@sru.edu.in
Assistant Professor
SR University
Microbiology, Computer Science Applications, Artificial Intelligence
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Mohammed Ali, P. Praveen, Sampath Kumar, Sallauddin Mohmmad, and M. Sruthi
AIP Publishing
Mohammed Ali Shaik, Praveen Pappula, T. Sampath Kumar, and Battu Chiranjeevi
AIP Publishing
Praveen Pappula, Mohammed Ali Shaik, Sampath Kumar Tallapally, Vadlakonda Anitha, and Nagavelli Yogendernath
AIP Publishing
Mamidala Sruthi, Thota Sravanthi, Mohammed Ali Shaik, Chittireddy Padmaja, and U. M. Gopal Krishna
AIP Publishing
Sampath Kumar Tallapally, Mohammed Ali Shaik, P. Praveen, and Sunitha Gadipe
AIP Publishing
Mohammed Ali Shaik, P. Praveen, T. Sampath Kumar, Masrath Parveen, and Swetha Mucha
AIP Publishing
Battu Chiranjeevi, Velpula Tejaswini, Akarapu Mahesh, Vallem Sushmalatha, Ravi Kiran Karre, and Mohammed Ali Shaik
AIP Publishing
Swetha Mucha, Sunitha Gadipe, Supraja Poladi, Mohammed Ali Shaik, and Sharvani Yedulapuram
AIP Publishing
Sampath Kumar Tallapally, Mohammed Ali Shaik, P. Praveen, and Sushma Latha Vallem
AIP Publishing
Sampath Kumar Tallapally, Mohammed Ali Shaik, P. Praveen, and Masani Ruchi Nandhan
AIP Publishing
Donagani Ramakrishna and Mohammed Ali Shaik
Institute of Electrical and Electronics Engineers (IEEE)
Mohammed Ali Shaik, Achyuthreddy Kethireddy, Sanjay Nerella, Samadarshini Pinninti, Vasanth Kathare, and Pavan Pitta
IEEE
The Sound Wave Scribe Voice Assistant paper is, about how people interact with computers. It uses the advancements in natural language processing (NLP) and machine learning (ML) to incorporate voice commands. Inorder to rely on the intelligence when a user talks to the system, the assistant picks up the sound through a microphone or other input tools. The raw sound goes through steps like reducing noise breaking it into segments and extracting features. Then the system changes the sound into text using speech recognition (ASR). Different NLP components like tokenization part of speech tagging and named entity recognition break down the text into parts. After that the system figures out what users want by analyzing the text. Natural language understanding (NLU) figures out what users are saying while context management ensures transitions in conversations. Depending on what users want the system creates responses that sound human like using natural language generation (NLG) techniques. Dialog management keeps track of context and knowledge graphs offer data for answers. Finally computer generated speech–made using text to speech (TTS) libraries–turns the responses back, into sounding spoken words. The systems flexibility goes beyond setting reminders and scraping the web. You can do it all with voice commands. With connections, to databases and online platforms the Sound Wave Scribe Voice Assistant steps up user ease becoming a resource, for voice activated tech.
Mohammed Ali Shaik and Nallani Lakshmi Sri
IEEE
Technological advancements have revolutionized stock market forecasting, with machine learning methods proving more accurate than traditional statistical approaches. Comparing various models, this study found that algorithms like Random Forest results in high performance in predicting Tesla's stock closing prices. These methods mitigate risks associated with investing while maximizing dividends, which are crucial for effective resource allocation and macroeconomic expansion in a country's financial market.
Mohammed Ali Shaik, Masrath Parveen, and Imran Qureshi
IEEE
Insect pests pose a serious threat to food security and agricultural profitability, as they cause direct damage to crops and transmit plant diseases. Manual monitoring methods are inadequate to detect and prevent infestations, especially in large-scale farming operations. This article explores the potential of using drone technology and machine learning algorithms to enhance insect pest management in agriculture. Drones can capture high-resolution images of fields, while machine learning can analyze the data and identify signs of insect activity. However, this approach faces several challenges, such as the diversity and complexity of insect species, their behavior, and their impact on crops. Therefore, a multidisciplinary collaboration among researchers, farmers, technologists, and entomologists is essential to develop effective and robust solutions. This article aims to provide an overview of the current state and future prospects of using drone technology and machine learning for insect pest management in agriculture.
