Wind power forecasting has gained significant attention due to advances in wind energy generation in power frameworks and the uncertain nature of wind. In this manner, to maintain an affordable, reliable, economical, and dependable power supply, accurately predicting wind power is important. In recent years, several investigations and studies have been conducted in this field. Unfortunately, these examinations disregarded the significance of data preprocessing and the impact of various missing values, thereby resulting in poor performance in forecasting. However, long short-term memory (LSTM) network, a kind of recurrent neural network (RNN), can predict and process the time-series data at moderately long intervals and time delays, thereby producing good forecasting results using time-series data. This article recommends a hybrid forecasting model for forecasting wind power to improve the performance of the prediction. An improved long short-term memory network-enhanced forget-gate network (LSTM-EFG) model, whose appropriate parameters are optimized using cuckoo search optimization algorithm (CSO), is used to forecast the subseries data that is extracted using ensemble empirical mode decomposition (EEMD). The experimental results show that the proposed forecasting model overcomes the limitations of traditional forecasting models and efficiently improves forecasting accuracy. Furthermore, it serves as an operational tool for wind power plants management.

Blockchain networks serve as a transparent and secure ledger storage solution, yet they remain vulnerable to attacks. There must be some mechanism to protect the blockchain network from attacks. Among various attacks, the Distributed Denial of Service (DDoS) attack is considered severe, which is challenging to detect accurately and reliably. Machine learning techniques are used to detect the attack, which requires exploring all global attack data in a single system, which is difficult in practice. This article proposes a distributed machine learning mechanism called Federated Machine Learning for detecting the presence of DDoS attacks. But in federated machine learning the model itself can be poisoned by the malicious collaborating node which is another problem that this article solves by storing the model in blockchain and by introducing a new reputation-based miner selection procedure. The proposed framework integrates the federation of machine learning within the blockchain network framework for detecting DDoS attacks. Under the integrated framework, miners are used to train the blocks and they also participate in the machine learning training. A dynamic reputation-based miner selection mechanism that can balance exploration and exploitation is proposed for optimal miner selection, which can ensure the high accuracy of the machine learning model and improve the security of blockchain from attacks like DDoS attacks and 51% attacks. The proposed framework is tested with Random Forest, Multilayer Perceptron, and Logistic Regression machine learning algorithms. The proposed mechanism achieved maximum accuracy of 99.1% using random forest model which is superior to the existing mechanism of detection of DDoS attacks.

Fruits have now become a product to the market's eye, as fruits being the top recommended food to be consumed for better health, the prices drive higher and higher day by day. The main reason for the increase in the price of fruits is the manual labor behind it. It is the sorting and grading done by such humans which takes a prolonged period of time, inconsistent, onerous, subjective, variable, costly and influenced by other factors such as the environment around them which holds these fruits at an untouchable rate to the normal low paid consumers. To tackle this and hopefully reduce the rising price in fruits we have come up with a solution that a Fruit freshness System needs to be put in place. As computer vision has been used by many researchers to sort and grade fruits, we decided the best way to aid our solution would be by the implementation of Computer Vision. The summary of this paper is that it provides an overview of the many methods which have been implemented to reduce and lower the manual labor in the grading and sorting of fruits in the market i.e., feature extraction, segmentation, preprocessing, classification which addresses the fruits and the quality of the fruits based on texture, color, shape, size, and it's defects. These steps lead to a much more accurate shelf-life date of the fruits which also tackles the problem of food wastage, this will decrease the wastage of fruits from turning spoiled much earlier than expected.

