Liqing Wang^*, Yiheng Xiao

Intelligent Automation & Soft Computing, Vol.39, No.4, pp. 619-631, 2024, DOI:10.32604/iasc.2024.052971

Abstract Neural Machine Translation is one of the key research directions in Natural Language Processing. However, limited by the scale and quality of parallel corpus, the translation quality of low-resource Neural Machine Translation has always been unsatisfactory. When Reinforcement Learning from Human Feedback (RLHF) is applied to low-resource machine translation, commonly encountered issues of substandard preference data quality and the higher cost associated with manual feedback data. Therefore, a more cost-effective method for obtaining feedback data is proposed. At first, optimizing the quality of preference data through the prompt engineering of the Large Language Model (LLM), More >

TATIANA KURILO^*, REBECCA D. PENTZ

Oncology Research, Vol.32, No.9, pp. 1401-1406, 2024, DOI:10.32604/or.2024.050266

Abstract Objectives: Rural patients have poor cancer outcomes and clinical trial (CT) enrollment compared to urban patients due to attitudinal, awareness, and healthcare access differential. Knowledge of cancer survival disparities and CT enrollment is important for designing interventions and innovative approaches to address the stated barriers. The study explores the potential disparities in cancer survival rates and clinical trial enrollments in rural and urban breast and lung cancer patients. Our hypotheses are that for both cancer types, urban cancer patients will have longer 5-year survival rates and higher enrollment rates in clinical trials than those in… More >

Ebtesam Ahmad Alomari^*

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.1, pp. 43-85, 2024, DOI:10.32604/cmes.2024.052256

Abstract As Natural Language Processing (NLP) continues to advance, driven by the emergence of sophisticated large language models such as ChatGPT, there has been a notable growth in research activity. This rapid uptake reflects increasing interest in the field and induces critical inquiries into ChatGPT’s applicability in the NLP domain. This review paper systematically investigates the role of ChatGPT in diverse NLP tasks, including information extraction, Name Entity Recognition (NER), event extraction, relation extraction, Part of Speech (PoS) tagging, text classification, sentiment analysis, emotion recognition and text annotation. The novelty of this work lies in its… More >

S. Vidivelli^*, Manikandan Ramachandran^*, A. Dharunbalaji

CMC-Computers, Materials & Continua, Vol.80, No.2, pp. 2423-2442, 2024, DOI:10.32604/cmc.2024.054360

Abstract This exploration acquaints a momentous methodology with custom chatbot improvement that focuses on proficiency close by viability. We accomplish this by joining three key innovations: LangChain, Retrieval Augmented Generation (RAG), and enormous language models (LLMs) tweaked with execution proficient strategies like LoRA and QLoRA. LangChain takes into consideration fastidious fitting of chatbots to explicit purposes, guaranteeing engaged and important collaborations with clients. RAG’s web scratching capacities engage these chatbots to get to a tremendous store of data, empowering them to give exhaustive and enlightening reactions to requests. This recovered data is then decisively woven into… More >

Zhaoliang Wu¹, Yuewei Wu^1,2, Xiaoli Feng¹, Jiajun Zou³, Fulian Yin^1,2,*

CMC-Computers, Materials & Continua, Vol.78, No.3, pp. 3391-3412, 2024, DOI:10.32604/cmc.2024.047076

Abstract Aspect-Based Sentiment Analysis (ABSA) is a fundamental area of research in Natural Language Processing (NLP). Within ABSA, Aspect Sentiment Quad Prediction (ASQP) aims to accurately identify sentiment quadruplets in target sentences, including aspect terms, aspect categories, corresponding opinion terms, and sentiment polarity. However, most existing research has focused on English datasets. Consequently, while ASQP has seen significant progress in English, the Chinese ASQP task has remained relatively stagnant. Drawing inspiration from methods applied to English ASQP, we propose Chinese generation templates and employ prompt-based instruction learning to enhance the model’s understanding of the task, ultimately More >

