@professor
PROFESSOR
Dr K LakshmiNadh
Computer Networks and Communications, Artificial Intelligence, Computer Science, Information Systems
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Kagithala Lakshminadh, Velavolu Sravanthi, Kollipara Koushik, and Chavatapalli Surya Bhaskar
IEEE
The proliferation of offensive language and content, often referred to as 'profanity,’ poses significant challenges across various digital platforms. Profanity detection in textual data plays a crucial rolein various domains such as social media monitoring, online content moderation, and cyberbullying prevention. This approach aims to enhance profanity detection in textual data using Bidirectional Long Short-Term Memory (BiLSTM) networks to prevent offensive content. The performance of profanity detection is improved in this work by utilizing a novel approach that makes use of cutting-edge deep learning techniques. To be more precise, This approach uses a Bidirectional Long Short-Term Memory network, a powerful deep learning architecture for sequence classification, to model the intricate relationships between words in textual data. Furthermore, this incorporates fine-tuned pre-trained word embeddings to capture semantic information and contextual cues, thereby augmenting the performance of the model. Through extensive experimentation and evaluation of exemplary datasets, the approach achieves a remarkable accuracy rate of 88.3%. Modern methodologies are outperformed by the suggested approach in terms of memory, accuracy, recall, and precision. The efficiency of the method opens up avenues for its application in real-world scenarios, facilitating more effective social media monitoring, online content moderation, and proactive cyberbullying prevention. The findings contribute to advancing the field of profanity detection and hold promise for future research in this domain.
Chepuri Rajyalakshmi, K. LakshmiNadh, and M Sathyam Reddy
IEEE
The rapid development of computer vision and machine learning in recent years has led to fruitful accomplishments in a variety of tasks, including the classification of objects, the identification of actions, and the recognition of faces, among other things. Nevertheless, identifying human emotions remains one of the most difficult tasks to do. To find a solution to this issue, a significant amount of work has been put in. In order to achieve higher accuracy in this reactivity towards a variety of speeches and vocal -based methods, computer intelligence, natural language modelling systems, and other similar technologies have been used. The examination of the emotions has the potential to be useful in a number of different settings. Cooperation with human computers is one example of such a field. Computers can help customers recognize emotions, make wiser decisions, and create more lifelike human-robot interactions. In recent times, there has been a lot of focus placed on the ability to forecast dynamic facial emotion expressions in videos. Therefore, this work proposes a deep convolutional neural networks (CNNs) model for emotion prediction from speech samples, facial expression images, and videos with enhanced prediction accuracy and reduced loss. In addition, the speech CNN model also utilizes mel-frequency Cepstrum coefficients (MFCC) as feature extraction from given speech samples. The proposed MFCC-CNN model resulted in superior performance than traditional models.
Lakshmi Narayana Gumma, Ramalingam Thiruvengatanadhan, Pattusamy Dhana Lakshmi, and Kurakula LakshmiNadh
International Information and Engineering Technology Association
ABSTRACT
K. Divya, S. N. Rao and K. LakshmiNadh
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
Location-based services rectangle measures quickly changing into vastly in different style. Additionally to services supported users' current location, several potential services believe users' currentlocation history, or their spatial-temporal place of origin.Malicious users might idle their spatial-temporal place of originwhile not a rigorously designed security system for users toprove their past locations. during this system, we tends to gift theSpatial-Temporal place of origin Assurance with Mutual Proofs theme. STAMP is meant for ad-hoc mobile usersgenerating location system proofs for every different in an exceedinglydistributed settings. However, it will simply accommodate trustyworthy mobile users and wireless access points. STAMP ensures theintegrity and non-transferability of the placement proofs andprotects users' privacy. A semi-trusted Certification Authority isemployed to distribute specific keys in addition as guard users against collusion by a light-weight entropy-based trust analysisapproach. Our image implementation is based on the Andriod platformshows that STAMP is low cost in terms of procedure and storageresources. Intensive simulation experiments show that ourentropy-based trust model is in a position to attains high collusion to detects the accuracy.
P.Naga Priyanka*, , Dr.K.Lakshmi Nadh, Dr. S.Siva Nageswara Rao, , and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
The network topology of association was always active but the association between them may not be always connected and properties are restricted. On the time there is a chance of node failures and detecting the node failure is important. Two node failure detection schemes are implemented which are binary and non-binary feedback schemes. These schemes unite locality estimation, localized monitoring and node association. These results are applicable to both attached and detached networks. The schemes accomplish high disappointment discovery rates, low forged positive rates, and low correspondence overhead.
K. LakshmiNadh, K.N. Rao, and Y.K.S. Krishna
Institution of Engineering and Technology
The earlier studies have shown that TCP distresses from performance diminution due to lean wireless channel characteristics and host mobility. For such networks generating acknowledgement for each data packet reduces TCP throughput. By sharing the same path for data and acknowledgement, it creates competition and collision, resulting in reduced TCP throughput. The TCP throughput is improved when one acknowledgement acknowledges out-of-order packets or full congestion window. This paper propose a solution "Improved Delay the Duplicate Acknowledgement" (IDDA) for a certain time period in order to avoid unnecessary fast retransmissions.