Md. Solaiman Mia | Green University of Bangladesh (original) (raw)

Papers by Md. Solaiman Mia

The fact that Pneumonia ranks among the world's most common causes of mortality, precise diagnosi... more The fact that Pneumonia ranks among the world's most common causes of mortality, precise diagnosis methods are absolutely necessary. Although chest X-rays are a quick way to identify Pneumonia, they can be challenging to interpret due to the similarities between Pneumonia and other lung conditions. This research presents a computer-aided approach to Pneumonia diagnosis that uses chest x-rays to enhance diagnostic decision-making. Moreover, situations such as the coronavirus pandemic, where widespread lockdowns are implemented and human contact poses significant risks, highlight the importance of computer-aided diagnosis like this. Consequently, a technique for the quick and automatic diagnosis of Pneumonia is presented in this work. Based on chest X-ray pictures, a deep learningbased architecture called "ESPD" is suggested for the automatic diagnosis of Pneumonia. A benchmark dataset comprising 5,856 chest X-ray pictures was utilized for the suggested deep-learning network's testing, evaluation, and training. The total accuracy of the suggested model was found to be 98.24%, consisting of 0.98 F1-Score, 0.98 precision, 0.98 recall, and 0.97 specificity. In comparison to previous methods in the literature, the suggested method was found to be quicker and less computationally expensive, and it also produced accuracy that showed promise.

More than 20 percent of our nation's GDP is generated by the agriculture sector, which serves as ... more More than 20 percent of our nation's GDP is generated by the agriculture sector, which serves as the foundation of the economy. Agriculture is defined as the science and art of cultivating the flora and fauna. Soil is an important natural resource and is frequently regarded as one of the most significant natural resources for food production. Lack of knowledge and instruments is the basic problem in maintaining agricultural resources. The majority of farmers are unable to assess the condition of their crops and land. But, the agriculture sector faces challenges like water scarcity, climate change, and low production due to outdated farming practices, wasting time, money, and fertility. The main contribution of research is to provide farmers with information and appropriate solutions. As a result, it plays a crucial role in promoting constructive change in the agriculture industry and enhancing the welfare of farming communities. In our proposed system, a portable device collects soil information through a few sensors. Soil moisture, humidity, temperature and pH sensors detect the condition, then data analysis provides a decision according to the data. Our decision will be provided to farmers through an SMS alert system. Using this device, the irrigation of water will be reduced and fertility will be easier for the farmers. Additionally, a web-based monitoring system is linked to an IoT platform named Blynk in this system. The adoption of smart farming technology increases modern agricultural output and makes it possible to plant. We have used the Arduino UNO on the backend to implement our model and build the suggested system.

People with disabilities have difficulty in communicating, social interaction, obsessions and rep... more People with disabilities have difficulty in communicating, social interaction, obsessions and repetitive behaviours. The situation gets risky when these disabled people left alone freely in the outside world. But they shouldn't be locked up for this reason. So we need a way to help and protect them. Sign language recognition is the field related to communication which is a visual language that uses body language and facial expressions to convey meaning. Recent technological advances have enabled the development of advanced sign language recognition systems that can interpret sign language and translate it into written and spoken language. These systems typically use computer vision techniques to analyse sign language gestures and movements and map them to written or spoken language. Sign language recognition technology have the potential to greatly improve the accessibility of communication for people with hearing and speech impairments and to improve communication between people who speak different languages. In this paper, our proposed system has achieved the accuracy of 91.67% which is better compared to the existing works in the literature.

Depression and anxiety are two distinct mental disorders. The likelihood of a person with anxiety... more Depression and anxiety are two distinct mental disorders. The likelihood of a person with anxiety developing depression is quite high. Addressing the prevalence of depression and anxiety among university level students is of paramount importance for their well-being and academic success. Without proper treatment, depression can cause severe negative effects on an individual's quality of life and their ability to perform daily tasks. A person suffering from an anxiety disorder may experience excessive and constant worry, fear or get highly concerned about future events or situations. The aim of this paper is to predict the stage of depression and anxiety of a person based on text input. There are four stages which are minimal, mild, moderate and severe. In this research, we have used Logistic Regression, Decision Tree, Random Forest, Neural Networks, K-Nearest Neighbor and a hybrid stacking model. For the hybrid model, we have used Linear Discriminant Analysis as a meta classifier which is a dimensionality reduction technique and it combines five Machine Learning classifiers. After analyzing and comparing performance of all the 5 classifiers and the hybrid model, we have observed that the hybrid stacking model provides better accuracy than all the other classifiers. The training of our proposed hybrid model was done using more than 10,800 data for depression prediction and more than 14,500 data for anxiety prediction. We got 99% testing accuracy in depression prediction and 97% testing accuracy in anxiety prediction by using our proposed hybrid model.

