Machine Learning and Artificial Neural Network for Predicting Heart Failure Risk

Heart failure is now widely spread throughout the world.Heart disease affects approximately 48%of the population.It is too expensive and also difficult to cure the disease.This research paper represents machine learning models to predict heart failure.The fundamental concept is to compare the correctness of various Machine Learning(ML)algorithms and boost algorithms to improve models’accuracy for prediction.Some supervised algorithms like K-Nearest Neighbor(KNN),Support Vector Machine(SVM),Decision Trees(DT),Random Forest(RF),Logistic Regression(LR)are considered to achieve the best results.Some boosting algorithms like Extreme Gradient Boosting(XGBoost)and Cat-Boost are also used to improve the prediction using Artificial Neural Networks(ANN).This research also focuses on data visualization to identify patterns,trends,and outliers in a massive data set.Python and Scikit-learns are used for ML.Tensor Flow and Keras,along with Python,are used for ANN model train-ing.The DT and RF algorithms achieved the highest accuracy of 95%among the classifiers.Meanwhile,KNN obtained a second height accuracy of 93.33%.XGBoost had a gratified accuracy of 91.67%,SVM,CATBoost,and ANN had an accuracy of 90%,and LR had 88.33%accuracy.

Detecting Deepfake Images Using Deep Learning Techniques and Explainable AI Methods

Nowadays,deepfake is wreaking havoc on society.Deepfake content is created with the help of artificial intelligence and machine learning to replace one person’s likeness with another person in pictures or recorded videos.Although visual media manipulations are not new,the introduction of deepfakes has marked a breakthrough in creating fake media and information.These manipulated pic-tures and videos will undoubtedly have an enormous societal impact.Deepfake uses the latest technology like Artificial Intelligence(AI),Machine Learning(ML),and Deep Learning(DL)to construct automated methods for creating fake content that is becoming increasingly difficult to detect with the human eye.Therefore,automated solutions employed by DL can be an efficient approach for detecting deepfake.Though the“black-box”nature of the DL system allows for robust predictions,they cannot be completely trustworthy.Explainability is thefirst step toward achieving transparency,but the existing incapacity of DL to explain its own decisions to human users limits the efficacy of these systems.Though Explainable Artificial Intelligence(XAI)can solve this problem by inter-preting the predictions of these systems.This work proposes to provide a compre-hensive study of deepfake detection using the DL method and analyze the result of the most effective algorithm with Local Interpretable Model-Agnostic Explana-tions(LIME)to assure its validity and reliability.This study identifies real and deepfake images using different Convolutional Neural Network(CNN)models to get the best accuracy.It also explains which part of the image caused the model to make a specific classification using the LIME algorithm.To apply the CNN model,the dataset is taken from Kaggle,which includes 70 k real images from the Flickr dataset collected by Nvidia and 70 k fake faces generated by StyleGAN of 256 px in size.For experimental results,Jupyter notebook,TensorFlow,Num-Py,and Pandas were used as software,InceptionResnetV2,DenseNet201,Incep-tionV3,and ResNet152V2 were used as CNN models.All these models’performances were good enough,such as InceptionV3 gained 99.68%accuracy,ResNet152V2 got an accuracy of 99.19%,and DenseNet201 performed with 99.81%accuracy.However,InceptionResNetV2 achieved the highest accuracy of 99.87%,which was verified later with the LIME algorithm for XAI,where the proposed method performed the best.The obtained results and dependability demonstrate its preference for detecting deepfake images effectively.

The Use of Telemedicine in Bangladesh during COVID-19 Pandemic

This paper presents the impact of telemedicine use among patients and healthcare professionals during the epidemic due to COVID-19 outbreak in Bangladesh. According to our findings, as the coronavirus outbreak quickly surges worldwide, many countries are adapting non-therapeutic preventative measures. Telemedicine is the exchange of medical information from one location to another using electronic communication. Telemedicine refers to the use of information and communication technology to provide healthcare support. During the pandemic, it is safer not to visit a hospital physically for consultation until and unless it is of utmost emergency. In this scenario, Telemedicine plays a vast role in developing both the quality and access to healthcare services during a pandemic. The current (COVID-19) scenario has shown us the significance of using Telehealth to deliver healthcare, especially as a means of decreasing the risk of cross-contamination caused by close contact. Bangladesh, like every other nation, has started using telemedicine as a means of providing digital healthcare services. As the outbreak continues, this paper finds that several telemedicine service providers in Bangladesh have increased their operation for serving the general mass. This paper finds the role of telemedicine during the COVID-19 pandemic as a bridge between providing safe healthcare consultation while keeping social distance as advised. The current situation of COVID-19 in Bangladesh has also been discussed in this paper. Despite some challenges of a telemedicine application in Bangladesh, the role of telemedicine is quite impactful during the pandemic.

