Hod of computer engineering

Internet of Things (IoT) refers to various interconnected devices, typically supplied with limited computational and communication resources. Most of the devices are designed to operate with limited memory and processing capability, low bandwidth, short range and other characteristics of low cost hardware. The resulting networks are exposed to traffic loss and prone to other vulnerabilities. One of the major concerns is to ensure that the network communication among these deployed devices remains at required level of Quality of Service (QoS) of different IoT applications. The purpose of this paper is to highlight delay contributing factors in Low Power and Lossy Networks (LLNs) since providing low end-to-end delay is a crucial issue in IoT environment especially for mission critical applications. Various research efforts in relevance to this aspect are then presented

Gas explosions in Nigeria have led to significant loss of lives and properties, with a rising trend over the past four years indicating a critical need for preventive solutions. This paper presents the development of an Internet of Things (IoT)-based system for the early detection and monitoring of Liquefied Petroleum Gas (LPG) leakages, aimed at reducing fire-related incidents in gas filling stations. The system is designed using an integrated circuit that incorporates gas sensors, an LCD display, a buzzer, and other supporting components, all interfaced with an ATmega328P microcontroller. Upon detection of gas leakage, real-time data is transmitted via GSM to a web-based application that handles data logging, analysis, and geographical tracking of gas stations. The web platform also serves as a tool for providing safety information and alerts to relevant stakeholders. Experimental results and performance evaluations indicate that the proposed system is effective in detecting gas leakages early, thereby enabling timely intervention and significantly reducing the risks of explosion. The system's deployment offers substantial benefits in terms of safety, economic loss prevention, and improved emergency response strategies within Nigeria's LPG distribution sector.

Gas explosions in Nigeria have led to significant loss of lives and properties, with a rising trend over the past four years indicating a critical need for preventive solutions. This paper presents the development of an Internet of Things (IoT)-based system for the early detection and monitoring of Liquefied Petroleum Gas (LPG) leakages, aimed at reducing fire-related incidents in gas filling stations. The system is designed using an integrated circuit that incorporates gas sensors, an LCD display, a buzzer, and other supporting components, all interfaced with an ATmega328P microcontroller. Upon detection of gas leakage, real-time data is transmitted via GSM to a web-based application that handles data logging, analysis, and geographical tracking of gas stations. The web platform also serves as a tool for providing safety information and alerts to relevant stakeholders. Experimental results and performance evaluations indicate that the proposed system is effective in detecting gas leakages early, thereby enabling timely intervention and significantly reducing the risks of explosion. The system's deployment offers substantial benefits in terms of safety, economic loss prevention, and improved emergency response strategies within Nigeria's LPG distribution sector.

In the time when the communication mode is changing towards the digital aspect, such as; computing devices and the internet, it is natural that there is a need to safeguard the safety as well as the privacy of the data being shared, which can also compromise the integrity. Image steganography is a technique that conceals messages in pictures taken on a digital camera, and serves as a means of secure data transmission. In this study, we provide a novel method for image watermarks which is highly secure and robust through the application of Recurrent Neural Systems and fuzzy logic. By merging fuzzy logic with the flexibility of Recurrent Neural networks, the proposed system enhances the protection and rate of hidden information even under noise, compression and other attacks. The model utilizes the learning capabilities of Recurrent Neural networks for optimization of the embedding process, while the Recurrent Neural model is useful for managing uncertainty and improving decision-making processes. Such two-layered systems ensure the inaudibility and invisibility of steganographic data while limiting the embedding of large amounts of visible data, which is highly effective. Robustness and security of the method is tested by using various images types within different environments. To enhance the efficiency and robustness of steganography of images, this work proposes an innovative two-layer method that combines fuzzy logic with Recurrent Neural Networks (RNNs). By enhancing embedding, strengthening attack resistance, and offering an adaptable, intelligent framework for safe data concealing, it advances the field. It was observed that compared to other techniques used in steganography approaches, it is pleasing to note that the whole embedding efficiency and resistance to attacks are far and above enhancement candidates. The results demonstrate that the seamless integration of fuzzy logic and Recurrent Neural Systems provides an efficient and scalable framework for secure image steganography.