Mohammed Ali Shaik, Yamsani Sahithi, Mandala Nishitha, Rekulapelli Reethika, Kondabathula Sumanth Teja, and Chinthala Pradhyumn Reddy
IEEE
Emotion recognition from images plays an important role in various industries, including healthcare, education and marketing, as well as in human-computer interactions. This paper aims to build a real-time emotion recognition system using deep learning to understand facial expressions and accurately infer emotional states. This system will use deep learning to extract features from facial images using Convolutional Neural Networks (CNNs). The results of this paper will help advance emotion recognition technologies and their applications in various industries, ultimately improving human-machine interactions and user experience.
Freddy Ajila, Saravanan Manokaran, Kanimozhi Ramaswamy, Devi Thiyagarajan, Praveen Pappula, Shaik Ali, Surrya Dillibabu, Uday Kasi, and Mayakannan Selvaraju
National Library of Serbia
It is well-known that nanofluids differ significantly from traditional heat transfer fluids in terms of their thermal and transfer characteristics. Two of CO2 transfer characteristics, its thermal conductivity and its viscosity, are crucial to improved oil retrieval methods and industries refrigeration. By combining molecular modelling with various machine learning algorithms, this study predicts the conduction characteristics of iron oxide CO2 nanofluids. It is possible to evaluate the accuracy of these transfer parameter estimates by applying machine learning methods such as decision tree, K-nearest neighbors, and linear regression. Predicting these transfer qualities requires knowing the size, fraction of nanoparticle volume, and temperature. To determine the characteristics, molecular dynamics simulations are run using the large-scale atom Vastly equivalent simulant. An inter- and intra-variable Pearson correlation was established to confirm that the input variables were reliant on m and thermal conductivity. The results were finally confirmed by using statistical coefficients of determination. For a variety of temperature ranges, volume fractions, and nanoparticle sizes, the study found that the decision tree model was the best at predicting the transport parameters of nanofluids. It has a 99% success rate.
B Rama, P Praveen, and Mohammed Ali Shaik
IEEE
The major goal is to create opportunities for deep learning algorithms to be used to understand better and diagnose Parkinson's disease. The loss of dopamine-producing neurons causes Parkinson's disease, a degenerative disorder. When the condition first manifests, patients have tremors, bradykinesia, poor posture, and balance among other mobility impairments that progressively get worse over time. Additionally, as the global ageing population grows exponentially, more people are developing Parkinson's disease, which places a significant financial strain on governments. Structural modifications in the brain of individuals suffering from Parkinson's disease, resulting from a deficiency in dopamine, can be visualized through the application of Magnetic Resonance Imaging (MRI). In this particular investigation, an attempt was made to classify MR images of both Parkinson's disease patients and unaffected individuals by utilizing a sophisticated deep learning neural network. The utilization of a convolutional neural network proves to be instrumental in augmenting the diagnostic capabilities concerning Parkinson's disease. The MR images are meticulously scrutinized and subjected to rigorous evaluation in order to derive accurate metrics pertaining to their classification. The primary objective of this investigation aims to establish an approach for accurately discerning and classifying ailments through the utilization of Magnetic Resonance Imaging (MRI). Deep learning exhibits remarkable proficiency in disease diagnosis and image interpretation. A burgeoning body of scholarly inquiry suggests that the identification and prognostication of Parkinson's disease may necessitate the application of deep learning methodologies. In terms of disease prediction, deep learning models wield immense potency. The best early detection accuracy deep learning algorithms are hence the subject of increased research. In this experiment, the illness stage will be determined by brain imaging. Also, to the study suggests an effective deep learning approach for early disease prediction utilizing MRI data. The data set came from Kaggle. In this article a deep learning method for diagnosing Parkinson's diseases is proposed that makes use of the CNN algorithm.