Development and Analysis of a Machine Learning Based Software for Assisting Online Classes during COVID-19

Amid the Covid-19 widespread, it has been challenging for educational institutions to conduct online classes, facing multiples challenges. This paper provides an insight into different approaches in facing those challenges which includes conducting a fair online class for students. It is tough for an instructor to keep track of their students at the same time because it is difficult to screen if any of the understudies within the class are not present, mindful, or drowsing. This paper discusses a possible solution, something new that can offer support to instructors seeing things from a more significant point of view. The solution is a facial analysis computer program that can let instructors know which students are attentive and who is not. There’s a green and red square box for face detection, for which Instructors can watch by seeing a green box on those mindful students conjointly, a red box on those who are not mindful at all. This paper finds that the program can automatically give attendance by analyzing data from face detection. It has other features for which the teacher can also know if any student leaves the class early. In this paper, model design, performance analysis, and online class assistant aspects of the program have been discussed.

Development of Web Based Online Medicine Delivery System for COVID-19 Pandemic

Average Bangladeshis spend a significant amount of income on medicine. A reliable and fast online medicine delivery system is not ubiquitous. Most people buy medicine from the local Pharmacies. They need to go to medicine stores to buy the specific medicine prescribed by the specialized doctors. Sometimes all prescribed medicines are not available in local Pharmacies therefore people need to go to other areas to buy the medicines. It is very time consuming and people need to spend money as well for this. In our country, traffic jams are a very big problem. People waste longer time on the road due to traffic jams. Here most of the pharmacies are closed at night time but sometimes in an emergency situation medicine is very essential. In this case an online web based e-commerce medicine delivery system is needed very much. In addition, currently the whole world is suffering due to COVID-19 pandemic. Coronavirus is very contagious which we all know. In this pandemic time it is not risk free to go out to buy medicine from the pharmacies. Due to COVID-19, medicine scarcity is also an important issue. In this situation, an online medicine delivery system can play an important role. By considering the above mentioned facts, a reliable and fast online solution is proposed. This paper presents the development of a web based online medicine delivery system. A reliable, fast, safe and user-friendly online based e-commerce web application has been developed in this paper. Medicine delivery system has also been included with this proposed system. This platform is a dynamic web application built in Hypertext Preprocessor (PHP) based Laravel framework with a powerful back end. It is hosted on a dedicated Virtual Private Server (VPS). This system is lightning fast and optimized very well for searching engines. With the help of the developed platform, drugs will be available at one’s doorstep very fast, safely and reliably. In this system, users can choose a medicine section of their choices and go through all the items that the system provides. Users can then select the desired drug items, add them to cart and then proceed to payment. It has payment integration of Cash on Delivery (COD) systems. After developing the system it has been tested and it works fine. It is a one-stop solution where people can find various medicines including COVID-19 related medicines and other items in this online platform. Besides medicine, here you can also find other health care products like food supplements, birth control products, hair care products, skincare products, beauty products, etc. People can order their required medicines or other medical related available items from online and the delivery support will provide the products door to door for the users. Using this system now users can get their needed medicine without leaving home. They can save money and they do not need to go out in this pandemic situation to buy medicine. In this crucial situation, the online medicine delivery system is very helpful and it will act as a blessing for the people.