In today's digital age, the repository and sharing of patient health records is of utmost signifi... more In today's digital age, the repository and sharing of patient health records is of utmost significance. However, it can be challenging to maintain the privacy of this data, as its daily transactions carry the threat of privacy breaches. Furthermore, some have raised concerns regarding the performance and privacy of blockchain-based applications, which are often used to store health data. To address these matters, this study offers an immune and privacy-conserving patient data-sharing system enabled by the blockchain technique. To assure the utmost security of patient health records stored on the blockchain, this design employs a cutting-edge access controller based on hash-256, including transaction signatures. Additionally, a consensus policy is implemented to safeguard sensitive information further. Patient health data is stored safely and securely by implementing these measures. The use of blockchain technology also assures the privacy, integrity, and scalability of health records. This study evaluates the data transaction performance while maintaining confidentiality in handling patient health records. It exhibits the average transactional time and allowable latency for accessing such health records.

In recent years, many studies have investigated the potential uses of recognizing emotions from s... more In recent years, many studies have investigated the potential uses of recognizing emotions from speech in a variety of sectors, attracting a lot of attention to this topic. The performance of Speech Emotion Recognition (SER) is significantly impacted by effective emotional feature extraction from speech. In this paper, we have presented a novel approach of multimodal SER using the interactive emotional dyadic motion capture database. Our primary focus lies in overcoming the common challenges of imbalanced dataset in emotion recognition research, which often leads to reduce the accuracy. To address this issue, we have employed a data balancing technique. Our multimodal model initially has shown promising results even before the implementation of DB techniques, but the incorporation of DB techniques marked the turning point in our study and has been able to significantly improve the model's performances such as, precision to 77.64%, recall to 77.21%, F1-score to 77.42% and accuracy to 79.32%. These outcomes unequivocally show the value of DB in overcoming the constraints of unbalanced dataset and support the efficacy of our proposed multimodal strategy for SER, along with providing insightful information for prospective uses in real-world situations as well as future developments in this field.

With cutting-edge technology development, the agricultural landscape is experiencing a revolution... more With cutting-edge technology development, the agricultural landscape is experiencing a revolutionary transformation. The Internet of Things (IoT)-driven Machine Learning (ML)-Blockchain framework 5.0 for agriculture presented in this paper is a groundbreaking system created to revolutionize crop forecasting and provide farmers with data-driven insights. The framework continually collects real-time data from sensor networks, utilizing the capabilities of the IoT to monitor critical environmental indicators and soil nutrient levels. ML techniques are used to analyze this extensive information, resulting in precise crop projections and customized insights for effective resource management. In this paper, we have experienced that the Support Vector Machine (SVM) model's prediction got an amazing accuracy for crops which is 97.73%. Blockchain technology plays a critical role in this system, providing a decentralized, tamper-proof ledger that ensures data transparency and integrity, bolstering credibility and facilitating collective decision-making among stakeholders, thereby cultivating trust and accountability within the agricultural community. Moreover, to enhance accessibility and engagement, a user-friendly online application has been created to enable stakeholders to access and examine crop projections and historical sensor data, facilitating user engagement and data visualization. The suggested framework imagines a new age in agriculture, where sustainable farming methods and precision farming boost crop yields and give agricultural communities more authority.

High levels of air pollution are a result from the growing number of vehicles in Bangladesh, part... more High levels of air pollution are a result from the growing number of vehicles in Bangladesh, particularly for the older and poorly maintained vehicles. Pollutants such as carbon monoxide, carbon dioxide, hydrocarbons and ammonia are released into the atmosphere from such vehicles. The majority of the models which are used in the existing researches are designed to identify gas pollution for vehicles, considering ideal cases such as normal highways. In this paper, we have focused not only on the ideal cases but also on the extreme cases, including the measurement of greenhouse gas emissions from moving cars in urban and hilly areas. Our proposed model's characteristics include measuring greenhouse gas values to warn the corresponding authorities by using some sensors, finding hilly places where polluted gases are most likely to be found through GPS, detecting unfit vehicles by emission values and providing an alert message to the authority. Notably, a plain route has an overall fuel economy of approximately 15-20% whereas, in the hilly regions, fuel increases 20% that causes 4% greater carbon emissions. In this research, we have taken this issue into consideration and attempted to resolve it by establishing a dynamic threshold.

