Fig 2 - uploaded by Mohammad Nuruzzaman Phd
Content may be subject to copyright.
Similar publications
In today's world there are millions of diseases with various symptoms foreach, no human can possibly know about all of these diseases and the treatmentsassociated with them. So, the problem is that there isn’t any place where anyone can have the details of the diseases or the medicines/treatments. What if there is a placewhere you can find your hea...
S-BOT, an acronym for Service BOT, is meant to provide services to end users in a multinational company. It serves the purposes of all the employees who might be in the need of technical enhancements without any fuss. This functionality provides redirection of service requests to the vendors, who will thereby be able to process it appropriately. Al...
Research background: Digitalization of tax administration communication means the creation of paperless communication between the tax subject and the tax administration. Artificial intelligence technology creates new digital communication channels and contribute to more efficient paperless tax administration. The global trend of the digital age are...
A evolução tecnológica, particularmente a Inteligência Artificial, tem contribuído significativamente para mudanças relevantes em quase todas as dimensões da nossa sociedade, nomeadamente na educação e, consequentemente, no Ensino à Distância. Tais mudanças exigem transformações significativas, especialmente no processo de ensino-aprendizagem, de f...
Citations
... Coordinating between centers in the surrounding environment is necessary for services to become more effective and efficient. Therefore, it is necessary to develop a system that can answer these problems, and one alternative solution is to implement a referral system (Aluh et al., 2018;Broglia et al., 2018;Nuruzzaman & Hussain, 2018;Titzler et al., 2018). ...
The research aims to determine the implementation of the referral system at the Centers for Character Development and Counseling Guidance (CCDGC) and Psychology Service Centers. This study uses a type of R&D with a descriptive approach. The participants in this research are the chairperson or secretary at the Center for Psychological Services, the CCDCG, and related parties in the internal referral system and system developers. Data analysis in the form of observation, documentation, and focus group discussion (FGD) was collected directly. This study's results indicate that the referral system carried out by the CCDCG can be implemented as needed. In addition, the Psychological Service Center in the psychological examination and consultation program can develop a referral system according to the needs of clients from outside the Universitas Negeri Surabaya (UNESA). This study implies that the implementation of the referral system makes it easier for users to access services according to their needs, and the psychology service center has an optimized SOP to rule the CCDCG at UNESA. The limitation of this study is that it is only focused on UNESA. Hence, further research can analyze the development of a referral system in the CCDCG to other institutions and compare it to UNESA.
... Chatbots still do not understand dialogues as well as a human being, but they can make simple tasks and, when they do not know the answer, they can redirect it to a human to continue the dialogue. Due to this big chatbot error risk, most of them usually send to the users a fixed list of options, where they can navigate, like an automatic telephone answering system, but using text instead of audio [6,7]. This leads to chatbot acceptance being very low nowadays, mainly because often users cannot solve their problems directly through the chatbot without the help of a human, which Chatbot Optimization using Sentiment Analysis and Timeline Navigation causes users' frustration and, consequently, the unwillingness to use this type of service, since it is seen as ineffective. ...
... This leads to chatbot acceptance being very low nowadays, mainly because often users cannot solve their problems directly through the chatbot without the help of a human, which Chatbot Optimization using Sentiment Analysis and Timeline Navigation causes users' frustration and, consequently, the unwillingness to use this type of service, since it is seen as ineffective. Research shows that around 75% of customers experience poor customer service and that generating meaningful, lengthy and informative responses remains a challenge [3,6]. ...
... As suggested by Nuruzzaman e Hussain [6], chatbots often lose context, and this could be optimized by using trees to create adaptive dialog timelines. Furthermore, Lee et al. [11] suggests that sentiment analysis improves communication between the user and the machine. ...
A chatbot or conversational agent is a software that can interact or ``chat'' with a human user using a natural language, like English, for instance. Since the first chatbot developed, many have been created but most of their problems still persist, like providing the right answer to the user and user acceptance itself. Considering such facts, in this work, we present a chatbot-building framework that considers the use of sentiment analysis and tree timelines to provide a better chatbot answer. For instance, as presented in our experiments, the user can be addressed to a human attendant when its sentiment is very negative, or even try another branch of the tree timeline, as an alternative answer, whenever the user sentiment is less negative.
