Indian Journal of Artificial Intelligence and Neural Networking

Journal Information
EISSN : 2582-7626
Published by: Lattice Science Publication (LSP) (10.54105)
Total articles ≅ 17

Latest articles in this journal

Indian Journal of Artificial Intelligence and Neural Networking, Volume 2, pp 8-14;

WHO (World Health Organization) classified COVID-19 (Corona virus Disease 2019) as a pandemic after a substantial number of individuals died from an illness. This virus has infected millions and continues to infect new victims every day. Traditional RT-PCR tests to identify COVID-19 are prohibitively expensive and time-consuming, thus researchers are turning to deep learning (DL)-based algorithms that utilize medical imagery such as computed tomography (CT) scans. This helps automate the scanning process. All areas of COVID-19 research targeted at halting the current epidemic are currently being conducted using deep learning. We looked at some of the newest DL-based models for detecting COVID-19 in CT lung images in this work. During our investigation, we gathered information on the many research resources that were accessible. This survey may serve as a starting point for a novice/beginner level researcher working on COVID-19 categorization. The COVID-19 and its rapid detection technique are described in full in this study. This is followed by a discussion of computed tomography (CT) and a review of deep learning and its different covid detection methods, such as RNN, CNNLSTM as well as DNN. Deep learning approaches have been used in several recent research on the identification of COVID-19 patients. To identify COVID-19, we reviewed the most recent DL approaches used in conjunction with CT scans. A DL system for disease detection during the COVID-19 epidemic is discussed in this study, as are many authors' methodologies and the relevance of their research efforts, as well as possible difficulties and future developments.
Indian Journal of Artificial Intelligence and Neural Networking, Volume 2, pp 1-7;

The heart is considered to be one of the most vital organs in the body. It contributes to the purification and circulation of blood throughout the body. Heart Diseases are responsible for the vast majority of fatalities around the world. Some symptoms, such as chest pain, a faster heartbeat, and difficulty breathing, have been documented. This data is reviewed regularly. In this review, a basic introduction related to the topic is first introduced. Furthermore, provide an overview of the healthcare industry. Then, an in-depth discussion of heart disease and the types of heart disease. After that, a summary of heart disease prediction, and different methods of heart disease prediction are also provided. Then, a short description of machine learning, also its different types, and how to use machine learning in the healthcare sector is discussed. And the most relevant classification techniques such as K-nearest neighbor, decision tree, support vector machine, neural network, Bayesian methods, regression, clustering, naïve Bayes classifier, artificial neural network, as well as random forest for heart disease is described in this paper. Then, a related work available on heart disease prediction is briefly elaborated. At last, concluded this paper with future research.
Indian Journal of Artificial Intelligence and Neural Networking, Volume 2, pp 1-14;

In current times the level at which Alzheimer’s disease is rising is at an alarming rate. This rise points to the need for much more accurate and faster modes of diagnosis that the country wants. Artificial intelligence can resolve this issue as it uses extensive human surveys and real-time machine medicine monitors. The use of biomarkers that work on detecting unusual changes in the brain and the spectrochemical analysis of blood that works on the principle of vibrational spectroscopy Inclusive of Raman spectroscopy and FTIR cannot be used at a large scale. The underemployment of these methods includes the requirement of highly trained professionals and the heterogeneous nature of the human population. Therefore, the following approaches may be employed to overcome these benefits and give individuals optimal health solutions; Random Forest technique, etc., artificial neural network. When the talk is shifted towards treating Alzheimer’s, there is no such drug to treat it thoroughly. Symptomatic treatment options are available based on specific known receptors of Alzheimer’s etiology. Artificial intelligence has also taken a pioneering step to fill this void. With its help, we can identify a lot more receptors influenced upon Alzheimer’s advent. Once these newly found receptors are considered, better symptomatic treatment can be provided. Drug classes like NMDA receptor antagonists, Statins, and Antipsychotics are readily available options for managing disease, but all of these have a low safety index and other side effects like bleeding and psychosis. Newly re-purposed drugs like Acitretin and minocycline etc., have minimalistic side effects and high safety margin, making them a better choice in the diseased state. After Artificial intelligence has entered the market, the fields of diagnostics and therapeutics and taken the most advantage of it alongside administration and regulation, therefore, this AI is a boon in the medical industry as it can help manage medicine-based disease registries and population management when it comes to Alzheimer’s diagnosis and treatment.
, Damodar Prasad Tiwari
Indian Journal of Artificial Intelligence and Neural Networking, Volume 1, pp 1-4;

Dimension reduction or feature selection is thought to be the backbone of big data applications in order to improve performance. Many scholars have shifted their attention in recent years to data science and analysis for real-time applications using big data integration. It takes a long time for humans to interact with big data. As a result, while handling high workload in a distributed system, it is necessary to make feature selection elastic and scalable. In this study, a survey of alternative optimizing techniques for feature selection are presented, as well as an analytical result analysis of their limits. This study contributes to the development of a method for improving the efficiency of feature selection in big complicated data sets.
Banya Arabi Sahoo
Indian Journal of Artificial Intelligence and Neural Networking, Volume 1, pp 1-3;