Zaid Abdulsalam Ibrahim^1,*, Muhammad Ilyas²

CMC-Computers, Materials & Continua, Vol.76, No.1, pp. 939-956, 2023, DOI:10.32604/cmc.2023.035798

Abstract Most research works nowadays deal with real-time Internet of Things (IoT) data. However, with exponential data volume increases, organizations need help storing such humongous amounts of IoT data in cloud storage systems. Moreover, such systems create security issues while efficiently using IoT and Cloud Computing technologies. Ciphertext-Policy Attribute-Based Encryption (CP-ABE) has the potential to make IoT data more secure and reliable in various cloud storage services. Cloud-assisted IoTs suffer from two privacy issues: access policies (public) and super polynomial decryption times (attributed mainly to complex access structures). We have developed a CP-ABE scheme in alignment… More >

A. Jenice Prabhu^1,*, D. Hevin Rajesh²

Computer Systems Science and Engineering, Vol.45, No.3, pp. 2363-2376, 2023, DOI:10.32604/csse.2023.028089

Abstract The applications of wireless sensor network (WSN) exhibits a significant rise in recent days since it is enveloped with various advantageous benefits. In the medical field, the emergence of WSN has created marvelous changes in monitoring the health conditions of the patients and so it is attracted by doctors and physicians. WSN assists in providing health care services without any delay and so it plays predominant role in saving the life of human. The data of different persons, time, places and networks have been linked with certain devices, which are collectively known as Internet of… More >

Sikandar Zulqarnain Khan^1,*, Sajjad Shaukat Jamal², Asher Sajid³, Muhammad Rashid⁴

CMC-Computers, Materials & Continua, Vol.73, No.1, pp. 1879-1894, 2022, DOI:10.32604/cmc.2022.028152

Abstract This paper presents an efficient crypto processor architecture for key agreement using ECDH (Elliptic-curve Diffie Hellman) protocol over . The composition of our key-agreement architecture is expressed in consisting of the following: (i) Elliptic-curve Point Multiplication architecture for public key generation (DESIGN-I) and (ii) integration of DESIGN-I with two additional routing multiplexers and a controller for shared key generation (DESIGN-II). The arithmetic operators used in DESIGN-I and DESIGN-II contain an adder, squarer, a multiplier and inversion. A simple shift and add multiplication method is employed to retain lower hardware resources. Moreover, an essential inversion operation… More >

S. Jerald Nirmal Kumar^1,*, S. Ravimaran², M. M. Gowthul Alam³

CMES-Computer Modeling in Engineering & Sciences, Vol.125, No.2, pp. 671-697, 2020, DOI:10.32604/cmes.2020.09361

Abstract Nowadays, succeeding safe communication and protection-sensitive data from unauthorized access above public networks are the main worries in cloud servers. Hence, to secure both data and keys ensuring secured data storage and access, our proposed work designs a Novel Quantum Key Distribution (QKD) relying upon a non-commutative encryption framework. It makes use of a Novel Quantum Key Distribution approach, which guarantees high level secured data transmission. Along with this, a shared secret is generated using Diffie Hellman (DH) to certify secured key generation at reduced time complexity. Moreover, a non-commutative approach is used, which effectively More >

Jianjun Gan^1,2, Y. X. Zhang^2,*

CMES-Computer Modeling in Engineering & Sciences, Vol.121, No.3, pp. 981-1009, 2019, DOI:10.32604/cmes.2019.07337

Abstract This study proposes a comprehensive method, which consists of field investigation, flume test and numerical simulation, to predict the velocity and sediment thickness of debris flow. The velocity and sediment thickness of the debris flow in mountainous areas can provide critical data to evaluate the geohazard, which will in turn help to understand the debris runout. The flume test of this debris prototype can provide friction coefficient and viscosity coefficient which are important for numerical simulation of debris flow. The relation between the key parameters in the numerical modelling using the Voellmy model and debris-flow More >