across all experimental scientific tests that assist victims to fight against the pandemic situation. The problem seems to have a large number of scientific COVID-19 articles with different risk factors. The quick identification of documents allows the processing and interpretation of inevitable essential knowledge for investigators. This article provides a solution by creating an unsupervised framework for the interpretation of clinical trials over COVID-19 risk factors with a diverse range of articles related to vaccines and treatments from a large corpus of documents. It also provides practical informative knowledge regarding COVID-19 risk factors and helps researchers to enable any single author to obtain appropriate information. The present application uses artificial intelligence, natural language processing approaches, incorporated throughout the search engines, to search for keywords to classify categories with normalized linguistic data. The text data are instead parsed in phrases and thresholds the text with recognition of data frame components with relevant outcomes.

Gait patterns and coordination are altered in diabetic cardiomyopathy patients with Parkinson's disease. There is little information with possible explanations. Fall identification and simulation in all age groups, including the use of Fuzzy logic and sensor data for evaluating gait error. The current proposal emphasizes about fall prediction and estimation of diabetic cardiomyopathy disorders for aged, adults and infants. The inputs for the fluctuating inference system are the patient's height, gyroscope, age and weight. RMS error, Estimation and identification are the output variables where inputs are from the MIMO-used sensor data. Input and output variables and rules are supplemented with the membership functions. The extracted features are equivalent to ordinary random mean square error values. The application of a fuzzy Mamdani technique uses a triangular-trapezoidal logic to obtain a random mean square error, classification and recognition requirements for the elderly, adults and children. IoT monitors the collected outputs and store in cloud. The accuracy of a study through triangular trapezoidal approaches of 20 patients with Parkinson's diabetes cardiopathy in the fuzzy logic is 95%. A wide range of fields such as digital control, data detection, decision interpretation, expert systems and computer vision have been employed successfully.

The COVID-19 pandemic has a rapid spread across the globe, which has deployed life threatening complications ever since it started from China in December 2019. A quick detection of positive cases on corona virus will prevent the further community spread and initiates a earlier treatment to common man. In Recent findings, the images of Chest X ray and CT scan have shown salient features that illustrates the severity of corona virus in lungs. Scientific advancement of Artificial Intelligence in deploying a deep learning based medical field is remaining powerful to handle a huge data with accurate and fast results in medical imaging to diagnose diseases more accurately and efficiently with further assistance in the remote areas. Proposed method is developed for analyzing chest X ray images to detect COVID-19 for binary classes with an accuracy of 99% and validation accuracy of 98%, where the loss is approximately 0.15% by using convolution 2D techniques that are applied on the open source datasets of COVID-19 available at GitHub and Kaggle.

Electrocardiogram (ECG) plays important role in detection and classification of cardiac irregularities. This research presents the approach for classification of heartbeat irregularity. Three different signals Cardiac Arrythmia (ARR), Normal Sinus Rhythm (NSR) and Congestive Heart Failure (CHF) are considered for research. A total of 162 records are considered for research. Then data collected is to be divided into two sets-training set and training set. Training set comprises of 70 percent of data and testing set comprises of remaining 30 percent. The paper mainly follows four stages, in stage 1 Arrhythmia signals and Non- Arrhythmia signals are collected from MIT- BIH database for further study. In stage 2 the collected Cardiac Arrhythmia (ARR), Normal Sinus Rhythm (NSR) and Congestive Heart Failure (CHF) signals are prepossessed. In stage 3 features are extracted from pre-possessed signals using Discrete Wavelet Transform (DWT) and all the features are concatenated into a single feature vector. In stage4 the extracted features are given to Support Vector Machine (SVM) classifier for classification of the model and the parameters such as precision, recall and F1 score are calculated. The accuracy obtained is 95.92 percent.

This work addresses the robot controlled by hand gesture and voice control. In the technology era, the space between the physical and the digital world is brought closer by the introduction of gesture concept. For all the dangerous tasks we prefer technology rather than people. Even though these robots are being controlled manually in the early stages, these can now be controlled via voice and gestures. This technology of gesture and voice recognition can be defined by the interaction between the computer and the body language of human beings. This constructs the communication link between technology and mankind. The target of this work is to upgrade the complete security to the robot and to simplify the controlling mechanism.

