25 results on '"Nafis, Md. Tabrez"'
Search Results
2. A secure technique for unstructured big data using clustering method
- Author
-
Nafis, Md Tabrez and Biswas, Ranjit
- Published
- 2022
- Full Text
- View/download PDF
3. A systematic review on machine learning approaches for cardiovascular disease prediction using medical big data
- Author
-
Azmi, Javed, Arif, Muhammad, Nafis, Md Tabrez, Alam, M. Afshar, Tanweer, Safdar, and Wang, Guojun
- Published
- 2022
- Full Text
- View/download PDF
4. RETRACTED ARTICLE: Enhanced bat algorithm for COVID-19 short-term forecasting using optimized LSTM
- Author
-
Rauf, Hafiz Tayyab, Gao, Jiechao, Almadhor, Ahmad, Arif, Muhammad, and Nafis, Md Tabrez
- Published
- 2021
- Full Text
- View/download PDF
5. Modeling infectious diseases: Understanding social connectivity to control infectious diseases
- Author
-
Wazir, Samar, Gour, Surendra, Nafis, Md Tabrez, and Khan, Rijwan
- Published
- 2021
- Full Text
- View/download PDF
6. The Impact of Randomized Algorithm over Recommender System
- Author
-
Shakil, Ubaid, Syed, Alam, Mohammed Talha, Sohail, Shahab Saquib, Saifi, Imran Khan, Mufti, Tabish, Aziz, Asfia, and Nafis, Md Tabrez
- Published
- 2021
- Full Text
- View/download PDF
7. Smart Parking: An Efficient System for Parking and Payment.
- Author
-
Ahmed, Ezaz, Arif, Mohammad, Rahmani, Mohammad Khalid Imam, Nafis, Md Tabrez, and Ali, Javed
- Published
- 2024
- Full Text
- View/download PDF
8. Predictive Modelling of Glycated Hemoglobin Levels Using Machine Learning Regressors.
- Author
-
Hashmi, Afshan, Nafis, Md Tabrez, Naaz, Sameena, Nandan, Durgesh, and Hussain, Imran
- Subjects
MACHINE learning ,STANDARD deviations ,HYPERGLYCEMIA ,PREDICTION models ,GLYCOSYLATED hemoglobin - Abstract
Diabetes is a chronic condition characterized by elevated levels of blood glucose, also known as hyperglycemia. Measurement of HbA1c is a widely used blood test that provides an essential tool for monitoring diabetic progression and assessing the effectiveness of diabetes management but this test is usually not conducted until there are some symptoms of diabetes in the patient and sometimes it goes unnoticed for a longer period resulting in the late detection of the disease. This study proposes a novel approach to HbA1c Prediction using machine learning regression algorithms on various features including Age, BMI, and hematological parameters. This study also compares the performance of ten machine learning regressors on the prediction of HbA1c level using performance metrics such as Mean square error, Root mean squared error, Mean absolute error MAE, R square, Adjusted R square, and Minimum Absolute Percentage Error. Result: Linear regression was found as the best performer with an R square and adjusted R square value of 1.00, Mean square error, Root mean squared error, Mean absolute error, and Minimum Absolute Percentage Error of 0.00. A higher HbA1c Level predicted using this method should go for actual HbA1c testing for confirmation. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
