Search

Artificial Intelligence has been used to interpret data to make decisions and understand the emotions of humans. Sentiment analysis is a technique for determining people's attitudes, feelings, and emotions about a certain purpose, such as people, or organizations. Since the emergence of the internet, individuals have used text messaging as a source to communicate with each other. As a result, in today's virtual community, robots must interpret emotions in views, comments, and textual exchanges to give emotionally aware replies to users. Emotion detection is a subtype of sentiment analysis that predicts a specific emotion rather than just reporting good, negative, or neutral. Many researchers have previously worked on voice and facial expressions for emotion identification in recent years. However, detecting emotions in the text is a time-consuming operation. Humans easily recognize emotions, but the real issue emerges with technology. To discern emotions in text, machines require an accurate algorithm. This study uses a data set from open-source Kaggle. Our algorithm, unlike previous research, can detect emotions from text with an at most accuracy of over 86%. [ABSTRACT FROM AUTHOR]

Aim: The main objective of this research work is to minimize the delay and enhance the efficiency of the sensor nodes in wireless sensor networks by Optimized Distributed Energy Efficient Clustering (O-DEEC) protocol and compared with Distributed Energy Efficient Clustering (DEEC) protocol. Materials and Methods: O-DEEC protocol uses various parameters such as innovative regional average energy coupled with centrality, threshold probability function and residual energy to select the cluster-head efficiently. The efficient CH selection enhances the efficiency of the routing protocol in WSN. In this work there are two groups in which each group has 20 sample size (n=20) by varying the number of rounds and time and it was calculated by calculator.net with pre-test power of 80% of the pre-test power (g-power). The required data is collected to evaluate the effectiveness of the Optimized Distributed Energy Efficient Clustering (O-DEEC) protocol in terms of Lifetime, Energy Consumption, Throughput, Packet Delivery Ratio and Delay. Results: From the SPSS results it is concluded that Delay has a statistically significant value (p<0.05) and Lifetime, Energy Consumption, Packet Delivery Ratio and Throughput has statistically insignificant value (p>0.05). The output obtained by the Optimized Distributed Energy Efficient Clustering (O-DEEC) protocol has better simulation results than Distributed Energy Efficient Clustering (DEEC) protocol with reference to 19.30% lower delay, 4.5% higher lifetime of the network, 5.6% lower energy consumption, 1.4% higher packet delivery ratio and 38% higher throughput. Conclusion: From the experiment's results and independent statistical T-test the proposed O-DEEC protocol can perform efficient routing when compared to DEEC protocol. [ABSTRACT FROM AUTHOR]

FPGAs are well tailored for a student to experiment and FGPA boards help to work on high-end applications like embedded, computer architecture and software/hardware co-design and can be used to implement almost any DSP algorithm. Practical work promotes experiential learning. Implementation of image processing is done using many boards where we aimed at working on zynq boards and attain efficient results. Spartan3E and basys3 are the boards belonging to FPGA family which we used aiming image processing which usually necessitates multiple outcomes involving simple algorithms and sometimes sophisticated transformations. Disparate algorithms lead to many applications where we focused on edge detection in different fields. Many steps involve in image processing where edge detection is one of them which leads to object recognition and using for trace recognition which is reliable in our daily applications. Finding the boundaries to recognize an object is the key point required for image processing. Since there are limitations while going for hardware implementation we would like to experiment on conventional operators. Images used in our project cover conventional lena image using sobel, canny, robert and prewitt techniques. Daily life applications are also covered in sports zone and tracking of objects by taking images of a badminton player and SRA building. Our results show that canny operator works efficiently and show less latency than other techniques. [ABSTRACT FROM AUTHOR]

To analyze image quality metrics and improve quality of the image for novel image recognition using data wavelet transformation algorithm and comparing over discrete cosine transformation algorithm. To modify data and produce image quality measurements, the data wavelet transformation algorithm employs numerical and functional analysis. Tensorflow and Keras are two Python libraries that were used to complete the implementation. The methods tested over 90 sets of different photographs, converting them to grayscale and delivering compressed images that can be used for test and train dataset images, respectively, for image quality improvement. The data set and test cases were successfully analyzed, and the Data wavelet transformation method (DWT) achieved 91 percent accuracy when compared to the discrete cosine transformation technique (DCT), which achieved 72 percent accuracy. The obtained data demonstrates the reliability in independent sample t tests with the level of s ignificance (p0.05). The Discrete cosine transformation technique performs much better in the entire process of predicting accuracy for picture quality measures. [ABSTRACT FROM AUTHOR]

