Papers by Manish Maheshwari
Journal of Healthcare Engineering
The Internet of Things (IoT) is now growing dramatically on various levels and helps to digitize ... more The Internet of Things (IoT) is now growing dramatically on various levels and helps to digitize various vital industries quickly. The most difficult obstacle for BCIs to overcome is the fact that not everyone has the same brain. Every new session requires the BCI to learn from the user’s brain, which is accomplished via the use of machine learning. However, this learning process is time-consuming. Calibration time refers to the amount of time it takes for the BCI to adapt to the user’s brain in order to properly categorize their thoughts and determine their meaning. The patient has had to wait an arduous and tiresome length of time for the system to be completely functioning up until now because of this calibration, which may take up to 20–30 minutes. The aim of this paper was to find a way to decrease the amount of time required for calibration to the smallest amount feasible. In the first section of this paper, a first effort is made to determine the optimum number of features re...
Computational Intelligence and Neuroscience, 2022
Sleep apnea is a serious sleep disorder that occurs when a person's breathing is interrupted ... more Sleep apnea is a serious sleep disorder that occurs when a person's breathing is interrupted during sleep. People with untreated sleep apnea stop breathing repeatedly during their sleep. This study provides an empirical analysis of apnea syndrome using the AI-based Granger panel model approach. Data were collected from the MIT-BIH polysomnographic database (SLPDB). The panel is composed of eighteen patients, while the implementation was done using MATLAB software. The results show that, for the eighteen patients with sleep apnea, there was a significant relationship between ECG-blood pressure (BP), ECG-EEG, and EEG-blood pressure (BP). The study concludes that the long-term interaction between physiological signals can help the physician to understand the risks associated with these interactions. The study would assist physicians to understand the mechanisms underlying obstructive sleep apnea early and also to select the right treatment for the patients by leveraging the potenti...
Applications of Mathematical Modeling, Machine Learning, and Intelligent Computing for Industrial Development
International Journal of Emerging Technology and Advanced Engineering
In today’s era most of the YouTuber’s are facing the major problem with electronic spam as troubl... more In today’s era most of the YouTuber’s are facing the major problem with electronic spam as troublesome Internet phenomenon. This work proposes a methodology for the detection of spam comments on the video-sharing website - YouTube. YouTube is running its own spam blocking system but continues to fail to block them properly. In this work, we examined several top- performance classification techniques for spam comment screening and proposed a novel methodology. In this work, we have analyzed such comments by applying conventional machine learning algorithms such as Naive Bayes, Random Forest, Support Vector Machine, Logistic regression, Decision Tree and will construct another model utilizing ensemble and hybrid approach. This paper proposed the YouTube spam comments detection framework, examined, and validated by using data collected from the YouTube using Naïve Bayes multinomial, Gradient Boosting, Random Forest and tested in Weka and Python data mining tools.
2022 6th International Conference on Intelligent Computing and Control Systems (ICICCS)
Folia Medica Indonesiana
Highlights: Association Rule Mining tools predict the association of early-onset Myocardial Infar... more Highlights: Association Rule Mining tools predict the association of early-onset Myocardial Infarction with Hypertension and Diabetes Mellitus. Association Rule Mining tools using clinical and biochemical attributes can predict the development of Hypertension and Diabetes Mellitus in Myocardial Infarction patients. : Cardiovascular diseases (CVDs) are a major cause of mortality in diabetic patients. Hypertensive patients are more likely to develop diabetes and hypertension contributes to the high prevalence of CVDs, in addition to dyslipidemia and smoking. This study was to find the different patterns and overall rules among CVD patients, including rules broken down by age, sex, cholesterol and triglyceride levels, smoking habits, myocardial infarction (MI) type on ECG, diabetes, and hypertension. The cross-sectional study was performed on 240 subjects (135 patients of ST-elevation MI below 45 years and 105 age matched controls). Association rule mining was used to detect new patter...
Journal of Healthcare Engineering, 2022
Due to the increasing number of medical imaging images being utilized for the diagnosis and treat... more Due to the increasing number of medical imaging images being utilized for the diagnosis and treatment of diseases, lossy or improper image compression has become more prevalent in recent years. The compression ratio and image quality, which are commonly quantified by PSNR values, are used to evaluate the performance of the lossy compression algorithm. This article introduces the IntOPMICM technique, a new image compression scheme that combines GenPSO and VQ. A combination of fragments and genetic algorithms was used to create the codebook. PSNR, MSE, SSIM, NMSE, SNR, and CR indicators were used to test the suggested technique using real-time medical imaging. The suggested IntOPMICM approach produces higher PSNR SSIM values for a given compression ratio than existing methods, according to experimental data. Furthermore, for a given compression ratio, the suggested IntOPMICM approach produces lower MSE, RMSE, and SNR values than existing methods.