9. Dynamic Adaptation of Activation Function to Fine Tune Video ResNet for Fight or Non-Fight Classification.
- Author
-
Faridi, Atif, Siddiqui, Farheen, Nandan, Durgesh, Nafis, Md Tabrez, and Ahad, Mohd Abdul
- Subjects
CONVOLUTIONAL neural networks ,VIDEOS - Abstract
The task of designing and training a 3D convolutional neural network (CNN) from scratch poses significant complexity, necessitating high levels of expertise to achieve a performance that rivals the state-of-the-art. To circumvent this, fine-tuning of neural networks has emerged as a formidable approach. This study focuses on the utilization of Video ResNet, a state-of-the-art architecture known for its proficiency in capturing spatiotemporal patterns from video data. A novel approach is proposed for the fine-tuning of the 3D CNN model (Video ResNet) that involves altering activation functions over epochs while maintaining the network weights and biases consistent. This dynamic approach was assessed under various hyperparameters, yielding encouraging results. Contrary to most studies that employ down-sampling of the temporal sequence to minimize memory requirements, this study introduces a sliding window-based approach to evade down-sampling and prevent potential information loss. The proposed methodology yielded an accuracy of 87.25% in the fight/non-fight classification on the RWF-2000 dataset, marginally surpassing the performance of the state-of-the-art model. The proposed method not only facilitates the development of a real-time video incident detection model but also addresses the issue of overfitting during training through the incorporation of adaptive dynamic activation functions. This study thus contributes to the ongoing advancements in the field of neural network fine-tuning and video data classification. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
10. Biomedical Text Classification Using Augmented Word Representation Based on Distributional and Relational Contexts.
- Author
-
Parwez, Md. Aslam, Fazil, Mohd., Arif, Muhammad, Nafis, Md Tabrez, and Auwul, Md. Rabiul
- Subjects
SEMANTICS ,KRIPKE semantics ,NATURAL language processing ,SCIENTIFIC literature ,RELATIONAL databases - Abstract
Due to the increasing use of information technologies by biomedical experts, researchers, public health agencies, and healthcare professionals, a large number of scientific literatures, clinical notes, and other structured and unstructured text resources are rapidly increasing and being stored in various data sources like PubMed. These massive text resources can be leveraged to extract valuable knowledge and insights using machine learning techniques. Recent advancement in neural network-based classification models has gained popularity which takes numeric vectors (aka word representation) of training data as the input to train classification models. Better the input vectors, more accurate would be the classification. Word representations are learned as the distribution of words in an embedding space, wherein each word has its vector and the semantically similar words based on the contexts appear nearby each other. However, such distributional word representations are incapable of encapsulating relational semantics between distant words. In the biomedical domain, relation mining is a well-studied problem which aims to extract relational words, which associates distant entities generally representing the subject and object of a sentence. Our goal is to capture the relational semantics information between distant words from a large corpus to learn enhanced word representation and employ the learned word representation for various natural language processing tasks such as text classification. In this article, we have proposed an application of biomedical relation triplets to learn word representation through incorporating relational semantic information within the distributional representation of words. In other words, the proposed approach aims to capture both distributional and relational contexts of the words to learn their numeric vectors from text corpus. We have also proposed an application of the learned word representations for text classification. The proposed approach is evaluated over multiple benchmark datasets, and the efficacy of the learned word representations is tested in terms of word similarity and concept categorization tasks. Our proposed approach provides better performance in comparison to the state-of-the-art GloVe model. Furthermore, we have applied the learned word representations to classify biomedical texts using four neural network-based classification models, and the classification accuracy further confirms the effectiveness of the learned word representations by our proposed approach. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
11. A Deterministic Model for Determining Degree of Friendship Based on Mutual Likings and Recommendations on OTT Platforms.
- Author
-
Khalique, Aqeel, Rahmani, Mohammad Khalid Imam, Saquib, Mohd, Hussain, Imran, Muzaffar, Abdul Wahab, Ahad, Mohd. Abdul, Nafis, Md Tabrez, and Ahmad, Mohd Wazih
- Subjects
RECOMMENDER systems ,FRIENDSHIP ,USER experience ,TELEVISION programs - Abstract
In recent years, the application of various recommendation algorithms on over-the-top (OTT) platforms such as Amazon Prime and Netflix has been explored, but the existing recommendation systems are less effective because either they fail to take an advantage of exploiting the inherent user relationship or they are not capable of precisely defining the user relationship. On such platforms, users generally express their preferences for movies and TV shows and also give ratings to them. For a recommendation system to be effective, it is important to establish an accurate and precise relationship between the users. Hence, there is a scope of research for effective recommendation systems that can define a relationship between users and then use the relationship to enhance the user experiences. In this research article, we have presented a hybrid recommendation system that determines the degree of friendship among the viewers based on mutual liking and recommendations on OTT platforms. The proposed enhanced model is an effective recommendation model for determining the degree of friendship among viewers with improved user experience. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