Deep Learning is one of the most popular computer science techniques, with applications in natural language processing, image processing, pattern identification, and various other fields.Despite the success of these deep learning algorithms in multiple scenarios, such as spam detection, malware detection, object detection and tracking, face recognition, and automatic driving, these algorithms and their associated training data are rather vulnerable to numerous security threats.These threats ultimately result in significant performance degradation.Moreover, the supervised based learning models are affected by manipulated data known as adversarial examples, which are images with a particular level of noise that is invisible to humans.Adversarial inputs are introduced to purposefully confuse a neural network, restricting its use in sensitive application areas such as biometrics applications.In this paper, an optimized defending approach is proposed to recognize the adversarial iris examples efficiently.The Curvelet Transform Denoising method is used in this defense strategy, which examines every subband of the adversarial images and reproduces the image that has been changed by the attacker.The salient iris features are retrieved from the reconstructed iris image by using a pre-trained Convolutional Neural Network model (VGG 16) followed by Multiclass classification.The classification is performed by using Support Vector Machine (SVM) which uses Particle Swarm Optimization method (PSO-SVM).The proposed system is tested when classifying the adversarial iris images affected by various adversarial attacks such as FGSM, iGSM, and Deepfool methods.An experimental result on benchmark iris dataset, namely IITD, produces excellent outcomes with the highest accuracy of 95.8% on average.

In general, the innovative foods produced on fruit and vegetable based farms are always high quality and healthy. Indicators of fruit and vegetable consumption include plasma vitamin C and arytenoids, which are plant pigments discovered in blood samples. The researchers decided to utilize blood samples rather than the more common food frequency questionnaire in their investigation. to assess the amount of food consumed in order to forestall measuring errors and to establish dependencies. Because vitamin C and arytenoids may be found in a wide variety of fruits and vegetables, we can use them as objective measures of our consumption of these food groups. The fact that individuals who do not consume a diet that is abundant in fruits and vegetables do not consume significant quantities of vitamin C and arytenoids is reflected in the plasma levels of these individuals. In this paper a smart machine learning algorithm was proposed to predict the micro plasma impacts. This monitors the regular shape and harvesting of different farm fresh products and predicts the impacts of it. This will helpful for farmers to enhance the harvesting.

Gesture Recognition which is an inevitable part of human computer interaction is an ever evolving active research area. This has been in use under varied applications like smart home systems, sign language recognition, augment reality and in device controls. The acquisition of hand gestures are usually through optical sensors, in this work a radar based hand gesture data set is used for classifying the gestures. Micro doppler signatures were used as the input to the model. Radar dataset has fewer data samples compared to optical based data sets. The proposed work uses separable convolutional neural networks model which does depth wise convolution followed by point wise convolution to reduce overfitting effect of the training data. The proposed model was built in such a way that the model is capable of classifying any unseen data without exactly mimicking the training samples. The proposed model has achieved 94.56% as the testing accuracy which is certainly better than the previous work on this Dop Net data set. Moreover the model has also minimized the computational hours of the model using separable convolutions.

Cyber-attacks are getting more sophisticated and nuanced. Intrusion Detection Systems (IDSs) are commonly used in a variety of networks to assist in the timely detection of intrusions. In recent years, blockchain technology has got a lot of attention as a way to share data without the need for a trusted third party. In particular, data recorded in a single block cannot be modified without impacting all subsequent blocks. For an effective update, an attacker will need to monitor the majority of network nodes, which is not feasible given the current network size. This work aims to create a deep learning-based IDS model with the potential of integrating blockchain technology with intrusion detection, inspired by the ability to apply blockchain in all fields. The proposed model outperforms the conventional systems with respect to accuracy in detecting the security attacks. (c) 2021 Elsevier B.V. All rights reserved.