In the next upcoming scenario, Internet of Things (IoT) is expected to have a great rise in coming future years with a mixture blend of various technologies together such as nanotechnology, cognitive computing, wireless technology, big data and cloud computing. With this blend of combination, the wide use of IoT leading to Internet of Nano Things (IoNT) will leave last longing impressions in the life of human beings and change the science technology completely. The heavy demand of smarter living, smarter devices (like fridges, lights, doors, wearable’s), smarter vehicles, smarter management (like parking, waste, signalling, water), all are bringing many security and privacy challenges with them that must be understood to get them tackled efficiently. This article presents an approach to study various IoT security protocols that are currently available for use.

A road sign detection and recognition system is providing a comprehensive assistance to the driver to follow the traffic signs by developing a system that will automatically detect and recognize traffic sign, thus providing accurate information to the driving system. This system comprises of capturing signboards using camera installed in the vehicle. This captured image will undergo for analysis, processing and identifying the signboard. The detected sign board will be notified to the user by sending a notification. This paper proposes a system which will classifies different types of traffic signs in real time video.

Rainfall is very important parameter in hydrological model. Many techniques and models have been developed for rainfall time series prediction. In this study an artificial neural network (ANN) based model was developed for rainfall time series forecasting. Proposed model used Multilayer perceptron (MLP) network with back propagation algorithm for training. Discharge and rainfall data are took as input parameter for ANN model to predict rainfall time series. Data preprocessing and model's sensitivity analysis were executed. Collected data is divided in three sets for optimal neural network training. The first set is the training set, used for calculate the gradient and updating the network weights and biases. The second set is the validation set. The error on the validation set is follow during the training process. The third set is test set. It is used to compare different models. Different topologies of Neural Networks were created with change in hidden layer, number of process...

Rainy seasons with heavy rainfall in catchment zones cause high potential of flooding at downstream, primarily due to the reservoirs’ capacity limit been surpassed. Discharge flow prediction can be used for the hydropower plant to limit downstream flow during rainy seasons. In this study, discharge flow prediction based on the Artificial Neural Network (ANN) is proposed in order to forecast hydropower discharges flow. A cascade hydropower scheme has been selected for this study. Data such as fore-bay elevation, inflow, and discharge flow from the cascade hydropower power plants have been collected and used as an input for the ANN models. The developed models are Feedforward Backpropagation Neural Network, Elman Neural Network, and Nonlinear Autoregressive with Exogenous Inputs (NARX). The models have been assessed with different training methods and the number of hidden neurons to assess their performances. Moreover, the models’ flow prediction performances been compared to the conv...

It has been estimated that by the end of 2020 there will be 50 billion connected devices world-wide [10]. The number of interconnected machines will very soon exceed the overall population count. Therefore it is of vital importance to be able to understand M2M interactions. M2M is a new business concept originating from the telemetry technology, used for automatic transmission and measurement of data from remote sources by wire, radio or other means [10]. M2M offers various opportunities as well as unique challenges. These devices vary from highly-mobile vehicles communicating in real-time, to immobile meter-reading appliances that send small amounts of data sporadically.M2M devices would typically operate unmanned and unguarded by humans and thus are subject to increased levels of security threats, such as physical tampering, hacking, unauthorized monitoring, etc. Terminal devices may also get geographically dispersed over time. Such M2M devices should therefore provide adequate se...

Road detection is an essential facilitator for the development of the autonomous robot navigation and the driver assistant system. It plays vital tasks in intelligent transportation systems and various applications. The main goal of this paper is to detect the driveable road region from the other entire region. Also this paper focuses on investigating the suitability of probability neural network for video based road detection. Through PNN boundary and nonboundary regions are differentiated efficiently. The proposed method is finally evaluated on the several videos.

