Browse Items (2150 total)
Sort by:
-
Movie Success Prediction from Movie Trailer Engagement and Sentiment Analysis
The diverse movie industry faces many challenges in the promotion of the product across different demographics. Movie trailer engagements provide valuable information about how the audience perceives the movie. This information can be used to predict the success of the upcoming movie before it gets released. The previous research works were mainly concentrating on Hindi language movies to predict success. The current research paper includes the success prediction of movies other than Hindi. This paper aims to analyze various Machine Learning models performance and select the best performing model to predict movie success. The developed model can efficiently classify successful and unsuccessful movies. For the current research, the data is collected from various sources through web scrapping and API calls in Sacnilk, The Movie Database (TMDB), YouTube, and Twitter. Different machine learning classification models such as Random Forest, Logistic Regression, KNN, and Gaussian Nae Bayes are tested to develop the best-performing prediction model. This research can help moviemakers to understand the popularity of the movie among the viewers and decide on an efficient promotional strategy to make the movie more successful. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Moving Towards Responsible Consumption: The Road Ahead for Sustainable Marketing
The fundamental tenet of consumerism revolves around the belief that the burgeoning consumption of goods is favourable for the economy. Since the dawn of the Industrial Revolution, humanity has witnessed an exponential upsurge in consumerism. It has been related both to the increase in the population size as well as an increase in our demands due to constant changes in lifestyle. Multiple sources have corroborated the fact that if this consumption behaviour continues unabated, we will soon face an acute shortage of resources of all kinds. Both consumer behaviour patterns such as addictive consumption and conspicuous consumption can be attributed to this. Amongst the solutions available, 'Demarketing' is one. It is a type of marketing when a brand wants to discourage you from buying its product. The paper is descriptive in nature and is based on secondary data which has been collected from journals, blogs, websites, magazines, books, etc. The paper intends to explore the theme of demarketing vis-vis the materialistic purchase behaviour of a modern-day consumer and green demarketing strategies that companies are adopting by way of sustainable marketing. The Electrochemical Society -
MR Brain Tumor Classification and Segmentation Via Wavelets
Timely, accurate detection of magnetic resonance (MR) images of brain is most important in the medical analysis. Many methods have already explained about the tumor classification in the literature. This paper explains the method of classifying MR brain images into normal or abnormal (affected by tumor), abnormality segments present in the image. This paper proposes DWT-discrete wavelet transform in first step to extract the image features from the given input image. To reduce the dimensions of the feature image principle component Analysis (PCA) is employed. Reduced extracted feature image is given to kernel support vector machine (KSVM) for processing. The data set has 90 brain MR images (both normal and abnormal) with seven common diseases. These images are used in KSVM process. Gaussian Radial Basis (GRB) kernel is used for the classification method proposed and yields maximum accuracy of 98% compared to linear kernel (LIN). From the analysis, compared with the existing methods GRB kernel method was effective. If this classification finds abnormal MR image with tumor then the corresponding part is separated and segmented by thresholding technique. 2018 IEEE. -
MRSP-Multi Routing Systems and Parameter Explanations to Build the Path in Underwater Sensor Network
The underwater network is currently widely used to locate moving objects beneath the sea, monitor marine security, and detect changes in the sea water. A large number of sensors, as well as a precise methodology, are necessary to detect changes in sea depth. The protocol should be revised in response to environmental and chronological changes. The sensor should have been designed with multiple knowledge to route packets in order to optimise transmissions. Because the node will choose the best route based on the circumstances, especially in an underwater network, the paper MRSP - multi routing systems and parameter validations to create the path in an underwater sensor network is discussed in the multi routing knowledge sensor operations, energy saving systems, redundancy reduction, and so on. All of these measures, combined with secure transmission with trusted neighbour selection, result in safer transmissions and more accurate path selection. 2022 IEEE. -
Mudhr: Malicious URL detection using heuristic rules based approach
Technology advancement helps the people in numerous ways such as it supports business development, banking, education, entertainment etc. Especially time critical and money related activities, people are fully really on internet and web applications. It saves valuable time and money. Despite of the benefits, it also gives wide space for the attackers to focus more victims. Malicious URL based attacks are most common and more dangerous attacks now a day which steals the credentials and sensitive data from the victims and perform malicious activities in the victim's space. Phishing, Spamming, drive by download are the example of such attacks and are preformed through malicious URL. Plenty of approaches are available to detect the malicious URL. That are grouped under three categories such as Blacklist based, Heuristic based and Machine Learning based approaches. Among the three, heuristic approach is better than the blacklist approach in term of better generalizing the malicious URL and gives equally accurate prediction with machine learning approach. This paper presents recent works in the field of malicious URL detection and novel technique to detect malicious URL based on the most important features derived from URL. 2022 Author(s). -