Novel Compact UWB Band Notch Antenna Design for Body-Centric Communications

This research analyzes and implements an innovative and tiny ultrawideband(UWB)antenna with band-notched features for body-centric communication.The shape of the designed antenna looks like a‘swan’with a slotted patch.Computer Simulation Technology(CST)is used to assess and investigate the performance of this antenna.With a band notch,this antenna can prevent interference from Wireless Local Area Network(WLAN)(5.15–5.825 GHz)and Worldwide Interoperability for Microwave Access(WiMAX)(5.25–5.85 GHz)systems.At first,the performance parameters like return loss response,gain,radiation patterns,and radiation efficiency of this UWB antenna are evaluated.After that,the human body effects on the antenna performance of the antenna are also examined to place the antenna at various distances away from 3-layers of phantom body model at different frequencies.All the on-body performance parameter results are compared and analyzed with free space performance parameter results.Lastly,by changing patch slot length and ground plane length,parametric studies were done for performance comparison.According to this research,it is noticed that the antenna is tiny and new.It shows good performance in body case as well.Hence,the antenna is very suitable for healthcare applications.

Miniaturized Novel UWB Band-Notch Textile Antenna for Body Area Networks

This paper presents the design and analysis of a miniaturized and novel wearable ultra-wideband(UWB)band-notch textile antenna for Body Area Networks(BANs).The major goal of building the antenna for wearable applications with band notch in X-band is to reject the downlink band(7.25 to 7.75 GHz)of satellite communication in the UWB frequency ranges of 3.1–10.6 GHz to keep away from interference.Computer Simulation Technology(CST)TM Microwave Studio,which is user-friendly and reliable,was used to model and simulate the antenna.The radiating element of the antenna is designed on Jeans’textile substrate,which has a relative permittivity of 1.7.The thickness of the jeans’fabric substrate has been considered to be 1 mm.Return loss,gain,bandwidth,impedance,radiation,and total efficiency,and radiation patterns are presented and investigated.The antenna is simulated placed on the three layers of the human body model,and the on-body results are summarized in comparison with free space.Results and analysis indicate that this antenna has good band-notch characteristics in the frequency range of 7.25 GHz to 7.75 GHz.The parametric study varying the relative permittivity of Jeans’fabric substrate of this antenna is also evaluated.In addition,effects on the antenna parameters of variation of ground plane size have been reported.The antenna is 25 mm×16 mm×1.07 mm in total volume.Results reveal that this antenna achieves the design goal and performs well both in free space and on the body.

Comparative Design and Study of A 60 GHz Antenna for Body-Centric Wireless Communications

In this paper performance of three different designs of a 60 GHz highgain antenna for body-centric communication has been evaluated. The basic structure of the antenna is a slotted patch consisting of a rectangular ring radiator withpassive radiators inside. The variation of the design was done by changing theshape of these passive radiators. For free space performance, two types of excitations were used—waveguide port and a coaxial probe. The coaxial probe signifi-cantly improved both the bandwidth and radiation efficiency. The centerfrequency of all the designs was close to 60 GHz with a bandwidth of more than5 GHz. These designs achieved a maximum gain of 8.47 dB, 10 dB, and 9.73 dBwhile the radiation efficiency was around 94%. For body-centric applications,these antennas were simulated at two different distances from a human torsophantom using a coaxial probe. The torso phantom was modeled by taking threelayers of the human body—skin, fat, and muscle. Millimeter waves have lowpenetration depth in the human body as a result antenna performance is lessaffected. A negligible shift of return loss curves was observed. Radiation efficiencies dropped at the closest distance to the phantom and at the furthest distance, theefficiencies increased to free space values. On the three layers human body phantom, all three different antenna designs show directive radiation patterns towards offthe body. All three designs exhibited similar results in terms of center frequency andefficiency but varied slightly by either having better bandwidth or maximum gain.

Investigain:A Productive Asset Management Web Application

The Investigain is a progressive web application to make mutual funds investments through a Systematic Investment Plan.The application utilizes the web’s modern capabilities,such as Asynchronous JavaScript and XML(AJAX),JavaScript,and Hypertext Marker Language(HTML5).The application also uses a powerful relational database management system,such as MySQL,to display asset management information.The application has two portals,one for investors and one for a particular asset manager or asset management company.Each investor has an account in the investor portal.The investor can view his/her profile,current balance,balance history,dividends,the units of mutual funds bought,unit price,the value of each mutual fund,and can pay installments using an embedded online payment gateway.Asset managers can monitor all investments,manage user accounts,and reimburse dividends using the admin portal.This paper also presents the experimental results of using the Investigain application,compares them with existing systems,and details the application’s prospect to improve its socio-economic conditions.The system’s frontend is designed with Bootstrap and jQuery frameworks.The backend is designed using Hypertext Preprocessor(PHP)server-side scripting language.The system demonstrated increased satisfaction from its clients.