In today’s world breast cancer(BC) is one of the most common cancers among women worldwide. According to WHO in 2022 there were 2.3 million women diagnosed with breast cancer and 6700,000 deaths globally [8]. Approximately 99% of breast cancer occurs in women and 1 % of breast cancer occurs in men. Both genders follow the same course of treatment. Half of breast cancer occurs in women with no specific risk factors other than sex and age. Breast cancer is a significant disease all over the world affecting every 1 in 8 women according to several research papers.ML alogrithmsBreast cancer is a significant health concern, being one of the most common cancers among women worldwide. Early and accurate diagnosis is critical for effective treatment and improving survival rates. However, existing diagnostic methods often rely on manual interpretation of medical images and biopsy results, which can be time-consuming and prone to human error. This project leverages the power of machine learning to develop a predictive model for early breast cancer detection, using a neural network architecture implemented in TensorFlow and Keras.
The model aims to classify breast tumors as malignant or benign by utilizing the sklearn breast cancer dataset. Initial data collection and preprocessing steps, such as standardization and feature selection, are crucial for enhancing the model's predictive capabilities. The neural network's architecture, carefully designed with optimal layers and activation functions, is trained using the Adam optimizer and evaluated with sparse categorical cross-entropy loss and accuracy metrics. Evaluation on a distinct test set, combined with data scaling techniques like StandardScaler, ensures the model's robustness and accuracy. The model's performance is benchmarked against existing methods, showcasing its efficacy and potential for real-world clinical application. This study not only addresses gaps in current diagnostic practices by introducing automation and reducing human error but also highlights the importance of machine learning in facilitating early intervention and personalized treatment strategies. The outcomes of this research are critical, as they promise to improve diagnostic accuracy, provide quicker results, and ultimately save lives, marking a significant advancement in the fight against breast cancer.

In recent years, there has been a noticeable surge in population, accompanied by the rapid development of industries, services, and agriculture within communities. This growth has intensified pressure on water resources, resulting in a simultaneous decline in both the quantity and quality of these vital resources. Dissolved organic carbon (DOC) stands out as a pivotal factor in determining the quality of natural freshwater bodies. It serves as a crucial indicator of water pollution, offering insights into the presence of both natural and man-made organic pollutants. This study focuses on predicting the levels of dissolved organic carbon in South Florida utilizing artificial intelligence algorithms. Specifically, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Multilayer Perceptron (MLP), Radial Basis Function (RBF), Decision Tree (DT), and Support Vector Regression (SVR) algorithms were employed. The Sparrow Search Algorithm was utilized to fine-tune the hyperparameters of these algorithms. The effectiveness of the hybrid models generated was evaluated through correlation and error parameters, along with the number of iterations required to achieve the lowest error rate. Upon comprehensive review, the SVR-SSA hybrid model emerged as the most promising, exhibiting an R2 value of 0.997293, a Root Mean Square Error (RMSE) of 0.2906, and a Normalized Mean Square Error (NMSE) of 5×10-4 at the thousandth iteration in the train dataset. These values for the test data set are calculated as 0.999754, 0.1625, and 2×10-4, respectively. Hence, it is deemed the most optimum model for this research endeavour.

The world is witnessing a significant paradigm shift in the delivery and management of industrial services, driven by the need for automated manufacturing in industries such as mining. This transformation is pivotal as it leverages the Internet to interconnect people and devices, giving rise to a new field known as the Industrial Internet of Things (IIoT). IIoT represents the fusion of IoT's computational capabilities with the principles of the industrial revolution, facilitating extensive scalability through the transition from IPv4 to IPv6. A crucial challenge within IIoT is the battery life of sensor nodes, which is directly influenced by the efficiency of their operating modules and protocols. Various protocols have been tested within IIoT-based Wireless Sensor Networks (WSNs) to address this issue. However, these protocols often fall short in terms of data rate performance, which is essential for supporting the diverse range of IIoT applications and services. This manuscript investigates the IPv6 packet delivery rate, focusing on energy efficiency and delay. The research identifies the G.9959 protocol as superior to IEEE 802.15.4 for IIoT adoption. Additionally, it examines the impact of bandwidth variation on energy efficiency. Through comprehensive simulations, the proposed scheme demonstrates superior performance compared to existing protocols, highlighting its potential for enhancing IIoT applications.