Sleep Bruxism is characterized by an unconscious act of tooth grinding or clenching of teeth tightly during sleep or awake state. Early diagnosis is advantageous to overcome the damage of jaw, damage of teeth and other health related problems. This paper focuses clenching of teeth in the sleep state only. This paper presents sleep bruxism disease detection and feature extraction. The electroencephalogram (EEG) signal analysis is one of the useful methods for detecting sleep bruxism disorder. For this analysis 10 subjects are considered. For these 10 subjects the EEG signal is extracted from frontal and temporal electrodes F7–T3, T3–T5 and T4–T6. These EEG signals are decomposed into five sub-bands D6-gamma, D7-beta, D8-alpha, D9-theta and A9-delta. The decomposition is done in nine levels since the signals considered has a sampling frequency of 512 Hz. The signal is decomposed using Daubechies order 2 wavelet. From the decomposed signals the detailed coefficients (D1 to D9) and approximation coefficient (A9) are extracted. From extracted coefficient features like energy, variance, mean and standard deviation are calculated to detect sleep bruxism disorder.

This paper presents feature extraction of Electroencephalogram (EEG) signal and identifying the Obstructive Sleep Syndrome (OSS), Central Sleep Syndrome (CSS) and Mixed Sleep Syndrome (MSS) using Daubechies order 2 wavelet transform. Wavelet transform is the powerful tool for feature extraction and classification. The EEG signal is decomposed into sub-bands and features are extracted. Based on the features the EEG signal is correlated with subjects abdomen movements, nasal air flow and ribcage movements. Then OSS, CSS and MSS are identified. The frequency of EEG signals goes high to low when event occurs. The signal amplitude of abdomen movements, nasal air flow and ribcage movements reduces and reaches zero level when event occurs. Recognizing the thresholds of all the artifacts leading to OSS, CSS, and MSS reduces the diagnosis time and saves life.

Design of low power systems become a preeminent role in the domain of VLSI. Various algorithms are being used to implement a reliable system. This paper discusses the diagnosis of various symptoms in the audio signal. Discrete Wavelet Transform is the mathematical block for the detection and analysis of the spectral components of an audio signal. The wavelet transform detects signal levels in the acoustic signal. These coefficients are further applied to mathematical blocks such as coastline, quasi-average and energy blocks to diagnosis symptoms respectively depending on the frequency ranges. The symptoms such as cough, sneeze having similar spectral ranges which are distinguish using Mel spectrum based analysis. The aim is to diagnosis the symptomatic patterns in human audio signals with low power design and area efficient computational architecture for the mathematical blocks. The proposed work employs the truncation multiplier design in the wavelet transform and energy parameter. Since the LSB parts are not required in the realization of the wavelet transform filters which reduce the power and area consumption thereby makes the design a power and area efficient system. It is observed a significant change in the power consumption

The electrocardiogram (ECG) is a graphical representation of the electrical activity of the heart. Signal modelling is a powerful technique used in the automatic ECG signal analysis. To identify different pathologies, some classification are applied to ECG signal. The peaks and segments are called features, helps us to recognize the ECG segments. Calculation of the general health indicators like beat-per-minute (bpm), QRS width and the presence/absence of a segment are done. The standard rule-set is applied to the above features to recognize the type of heart ailment the patient is suffering from. The decision making is implemented by a multi-level system and fuzzy logic. This is the flow of events of the project.

Agricultural productivity plays a major role in an Indian economy; therefore the disease detection in the field of agriculture is important. Farmers struggle a lot for proper crop production due to multiple diseases affecting the plant so there is a need to detect the disease at initial stage. One major disease in the crop is leaf spot. The purpose of the proposed system is to identify the leaf spot using image processing techniques. In this research the disease detection is done in four stages, image acquisition, image segmentation, feature extraction and classification. For image segmentation is done with K-means clustering method and features are computed from disease affected cluster. Features such as Contrast, Correlation, Energy, Homogeneity, Mean, Standard Deviation and Variance are extracted. The extracted features from disease cluster are given as classifier inputs to classify the disease. The classifier used in this paper is neural network (NN) classifier. It is observed that the accuracies for bacterial leaf spot and target spot of cotton leaf diseases as 90% and 80% respectively. For tomato leaf diseases- septoria leaf spot and leaf mold as 100%.

It deals with the detection of heart diseases as a deciding path for treatment. The proposed work is for finding an effective technique for ECG Signal Analysis with modest reasonable accuracy and minimum computation time. ECG signal Patterns and heart rate are the parameters to indicate cardiac health. ECG signals are recorded by placing the surface electrodes on body to pick up rhythmically produced due to repolarization and depolarization activity of heart. For Instance the arrhythmia of ECG rhythm are irregular, it neither too slow nor too fast significant based on difference observed between normal sinus heart rhythm and types of arrhythmia. To avoid any risk, the recognition using computer based for classification of ECG signals pinched significant attention since last few decades. The predominant attributes used in detection of cardiac cycle for arrhythmic activity are Heart Rate, QRS complex and intervals and ST segment. Algorithms used for detection and also classification of various ECG signal abnormalities, some recordings from databases of arrhythmias is used in training and also testing classification based on Neural Networks. The data mining tool like Multilayer Perceptron, Radial Basis Functions Neural Networks are implemented for classification purpose due to its simplicity, adaptiveness and easy implementation produced high efficiency.