12. Enhanced bat algorithm for COVID-19 short-term forecasting using optimized LSTM.
- Author
-
Rauf, Hafiz Tayyab, Gao, Jiechao, Almadhor, Ahmad, Arif, Muhammad, and Nafis, Md Tabrez
- Subjects
COVID-19 ,ALGORITHMS ,COVID-19 pandemic ,DEEP learning ,RECURRENT neural networks ,TRAFFIC estimation ,INFECTIOUS disease transmission ,RANDOM walks - Abstract
The highly infectious COVID-19 critically affected the world that has stuck millions of citizens in their homes to avoid possible spreading of the disease. Researchers in different fields are continually working to develop vaccines and prevention strategies. However, an accurate forecast of the outbreak can help control the pandemic until a vaccine is available. Several machine learning and deep learning-based approaches are available to forecast the confirmed cases, but they lack the optimized temporal component and nonlinearity. To enhance the current forecasting frameworks' capability, we proposed optimized long short-term memory networks (LSTM) to forecast COVID-19 cases and reduce mean absolute error. For the optimization of LSTM, we applied bat algorithm. Furthermore, to tackle the premature convergence and local minima problem of BA, we proposed an enhanced variant of BA. The proposed version utilized Gaussian adaptive inertia weight to control the individual velocity in the entire swarm. In addition, we substitute random walk with the Gaussian walk to observe the local search mechanism. The proposed LSTM examines the personal best solution with the swarm's local best and preserves the optimal solution by combining the Gaussian walk. To evaluate the optimized LSTM, we compared it with the non-optimal version of LSTM, recurrent neural network, gated recurrent units, and other recent state-of-the-art algorithms. The experimental results prove the superiority of the optimized LSTM over other recent algorithms by obtaining 99.52 % accuracy. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
13. Identification of Thoracic Diseases by Exploiting Deep Neural Networks.
- Author
-
Albahli, Saleh, Rauf, Hafiz Tayyab, Arif, Muhammad, Nafis, Md Tabrez, and Algosaibi, Abdulelah
- Subjects
X-ray imaging ,DEEP learning ,IDENTIFICATION ,DISEASES - Abstract
With the increasing demand for doctors in chest related diseases, there is a 15% performance gap every five years. If this gap is not filled with effective chest disease detection automation, the healthcare industry may face unfavorable consequences. There are only several studies that targeted X-ray images of cardiothoracic diseases. Most of the studies only targeted a single disease, which is inadequate. Although some related studies have provided an identification framework for all classes, the results are not encouraging due to a lack of data and imbalanced data issues. This research provides a significant contribution to Generative Adversarial Network (GAN) based synthetic data and four different types of deep learning-based models that provided comparable results. The models include a ResNet-152 model with image augmentation with an accuracy of 67%, a ResNet-152 model without image augmentation with an accuracy of 62%, transfer learning with Inception- V3 with an accuracy of 68%, and finally ResNet-152 model with image augmentation but targeted only six classes with an accuracy of 83%. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
14. Neutrosophy Logic and its Classification: An Overview.
- Author
-
Muzaffar, Aiman, Nafis, Md. Tabrez, and Sohail, Shahab Saquib
- Subjects
- *
NEUTROSOPHIC logic , *LOGIC , *EXPONENTIAL functions , *SOFT computing , *CLASSIFICATION - Abstract
Over the past few years, neutrosophy has gained an exponential growth and has attracted a good number of researchers especially those who focus on soft computing based uncertainty computation. This paper presents the various techniques in neutrosophy. The various techniques are discussed lucidly which help a naïve researcher in this field to understand the on-going researches and establish a strong base. We have summarized the previous work carried out in the field of neutrosophic logic, set, measure, and also classification techniques in neutrosophy and the relevant research work has been discussed. Further, various applications in the field of neutrosophy are elaborated. The major contributions of the existing research in neutrosophy is reviewed and presented from different perspectives. The development of newer algorithms for solving the problems of neutrosophy will provide impetus to the existing research in this field. [ABSTRACT FROM AUTHOR]