Industries evolve. Our thinking changes as well. Programming languages need evolvement too. “The thing is that ideas for new features with its ways of thinking will be flourished, and so perfectly designed those languages won’t be perfect anymore.” Where did logical programming go? “Notice that you can use this paradigm and just provide a set of constraints for a website and expect the website to develop automatically based on them.” It is possible to implement that. Likewise, new paradigms will sooner or later be born. It can’t be that we’ve explored everything. “Technologies are born likewise the old way of thinking, which represents by the previous programming languages might not be adequate. This project is an open-source modern object-oriented programming language that aims to bridge the gap between modern expressive programming paradigms like python and strictly typed rigid languages like Java and C#. Our goal is to provide the usefulness of an object-oriented programming lang...

The Internet of Things (IoT) represents a paradigm shift in how perceive and interact with the physical world through technology. At its essence, IoT is a concept where everyday objects, equipped with sensors, software, and connectivity, can collect and exchange data over the internet. This interconnected network of devices enables seamless communication and interaction between physical and digital systems, creating opportunities for automation, efficiency improvements, and enhanced decision-making capabilities. IoT applications span a wide range of domains including smart homes, healthcare, agriculture, transportation, and manufacturing, where sensors gather real-time data, which is then processed and analyzed to derive actionable insights. The theoretical underpinnings of IoT emphasize connectivity, data analytics, automation, and the potential for transformative impact across industries. However, challenges such as security, privacy, interoperability, and managing vast amounts of data remain critical considerations in realizing the full potential of IoT. As technology advances and standards evolve, the theoretical promise of IoT continues to drive innovation, offering a vision of a more connected, intelligent, and efficient world.

Nowadays, many people are using smartphone with many new applications i.e., technology is growing day by day. A chat bot has information stored in its database to identify the sentences and making a decision itself as response to answer a given question. The college enquiry chat bot will be built using algorithm that analyses queries and understand user's message. This chat bot is implemented using RASA. Rasa is an open-source framework for building AI bots which consists of two components: Rasa NLU and Rasa core. Rasa core is the component which handles the dialog engine for the framework and helps in creating more complex chatbots with customization. Rasa's NLU helps the developers with the technology and the tools necessary for capturing and understanding user input, determining the intent and entities. To design a College Enquiry Chatbot for Students to solve their quires within few minutes. Hardware requirements are i3 processor-based computer and 2GB-RAM. Software requirements include Rasa and Python 3.6 or higher. The aim is to implement a chatbot which can resolve student's queries, search the result for query and give the solution. The chatbot will handle the queries, ultimately reducing the human effort.

Internet-of-things (IoT) networks are distinguished by nodes with limited computational power and storage capacity, making Low Power and Lossy Networks (LLNs) protocols essential for effective communication in resource-constrained environments. One such protocol is the Routing Protocol for Low-Power and Lossy networks (RPL), which establishes and manages routes in RPL-based networks. RPL contributes to optimized routing and reduced network overhead in LLNs. However, the RPL-based protocol is susceptible to various internal and external vulnerabilities that require thorough exploration and mitigation. Experimental results illustrate the impact of several RPL attacks, including the DODAG Information Solicitation (DIS) attack, version number attack, decreased rank attack, and worst parent selection (WPS) attack. For simulation purposes, we employed the Contiki Cooja network simulator. Further, we conduct a comparative analysis of these RPLbased attacks, revealing that the WPS attack has a significant impact on the network performance compared to other attacks mentioned in the paper.