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder. Such disorders are found in chil... more Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder. Such disorders are found in childhood life. Children with ASD have less capabilities in communication and social skills. Therapies are used to develop communication and social skills. Recently researchers are trying to use robots in such therapies. In this paper, we have presented social skill learning test cases for children with ASD. Autism conditions are measured in 30 children in a special school. Among them, twelve children are selected who have similar ASD conditions. Then six children participated in training with humans and another six children participated in training with robots. The learning session continued for three alternative days for a child of a week and the duration of each session was two hours for each day. We have taken an assessment test before and after the learning sessions by a human trainer. We have found better performances from children who have participated in robotic sessions rather than the children who have participated in human sessions.

Because there is more demand for freshwater around the world and the world's population is growin... more Because there is more demand for freshwater around the world and the world's population is growing at the same time, there is a severe lack of freshwater resources in the central part of the planet. The world's current population of 7.2 billion people is expected to grow to over 9 billion by the year 2050. The vast majority of freshwater is used for things like cooking, cleaning, and farming. Most industrialised countries are in desperate need of smart irrigation systems, which are now a must-have because of how quickly technology is improving. In article presents IoT based Sensor integrated intelligent irrigation system for agriculture industry. IoT based humidity and soil sensors are used to collect soil related data. This data is stored in a centralized cloud. Features are selected by CFS algorithm. This will help in discarding irrelevant data. Clustering of data is performed by K means algorithm. This will help in keeping similar data together. Then classification model is build using the SVM, Random Forest and Naïve Bayes algorithm. Model is trained, validated and tested using the acquired data. Historical soil and humidity related data is also used in training the model. K-means SVM hybrid classifier is achieving better results for classification, prediction of water demand and saving fresh water by intelligent irrigation. K-means SVM hybrid classifier has achieved accuracy rate of 98.5 percent. Specificity, recall and precision of K-means SVM hybrid classifier is also higher than random forest and naïve bayes classifier.

International Conference on Digital Applications, Transformation & Economy (ICDATE), 2023

Fake websites have become a growing concern in today's digital age, as they are designed to decei... more Fake websites have become a growing concern in today's digital age, as they are designed to deceive users into sharing personal and financial information. This research investigates the performance of Machine Learning algorithms, including Random Forest, LightGBM, and XGBoost, for detecting fake websites. We have utilized a categorical dataset with four types of websites: benign, defacement, phishing, and malware, and extracted several features from website content and metadata to train and test the algorithms. The results show that Random Forest achieved the highest accuracy (97%), outperforming both LightGBM (96%) and XGBoost (96.2%). This study highlights the effectiveness of using ensemble learning algorithms for detecting fake websites and continued research in this area can improve their performance and help safeguard against digital threats.

2023 International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM)

In the modern world of software development, ensuring reliability and performance is of paramount... more In the modern world of software development, ensuring reliability and performance is of paramount importance. However, despite the best efforts from the developers, software defects can still emerge, causing frustration and wasted resources. Due to the numerous defects found during the software development process, researchers have developed numerous ways for defect prediction models. However, these models cut down the time and expense of development when problems in a concurrent software product are anticipated. Due to the increased amount of defects brought on by software complexity, manual defect detection can become an extremely time-consuming procedure. This encouraged researchers to create methods for the automatic detection of software defects. The study of this paper has shown that a combination of machine learning algorithms could be applied effectively for software defect prediction. Interestingly, the combination of Artificial Neural Network and Random Forest classifier has been performed with the mean accuracy of 91%, while the hyper-parameter optimization model classifier has been performed with the mean accuracy of 83%, 83%, 84%, 77% and 80% for Support Vector Machine, Random Forest, Logistic Regression, Naive Bayes Gaussian and Decision Tree, respectively. These findings have demonstrated the potential of Machine Learning in the area of software development.