- Published
- 2020
15. IoT ENABLED TRAFFIC CONTROL MODEL USING RASPBERRY PI.
- Author
-
Faisal Malik, Syed Mohd, Khan, Mohd Hamzah, and Nafis, Md. Tabrez
- Subjects
TRAFFIC engineering ,RASPBERRY Pi ,COMPUTERS in traffic engineering ,TRAFFIC cameras ,TRAFFIC incident management ,INTERNET of things - Abstract
In this paper a new methodology is described to efficiently handle and managed traffic in a highly populated and congested area. The traffic management system's framework make use of an essential technology required which is IoT .It also has other important parts such as an autonomous activity controller raspberry-pi, pi-camera, RFID ,IR sensors .To further help to navigate the traffic the proposed framework uses decisive algorithm and round-robin algorithm to find the Optimum path through traffic. Raspberry pi is used to manage all components collectively and individually. Total traffic in a region is determined by the help of IR sensors which uses RFID to distinguish high priority vehicles such as ambulance and VIPS from day to day traffic. There is an additional benefit of using RFID it can be used to locate the robbed or snatched vehicles. The proposed framework has two major parts i.e autonomous and manual. The algorithm used to navigate traffic play a vital part in making the proposed framework work efficiently. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
16. ANALYTICAL STUDY OF IMAGE CLASSIFICATION USING DEEP LEARNING.
- Author
-
Yousuf, Salihah and Nafis, Md Tabrez
- Subjects
DEEP learning ,IMAGE processing ,ARTIFICIAL neural networks ,ARTIFICIAL intelligence ,MACHINE learning - Abstract
The machine learning technology has received increased attention in recent years in several vision tasks such as image classification, image detection, and image recognition. In particular, recent advances of machine learning techniques bring encouragement to image classification with convolutional neural networks. CNN has been established as a powerful class of models for image recognition problems and even in some cases they outperform humans. The main purpose of the work presented in this paper is the rise and development of machine learning, deep learning, CNN and to give an overview on using machine learning for image classification. At the end the comparison of CNN with traditional method is discussed. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
17. Node Scaling of Telecom services on Emerging Cloud.
- Author
-
Mehtab, Huma and Nafis, Md Tabrez
- Subjects
INTERNET ,CLOUD computing ,TELECOMMUNICATION ,DISTRIBUTED computing ,COST control - Abstract
Invention of internet has given boost to the new emerging business called the Cloud Computing. Cloud computing has given advantages to make way for reducing operational costs. It gives companies and individuals to get various services without investing in traditional way, user pay for the service they use, for the time they use them. In this paper we will try to discuss how telecom operators, as a leader in providing telecom services, can do to be competitive with multinational companies in market as cloud service providers. As companies already have infrastructure, it gives them a head start in the emerging field. Also we will try to explain model to use in the vendor, which will help telecom operators launch cloud services. [ABSTRACT FROM AUTHOR]
- Published
- 2017
18. Spam Mail Detection Using Hybrid Secure Hash Based Naive Classifier.
- Author
-
Ajaz, Sana, Nafis, Md. Tabrez, and Sharma, Vishal
- Subjects
EMAIL ,SPAM email ,NAIVE Bayes classification ,SPAM filtering (Email) ,CONTENT filters (Computer science) - Abstract
E-mail is the most prevalent approaches for communication because of its obtain ability, quick message altercation and low distribution cost. Spam mail seems as a serious issue influencing this application today's internet. Spam may contain suspicious URL's, or may ask for financial information as money exchange information or credit card details. Classification is a way to get rid of those spam messages. Naïve byes classification based spam filtering technique is a popular method. In this work a detection of spam mail is proposed by using Naïve byes classification method by combining secure hash algorithm (SHA-512) as security purpose. Experimental results present a significant improvement in accuracy with higher F-measure compare to traditional algorithms. [ABSTRACT FROM AUTHOR]