MuLSA-Multi Linguistic Sentimental Analyzer for Kannada and Malayalam using Deep Learning
Natural language Processing has been always a topic of interest in artificial intelligence. Opinion mining or Sentiment Analysis is an important application of Natural language Processing. Sentiment Analysis of text is to extract the sentiments underlined in the text. In this paper, a multi-linguistic sentimental analyzer (MuLSA), is implemented, a model that would address Malayalam, Kannada and English text. This model explores two languages in three categories of the text, its original script, transliterated script, and the combination of both along with English. Deep Learning, Recurrent Neural Network with LSTM is used as the basis for this model. The model exhibits 82% of prediction accuracy. 2021 IEEE. -
Multi-Agent Deep Reinforcement Learning for Hybrid Motion Planning in Dynamic Environments
This research presents a novel approach to addressing the challenges of gesture forecasting in impenetrable and dynamic atmospheres by integrating a hybrid algorithm within a multi-agent system framework. Traditional methods such as Force-based motion planning (FMP) & deep reinforcement learning (RL) often struggle to handle complex scenarios involving multiple autonomous agents due to their inherent limitations. To overcome these challenges, we propose a hybrid algorithm that seamlessly combines the strengths of RL and FMP while leveraging the coordination capabilities of a multi-agent system. By integrating this hybrid algorithm into a multi-agent framework, we demonstrate its effectiveness in enabling multiple agents to navigate densely populated environments with dynamic obstacles. Through extensive simulation studies, we illustrate the superior performance of our approach compared to traditional methods, achieving higher success rates and improved efficiency in scenarios involving simultaneous motion planning for multiple agents. A hybrid motion planning algorithm is also introduced in this very research. Performance Comparison of Hybrid Algorithm, Deep RL, and FMP are also discussed in the result section. This research paves the way for the development of robust and scalable solutions for motion planning in real-world applications such as collaborative robotics, autonomous vehicle fleets, and intelligent transportation systems. 2024 IEEE. -
Multi-Layer Ensemble Deep Reinforcement Learning based DDoS Attack Detection and Mitigation in Cloud-SDN Environment
Cloud computing (CC) remains as a promising environment which offers scalable and cost effectual computing facilities. The combination of the SDN technique with the CC platform simplifies the complexities of cloud networking and considerably enhances the scalability, manageability, programmability, and dynamism of the cloud. This study introduces a novel Multi-Layer Ensemble Deep Reinforcement Learning based DDoS Attack Detection and Mitigation (MEDR-DDoSAD) technique in Cloud-SDN Environment. The major aim of the presented technique lies in the recognition of DDoS attacks from the cloud-SDN platform. The MEDR-DDoSAD technique transforms the input data into images and the features are derived via deep convolutional neural network based Xception model. 2022 IEEE. -
Multi-lingual Spam SMS detection using a hybrid deep learning technique
Nowadays, the incremental usage of mobile phones has made spam SMS messages a big concern. Sending malicious links through spam messages harms our mobile devices physically, and the attacker might have a chance to steal sensitive information from our devices. Various state-of-the-art research works have been proposed for SMS spam detection using feature-based, machine, and deep learning techniques. These approaches have specific limitations, such as extracting and selecting signifi-cant and quality features for efficient classification. Very few deep learning techniques are only used for classifying spam detection. Moreover, the benchmark spam datasets written in English are mostly used for evaluation. Very few papers have detected spam messages for other languages. Hence, this paper creates a multilingual SMS spam dataset and proposes a hybrid deep learning technique that combines the Convolutional Neural Network and Long Short-Term Memory (LSTM) model to classify the message dataset. The performance of this proposed hybrid model has been compared with the baseline deep learning models using accuracy, precision, recall, and F1-score metrics. 2022 IEEE. -
Multi-view video summarization
Video summarization is the most important video content service which gives us a short and condensed representation of the whole video content. It also ensures the browsing, mining, and storage of the original videos. The multi- view video summaries will produce only the most vital events with more detailed information than those of less salient ones. As such, it allows the interface user to get only the important information or the video from different perspectives of the multi-view videos without watching the whole video. In our research paper, we are focusing on a series of approaches to summarize the video content and to get a compact and succinct visual summary that encapsulates the key components of the video. Its main advantage is that the video summarization can turn numbers of hours long video into a short summary that an individual viewer can see in just few seconds. Springer India 2016. -