4th International Conference on Sustainable Technologies for Industry 4.0 (STI), 2022

With the recent increasing interest in the study of the emotional component of speech signals, a ... more With the recent increasing interest in the study of the emotional component of speech signals, a number of methods have been put forth to ascertain the emotional content of uttered words. Often, we can tell how someone is feeling by looking at their faces. Another method is to detect someone’s emotions by auditory cues or speech. With a more straightforward architecture and fewer learnable parameters, the aim of this paper is to identify someone’s emotion from an audio input. Three aspects have been suggested in the proposed methodology named MFCC (Mel-frequency Cepstral Coefficients), Mel-spectrogram and Chromagram, and MLP (Multilayer Perceptron). These features have been employed in this paper, because they perform better. MLP is a supervised machine learning, which is frequently used in various research to categorize human voice recognition. In addition, MLPs are appropriate for classification prediction issues where inputs are given as a class or label. They are also appropriate for regression prediction issues in which a real-valued quantity is forecasted from a collection of inputs. With the help of our proposed methods, we are able to achieve an accuracy of 80% on the RAVDESS Dataset.

4th International Conference on Sustainable Technologies for Industry 4.0 (STI), 2022

Autistic children face difficulties with communication, social interactions, obsessive interests ... more Autistic children face difficulties with communication, social interactions, obsessive interests and repetitive behaviors; as a result, they face a high risk of getting into critical situations if they are left free and alone in the outside world. But they should not be caged for this reason. So, there is a need for a way that can help and protect them. This paper brings an IoT (Internet of Things)-based support system for children with ASD (Autism Spectrum Disorder). The proposed system uses several IoT devices such as Accelerometer sensor, Gas sensor, Temperature sensor, Heart rate sensor, etc. which are linked up with a modern microcontroller called Arduino Uno for monitoring and helping the children with ASD to learn and improve their quality of life. The proposed system uses the sensors to read the surrounding environment of the child and then analyze if there is any risky situation going around. Finally, based on the results, it notifies the parents or supervisor of the autistic children. Additionally, a GSM (Global System for Mobile communication) module is used to communicate with their parents. The system keeps tracking all real-time surrounding environment data. It analyzes sensors’ readings against different threshold values collected from the experiments in different scenarios to determine whether any risk has occurred or not.

4th International Conference on Sustainable Technologies for Industry 4.0 (STI), 2022

Software industries are rising rapidly and usage of IT devices are increasing exponentially. Ener... more Software industries are rising rapidly and usage of IT devices are increasing exponentially. Energy has become a global concern amongst all software industries. Existing SDLC (Software Development Life Cycle) model cannot meet the energy related issues associated with the devices, particularly smartphones that have limited battery life. In this paper, we have proposed a modified SDLC model that contains total seven steps which includes requirement analysis, design, coding, EE (Energy Efficiency) analysis, unit testing, integration testing and deployment. Among them, our main contribution is on EE analysis which checks a code based on three parameters named Memory Usage, Execution Cycle (CPU Usage) and Energy Usage. The process starts from the coding phase which is the third phase of our proposed model. A loop starts in coding phase and continues up to unit testing phase including the EE analysis. This loop checks a code either it is efficient or not based on some criteria. Efficient data access pattern, data representation, data organization, data precision choice, I/O configuration, dead code elimination, code transformation & increase of concurrency can produce different impact in software execution. We have achieved significant change in energy usage and memory usage by applying the above mentioned techniques. Calculated energy usage and memory usage of a software developed by traditional agile method is 0.1259mW & 39.40%, respectively whereas our proposed model achieved 0.0119mW & 27.33%, respectively. Our proposed SDLC model mainly focus on coding phase and it can reduce energy consumption rate of a software.

International Conference on Computer, Electrical & Communication Engineering (ICCECE), 2023

Rice pest detection is a very important part for the development of our agriculture. Numerous far... more Rice pest detection is a very important part for the development of our agriculture. Numerous farmers are impacted worldwide by rice pests that frequently endanger the sustainability of rice production. There are many types of machine learning techniques for detecting the rice pests. CNNs (Convolutional Neural Networks) are currently regarded as the state-of-the-art technology for image recognition. Most of the models in existing researches worked with datasets that have small number of images and classes. In this paper, We have performed the training of our proposed model with 10400 images, containing ten different classes including Bacterial Leaf Blight, Bacterial Leaf Streak, Bacterial Panicle Blight, Blast, Brown Spot, Dead Heart, Downy Mildew, Healthy, Hispa and Tungro. A custom CNN has been used in the proposed model for pest detection, which will detect different classes of rice pests. To implement our model, we have used the Keras framework with a TensorFlow backend. In addition, our proposed model gives 88.18% validation accuracy while having only 0.57 million parameters.