... Generally, chatbots are used as virtual assistants to solve customer service problems at the right time (Liu, 2020;Nuruzzaman, 2018). However, they can be used to address the concerns of e-learners (Mohd, 2022)in specific situations. ...
In the operation of online and distance learning institutions, tutors are responsible for coaching, mentoring, and guiding learners during their courses. However, when a learner needs a tutor, the tutor is sometimes overwhelmed and unable to satisfy the learner in time.Moreover, the mode and time of work differ from student to student, which makes monitoring very difficult. Thus, to overcome the unavailability of a tutor or teacher, we proposed a conversational agent that can address the concerns of students in real time based on the teachers course. The objective was to design a chatbot that can interact with the learner, understand his/her concerns and provide accurate answers at any time, autonomously browsing the course of the concerned teacher. We used a natural language processing (NLP) method to enable our chatbot to understand human language and respond to questions asked. The results showedthat our chatbot manages to provide an adequate response depending on the context.
... In RNN family, information is passed recursively along the time axis with a weighted decay, which means, more recent time will have an impact with larger weight. But the importance of the information does not always depend on the happening time in real problems [17]. Hence, in order to store crucial long temporal information, many adaptive RNNs have been proposed for use. ...
Stock price prediction is crucial but also challenging in any trading system in stock markets. Currently, family of recurrent neural networks (RNNs) have been widely used for stock prediction with many successes. However, difficulties still remain to make RNNs more successful in a cluttered stock market. Specifically, RNNs lack power to retrieve discerning features from a clutter of signals in stock information flow. Making it worse, by RNN a single long time cell from the market is often fused into a single feature, losing all the information about time which is essential for temporal stock prediction. To tackle these two issues, we develop in this paper a novel hybrid neural network for price prediction, which is named frequency decomposition induced gate recurrent unit (GRU) transformer, abbreviated to FDGRU-transformer or FDG-trans). Inspired by the success of frequency decomposition, in FDG-transformer we apply empirical model decomposition to decompose the complete ensemble of cluttered data into a trend component plus several informative and independent mode components. Equipped with the decomposition, FDG-transformer has the capacity to extract the discriminative insights from the cluttered signals. To retain the temporal information in the observed cluttered data, FDG-transformer utilizes hybrid neural network of GRU, long short term memory (LSTM) and multi-head attention (MHA) transformers. The integrated transformer network is capable of encoding the impact of different weights from each past time step to the current one, resulting in the establishment of a time series model from a deeper fine-grained level. We appy the developed FDG-transformer model to analyze Limit Order Book data and compare the results with that obtained from other state-of-the-art methods. The comparison shows that our model delivers effective price forecasting. Moreover, an ablation study is conducted to validate the importance and necessity of each component in the proposed model.
... The research done on customer services finds out whether customers have experienced good or poor customer service. It showed that nearly 75% of customers have experienced poor customer service [2]. This paper provides a systematic review of natural language processing in customer services in all categories using text and speech in different languages. ...
Artificial intelligence and natural language processing (NLP) are increasingly being used in customer service to interact with users and answer their questions. The goal of this systematic review is to examine existing research on the use of NLP technology in customer service, including the research domain, applications, datasets used, and evaluation methods. The review also looks at the future direction of the field and any significant limitations. The review covers the time period from 2015 to 2022 and includes papers from five major scientific databases. Chatbots and question-answering systems were found to be used in 10 main fields, with the most common use in general, social networking, and e-commerce areas. Twitter was the second most commonly used dataset, with most research also using their own original datasets. Accuracy, precision, recall, and F1 were the most common evaluation methods. Future work aims to improve the performance and understanding of user behavior and emotions, and address limitations such as the volume, diversity, and quality of datasets. This review includes research on different spoken languages and models and techniques.
... Chatbots nowadays are becoming an essential element of the Human Interface Mediums (HIMs) like the internet and mobile phones (Nuruzzaman & Hussain, 2018). A chatbot is a service governed by rules and recently by artificial intelligence. ...