Multilayer classification based Alzheimer's disease detection
Hippocampus, a small brain region plays a role in the initiation of the neurodegenerative pathways that leadto Alzheimer's. Humans with MCI are probable to develop Alzheimer's disorder. Hippocampal volume has been proven to indicate which patients with MCI will later develop Alzheimer's. Brain degeneration in MCI progresses over time and varies from person - to - person, making early detection difficult. Magnetic resonance imaging is a tool in diagnosing clinically suspected Alzheimer's disease. Information about the historical development of structural changes as the disease progresses from preclinical to overt stages is shaping understanding of the disease, and also guides diagnosis and treatment decisions in the future. In this study, we developed a new multilayer classification method to identify Alzheimer's disease from brain MRI using contour model and multilayer classifier. This method is evaluated on 436 samples of OASIS dataset and achieved accuracy of method is 93.75 %. 2024 Author(s). -
Multilevel Quantum Inspired Fractional Order Ant Colony Optimization for Automatic Clustering of Hyperspectral Images
Hyperspectral images contain a wide variety of information, varying from relatively large regions to smaller manmade buildings, roads and others. Automatic clustering of various regions in such images is a tedious task. A multilevel quantum inspired fractional order ant colony optimization algorithm is proposed in this paper for automatic clustering of hyperspectral images. Application of fractional order pheromone updation technique in the proposed algorithm produces more accurate results. Moreover, the quantum inspired version of the algorithm produces results faster than its classical counterpart. A new band fusion technique, applying principal component analysis and adaptive subspace decomposition, is successfully proposed for the pre-processing of hyperspectral images. Score Function is used as the fitness function and K-Harmonic Means is used to determine the clusters. The proposed algorithm is implemented on the Xuzhou HYSPEX dataset and compared with classical Ant Colony Optimization and fractional order Ant Colony Optimization algorithms. Furthermore, the performance of each method is validated by peak signal-to-noise ratio which clearly indicates better segmentation in the proposed algorithm. The Kruskal-Wallis test is also conducted along with box plot, which establishes that the proposed algorithm performs better when compared with other algorithms. 2020 IEEE. -
Multilevel Security and Dual OTP System for Online Transaction Against Attacks
In the current internet technology, most of the transactions to banking system are effective through online transaction. Predominantly all these e-transactions are done through e-commerce web sites with the help of credit/debit cards, net banking and lot of other payable apps. So, every online transaction is prone to vulnerable attacks by the fraudulent websites and intruders in the network. As there are many security measures incorporated against security vulnerabilities, network thieves are smart enough to retrieve the passwords and break other security mechanisms. At present situation of digital world, we need to design a secured online transaction system for banking using multilevel encryption of blowfish and AES algorithms incorporated with dual OTP technique. The performance of the proposed methodology is analyzed with respect to number of bytes encrypted per unit time and we conclude that the multilevel encryption provides better security system with faster encryption standards than the ones that are currently in use. 2019 IEEE. -
Multilingual Sentiment Analysis of YouTube Live Stream using Machine Translation and Transformer in NLP
YouTube has become one of the all-inclusive video streaming sources on the internet. Today, the news is streamed on YouTube, marketing of a product is done live on YouTube and it has become a platform for one of the biggest PR producers for companies. Various companies have proposed an optimized way of understanding and getting the opinions of the viewers from YouTube live chat and find the best possible way to provide relevant and informative content to boost the business strategy. This study uses Natural Language Processing (NLP) based approach along with NLP transformers to classify and analyses the sentiment. 2022 IEEE. -
Multimodal Classification on PET/CT Image Fusion for Lung Cancer: A Comprehensive Survey
Medical image fusion has become essential for accurate diagnosis. For example, a lung cancer diagnosis is currently conducted with the help of multimodality image fusion to find anatomical and functional information about the tumor and metabolic measurements to identify the lung cancer stage and metastatic information of the disease. Generally, the success of multimodality imaging for lung cancer diagnosis is due to the combination of PET and CT imaging advantages while minimizing their respective limitations. However, medical image fusion involves the registration of two different modalities, which is time-consuming and technically challenging, and it is a cause of concern in a clinical setting. Therefore, the paper's main objective is to identify the most efficient medical image fusion techniques and the recent advances by conducting a collective survey. In addition, the study delves into the impact of deep learning techniques for image fusion and their effectiveness in automating the image fusion procedure with better image quality while preserving essential clinical information. The Electrochemical Society -
Multimodal Early Fusion Strategy Based on Deep Learning Methods for Cervical Cancer Identification