Journal of Sensors, 2023

According to the World Health Organization, heart disease is the biggest cause of death worldwide... more According to the World Health Organization, heart disease is the biggest cause of death worldwide. It may be possible to bring down the overall death rate of individuals if cardiovascular disease can be detected in its earlier stages. If the cardiac disease is detected at an earlier stage, there is a greater possibility that it may be successfully treated and managed under the guidance of a physician. Recent advances in areas such as the Internet of Things, cloud storage, and machine learning have given rise to renewed optimism over the capacity of technology to bring about a paradigm change on a global scale. At the bedside, the use of sensors to capture vital signs has grown increasingly commonplace in recent years. Patients are manually monitored using a monitor located at the patient’s bedside; there is no automatic data processing taking place. These results, which came from an investigation of cardiovascular disease carried out across a large number of hospitals, have been used in the development of a protocol for the early, automated, and intelligent identification of heart disorders. The PASCAL data set is prepared by collecting data from different hospitals using the digital stethoscope. This data set is publicly available, and it is used by many researchers around the world in experimental work. The proposed strategy for doing research includes three steps. The first stage is known as the data collection phase, the data is collected using biosensors and IoT devices through wireless sensor networks. In the second step, all of the information pertaining to healthcare is uploaded to the cloud so that it may be analyzed. The last step in the process is training the model using data taken from already-existing medical records. Deep learning strategies are used in order to classify the sound that is produced by the heart. The deep CNN algorithm is used for sound feature extraction and classification. The PASCAL data set is essential to the functioning of the experimental environment. The deep CNN model is performing most accurately.

International Symposium on Information Technology and Digital Innovation (ISITDI), 2022

Road accidents have become a big concern in Bangladesh. In case of an accident, some people are u... more Road accidents have become a big concern in Bangladesh. In case of an accident, some people are unable to reach a hospital promptly. Ambulance shortages and a lack of a timely method of relaying information to the relevant authorities, the authors have proposed an Internet of Things (IoT) based preventive, detection and emergency solution. The main contribution of this research is to reduce the number of accidents. In this proposed system, a car will stop around 30 cm ahead of any obstacle. The system assesses whether a driver has consumed alcohol. If the sensor detects the presence of alcohol, the driver will be unable to start the car. The sleep sensor continually monitors whether the driver is asleep. The system's architecture reduces the amount of time it takes between an accident occurring in a specific place and Google Streetline determining the shortestpath hospital response. When an accident happens for unknown causes, the server sends an SMS alert with location data to the owner.

GUB Journal of Science and Engineering, 2021

By natural process, the world population will in-crease day by day. In rhythm, the tendency of th... more By natural process, the world population will in-crease day by day. In rhythm, the tendency of the food will also be rising. So, it is a great challenge to supply food and increase its availability for the huge amount of people of the world, which helps to fulfill their fundamental civil rights. Nowadays, many agriculturedependent countries are fully dependent on the orthodox agriculture process. To develop such types of conditions, people should attract to modern cultivation practices. In the modern era, the Internet of things (IoT) is an optimal solution for preventing such types of challenges. IoT can connect with neoteric agriculture technology. Byusing this technique, farmers can directly connect themselves and control their felds and monitor their feld environmental conditions from anywhere around the world. By the use of unique forms of sensors, models, strategies, and technologies farmers can collect much real-time information and it helps a bearer to increase his productivity of farming. The goal of this paper is to reconsider some very recent works on smart and prompt agriculture processes. In this review paper, we have spoken about the techniques, and methodologies and summarized the state-of-the-art literature. We also made a comprehensive discussion and profound analysis of those recent works. Finally, we have given some future suggestions about smart farming techniques based on our discussion and analysis.

Australian Journal of Engineering and Innovative Technology, 2022

Traditional farming is labour-intensive, and the need to constantly check crops may be a strain o... more Traditional farming is labour-intensive, and the need to constantly check crops may be a strain on farmers. On another side, agricultural yield space is shrinking by the day. So, without a question, managing a huge amount of food that is legally right for us is a very difficult problem for any human being. There may always be a footprint available to meet the high demand. By achieving the idea of smart farming based on new technology by using the Internet of Things (IoT), the authors have presented a strategy in this study work by which a farmer may manage water irrigation, detect the total amount of brightness, and monitor the moisture level of soil and current status of crops using IoT. By utilizing such a technology, the farmer would obtain an auto lighting system, an auto water irrigation system, prohibit external vehicles, and conserve electricity by utilizing real-time data obtained from various types of sensors and utilizing a Wi-Fi system. The suggested system's hardware is all directly linked to the NodeMCU ESP8266. An algorithm has been created to manage the entire project. The solar panel will supply the entire system's necessary electric power, allowing us to save money, conserve electricity, and make the total system more environmentally friendly. This work’s suggested system can identify meteorological conditions that are beneficial to agriculture. This proposed concept has exceptional performance potential as an interface between sensors as input and the IoT as an output medium. The suggested system is compared to other existing systems in a variety of ways.