- Published
- 2017
19. Classification Technique for Sentiment Analysis of Twitter Data.
- Author
-
Huda, Kirti, Nafis, Md Tabrez, and Shaukat, Neshat Karim
- Subjects
SENTIMENT analysis ,ONLINE data processing ,TEXT mining ,INFORMATION retrieval - Abstract
The sentiment analysis is the technique which can analyze the behavior of the user. The data which is analyzed is the twitter data. The four steps are followed for the sentiment analysis in the first step, the first step is applied in which data pre-processed. In the second step feature of the data will be extracted which is given as input to the third step in which data is classified for the sentiment analysis. In this paper, pattern based technique is applied for the feature extraction in which patterns are generated from the existing patterns which increase the accuracy of data classification. The proposed algorithm is been implemented in python using the nltk tool box and it is been analyzed that execution time is reduced and accuracy is increased at steady rate. [ABSTRACT FROM AUTHOR]
- Published
- 2017
20. A Steganography Technique Based on the Huffman Codes and PM1 Technique.
- Author
-
Dwivedi, Sonal and Nafis, Md. Tabrez
- Subjects
CRYPTOGRAPHY ,DATA transmission systems ,DIGITAL communications ,GENETIC algorithms ,COMBINATORIAL optimization - Abstract
In this age of technology, everyday huge amount of data is transferred across the network. The higher the amount of data transmission the larger the amount of security is needed. In this scenario security of the data stands as the basic need and it needs to be addressed and solved first. In this paper combination of a standard table and Plus Minus 1 (PM1) steganography using Genetic Algorithm (GA) is proposed which would not only allow transmission of a large amount of data but would also eliminate the need of embedding the look-up table along with the image. [ABSTRACT FROM AUTHOR]
- Published
- 2017
21. Students Academic Performance Using Partitioning Clustering Algorithms.
- Author
-
Humamuddin, Nafis, Md. Tabrez, and Owais, Syed Taha
- Subjects
DATA mining ,K-means clustering ,COMPUTER algorithms ,TIME management ,PATTERN recognition systems - Abstract
With time, the data is growing at a very high rate. The issue is not in storing the data, but in extracting the valuable information from it. Data mining techniques serve as a good means for extracting valuable patterns (knowledge) from the data. Now, talking about the Educational Field, Academic Institutes and Universities are worried about their student's performance because it's a key factor for the growth and ranking of the institutes. Data in educational institutes is also growing at a very high rate as the number of students are increasing every year. It's a tedious task to monitor and predict the performance of students by normal methods. Data Mining techniques are very helpful in doing this job. In this paper, we have used K-Means, K-Medoids and X-Means clustering algorithms which will help in categorizing the students into several groups based on their performance. [ABSTRACT FROM AUTHOR]
- Published
- 2017
22. Sentimental Classification of Social Media using Data Mining.
- Author
-
Laeeq, Farhan, Nafis, Md. Tabrez, and Beg, Mirza Rahil
- Subjects
DATA mining ,SUPPORT vector machines ,DECISION trees ,NAIVE Bayes classification - Abstract
In Today's life, social networking sites provides a great source of communication. So it provides the important source for understanding the emotions of people. In this paper, we use data mining techniques for the purpose of classification to perform sentiment analysis. We collect the facebook dataset and apply the optimized selection(Brute Force) and then we use three different classifiers and also compare their results in order to find which one gives better results.Rapid Miner tool is being used, which helps in building the classifier as well as able to apply it to the testing dataset. [ABSTRACT FROM AUTHOR]
- Published
- 2017
23. Disease Symptoms Analysis Using Data Mining Techniques to Predict Diabetes Risk.
- Author
-
Kamal, Jawad, Tanveer, Safdar, and Nafis, Md. Tabrez
- Subjects
DATA mining ,DIABETES risk factors ,SYMPTOMS ,DATA extraction ,MEDICAL decision making - Abstract
Data mining field concentrates on theories, concepts, methodologies and mainly on extraction of useful knowledge from large amounts of data for decision making. During their day to day activities healthcare industry generates large amounts of healthcare information that has not been efficiently used to extract unknown information. Therefore the discovery of interesting and useful information usually remains hidden. Diabetes is a healthcare problem and is increasing at a greater rate with every passing year. If not recognized early, can lead to severe health problems, even in organ failures. Several data mining techniques like clustering, classification, association rule mining are used to identify early symptoms of the diseases and stopping them getting to a chronic level. In this paper, an efficient approach has been designed for prediction of risk of getting diabetes using diabetes database. The approach in this paper used more than one data mining techniques showing enhanced result in disease prediction. The data for diabetes is collected and processed to facilitate the mining process. Firstly, the preprocessed database is mined to extract frequent patterns related to diabetes using FP-Growth algorithm. After that ID3 algorithm approach has been used as the training algorithm to depict the risk of diabetes using a Decision Tree. [ABSTRACT FROM AUTHOR]
