Deep Learning Methods for Lung Cancer Nodule Classification: A Survey

Lung cancer is one of the leading causes of cancer related deaths. It is due to the complexity of early detection of nodules. In clinical practice, radiologists find it difficult to determine whether a condition is normal or abnormal by manually analysing CT scan or X-ray images for nodule identification. Currently, various deep learning techniques have been developed to identify lung nodules as benign or malignant, but each technique has its own advantages and drawbacks. This work presents a thorough analysis based on segmentation techniques, Related features-based detection, multi-step detection, automatic detection, and deep convolutional neural network techniques. Performance comparison was conducted on a selected works based on performance measures. A potential research direction for the recognition of lung nodules is given at the end of this study.

Machine Learning Based Clinical Diagnosis of Liver Patients with Instance Replacement

With the rapid increase in number of clinical data and hence the prediction and analysing data becomes very difficult. With the help of various machine learning models, it becomes easy to work on these huge data. A machine learning model faces lots of challenges; one among the challenge is feature selection. In this research work, we propose a novel feature selection method based on statistical procedures to increase the performance of the machine learning model. Furthermore, we have tested the feature selection algorithm in liver disease classification dataset and the results obtained shows the efficiency of the proposed method.

Detection of Cotton Plant Diseases Using Deep Transfer Learning

Agriculture is a vital part of every country’s economy, and India is regarded an agro-based nation. One of the main purposes of agriculture is to yield healthy crops without any disease. Cotton is a significant crop in India in relation to income. India is the world’s largest producer of cotton. Cotton crops are affected when leaves fall off early or become afflicted with diseases. Farmers and planting experts, on the other hand, have faced numerous concerns and ongoing agricultural obstacles for millennia, including much cotton disease. Because severe cotton disease can result in no grain harvest, a rapid, efficient, less expensive and reliable approach for detecting cotton illnesses is widely wanted in the agricultural information area. Deep learning method is used to solve the issue because it will perform exceptionally well in image processing and classification problems. The network was built using a combination of the benefits of both the ResNet pre-trained on ImageNet and the Xception component, and this technique outperforms other state-of-the-art techniques. Every convolution layer with in dense block is tiny, so each convolution kernel is still in charge of learning the tiniest details. The deep convolution neural networks for the detection of plant leaf diseases contemplate utilising a pre-trained model acquired from usual enormous datasets, and then applying it to a specific task educated with their own data. The experimental results show that for ResNet-50, a training accuracy of 0.95 and validation accuracy of 0.98 is obtained whereas training loss of 0.33 and validation loss of 0.5.

A Deep Learning Framework for Intrusion Detection and Multimodal Biometric Image Authentication

Nowadays, a demand is increased all over the world in the field of information security and security regulations. Intrusion detection (ID) plays a significant role in providing security to the information, and it is an important technology to identify various threats in network during transmission of information. The proposed system is to develop a two-layer security model: (1) Intrusion Detection, (2) Biometric Multimodal Authentication. In this research, an Improved Recurrent Neural Network with Bi directional Long Short-Term Memory (I-RNN-BiLSTM) is proposed, where the performance of the network is improved by introducing hybrid sigmoid-tanh activation function. The intrusion detection is performed using I-RNN-BiLSTM to classify the NSL-KDD dataset. To develop the biometric multimodal authentication system, three biometric images of face, iris, and fingerprint are considered and combined using Shuffling algorithm. The features are extracted by Gabor, Canny Edge, and Minutiae for face, iris, and fingerprint, respectively. The biometric multimodal authentication is performed by the proposed I-RNN-BiLSTM. The performance of the proposed I-RNN-BiLSTM has been analysed through different metrics like accuracy, f-score, and confusion matrix. The simulation results showed that the proposed system gives better results for intrusion detection. Proposed model attains an accuracy of 98% for the authentication process and accuracy of 98.94% for the intrusion detection process.

Examination of the Non-Orthogonal Multiple Access System Using Long Short Memory Based Deep Neural Network

This paper investigates deep learning (DL) non-orthogonal multiple access (NOMA) receivers based on long short-term memory (LSTM) under Rayleigh fading channel circumstances. The performance comparison between the DL NOMA detector and the traditional NOMA method is established, and results have shown that the DL-based NOMA detector performance is far better in comparison with conventional NOMA detectors. Simulation curves are compared with the performance of the DL detector in terms of minimum mean square estimate (MMSE) and least square error (LSE) estimate, taking all realistic circumstances, except the cyclic prefix (CP), and clipping distortion into account. The simulation curves demonstrate that the performance of the DL-based detector is exceptionally good when it equals 1 when the noise signal ratio (SNR) is more than 15 dB, assuming that the DL method is more resilient to clipping distortion.

A Systematic Literature Review of Educational Apps: What Are They Up To?