International Conference on Digital Applications, Transformation & Economy (ICDATE), 2023

2023 International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM)

4th International Conference on Sustainable Technologies for Industry 4.0 (STI), 2022

International Conference on Computer, Electrical & Communication Engineering (ICCECE), 2023

Journal of Sensors, 2023

International Symposium on Information Technology and Digital Innovation (ISITDI), 2022

GUB Journal of Science and Engineering, 2021

Australian Journal of Engineering and Innovative Technology, 2022

Proceedings of ICICC 2022, vol. 3, 2023

The population of the world in 2021 was approximate 7.9 billion which will be increased about 10 ... more The population of the world in 2021 was approximate 7.9 billion which will be increased about 10 billion by 2050. In this symphony, the necessity of food and pure water will await about double. On the other hand, the space of free land for agriculture is decreasing day by day. So, it is a very hard challenge for everyone to manage a huge amount of food which is a courtly right for us. Always this challenge is might be a footprint for fulfilling the great demand. For solving such types of problems, we have to connect with the modern technological systems. Nowadays, the Internet of Things (IoT) is an optimal way to prevent such types of challenges. In this paper, we proposed a model by which a farmer can control lighting system, water pump, soil condition, and crops condition with the help of IoT. By implementing such type of model, the farmer will be able to monitor an auto lighting system, an auto water irrigation system, prevent external objects, save the electric power and analyze real-time data which are collected from different types of sensors by using a Wi-Fi system. All the hardware of the proposed model is directly connected with NodeMCU ESP8266. The essential energy of the whole system depends on the solar panel which reduces the cost, saves electricity and makes the total system eco-friendly and cost-effective. By using our proposed model, the farmers can detect the condition of the weather which makes a good impact on agriculture. For the current demand, the proposed model will make a good platform to complete our civil rights in upcoming future.

his scholarly guidance, important suggestions, endless patience, constant supervision, valuable c... more his scholarly guidance, important suggestions, endless patience, constant supervision, valuable criticism, and enormous amount of work for going through our drafts and correcting them, and generating courage from the beginning to the end of the research work has made the completion of the project possible. We would like to express our deep gratitude to Mrs. Lafifa Jamal, Assistant Professor, Dept. of CSEDU for her support and help for our work. The discussions with her on various topics our works have helped us to enrich our knowledge and conception regarding this work. Last but not the least; we are highly grateful to our parents and family members for their support and constant encouragement, which have always been a source of great inspiration for us.

2020 2nd International Conference on Sustainable Technologies for Industry 4.0 (STI), 2020

English Premier League (EPL) is the world’s most popular football league. Since this is a promine... more English Premier League (EPL) is the world’s most popular football league. Since this is a prominent league, there has been a variety of preceding endeavors both commercially and scholastically to predict EPL match results. In this paper, machine learning, a promising tool of the fourth industrial revolution (Industry 4.0), has been used to introduce a model for predicting the outcomes of EPL matches both in multi-class (home, draw, and away) and in binary-class (home, and not-home) with the last ﬁve seasons football matches. We have employed ﬁve machine learning algorithms along with different machine learning techniques ranging from data pre-processing to hyper-parameter optimization which ﬁnd the best results. In addition, the comparative results demonstrate that, our proposed model gives 70.27% accuracy in multi-class and 77.43% accuracy in binary-class compared to the best known existing models in the literature.

Reversible logic has become popular in recent years. In many technologies area, the application o... more Reversible logic has become popular in recent years. In many technologies area, the application of reversible logic is increasing day by day. The main advantages of reversible logic are: there is no information loss and reduce of power. In this paper, we have proposed a novel Reversible Programmable Read Only Memory (RPROM). For our proposed RPROM, we have also proposed a 4×4 Reversible Decoder Gate named ITS, which has no garbage output and the quantum cost is lowest than any other existing reversible decoder. We have also proposed a reversible gate named TI, which is used in our proposed RPROM design. Our proposed design is 30.90% better w.r.t. quantum cost and 31.58% better w.r.t. total number of garbage outputs than the existing ones. We also proved that, proposed reversible decoder gate is 60% better than the existing ones w.r.t. quantum cost.