- Published
- 2017
24. Scalable Geo Web Techniques using Spatial Data Mining for Air Pollution.
- Author
-
Singh, Dharmendra, Tanweer, Md. Safdar, and Nafis, Md Tabrez
- Subjects
DATA mining ,AIR pollutants ,GEOSPATIAL data ,ONLINE data processing ,AIR pollution - Abstract
This paper proposes to bolster Geo Web Techniques and spatial data mining techniques for air pollution in Delhi-NCR for real time analysis and identification of relationship among the pro &anti pollutant objects effecting in a specific zone of area. A Geo Web based solution is proposed by provisioning of feature and attribute data services over the web. The functional constituents are collection, transformation, Spatial Data Mining, OGC Web Services i.e. Web Map Service (WMS),Web Feature Service (WFS) ,Web Coverage Service (WCS) query and Geo Web Publishing elements. The collecting element provisioned to access the onsite monitored data through a interface with sources of actual data sets . It need to transform the data into the required spatial format and mining component give an interface to the end user. Spatial information mining systems can be connected to different fields' specifically human services, metrological information, activity examination, client insight, transport administration, urban arranging and utilities industry. Albeit spatial data mining does not yet belong to the most commonly used spatial information analysis, it was found effective to detect solid relationship among geological feature objects. [ABSTRACT FROM AUTHOR]
- Published
- 2017
25. Introducing "α-Sustainable Development" for transforming our world: A proposal for the 2030 agenda.
- Author
-
Biswas, Siddhartha Sankar, Ahad, Mohd Abdul, Nafis, Md Tabrez, Alam, M. Afshar, and Biswas, Ranjit
- Subjects
- *
GOVERNMENT agencies , *FUZZY measure theory , *SET theory , *FUZZY sets , *SUSTAINABLE development - Abstract
In this paper the authors introduce the "Theory of α-Sustainable Development" which is developed using fuzzy set theory. The existing concept and definition of "Sustainable Development" is correct and well understood by the world, but is not very precisely defined. In our "Theory of α-Sustainable Development" we say that every development (D) is a sustainable development up to certain extent depending upon the fuzzy measure 'α' of the amount of sustainability of D. We propose double categorization of every hybrid-pillar (HP) Development for better evaluation: Categorization in Type-1 and Categorization in Type-2. For a single-pillar development D the value of the fuzzy measure α is a non-negative number in [0,1], and the same is also true for a hybrid pillar (2P or 3P) development D while categorizing under Type-2. However, while categorizing the HP-Developments under Type-1, the value of α is an ordered pair (α 1 , α 2) where α 1 and α 2 are in [0,1]. Every development D is graded to be qualified as one of the five categories of sustainable development: SSD, GSD, PSD, WSD and NSD. In 'Theory of α-Sustainable Development' the existing core notion of 'Sustainable Development' is neither compromised nor diluted. The theory initially discusses about 'single-pillar Sustainable Development' and then about 'multi-pillar Sustainable Development' (also called by Hybrid Pillar Sustainable Development). The notion of 'α-Sustainable Development' will be very much useful to the corresponding regulatory bodies to improve the practices of dealing a development D with the existing notion of Yes-No type of sustainable development. Mathematically, the core aim of this paper is to grade a development D in the continuous range [0,1] instead of the existing notion of grading in the discrete range {0, 1}. This work deals only with those type of developments which are completely constructed, not about reviewing the interim progress of them. The "Theory of α-Sustainable Development" is an open proposal to the 2030 Agenda meeting, and will surely enrich the policy of ESD for educating the present and future generation people and thus to retain the sustainability of our planet as a whole. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.