The work in this thesis focused on creating a cyber security solution with the ability to protect, identify, classify, and manage risk priority with time efficiency. The main idea is to handle the threats and vulnerabilities based on the separation of the information system into three levels: Network level, device level, and human factor level. For each level, the system was modeled and a solution was presented and tested. And at the end, all of the solutions were applied to an information system to verify its usability and effectiveness. To determine the solutions, a bibliographic study was made so we can specify what contribution can be offered. And the results were crossed with the idea of the protection for the three levels mentioned previously. From the study, we deduced that there was not a single work that tried to present a solution to protect an information system for the three levels. Most of the work was focused on a certain level only. Thus, our work in the thesis managed to create a solution for the three levels. For the network level, a unidirectional network device A.K.A. data diode was used. Data diodes are a paradigm of cyber security which have not been studied extensively even though they can be used to overcome some of the limitations that exist today with current approaches to cyber security such as basic firewalls, and intrusion detection systems. The novelty of the work consists of on presenting a cost-effective solution with off-the-shelf components. We developed special software to use this data diode and we demonstrated its effectiveness especially in protecting the highly sensitive data due to its physical nature. Furthermore, we managed to demonstrate how its presence didn’t affect the data flow yet provided the utmost security. For the device level, we worked on protecting the flow of data. Of course, Artificial Intelligence (AI) algorithms and machine learning became an important pillar in the “Cyber security revolution”. These technologies have already become part of everyday life and are being used by organizations for various purposes such as predictive maintenance, fraud detection etc. So, we collected a dataset of 54.000 records. Using a python script created a model using the KNN algorithm and that model was used in the medical software to the label on the fly the received data. Furthermore, to better protect the device level, we have developed software for managing cyber threats which includes methods and tools for risk assessment and attack classification. Several classifications of threats have been developed but the most renowned one is the CVSS. However, the scoring of the vulnerabilities is not unique. So, choosing which vulnerability must be remediated first will yield to a decision-taking problem. Additionally, manual prioritization can be achieved in small networks where the number of threats is limited, but, in large networks automation is a must to help security officers to take the right decisions. Consequently, our developed software will collect inputs from NVD, the Exploit Database, and Computer Incident Response Center Luxembourg to apply them onto a weighted mathematical formula in order to provide a new priority list for all known vulnerabilities. All what the security officer has to do is cross reference it with the spotted vulnerabilities to have a priority list that he can follow for remediating his system. As for the human level, we focused on the ignorance aspect to create a human firewall through cyber awareness. An AI-based conversational bot was created that provides information related to the company policies and procedures, information about cyber security and a test to evaluate the level of cyber awareness. This bot is used to make the interaction with the user appealing and friendly through the use of WhatsApp as a way of communication. The implementation and simplicity of the interaction with the bot were tested and evaluated.
... ANNbased conversational models bots can develop relying on both retrieval and generative approaches to respond [48]. This type of chatbot uses different algorithms for modelling conversational behaviours that can mention in the recurrent neural network (RNN) and sequence to sequence and Long Short-Term Memory networks (LSTMs) [120]. ...
Any organization needs to improve their products, services, and processes. In this context, engaging with customers and understanding their journey is essential. Organizations have leveraged various techniques and technologies to support customer engagement, from call centres to chatbots and virtual agents. Recently, these systems have used Machine Learning (ML) and Natural Language Processing (NLP) to analyze large volumes of customer feedback and engagement data. The goal is to understand customers in context and provide meaningful answers across various channels. Despite multiple advances in Conversational Artificial Intelligence (AI) and Recommender Systems (RS), it is still challenging to understand the intent behind customer questions during the customer journey. To address this challenge, in this paper, we study and analyze the recent work in Conversational Recommender Systems (CRS) in general and, more specifically, in chatbot-based CRS. We introduce a pipeline to contextualize the input utterances in conversations. We then take the next step towards leveraging reverse feature engineering to link the contextualized input and learning model to support intent recognition. Since performance evaluation is achieved based on different ML models, we use transformer base models to evaluate the proposed approach using a labelled dialogue dataset (MSDialogue) of question-answering interactions between information seekers and answer providers.
... The developed ML algorithm can determine the welding speed, the power required, and the weld's position, which is vital for developing quality welds having high strength [18,19]. Besides, ML is also implemented in marketing, healthcare, and medicine for mainly diagnosis and image processing [20][21][22], e-commerce, energy fields for cost optimization and material selection [12,[23][24][25], banking and financial sectors, automobile, customer service, governance and surveillance, transportation sectors, and so on [26][27][28][29][30][31][32][33][34]. Data collection and preparation are the essential stages in ML because the model's accuracy relies on input data. ...