Anomaly-based detection is coupled with recognizing the uncommon, to catch the unusual activity, and to find the strange action behind that activity. Anomaly-based detection has a wide scope of critical applications, from bank application security to regular sciences to medical systems to marketing apps. Anomaly-based detection adopted by various Machine Learning techniques is really a type of system that consists of artificial intelligence. With the ever-expanding volume and new sorts of information, for example, sensor information from an incontestably enormous amount of IoT devices and from network flow data from cloud computing, it is implicitly understood without surprise that there is a developing enthusiasm for having the option to deal with more conclusions automatically by means of AI and ML applications. But with respect to anomaly detection, many applications of the scheme are simply the passion for detection. In this paper, Machine Learning (ML) techniques, namely the SVM, Isolation forest classifiers experimented and with reference to Deep Learning (DL) techniques, the proposed DA-LSTM (Deep Auto-Encoder LSTM) model are adopted for preprocessing of log data and anomaly-based detection to get better performance measures of detection. An enhanced LSTM (long-short-term memory) model, optimizing for the suitable parameter using a genetic algorithm (GA), is utilized to recognize better the anomaly from the log data that is filtered, adopting a Deep Auto-Encoder (DA). The Deep Neural network models are utilized to change over unstructured log information to training ready features, which are reasonable for log classification in detecting anomalies. These models are assessed, utilizing two benchmark datasets, the Openstack logs, and CIDDS-001 intrusion detection OpenStack server dataset. The outcomes acquired show that the DA-LSTM model performs better than other notable ML techniques. We further investigated the performance metrics of the ML and DL models through the well-known indicator measurements, specifically, the F-measure, Accuracy, Recall, and Precision. The exploratory conclusion shows that the Isolation Forest, and Support vector machine classifiers perform roughly 81% and 79% accuracy with respect to the performance metrics measurement on the CIDDS-001 OpenStack server dataset while the proposed DA-LSTM classifier performs around 99.1% of improved accuracy than the familiar ML algorithms. Further, the DA-LSTM outcomes on the OpenStack log data-sets show better anomaly detection compared with other notable machine learning models.

Deep neural networks have shown significant progress in biometric applications. Deep learning networks are particularly vulnerable to Adversarial examples where adversarial examples are manipulated input data. The adversarial attacks make the biometric system to fail in terms of performance. An effective defensive mechanism against adversarial attacks is introduced in the proposed work which is used to detect adversarial iris examples. The proposed defensive mechanism is based on Discrete Wavelet Transform (DWT) which examines the high and mid spectrum of wavelet sub bands. The model then recreates the various denoised versions of the iris images based on DWT. The U-net based Deep convolutional architecture is used for further classification. The proposed process is tested by classifying adversarial iris images affected by various adversarial attacks such as FGSM, Deepfool and iGSM methods. An experimental analysis on a benchmark iris image database, namely IITD, generates excellent results with an average accuracy of 94 percent. Experiment results show that the proposed strategy performs better in detecting adversarial attacks than other state of art defensive models.

Blockchain which emerged in the last decade has been considered as a very powerful and potential technology since it has been applied and gained popularity from various domains like supply chain, healthcare, energy, music, food, finance, insurance, government, etc. There are several use cases in the health care where we can apply blockchain for maintaining electronic medical records, remote patient monitoring records, drug supply chain, insurance claims, hospital information system, etc. Any intentionally modified data or data misrepresentation or deception in the insurance could intend to result in unauthorized benefits. These fraudulent claims keep increasing annually and because of this, the health insurance system is on a greater disadvantage. So by using blockchain we can overcome the various challenges and issues in the current system. Our focus is to build a secure system to securely manage the health care data and also to track the insurance activities so that we can prevent health insurance fraud. We design a blockchain based solution for health care data collection andinsurance claims by deploying blockchain since it is secure, tamper proof, immutable. Thus it also gives us added security since it is impossible for anyone to modify/claim the insurance falsely since only the authorized people will beable to do so. We have used ganache blockchain to experiment the same and used solidity language for the coding.