Journal of Healthcare Engineering, 2021
One of the most important and difficult research fields is newborn jaundice grading. The mitotic ... more One of the most important and difficult research fields is newborn jaundice grading. The mitotic count is an important component in determining the severity of newborn jaundice. The use of principal component analysis (PCA) feature selection and an optimal tree strategy classifier to produce automatic mitotic detection in histopathology images and grading is given. This study makes use of real-time and benchmark datasets, as well as specific approaches for detecting jaundice in newborn newborns. According to research, the quality of the feature may have a negative impact on categorization performance. Additionally, compressing the classification method for exclusive main properties can result in a classification performance bottleneck. As a result, identifying appropriate characteristics for training the classifier is required. By combining a feature selection method with a classification model, this is possible. The major outcomes of this study revealed that image processing techni...
International Journal of Modern Physics B, 2020
Data processing with multiple domains is an important concept in any platform; it deals with mult... more Data processing with multiple domains is an important concept in any platform; it deals with multimedia and textual information. Where textual data processing focuses on a structured or unstructured way of data processing which computes in less time with no compression over the data, multimedia data are processing deals with a processing requirement algorithm where compression is needed. This involve processing of video and their frames and compression in short forms such that the fast processing of storage as well as the access can be performed. There are different ways of performing compression, such as fractal compression, wavelet transform, compressive sensing, contractive transformation and other ways. One way of performing such a compression is working with the high frequency component of multimedia data. One of the most recent topics is fractal transformation which follows the block symmetry and archives high compression ratio. Yet, there are limitations such as working with ...
Pattern Association is the process of forming association between related patterns that maps a se... more Pattern Association is the process of forming association between related patterns that maps a set of input patterns to a set of output patterns. The pattern that has to be associated may be of same type or of a different type. Associative memory net can be seen as a simplified model of a human brain which stores and retrieves patterns by association. In this paper, an efficient new fuzzy model for association of color image is introduced. A new color quantization ordering scheme that focuses on color as feature and considers Hue-Value and Saturation (HVS) space is proposed. Using fuzzy if-then rules pixel color is quantized into 54 colors. Fuzzy histogram of these 54 colors is calculated and stored in feature database. We propose a simplified associative memory model to store associations between feature vectors.
In current digital era, every experimental instruments, clinical system, laboratory apparatuses a... more In current digital era, every experimental instruments, clinical system, laboratory apparatuses are embedded with digital devices, due to the digitization of research and experimental processes, biological databases has increased in volume tremendously. However, the high performance computing devices and software tools to deal with this complex and increased volume of data is still persists as a big challenge among the computer scientists and biologists. This papers introduces the various analysis and visualization tools in bioinformatics, bioinformatics big databases and a high level bioinformatics system architecture is proposed to handle the voluminous data in bioinformatics.
Computational Intelligence and Neuroscience
A large amount of patient information has been gathered in Electronic Health Records (EHRs) conce... more A large amount of patient information has been gathered in Electronic Health Records (EHRs) concerning their conditions. An EHR, as an unstructured text document, serves to maintain health by identifying, treating, and curing illnesses. In this research, the technical complexities in extracting the clinical text data are removed by using machine learning and natural language processing techniques, in which an unstructured clinical text data with low data quality is recognized by Halve Progression, which uses Medical-Fissure Algorithm which provides better data quality and makes diagnosis easier by using a cross-validation approach. Moreover, to enhance the accuracy in extracting and mapping clinical text data, Clinical Data Progression uses Neg-Seq Algorithm in which the redundancy in clinical text data is removed. Finally, the extracted clinical text data is stored in the cloud with a secret key to enhance security. The proposed technique improves the data quality and provides an e...
The Computer Journal
The electroencephalography (EEG) signal is corrupted with some non-cerebral activities due to pat... more The electroencephalography (EEG) signal is corrupted with some non-cerebral activities due to patient movement during signal measurement. These non-cerebral activities are termed as artifacts, which may diminish the superiority of acquired EEG signal statistics. The state of the art artifact elimination approaches applied canonical correlation analysis (CCA) for confiscating EEG motion artifacts accompanied by ensemble empirical mode decomposition (EEMD). An improved cascaded approach based on Gaussian elimination CCA (GECCA) and EEMD is applied to suppress EEG artifacts effectively. However, in a highly noisy environment, a novel addition of median filter before the GECCA algorithm is suggested for improving the accuracy of onslaught the EEG signal. The median filter is opted due to its edge preserving nature and speed. This proposed approach is appraised using efficacy grounds for instance Del signal to noise ratio, Lambda (λ), root mean square error and receiver operating charact...
