The analysis of sentiments is essential in identifying and classifying opinions regarding a source material that is, a product or service. The analysis of these sentiments finds a variety of applications like product reviews, opinion polls, movie reviews on YouTube, news video analysis, and health care applications including stress and depression analysis. The traditional approach of sentiment analysis which is based on text involves the collection of large textual data and different algorithms to extract the sentiment information from it. But multimodal sentimental analysis provides methods to carry out opinion analysis based on the combination of video, audio, and text which goes a way beyond the conventional text-based sentimental analysis in understanding human behaviors. The remarkable increase in the use of social media provides a large collection of multimodal data that reflects the user's sentiment on certain aspects. This multimodal sentimental analysis approach helps in classifying the polarity (positive, negative, and neutral) of the individual sentiments. Our work aims to present a survey of recent developments in analyzing the multimodal sentiments (involving text, audio, and video/image) which involve humanmachine interaction and challenges involved in analyzing them. A detailed survey on sentimental dataset, feature extraction algorithms, data fusion methods, and efficiency of different classification techniques are presented in this work.
Analyzing the sentiments of people from social media content through text, speech, and images is becoming vital in a variety of applications. Many existing research studies on sentiment analysis rely on textual data, and similar to the sharing of text, users of social media share more photographs and videos. Compared to text, images are said to exhibit the sentiments in a much better way. So, there is an urge to build a sentiment analysis model based on images from social media. In our work, we employed different transfer learning models, including the VGG-19, ResNet50V2, and DenseNet-121 models, to perform sentiment analysis based on images. They were fine-tuned by freezing and unfreezing some of the layers, and their performance was boosted by applying regularization techniques. We used the Twitter-based images available in the Crowdflower dataset, which contains URLs of images with their sentiment polarities. Our work also presents a comparative analysis of these pre-trained models in the prediction of image sentiments on our dataset. The accuracies of our fine-tuned transfer learning models involving VGG-19, ResNet50V2, and DenseNet-121 are 0.73, 0.75, and 0.89, respectively. When compared to previous attempts at visual sentiment analysis, which used a variety of machine and deep learning techniques, our model had an improved accuracy by about 5% to 10%. According to the findings, the fine-tuned DenseNet-121 model outperformed the VGG-19 and ResNet50V2 models in image sentiment prediction.
The presence of spam content in social media is tremendously increasing, and therefore the detection of spam has become vital. The spam contents increase as people extensively use social media, i.e., Facebook, Twitter, YouTube, and E-mail. The time spent by people using social media is overgrowing, especially in the time of the pandemic. Users get a lot of text messages through social media, and they cannot recognize the spam content in these messages. Spam messages contain malicious links, apps, fake accounts, fake news, reviews, rumors, etc. To improve social media security, the detection and control of spam text are essential. This paper presents a detailed survey on the latest developments in spam text detection and classification in social media. The various techniques involved in spam detection and classification involving Machine Learning, Deep Learning, and text-based approaches are discussed in this paper. We also present the challenges encountered in the identification of spam with its control mechanisms and datasets used in existing works involving spam detection.
Dynamic Analysis of a Composite Moving Beam Ganesh Chandrasekaran Examples of beams moving relative to supports in the longitudinal direction can be found in conveyor belts, cassette tapes, band-saw blades, spacecraft antennas and robotic arms. While it is appropriate to model some of the above examples as isotropic, new materials such as polymer and metal matrix composites may offer definite benefits in certain applications. In this thesis, an attempt is made at studying the dynamic characteristics of a composite-moving beam. The model considered is an overhang beam on simple supports oscillating in the longitudinal direction. The lateral response of the beam is studied due to an initial lateral deflection. The beam is made-up of laminated composite materials. Both symmetric and unsymmetrical lay ups are considered. Since unsymmetrical lay ups introduce bending-axial coupling, axial deformation needs to be considered also. First Order Shear Deformation theory (FSDT) is used to formulate the problem since transverse shear deformations are important for composite beams. When reducing laminate plate theory to corresponding beams, plane strain and plane stress assumptions are considered. Within the plane stress approximation, two ways of reduction from (x,y) equations to x-equations are possible. One is to set all y-related forces and moment resultants zero; other is to keep the cross resultants non zero. Also, as a comparison, results are obtained based on Classical Laminate Plate theory (CLPT). The discretization in the space domain is achieved with the use of higher-order finite elements. Since there is relative motion between the beam and supports, traditional methods of applying essential conditions in the finite element analysis are cumbersome. Thus, the concept of Lagrange multipliers is used to apply the essential conditions. The resulting system of coupled ordinary differential equations in time domain is solved using Newmark's method. The use of Lagrange multipliers result in positive indefinite inertia and stiffness matrices and thus care must be taken in solving such system of equations. Results are presented in terms of tip displacements of the moving beam. A parametric study is carried out by varying the frequency of axial motion, different composite lay-ups and ply angles. iii ACKNOWLEDGEMENT I express my sincere gratitude to Dr. Nithi Sivaneri for providing me with an opportunity to work with him. I admire him as an academician and was fortunate to have him as my advisor. The technical insight he provided into the research was remarkable. His professional guidance is commendable and I would always be thankful for the support he rendered during the course of this research. Special thanks go to Drs. Ever J. Barbero, Kenneth H. Means and Hemanth Thippesamy, my committee members, for their valuable help, advice and suggestions which aided the successful completion of this research. I would like to express my sincere thanks to the Department of Mechanical and Aerospace Engineering and the Department of Ch...
Patients with focal temporal lobe seizures often experience loss of consciousness. In humans, this loss of consciousness has been shown to be positively correlated with EEG neocortical slow waves, similar to those seen in non-REM sleep. Previous work in rat models of temporal lobe seizures suggests that decreased activity of subcortical arousal systems cause depressed cortical function during seizures. However, these studies were performed under light anesthesia, making it impossible to correlate behavior, and therefore consciousness, to electrophysiologic data. Further, the genetic and molecular toolkits allowing for precise study of the underlying neural circuitry are much more developed in mice than in rats. Here, we describe an awake-behaving, head-fixed mouse model of temporal lobe seizures with both spared and impaired behavior reflecting level of consciousness. Water-restricted mice were head-fixed on a running wheel and trained to associate an auditory stimulus to the delivery of a drop of water from a dispenser. To investigate the effect of seizures on behavior, seizures were electrically induced by stimulating either the left or right hippocampus via a chronically-implanted electrode, while mice were performing the task. Behavior was measured by monitoring lick responses to the auditory stimulus and running speed on the wheel. Further, local field potentials (LFP) signals were simultaneously recorded from hippocampus and orbitofrontal cortex (OFC). Induced focal seizures were 5-30s in duration, and repeatable for several weeks (n=20 animals). Behavioral responses showed a decrease in lick rate to auditory stimulus, and decreased running speed during seizures (p<0.01, n=20 animals). Interestingly, licking response to sound could vary from being impaired to normal during seizures. We found that behavioral impairment is correlated with large amplitude cortical slow-wave activity in frontal cortex, as seen in patients with temporal lobe seizures. These results suggest that induced focal limbic seizures in the mouse can impair consciousness and that the impaired consciousness is correlated with depressed cortical function resembling slow wave sleep. This novel mouse model has similar characteristics with previously studied rat models and human temporal lobe seizures. By leveraging the genetic and molecular techniques available in the mouse, this model can be used to further uncover fundamental mechanisms for loss of consciousness in focal seizures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.