It is essential to enhance the accuracy of automatic cervical cancer diagnosis by combining multiple forms of information obtained from a patients primary examination. However, existing multimodal systems are not very effective in detecting correlations between different types of data, leading to low sensitivity but high specificity. This study introduces a deep learning system for automatic diagnosis of cervical cancer by incorporating multiple sources of data. First, a convolutional neural network (CNN) to transform the image database to a vector that can be combined with non-image datasets is used. Subsequently, an investigation of jointly the nonlinear connections between all image and non-image data in a deep neural network is performed. Proposed deep learning-based method creates a unified system that takes advantage of both image and non-image data. It achieves an impressive 89.32% sensitivity at 91.6% specificity when diagnosing cervical intraepithelial neoplasia on a wide-ranging dataset. This result is far superior to any single-source system or prior multimodal approaches. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Multimodal Emotion Recognition in HumanComputer Interaction Using MFF-CNN
The rise of technology in the digital era has amplified the importance of understanding human emotions in enhancing humancomputer interactions. Traditional interfaces, mainly focused on logical tasks, often miss the nuances of human emotion, creating a gap between human users and technology. Addressing this gap, the development of the HumanComputer Interface for emotional intelligence uses advanced algorithms and deep learning models to accurately recognize emotions from various cues like facial expressions, voice, and written text. This paper presented a significant approach for emotion detection in HCI and the challenges faced in capturing genuine emotional responses. Historically, the emphasis in HCI design was on operational tasks, neglecting emotional nuances. However, the tide is changing toward embedding emotional intelligence into these interfaces, leading to enhanced user experiences. This research introduces the MFF-CNN, a neural network model combining both textual and visual data for accurate emotion detection. Through sophisticated algorithms and the integration of advanced machine learning techniques, this paper presents a refined approach to emotion detection in HCI, supported by a comprehensive review of related works and a detailed methodology. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Multimodal Emotion Recognition Using Deep Learning Techniques
Humans have the ability to perceive and depict a wide range of emotions. There are various models that can recognize seven primary emotions from facial expressions (joyful, gloomy, annoyed, dreadful, wonder, antipathy, and impartial). This can be accomplished by observing various activities such as facial muscle movements, speech, hand gestures, and so forth. Automatic emotion recognition is a significant issue that has been a hotly debated research topic in recent years. At the moment, several research people have taken a component in inheriting or extra multimodal for higher understanding. This paper indicates a method for emotion recognition that makes use of 3 modalities: facial images, audio indicators, and text detection from FER and CK+, RAVDESS, and Twitter tweets datasets, respectively. The CNN model achieved 66.67 percent on the FER-2013 dataset of labeled headshots while on the CK+ dataset, 98.4 percent accuracy was obtained. Finally, diverse fusion strategies had been approached, and each of those fusion techniques gave distinctive results. This project is a step towards the sense of interaction between human emotional aspects and the growing technology that is the future of development in today's world. 2022 IEEE. -
Multimodal Face and Ear Recognition Using Feature Level and Score Level Fusion Approach
Recent years have seen a significant increase in attention in multimodal biometric systems for personal identification especially in unconstrained environments. This paper presents a multimodal recognition system by combining feature level fusion of ear and profile face images. Multimodal biometric systems by combining face and ear can be used in an extensive range of applications because we can capture both the biometrics in a non-intrusive manner. Local texture feature descriptor, BSIF is used to extract discriminative features from biometric templates. Feature level and score level fusion is experimented to improve the performance of the system. Experimental results on different public datasets like GTAV, FEI, etc., show that the proposed method gives better performance in recognition results than individual modality. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Multiple Approaches in Retail Analytics to Augment Revenues
Knowledge is power. The retail sector has been revolutionized around the clock by the plentiful product knowledge available to customers. Today, customers can use the knowledge available online at any time to study, compare and purchase products from anywhere. Retail companies can stay ahead of shopper trends by using retail information analytics to discover and analyze online and in-store shopper patterns. A product recommender will suggest products from a wide selection that would otherwise be very difficult to locate for the customer. The algorithm would recommend various products, increase the sales of items that would otherwise be difficult to sell. Market basket analysis is a common use scenario for the search for frequent patterns, which involves analyzing the transactional data of a retail store to decide which items are bought together. To do so data from online resource has been taken, which is analyzed and several conclusions were made. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.