Renewable energies such as wind and solar begin receiving remarkable popularity in accordance with the energy demand, expeditious expansion of solar and wind energy generation involves acute forecasting of wind and solar power, so in past and recent years it has become an intensive research area. An accurate forecast of wind power to maintain an affordable, secure, and economical power supply is most significant. Numerous investigations and research have been performed in this area in recent years. This research article aims to develop a short-term wind power forecasting model to improve the accuracy of the prediction. Therefore, a novel approach based on LSTM (Long Short-Term Memory) is proposed to forecast from 1 to 6 hours ahead of wind power. A recursive strategy is used when predicting short-term wind power, unlike the conventional LSTM approach. The proposed model is implemented using historical generated wind power data for Gujarat state. A comparative analysis is performed between the proposed and existing approach presented in the literature, from the analysis, it is noted that the proposed R-LSTM (Rolling-LSTM) model outperformed with minimal error and better accuracy.

In biometric applications, deep neural networks have presented significant improvements. However, when presenting carefully designed input training data known as adversarial examples, their output is severely reduced. These types of attacks are termed as adversarial attacks, and any biometric security system is greatly affected by these attacks. In the proposed work, an effective defensive mechanism has been developed against adversarial attacks which are introduced in iris images. The proposed defensive mechanism is following the concept of wavelet domain processing and it investigates the mid and high frequency components of wavelet domain components. Based on this, the model reproduces the various denoised copies of input iris images. The proposed strategies are intended to denoise each sub-band of the wavelet domain and assess the sub-bands most likely to be affected by the adversary using the reconstruction error measured for each sub-band. We test the effectiveness of the proposed adversarial protection mechanism against various attack methods and analyzed the results with other state of the art defense approaches.

The cloud computing environment when deployed correctly is responsible for delivering scalability, cost efficiency, reliability, security and interoperability to the end users. Log analysis is considered to be an indispensable component of security regulations and framework, since these computer-generated records help the organizations, businesses and networks to respond to different kinds of risks that are possible to cloud environment in a reactive and proactive manner. In this paper, an Integrated Deep Auto-Encoder and Q-learning-based Deep Learning (IDEA-QLDL) Scheme is proposed for attaining maximum prediction accuracy during the process of exploring log data and classifying them into genuine and anomalous. It initiates the process of acceptance or denial based on the continuous investigation of behavioral patterns that are highly applicable for classification. The results of the proposed IDEA-QLDL Scheme confirmed its predominance in improving the classification accuracy, precision, recall and detection time compared to the benchmarked schemes considered for investigation.

Radar sensing technology that uses Frequency Modulated Continuous Wave Radar(FMCW) has been a promising solution for Human Activity Classification in recent years. Poor monitoring has taken a lot of lives in the recent COVID-19 pandemic which has emphasized the need for better monitoring systems. In this work, we have explored various color spaces and used LAB color space based micro doppler signatures as the Deep Learning model input. We have proposed a novel widened convolutional neural network architecture with parallel input layers for better feature extraction. This helps in yielding classification among 6 Activities of data captured under realistic environments, unlike other radar data sets captured only in lab environments. We have obtained good recognition rates with this architecture that uses LAB based Color space images as input.

Despite being known for their robust performance in the biometrics domain, Deep Convolutional Neural Networks always face a high risk of being fooled by precisely engineered input samples. These samples are called adversarial examples and such attacks are called adversarial attacks. These attacks pose great threat to any biometric security system. In this paper, to guard against adversarial iris images, we propose defensive schemes. The first strategy we propose relies on our adversarial denoising encoder architecture. The second strategy relies on wavelet transformation to divide them into wavelet sub-bands following an U-net architecture wavelet domain denoising on processing each sub-band to remove the adversarial noise. We measure the efficiency against numerous attack scenarios of the suggested adversarial defence mechanism and equate the findings with state-of-the-art defence strategies.