To enhance the detection of leaf disease through image recognition and classifying leaf diseases using Convolutional neural networks and to compare the performances in leaf disease through novel predictive analysis with artificial neural networks. Convolutional neural networks find the optimal policy by learning the optimal values for each state-action pair. The implementation has been carried out for novel predictive analysis with the help of python libraries such as Tensorflow and Keras. The algorithms tested over 45 sets of early blight potato leaves and late blight potato leaves images and 45 sets of healthy potato leaves images which have been utilized for test and training dataset images respectively, that are classified for recognition of diseases. The novel predictive analysis on the data set and test cases has been performed successfully and acquired 91% accuracy for the Convolutional neural networks algorithm and compared to the artificial neural network algorithm (ANN), which gave 80% accuracy. With the level of significance (p<0.005), the resultant data depicts the reliability in independent sample t tests. On the whole process of prediction of accuracy for the image recognition, the Convolutional neural networks algorithm gives significantly better performance when compared to ANN algorithm. [ABSTRACT FROM AUTHOR]

Augmented Reality (AR) is a thriving phase of 21st century. AR plays a major role in almost in every latest advancement in this world. It has its fair equal part to both the sides of a coin. The interactive experience of AR solves many of our day-to-day problems. This paper reviews the applications, challenges and future trends of Artificial Intelligence (AI) techniques and methods involved in the AR applications. AR plays a major role in the health care sector by serving useful purposes such as a smart care structure, diagnosis etc., AR also has tremendous applications in the field of Medical, Education, smart city, entertainment and gaming, architecture navigation and marketing. Traditional tracking algorithms still struggle to capture the effects and fluctuations of occlusion. AR makes the unimaginable possible when driven by Artificial Intelligence. [ABSTRACT FROM AUTHOR]

Machining of Aluminum Alloys are performed on the machines that also machines steel. But best suited conditions for machining such as work piece rotational speed, feed rate can be achieved by machines that specially designed exclusively for machining of Aluminum alloys. Aluminum Alloy possess special properties which makes the machining quite difficult. The surface roughness of the aluminum alloy is considered as an important factor for smooth surface finish. There is a direct relation of type and method of flushing the coolant with surface roughness of the machined Aluminum alloy. ln this study attempt is made to increase the surface roughness of the Aluminum alloy by using minimum quantity lubrication technique rather than wet machining. The cutting parameters taken in consideration in this study is depth of cut,feed rate and cutting force. The investigation is done with dry machining, wet machining and minimum quantity machining and the surface roughness is calculated for all the conditions. By examining the Signal to noise ratio and Analysis of Variance (ANOVA) the effect of feed rate is more than the cutting force follows with depth of cut. Experimental result shows that Ra value for Minimum quantity machining is 0.2623 µm is less compared to wet machining of 0.3382 µm [ABSTRACT FROM AUTHOR]

The study of non-equilibrium thermal convection in an anisotropic porous layer saturated with a visco-elastic fluid is carried out to find how the anisotropy and non-equilibrium of temperature affect the onset of convection. The small perturbation method is applied to obtain the linearized form of equations are then solved by using the normal mode technique. The viscoelasticity is considered by taking Oldrovd-B momentum equation and two separate expressions are used for the energy equation, out of these one represents solid and anther for fluid medium. The effect of both anisotropy and non-equilibrium on the oscillatory and stationary modes of convection has been studied. Apart from these the effect of conductivity ratio, diffusivity ratio, and Darcy Prandtl number is also observed and presented graphically. The stability of the system is protected by thermal anisotropy and diffusivity ratio. But mechanical anisotropy and conductivity ratio are taking the system in destabilizing mode. [ABSTRACT FROM AUTHOR]