Prediction of Covid-19 Based on Chest X-Ray Images Using Deep Learning with CNN

The COVID-19 pandemic has caused trouble in people’s daily lives andruined several economies around the world, killing millions of people thus far. Itis essential to screen the affected patients in a timely and cost-effective manner inorder to fight this disease. This paper presents the prediction of COVID-19 withChest X-Ray images, and the implementation of an image processing systemoperated using deep learning and neural networks. In this paper, a Deep Learning,Machine Learning, and Convolutional Neural Network-based approach for predicting Covid-19 positive and normal patients using Chest X-Ray pictures is proposed. In this study, machine learning tools such as TensorFlow were used forbuilding and training neural nets. Scikit-learn was used for machine learning fromend to end. Various deep learning features are used, such as Conv2D, Dense Net,Dropout, Maxpooling2D for creating the model. The proposed approach had aclassification accuracy of 96.43 percent and a validation accuracy of 98.33 percentafter training and testing the X-Ray pictures. Finally, a web application has beendeveloped for general users, which will detect chest x-ray images either as covidor normal. A GUI application for the Covid prediction framework was run. Achest X-ray image can be browsed and fed into the program by medical personnelor the general public.

Novel Design of UWB Jeans Based Textile Antenna for Body-Centric Communications

This research presents an ultra-wideband (UWB) textile antenna designfor body-centric applications. The antenna is printed on a 1 mm thick denim substrate with a 1.7 relative permittivity. The jeans substrate is sandwiched between apartial ground plane and a radiating patch with a Q-shaped slot. The slotted radiating patch is placed above the substrate and measures 27.8 mm × 23.8 mm. In freespace, the antenna covers the ultra-wideband spectrum designated by the FederalCommunication Commission (FCC). Various parameters of the antenna designwere changed for further performance evaluation. Depending on the operating frequency, the antenna's realized gain varied from 2.7 to 5 dB. The antenna achievedhigh radiation efficiency with an omnidirectional radiation pattern. A parametricstudy was performed in research on varying antenna substrates and other components of the antenna. The three outermost layers of the human body are used tomodel a human phantom for on-body simulation. After that, the antenna wasplaced at five different distances from the phantom. The findings demonstrate thatat close distances to the phantom, the antenna's gain and efficiency at lower frequencies are reduced. The antenna's radiation efficiency and gain were muchhigher at higher frequencies for distances greater than 6 mm. Compared to freespace, the antenna's radiation pattern was more omnidirectional, especially athigher frequencies. This antenna is novel, compact and has an ultra wide bandwidth, a maximum of 94.60% radiation efficiency and a 5 dBi gain that will makeit a good candidate for body-centric communications.

New Wavelet Thresholding Algorithm in Dropping Ambient Noise from Underwater Acoustic Signals

Underwater Wireless Communication, largely dependent on the acoustic communication between the machines, is largely affected by various types of noise in the shallow and deep water. However ambient noise which is due to multiple sources (e.g. shipping, wind) and no one source dominates. Ambient noise masks the acoustic signal to a large extent. Hence today it has drawn the attention of the experts to reduce its effect on the received signal. This paper discusses ambient noise problem and devises a new wavelet thresholding method to reduce its effect. Afterwards a comparative study on statistical parameters is shown to prove the efficiency of the devised method.

Design and Analysis of a Compact Band Notch UWB Antenna for Body Area Network

This paper presents the design of a small printed ultra wideband antenna with Band Notched characteristics. Both the free space and on-body performances of this antenna were investigated through simulation. The newly designed UWB antenna is more revised small form factor sized, with the ability to avoid interference caused by WLAN (5.15 - 5.825 GHz) and WiMAX (5.25 - 5.85 GHz) systems with a band notch. The return loss response, gain, radiation pattern on free space of the antenna were investigated. After that, the on-body performances were tested on 3-layer human body model with radiation pattern, gain, return loss, and efficiency at 3.5, 5.7, 8, 10 GHz and all the results were compared with free space results. As the on-body performance was very good, the proposed antenna will be suitable to be used for multi-purpose medical applications and sports performance monitoring.