As the use of Educational Apps rises every day and the population begins its use at an increasingly early age, it becomes relevant to understand the positive and negative aspects of this technological tool. However, the information may seem overwhelming, especially for those starting investigations on this topic. For this reason, a Systematic Literature Review was conducted on 119 published scientific papers, in order to create a work that synthesizes all the recent data about most used keywords, funding aid, authors and publishing journals, just to name a few. Additional data also reveals the need, expressed by authors and backed by their research, to evaluate the effectiveness of the Educational Apps. As an additional point, some solutions are offered to deal with the aforementioned problem, as well as some recommendations for the correct development of applications.

Paddy Plant Disease Recognition, Risk Analysis, and Classification Using Deep Convolution Neuro-Fuzzy Network

A significant number of the world’s population is dependent on rice for survival. In addition to sugarcane and corn, rice is said to be the third most growing staple food in the world. As a consequence of intensive usage of man-made fertilizers, paddy plant diseases have also risen at a faster pace in current history. Exploring the possible disease spread and classifying to detect the consequent impact at an early stage will prevent the loss and improve rice production. The core task of this research is to recognize and quantify different kinds of infections (disease) affecting the paddy plant crop, such as brown spots, bacterial blight, and leaf blasts. Both detection and recognition are carried out based on the risk analysis of paddy crop leaf images. We suggest a Deep Convolutional Neuro-Fuzzy Method (DCNFM) that combines one of the advanced machine learning variant, namely deep convolutional neural networks (DCNNs) and uncertainty handler called fuzzy logic. The synthesis has the benefits of both fuzzy logic and DCNNs when dealing with unstructured data, extracting essential features from imprecise and ambiguous datasets. From the crop field, continuous image data are captured through image sensors and fed as a primary input to the proposed model to analyze the risk and then later to classify them for precise recognition/detection of the disease. The detection/recognition rate of the DCNFM is found to be 98.17% which is comparatively found to be effective in comparison with the traditional CNN model.

Java Bytecode Control Flow Classification: Framework for Guiding Java Decompilation

Decompilation is the main process of software development, which is very important when a program tries to retrieve lost source codes. Although decompiling Java bytecode is easier than bytecode, many Java decompilers cannot recover originally lost sources, especially the selection statement, i.e., if statement. This deficiency affects directly decompilation performance. In this paper, we propose the methodology for guiding Java decompiler to deal with the aforementioned problem. In the framework, Java bytecode is transformed into two kinds of features called frame feature and latent semantic feature. The former is extracted directly from the bytecode. The latter is achieved by two-step transforming the Java bytecode to bigram and then term frequency-inverse document frequency (TFIDF). After that, both of them are fed to the genetic algorithm to reduce their dimensions. The proposed feature is achieved by converting the selected TFIDF to a latent semantic feature and concatenating it with the selected frame feature. Finally, KNN is used to classify the proposed feature. The experimental results show that the decompilation accuracy is 93.68 percent, which is obviously better than Java Decompiler.

Real Time Traffic Prediction Based On Social Media Text Data Using Deep Learning

Due to urbanization Traffic management is one of the major issues in contemporary civic management, considering this circumstance traffic analysis is turning into the need of the present world. Text data generated by Twitter, Facebook and other social media platforms can be used for traffic management. Big data helps in traffic prediction and traffic analysis of advancing metropolitan zones. Constant traffic investigation requires preparing of information streams that are produced persistently to increase fast experiences. To measures stream information at a fast rate advancements on high figuring limit is required. Social media text data can be processed by using batch processing and stream processing with big data architecture through Spark and Hadoop framework. In this paper big data architecture is proposed for real time traffic text data analysis. In architecture Spark and Kafka are used in combination. Kafka helps in pipelines text data used in conjunction with spark stream processing engine. Big data architecture using Spark, Kafka with ability for processing and preparing huge measure of information, have settled the serious issue of handling and putting away constantly streaming data. The traffic information from Twitter API is streamed. In The proposed model pointed toward ensemble neural network model to reduce the variance in results for better prediction foreseeing traffic stream text data by incorporating Spark and Kafka that will be of an extraordinary incentive to the public authority for traffic management and analysis.

Design of Four-Core Uncoupled Multicore Fiber for Next-Generation Inter-Data Center Networks

The increasing demands within and between the data centers used for data traffic has required. Efficient links are important to data center applications for supporting the unlimited demand. Transmission capacity of single-mode fiber (SMF) is limited by fiber nonlinearity which prevents the increasing transmission power and finite amplifier bandwidth. Single-mode multi-core fibers (SM-MCFs) that are expected to overcome the current limitation of optical communication capacity. However, the inter-core crosstalk still has an effect on SM-MCF, which can limit the transmission of the inter-data center. In this paper, the design of four-core uncoupled multicore fiber is discussed for next generation inter-data center networks in order to support the unlimited use of data traffic in the future. The objective of this paper is to determine the appropriate range of core radius and core pitch, which are taken into consideration to reduce the inter-core crosstalk inside the optical fiber. These parameters can be able to improve various constraints to achieve the best multi-core fibers design. From the simulation concerned with the inter-core crosstalk, the experiment results show that the range of core pitch is at 47.5 μm to 50 μm and the range of core radius starts from 4.5 μm to 5.5 μm, that can achieve with crosstalk lower than – 30 dB/100 km for the future inter-data center networks.