International Journal of Computer Science and Mobile Computing
Content-Based Image Retrieval systems backups the image retrieval process using the primary chara... more Content-Based Image Retrieval systems backups the image retrieval process using the primary characteristics of image like colour, shape, texture and spatial locations clubbed with the semantic approaches for better efficiency and performance. Various information measures have been proposed in order to increase the level of Retrieval. A method of picture information measures based upon the concept of the minimum number of gray level changes to convert a picture into one with a desired histogram is presented. In search of finding a new perspective an integrated approach of Picture Information Measure (PIM) employed with the primitive visual feature color. The retrieval results obtained by applying color histogram (CH) on PIM (PIM of Red Green and Blue and there integrated variation) + Color Moment to a 1000 image database demonstrated significant improvement in retrieval effectively.
Searching online has become part of the everyday lives of most people. Whether to look for inform... more Searching online has become part of the everyday lives of most people. Whether to look for information about the latest gadget to getting directions to a popular trend, most people have made search engines part of their daily routine. Beyond trivial applications, search engines are increasingly becoming the sole or primary source directing people to essential information. For this reason, search engines occupy “a prominent position in the online world”; they have made it easier for people to find information among the billions of web pages on the Internet. Due to the large number of websites, search engines have the complex task of sorting through the billions of pages and displaying only the most relevant pages in the search engine results page (SERP) for the submitted search query. With the continued growth of the Internet and the amount of websites available, it has become increasingly difficult for sites looking for an audience to achieve visibility. There are millions of new we...
ACM Transactions on Multimedia Computing, Communications, and Applications
To enhance the ability of intrusion detection system (IDS) with detection accuracy and low false ... more To enhance the ability of intrusion detection system (IDS) with detection accuracy and low false positive rate, artificial immune system (AIS) based multi agent IDS is proposed that is inspired by ...
Journal of Medical Systems
This paper proposes an innovative image cryptosystem algorithm using the properties of the block ... more This paper proposes an innovative image cryptosystem algorithm using the properties of the block encryption, 4D logistic map and DNA systems. Multiple key sequences are generated and pixel substitution is performed by using nonlinear 4D logistic map, then encryption is performed by using DNA rules to ensure that the different blocks are encrypted securely. The results of the experiment indicate that the proposed Non Linear 4D Logistic Map and DNA (NL4DLM_DNA) sequence based algorithm gives better performance, which is analyzed on the basis of security, quality, attack resilience, diffusion and running time as compared to some previous works.
With the advancement in image capturing device, the image data been generated at high volume. If ... more With the advancement in image capturing device, the image data been generated at high volume. If images are analyzed properly, they can reveal useful information to the human users. Content based image retrieval address the problem of retrieving images relevant to the user needs from image databases on the basis of low-level visual features that can be derived from the images. Grouping images into meaningful categories to reveal useful information is a challenging and important problem. Clustering is a data mining technique to group a set of unsupervised data based on the conceptual clustering principal: maximizing the intraclass similarity and minimizing the interclass similarity. Proposed framework focuses on color as feature. Color Moment and Block Truncation Coding (BTC) are used to extract features for image dataset. Experimental study using K-Means clustering algorithm is conducted to group the image dataset into various clusters.
In this paper, we describe a new method to identify the writer of handwritten documents. There ar... more In this paper, we describe a new method to identify the writer of handwritten documents. There are many methods for signature verification or writer identification, but most of them require segmentation or connected component analysis. They are the kinds of content dependent identification methods as signature verification requires the writer to write the same text (e.g. his name). In our new method, we take the handwriting as an image containing some special texture, and writer identification is regarded as texture identification. This is a content independent for a particular script. We apply the well-established 2-D Gabor filtering technique and grey scale co-occurrence matrices to extract features of such textures and a weighted Euclidean distance classifier and K-nearest neighbor classifier to fulfill the identification task. Experiments are made using handwritings from different people in different languages and very promising results were achieved.
The fundamental data clustering problem may be defined as the process of grouping the data object... more The fundamental data clustering problem may be defined as the process of grouping the data objects into classes or clusters, so that objects within a cluster have high similarity in comparison to one another but are very dissimilar to objects in other clusters. This paper produces an efficient new model for grouping of color images. A new color quantization ordering scheme that focuses on color as feature and considers Hue-Value and Saturation (HVS) space is proposed. Image pixel color is quantized into 54 colors and histogram of these 54 colors is calculated. To form clusters of images k-means algorithm is applied. Clustering analyzes data objects without consulting a known class label. In general, the class labels are not present in the training data simply because they are not known to begin with. Clustering can be used to generate such labels. The objects are clustered or grouped based on the principle of maximizing the intraclass similarity and minimizing the interclass similar...
Uploads
Papers by Manish Maheshwari