Experimental Study of On-Body Radio Channel Performance of a Compact Ultra Wideband Antenna

In this paper, on-body radio channel performance of a compact ultra wideband (UWB) antenna is investigated for body-centric wireless communications. Measurement campaigns were first done in the chamber and then repeated in an indoor environment for comparison. The path loss parameter for eight different on-body radio channels has been characterized and analyzed. In addition, the path loss was modeled as a function of distance for 34 different receiver locations for propagation along the front part of the body. Results and analysis show that, compared with anechoic chamber, a reduction of 16.34% path loss exponent is noticed in indoor environment. The antenna shows very good on-body radio channel performance and will be a suitable candidate for future efficient and reliable body-centric wireless communications.

Wearable Antenna for Power Efficient On-Body and Off-Body Communications

A novel dual-band and diverse radiation pattern antenna is proposed for power efficient on-body and off-body communications intended for various applications in healthcare and sport monitoring. The antenna is dual band at 2.45 GHz (ISM band) with omnidirectional radiation pattern over the body surface to communicate power efficiently with other co-located body worn devices and at 1.9 GHz (PCS band), it has directive radiation pattern towards off the body to communicate from on-body device to off-body devices. The free space and on-body performances of the antenna are investigated by both simulation and experiment. The antenna shows very good on-body radiation efficiency of 58% at 2.45 GHz and 61% at 1.9 GHz. Good on-body gain is noticed at both frequency bands. Results show that the gain of the proposed antenna increases by 4.7% at 2.45 GHz and 3.2% at 1.9 GHz when placed on the body.

Design and Investigation of Energy Harvesting System from Noise

In order to survive in this modern world, electricity is an essential thing. Electricity allows us to power the technology we use every day. Without electricity, people can’t imagine their lives. As a developing country, Bangladesh still lacks electricity every day. The electricity supply to the rural areas is very poor. It is known that energy can be converted from one form to another form. As noise is the energy, it can also be converted into various forms of energy. Noise can be represented as a sound that is loud or unpleasant and causes disturbances such as street traffic sounds, construction sounds, airports, etc. Using a suitable transducer, noise (sound) energy can be transferred into a viable source of electricity generation. This can be accomplished by employing a transducer and converting noise-induced vibrations into electrical energy. Our main goal is getting enough energy, reducing the pressure of the main grid of electricity and decreasing fossil fuel imports. This paper presents the design and investigation of an energy harvesting system from noise. In this paper, an application is designed to get energy from noise by using a speaker as a transducer. Voltage has been stepped up by using a transformer, a diode which gives DC value which can be tapped into a battery and provide energy from the battery when it is needed. The embedded device was initially tested by clapping hands and tested further by using car horns. The vibrations created by car horns and other noises have been converted into electrical energy through the principle of electromagnetic induction. In total, the application produced optimal results of 0.5 - 1.0 volts which were stepped up using a transformer while maintaining the whole system being low cost and user-friendly.

Development of a Comparison Based Hotel and Resort Booking System in Bangladesh

With the rise of population and the industrial revolution, it is obvious that hotels and resorts are increasing drastically day by day. In the 21st century, tourism is a trend. Everyone loves to travel and the reasons vary from person to person. Whether it is to have a cheerful and peaceful mind and place or business purposes, either way, hotels and resorts actually doing their jobs very well. This, tourism is a promising sector for any country and Bangladesh is no different. But the problem is we have to do the hotel booking and reservation manually most of the time. Sometimes it is too troublesome and knowing about the suitable hotels and resorts is too difficult. Though there are some online platforms available, they are not our country-oriented such as the payment system is not preferable for us. To solve this problem Vhromon is developed, a comparison-based hotel and resort booking system where anyone can book a hotel or resort by just login from the internet. Vhromon is an interactive online platform and it is user-friendly and easy to get like most of the platforms available nowadays. But they do not have all the hotels and resorts enlisted, only the well-known ones. On the other hand, Vhromon has everything enlisted where customers can compare them and can choose the right one for them. Furthermore, this system has a vendor panel where any hotel or resort owner can add their hotel or resort easily without any hassle, unlike the existing one.