Mohammed Ali Shaik, Yamsani Sahithi, Mandala Nishitha, Rekulapelli Reethika, Kondabathula Sumanth teja, and Pradhyumn Reddy
IEEE
In the current digital era, it is essential to effectively communicate in online settings, and emojis have emerged as a key tool for doing so. In order to improve the precision and usability of emoji selection within digital communication systems, this study offers a novel alternative. The creation of an advanced emotion classification system, supported by a semantic search algorithm, forms the basis of the suggested system. The solution provides a seamless and context-aware experience, in contrast to conventional methods that rely on manual emoji selection or imprecise keyword-based emotion detection. The system surpasses the restrictions of keyword matching by effectively identifying the emotional content within phrases or paragraphs by utilizing cutting-edge natural language processing techniques. Emoji suggestions are given to users by the system along with a Random Forest-based emotion categorization algorithm and real-time emoji-Emotion mapping, redefining how emotions are communicated in digital chats.
Mohammed Ali Shaik, Mohammad Azam, Thota Sindhu, Kamuni Abhilash, Anjana Mallala, and Anishetty Ganesh
IEEE
The COVID-19 pandemic has emphasized concerns regarding the presence of microorganism contamination in public environments. Measures aimed at diminishing the transmission of viruses have encompassed strategies like movement limitations, the enforcement of social distancing, mask mandates, and the promotion of hand hygiene. Nevertheless, the challenge of preventing indirect virus transmission through surface contact persists, particularly in locations where individuals interact with potentially contaminated surfaces, such as touchscreen menus in restaurants. Both businesses and the general populace are actively exploring methods to alleviate the spread of germs through surface contact. The primary objective of this paper is to implement hybrid model which uses Convolutional neural network prowess in handling spatial data along with the decision tree is used for attaining efficacy in managing structured data related to food ordering system. Hand gesture-based ordering systems eliminate the necessity to touch shared surfaces physically, such as menus or touchscreen kiosks, thus diminishing the potential for germ transmission.
Masrath Parveen and Mohammed Ali Shaik
IEEE
Organizations of all sizes and sectors are increasingly conducting penetration tests as a preventative step to discover and mitigate potential vulnerabilities as cyber threats continue to emerge. With a focus on penetration testing's function in cyber security, this research seeks to provide a thorough review of the practice and its numerous methodologies. The purpose is to first present the idea of penetration testing, its goals, and its applicability to contemporary cyber security. It then goes on to investigate some of the most popular penetration testing techniques, such as network scanning, vulnerability scanning, and exploitation. The paper concluded by emphasizing some of the difficulties and restrictions related to penetration testing and outlining potential future research topics. Overall, the useful resources for organizations seeking to learn concerning how penetration testing fits into the range of cyber security options.
Mohammed Ali Shaik, Makkaji Yasha Sree, Sanka Sri Vyshnavi, Thogiti Ganesh, Dasari Sushmitha, and Narmetta Shreya
IEEE
In the age of digital media, fake news is a serious problem because it spreads misinformation and harms individuals, organizations, and even entire nations which is a challenging aspect. This study proposes a machine learning approach for detecting fake news. In the proposed approach, a categorization model is developed with four different types of machine learning algorithms, evaluating the content and aesthetic components of news stories. The performance of the proposed model is analyzed by using a large dataset of real and fake news articles and the results show that it outperforms many existing systems. The proposed findings demonstrate the potential of machine learning techniques, such as logistic regression, decision tree, random forest, and passive aggressive algorithms to address the fake news detection challenges.
Mohammed Ali Shaik, Radhandi Sreeja, Safa Zainab, Panthangi Shiva Sowmya, Thipparthy Akshay, and Sudireddy Sindhu
IEEE
One of the main causes of death in the world is heart disease. Early heart disease detection and treatment can lower mortality rates and enhance quality of life which is the major challenge. “Machine learning” algorithms can accurately predict the likelihood of getting the heart disease by using data like: “age, gender, lifestyle factors, medical history, and laboratory testing”. Building a ML model for “heart disease prediction” which is merely relies on the various relevant factors is the primary goal of this paper. For this research project, we used 4 different datasets which comprises of distinct factors that are relevant to heart disease. The model building is made through ML algorithms: “Random forest, K-nearest neighbour, logistic regression, and decision tree”. The study demonstrates that, when compared to other ML techniques, logistic regression and KNN provide better prediction accuracy in a shorter amount of time.
Mohammed Ali Shaik and Dhanraj Verma
AIP Publishing
Mohammed Ali Shaik, MD. Riyaz Ahmed, M. Sai Ram, and G. Ranadheer Reddy
AIP Publishing