In the modern era, welding systems have been made smart with the inclusion of contemporary information technologies such as intelligent manufacturing and machine learning (ML). The ML has been integrated with a wide application area of metal joining to achieve the status of intelligent welding systems (IWS). The IWS, using ML, has drawn massive consideration from researchers and industrialists to obtain high product quality and cost-effective solutions. Intelligent welding uses modern computers for sensing, learning, decision-making, monitoring, and control, thus replacing/minimizing human interference. ML-integrated welding is primarily for modeling, identification, optimization, prediction, and controlling multiple variables. Citing the necessity and importance of ML models in weld quality and process optimization, the current study is aimed on describing basics of ML techniques, their types, models, and adaptability scenarios in numerous industrially sought IWS.
... However, the expertise of those intelligent systems is reliable only on a single or a couple of services, especially in this pandemic situation where we need a plethora of services together in a system. Therefore, after research [2,3] over different platforms about what services are less prominent and more in need amongst the people, this system aims to showcase a collection of required and vital services to the people under one hood as a comprehensive healthcare project. ...
... II. LITERATURE REVIEW Siddhant Singh et al. [1] have surveyed various AI chatbots and the technologies they have used. Likewise, Mohammad Nuruzzaman et al. [2] surveyed the abundance and implementation of deep learning-based chatbots in the customer service industry. These two papers helped to grasp the scenario of the recent adaptations in the chatbot domain. ...
The Covid-19 pandemic has brought many changes in the healthcare industry lately. As things are going normal with time, many health projects designed and used during emergencies are left unexploited. To make the perpetual use of those technologies, the current need should be taken into consideration along with necessary ideas and frameworks to evolve the existing system into. To demonstrate the same, in this paper, we have presented a package of healthcare services powered by Artificial Intelligence via a chatbot system, where a user can entertain the services either by an interactive Graphical User Interface or a conversational chatbot system. This proposed system showcases how a similar Covid-19 system can be developed into a sophisticated healthcare service. This paper emphasises adding Artificial Intelligence to any conventional software via chatbot services which would broaden the services it provides even further. In order to find out the probable best technology to integrate AI with, about 50 papers have been analysed and out of which 27 relevant papers have been included in the literature review. In future, we intend to add medical support and other intelligence-based services to our system in order to meet user requirements and essential features in the field of healthcare.
... In the same context, a study (Fu, Cheng, Tu, & Zhang, 2016); (Nuruzzaman & Hussain, 2018) on the importance of neural networks to detect fraud as they are used to scan huge numbers of similar transactions to detect fraud and identify areas of fraud and potential fraud, and this ability to scan all transactions has extraordinary importance in preventing fraud and industries with fraudulent problems such as credit card industry and health insurance, and that Neural networks enable the solution of complex problems in the fields of machine learning, systems engineering, market forecasting, complex systems, continuous improvement of non-linear systems, processes, systems, and financial and economic analysis (Chen, Guo, Huang, & Lin, 2022). The researcher believes that neural networks as one of the techniques of artificial intelligence enable to enhance the performance of the management accountant as it works to process large amounts of accounting data and the difficulty of predicting prices and identify the possibilities of fraud and fraud as well as identify the relationships and trends between Financial, accounting, and administrative statements. ...
The study aimed to determine the impact of artificial intelligence techniques on the development of the role of management accountants while exploring the extent of the awareness of management accountants of the importance of artificial intelligence techniques, and the study reached a set of results, the most important of which is that expert systems enable management accountants to store and interpret human experience and use it in providing advice and advice to management accountants and help reach appropriate decisions in the light of the evidence provided to expert systems, and data analytics enable the management accountant to detect patterns New relationships in large amounts of data to reach a lot of conclusions that benefit decision makers in companies, and neural networks enable the solution of complex problems in the fields of machine learning, systems engineering, market forecasting, complex systems, continuous improvement of systems, processes, non-linear systems, financial and economic analysis, the study also recommended the need for governments to provide strong support for the application of artificial intelligence systems in the field of accounting with the guidance of corporate management sufficient attention to the application of intelligence systems Artificial with improved quality of accounting curricula and learning programs in universities.