AI is the incredibly exciting technique to the world. According to John McCarthy it is “The science and engineering of making intelligent machine, especially intelligent computers”. AI is the way of creating extraordinary powerful machine which is similar as human being. The AI is being accomplished by studying how human brain think, how they learn, decide, work, solving the real world problem and after that verify the outcomes and studying it. Primarily you can learn here what AI is and how it works, its types, its history, its agents, its applications, its advantages and disadvantages.
Jaya Kumari, , Gourav Saxena,
Indian Journal of Artificial Intelligence and Neural Networking, Volume 1, pp 12-16;

Face recognition techniques play a crucial role in numerous disciplines of data security, verification, and authentication. The face recognition algorithm selects a face attribute from an image datasets. Recognize identification is an authentication device for verification as well as validation having both data analysis and feasible significance. The facerecognizing centered authentication framework can further be considered an AI technology implementation for instantly identifying a particular image. In this research, we are presenting a hybrid face recognition model (HFRM) using machine learning methods with “Speed Up Robust Features” (SURF), “scale-invariant feature transform” (SIFT), Locality Preserving Projections (LPP) &Principal component analysis (PCA) method. In the proposed HFRM model SURF method mainly detects the local feature efficiently. SIFT method mainly utilizes to detect the local features and recognize them. LPP retains the local framework of facial feature area which is generally quite meaningful than on the sequence kept by a ‘principal component analysis (PCA) as well as “linear discriminate analysis” (LDA). The proposed HFRM method is compared with the existing (H. Zaaraoui et al., 2020) method and the experimental result clearly shows the outstanding performance in terms of detection rate and accuracy % over existing methods.
Indian Journal of Artificial Intelligence and Neural Networking, Volume 1, pp 7-11;

Visual encryption technology becomes the latest research area in which a lot of scopes persist. Presently such a particular cryptosystem procedure is now used by numerous other countries around the world for the private transmission of formal records, financial documents, content visuals, digital voting, and so on. Visualization Cryptographic algorithms one of the protected methods of transferring pictures online. The main benefit of image encryption has been that it disguises peripheral vision with encrypt data secret data with no computation usually needed. In this work a hybrid visual cryptography method using a sigmoid function (HVMSF) for enhancing the security in gray images. HVMSF strategy utilizes a chaos framework to scramble pixel values as well as blocks while using the Modified Arnold Cat Map method (MACM) as well as the Henon Map method (HMM). The methodology includes a confusion procedure wherein the location of each image pixel is shuffled by utilizing MACM. The shuffling of image pixel leads to the creation of a subset pixel which will be protected for transmitting. This proposed HVMSF mainly tries to overcome the limitation of the previous approaches by applying sigmoid function in image feature space for contrast enhancement throughout the consequent source images. The experimental outcomes precisely show that the suggested strategy can further give additional effectiveness to ensure the protection of transmitting information out over previous techniques.
Ms. Judy Flavia, Aviraj Patel, Diwakar Kumar Jha, Navnit Kumar Jha
Indian Journal of Artificial Intelligence and Neural Networking, Volume 1, pp 23-28;

In the project we are demonstrating the combined usage Augmented Reality(AR) and brain faced com- puter interface(BI) which can be used to control the robotic acurator by. This method is more simple and more user friendly. Here brainwave senor will work in its normal setting detecting alpha, beta, and gam- ma signals. These signals are decoded to detect eye movements. These are very limited on its own since the number of combinations possible to make higher and more complex task possible. Asa solution to this AR is integrated with the BCI application to make control interface more user friendly. This application can be used in many cases including many robotic and device controlling cases. Here we use BCI-AR to detect eye paralysis that can be archive by detecting eye lid movement of person by wearing head bend.
M.S.Antony Vigil, Rishabh Jain, Abhinav Chandra, Tanmay Agarwal
Indian Journal of Artificial Intelligence and Neural Networking, Volume 1, pp 17-22;

There are a variety of deep learning algorithms available in the supervision of ships, but they are dealing with multiple issues of inaccurate identification on rate and in a dequatetargetdetecti on speed. At this stage, an algorithm is given оnСоnvоlutiоnаlNeuralNetwork for target identification and detection using the ship image. The study involves the investigation of the reactions of hyper spectral atmospheric rectification on the accurate and precise results of ship detection. The ship features which were detected from two atmospheric rectified algorithms on airborne hyperspectral data were corrected by the application of these algorithms with the help of an unsupervised target detection procedure. High accuracy and fast ship identification was a result of this algorithm and using unique modules, improving the loss function and enlargement of data for the smaller targets. The results of the experiments show that our algorithm has given much better detection rate as compared to target detection algorithm using traditional machine learning.
Indian Journal of Artificial Intelligence and Neural Networking, Volume 1, pp 1-6;

Plagiarism is an act of using another person’s words, idea or information without giving credit to that person and presenting them as your own. With the development of the technologies in recent years, the act of Plagiarism increases significantly. But luckily the plagiarism detection techniques are available and they are improving day by day to detect the attempts of plagiarizing the content in education. The software like Turnitin, iThenticate or Safe Assign is available in the markets that are doing a great job in this context. But the problem is not fully solved yet. These software(s) still doesn’t detect the rephrasing of statements of another writer in other words. This paper primarily focuses to detect the plagiarism in the suspicious document based on the meaning and linguistic variation of the content. The techniques used for this context is based on Natural language processing. In this Paper, we present how the semantic analysis and syntactic driven Parsing can be used to detect the plagiarism.
Back to Top Top