Development of Online Based Smart House Renting Web Application

The house rental issue is one of the elemental parts of society. Nowadays, it is extremely difficult to find suitable accommodation in city areas if people search for it physically. On the other hand, the land owner also needs to rent the house. It can be difficult to find tenants just to hang a lease sign on a building, and as a result, they lose money. An online common platform can play a vital role in this case. The purpose of the study is to develop a common web-based online platform for both tenants and house owners so that both tenants and landowners will mutually benefit from the system. This paper presents the development of web applications for the people of Bangladesh where both house owners and tenants can register and tenants can have houses for rent via sophisticated contact with the house owner. In this paper, a common online-based smart house rental web application has been developed both for tenants and for house owners. This web application is very user-friendly, efficient and it has got many unique features that are not offered by other currently available house rental websites here in Bangladesh. Tenants can register using their phone number, store information about their identity, search for available houses, send messages to house owners, and choose a suitable house using developed web applications. House owners can also register for the system, which will manually verify and authenticate the knowledge provided by the house owner can view a tenant’s information history whenever a tenant makes contact through text and supply house-related information accordingly. The proposed online smart house system has been tested and validated. It works very efficiently with many features. The application provided faster and improved opportunities to get houses, as well as ensuring the availability of houses for rent in the greatest number of areas. The system will help to spread trustworthy services nationwide and supply users with the chance to speak and improve the house rent in Bangladesh. Because it has many smart features, this developed online smart house rental web application will make it very easy for tenants to find a house to rent. House owners, on the other hand, can easily rent out their properties.

Development of a Novel Integrated Web-Based System for Advertisement Service

This paper presents the design and implementation of a web-based application for an advertising system. There are many places in our country where billboard advertising has not become popular yet. Also, there are many companies that don’t prefer to promote their services or products through billboards for not having a proper advertising system. There is also no such platform where vehicles can be used for advertisement purposes. While researching on these issues, there was found no connecting bridge between the vendors and the customers, which is one of the main reasons for not utilizing the billboards properly and kept them empty. To solve the mentioned problem, we came up with an idea to develop a website to allow the vendors to showcase their empty billboards and vehicles which can be used for advertising purposes and it allows the customer to choose any of the available billboards/vehicles for advertising without hassle. The main purpose of this research work is to create a web-based common platform for companies who want to rent advertising space on billboards and on the walls of vehicles, and also for the owners of the billboards and vehicles. The main contribution of this paper is to develop an online web application for companies who want to rent empty space on billboards and the walls of vehicles. In order to maintain the advertising system, the admin of the website has made appropriate rules and regulations which will fulfill the demands of the vendors and customers. Here, the system has discussed all the details, such as the connection between the vendors and customers, the efficiency of the website, transaction method, etc. The proposed web application developed in this paper has been tested and it is found to be user-friendly and very efficient.

Blockchain Application in Banking System

The 21st Century is all about technology. People are open to accepting new technologies as the need for modernization is increasing every single day. Blockchain is one of those new and revolutionary technologies that will have a significant impact on the market and industry. In layman’s terms, Blockchain is a data structure that stores transactional records while also ensuring security, transparency, and decentralization. There is a digital signature on every transaction on a blockchain, which proves the authenticity of the blockchain. In a Blockchain, data is stored which is tamper-proof and cannot be changed as it uses encryption and digital signatures. To change a record on a blockchain, one needs to change several records, and one needs to change the distributed ledger. That’s why it’s quite impossible to change the data which has already been entered into a Blockchain. The Blockchain is a technology that will allow transactions simply, safely, effectively, and also safely. This is a very promising technology. It’s already in a lot of places. It can also solve any problem in the banking sector. This technology became famous after introducing the first cryptocurrency, which is known as bitcoin. Right now, there is a huge problem with banking, and the Blockchain can solve these problems. This paper will demonstrate transacting over a secure, blockchain-based network and therefore eliminate the need for intermediary entities. This paper is a review-based paper that provides the application and opportunities of the Blockchain in the banking system. The purpose of this paper is to provide a review of the application and opportunities of the Blockchain for a secure banking system. In this review investigation and analysis of this paper at the beginning, related work from other authors in the same fields has been discussed. Then the working method of the Blockchain technology has been introduced with analysis. The use of blockchain technology for secure banking has been discussed. The main achievement of this paper is to demonstrate how the Blockchain works and how it can be useful in the secure banking industry.