Abstract: Emotion recognition deals with sentiment analysis in Natural Language Processing which mainly focused on extraction and analysis of emotions. Individuals show their emotions through their conversations, emojis, short notes. Various resources like ECG, writings and videos and audios are commonly used to analyze emotions. Nowadays, information from Facebook, Twitters and Instagram etc., are used as a resource for text mining to find hidden emotions. Emotion retrieval behind these posts is a large and complex work. With the assistance of attitude detection, gadgets will create higher choices to assist their users. Hence, attitude detection from text is important in many areas such as decision making, user-robot interaction etc. Work done in this field is very less as compare to other fields. Therefore, it broadens our scope in the field of attitude detection from text. In this paper, we propose a hybrid model which extract phrasal words from the input and calculate the affect vector for the extracted words. Then based on affect vector, the proposed model categorize the sentence into appropriate target class. This survey paper covers the existing emotion detection models, available datasets, their options and their drawbacks. We have a tendency to concentrate on reviewing analysis efforts analyzing emotions supported text and summarize basic achievements within the field and highlight potential extensions for higher outcome.

Solar irradiance forecasting will turn into a major challenge in the future integration of solar energy resources into existing structures of energy supply. There are squeezing requirements for app...

Voice modality in human-machine interaction has gained popularity in the last decade due to advances in voice technology. All digital devices support voice as input while employing voice assistants. It is the most used way of interaction in headless digital appliances and IoT devices. Emerging audio spoofing techniques pose a significant threat to Automatic Speaker Verification (ASV). False wakeup of voice assistants and their response on recorded audio replay imposes security concerns and customer's hesitancy. As applications of ASV and replay detection are ubiquitous, it is essential to make these systems robust. We propose a two-stage hybrid model: genuinization transformer to efficiently differentiate between the distribution of synthetic and genuine speech and non-speech audio, followed by Residual Squeeze-and-Excitation networks (ResSEnet) to learn relevant latent features and classify audio input as spoofed and bonafide. To handle both speech and non-speech audio sounds effectively, we use log-mel features. The proposed model is evaluated using the ASVspoof 2019 Logical Access (LA) dataset. Experimental results show that our proposed model significantly elevates performance compared to the baseline and state-of-the-art models.

Entertainment industry is growing at a very rapid pace where a huge amount of money is being put into the making of the films. The success or failure of a movie is determined by the box office collection. The box office collection is dependent on various factors like director, actors, actresses, technicians, production house, musicians, marketing, etc. But yet it is highly influenced by the reviews and feedbacks given by the people, critics, media, etc. Due to the latest trends in the marketing field, digital media is used as a form of recommendation system where users read the reviews about a movie, or the ratings rated before making any decision to watch a movie. The existing problem that are identified with these reviews is that nowadays bots are being deployed to increase the reviews, and also fake reviews, negative reviews are also a major concern since most of the reviews are given by people without watching the movies. These problems create huge financial loss to the company, the people associated with it and also the movie industry as a whole. So in order to overcome the existing problems we are considering using blockchain technology as the future of entertainment industry. Since blockchain is a distributed network we can use it to store the reviews given by the user which is nontamperable and this in turn can help rate a movie correctly. Because of the genuine reviews stored in blockchain, movie goers can choose the correct film and make a good film successful thereby increasing the box office collection of the movie.

Human activity recognition has become an obligatory necessity in day to day life and possible solutions can be provided with the technological advancement of sensing field. Radar based sensing with its unbeatable unique features has been a promising solution for identifying and distinguishing human activities in recent years. The ascent of loss of life among elderly people in care homes during COVID-19 is mainly due to poor monitoring services, that was not able to track their daily life activities. This has even more emphasized the need for savvy activity monitoring and tracking system. In this work, we have used a dataset that has captured six daily life activities of people from different locations during different times under realistic environments, unlike an regular controlled data collection environment. We have proposed a novel tower based convolutional neural network architecture that has employed parallel input layers with individual color channel images sent as inputs to the model. We have concatenated all the unique signature features from each channel to have better and robust feature representation to the model. We have analyzed the proposed model with different color spaces like RGB, LAB, HSV as inputs and found that our chosen input type performs better with the proposed model with significant test accuracy results. We have also compared our proposed model with other existing state of art architectures for radar based human activity recognition.