Planning and performance of any wireless channel in different environment is analysed by the path loss prediction models. In this paper the path-loss between the Base-Station (BS) and Mobile-Station (MS) for the Received-Signal-Strength (RSS) in different wireless environments is estimated. Non-isotropic antennas are used with different transmitter and receiver gains. A mathematical expression is proposed to compute path loss with antenna gains of 0.5 and 1 by varying the distance up to 1km. Then the path loss is optimized by introducing the path loss component that varies with environment. The path loss component is varied from 2 to 6. The shadowing effect is modelled by log-distance method. In this paper Gaussian random variable is considered with a mean zero and standard deviation is taken as 3dB. Simulation results show the path loss component increases by increasing the gain of antenna. The path loss is also calculated by IEEE 802.16d model and Hata-model. It is observed that as the gain of antenna decreases the path-loss increases and vice-versa. Path-loss also increases by distance and shadowing effects.

Many heart diseases can be identified and cured at very early stage by studying the changes in the features of electrocardiogram (ECG) signal. In this paper, an algorithm to detect Atrial Fibrillation (AF) in the ECG signal is developed. For correct detection of AF, pre-processing and feature extraction of ECG signal shall be performed before it detects AF. After considering the ECG signal from the database, in the preprocessing stage de-noising of the ECG signal is carried out in order to obtain a clean ECG signal. After pre-processing, before feature extraction R peak detection is carried out for the signal. Since R peak is having the highest amplitude, and therefore it is detected in the first round and subsequently location of other peaks of the ECG signals are performed. After completing preprocessing and feature extraction using Discrete Wavelet Transform (DWT) applied based on inverted T wave logic and ST-segment elevation. Our classification algorithm was demonstrated to successfully acquire, analyze and interpret ECGs for the presence of AF indicating its potential to support m-Health diagnosis, monitoring, and management of therapy in AF patients.

The energy depletion is the major drawback in wireless sensor networks (WSNs). Sensor nodes use utilize tiny sized batteries, which can neither be replaced nor recharged. Hence, the energy must be optimally maintained in such battery-operated networks. One of the popular method of optimizing the energy efficiency is through clustering. In clustering methodology, all the sensor hubs are assembled into number of groups and each group is allocated with a group head called cluster head (CH). The CH consumes high energy than remaining sensor nodes (SNs) as they are responsible for data collection and data transmission. The cluster heads are usually overloaded with large number of sensing nodes and thereby leads to faster death. Thereby degrades the network execution. In this paper, we propose three different protocols—distributed energy-efficient clustering (DEEC), developed DEEC (DDEEC) and enhanced distributed energy-efficient clustering (E-DEEC). These protocols are compared with energy depletion of cluster head and lifetime. Simulations are carried by considering 500 sensor nodes and 30 cluster heads within a communication range of \( 200\times 200\) m for 10,000 iterations. It is observed that number of nodes alive are 70% more in E-DEEC than DEEC and DDEEC. The packets transmitted to the BS are 80% more in E-DEEC than DEEC and DDEEC. The E-DEEC protocol enhances the network lifetime than DECC and DDEEC.

Wireless sensor networks have plenty of small sensor nodes. These sensor nodes direct the sensed data to the Base Station (BS). The transmission of data to the BS utilizes more energy. Many clustering algorithms are available for improving energy efficiency in homogenous and heterogeneous networks. This paper investigates the protocol which minimizes the energy consumed with respect to network lifetime and stability period. In this paper it is considered the Distributed Energy Efficient Clustering (DEEC) and Threshold Distributed Energy Efficient Clustering (TDEEC) in different heterogeneous network scenarios. The performance of TDEEC and DEEC is compared by varying the parameters-advanced nodes, super nodes, fraction of advance and super nodes. The network life and stability period is approximated for 100 nodes in 10000 rounds. It is observed that numbers of nodes alive are more in TDEEC than DEEC after completion of 10000 rounds. The packets transmitted to the BS in TDEEC increases from 2lakhs to 7 lakhs for 1700 to 7000 rounds but in DEEC packets transmitted to the BS are maintained constant 2 lakhs after 7000 rounds. It is observed the TDEEC is the best protocol when compared to DEEC based on stability period and network life-time.