Deep learning is associate AI feature that mimics the human brain's operations within the process of knowledge for object detection, speech recognition, language translation, and higher cognitive process. The prediction of cancer at earlier stages in recent years is mandatory to maximize the probability of the sufferer's survival. Lung cancer, which is known as one of the most prevalent diseases in humans worldwide, is the most dreadful type. As high-resolution images are made, medical image processing is very capable and offers key developments in current three-dimensional (3D) medical imaging science and medicine. A major area of technical imaging needs to be developed due to developments in computer-assisted diagnosis and continued advancement in the field of computerized medical image visualization. Since lung cancer is a very common cancer, there are several forms of cancer. The classification of computed tomography (CT) images has increased the early identification of ...

It is proposed to have a study on the diagnosis of Brain Tumors using Neural Networks. The Neural Networks are best at identifying patterns or trends in data and they are well suited for predicting or forecasting. Hence Neural Networks are extensively applied to biomedical systems. A special work is carried out on Neural Networks effort on diagnosis of Brain Tumors. This paper focuses on the importance and applications of neural networks in the medical world, particularly in the diagnosis of Brain Tumors. The detailed study on Primary and Secondary Brain Tumor are taken here. A new development framework for Neural Networks helps for diagnosing Brain Tumors more efficiently and accurately. The UIMS are applied for decision support system.

The idea we're throwing out here is a super cool weatherwatching setup that uses IoT to keep an eye on the weather wherever you are. IoT is like this techy magic that lets us link up all sorts of stuff to the internet, like sensors and whatnot. This system is all about keeping tabs on the temperature, how much water is in the air, and the CO levelthat's the carbon monoxide stuff, you know, what comes out of your car's exhaust. It's got sensors that do the detective work and then sends that info to a web page, which shows it off in fancy graphs. The cool part? You can check out this data from anywhere on the planet with an internet connection. It's like having a personal weather station that fits in your pocket!.

In this work, heart disease is regarded as one of the main causes in the world today. Doctors cannot easily predict it because it is a difficult task that requires experience and more predictive knowledge. There is a lot of knowledge available in the healthcare system on the web. However, there is a lack of effective analysis tools to capture the patterns and relationships hidden in the data. The automatic diagnosis system will improve medical efficiency and will reduce costs. The aims to predict the occurrence of disease-supporting data collected from medical research, especially in heart disease. The goal is to apply data processing technology to extract hidden patterns on the data set. These patterns are known for heart disease, and to predict whether patients have heart disease. The existence of these patterns is scored according to the scale.

In this paper, 2 unique hybrid (quantum-classical) RNN pipelines are presented; operating on character and sequence levels, where the musical information is stored as a quantum wave state and operated on by the quantum part which is created by the classical part, to sequentially modify the wave state in order to be observed as music.

The production of methane gas by cattle presents a significant environmental problem. Methane gas contributes to global warming through the greenhouse effect. The methane production of individual herds of cattle can be influenced by many factors, including diet and genetics. The purpose of this study is to develop and present a method of effectively and affordably measuring the relative methane production of cattle using a microcontroller board and compatible environmental sensors. Using this method, members of the industry can monitor the impact of their cattle on the environment at a low cost without changes to the routine of the herd. Results from our sensors clearly show a difference in gas concentration between an environment with cattle and one without. Therefore, even with budget sensors, the measurement of the gas is possible. The results from our method can be used to minimize the methane emissions of a herd by comparing emissions during periods of differing diet and making...

The IoT devices vary in terms of processing power, storage capacity, memory, and energy capabilities. These device heterogeneities pose unique challenges for efficient data dissemination. The authors propose a data dissemination framework designed to address IoT system challenges. The framework focuses on reducing network congestion and traffic, minimising data transmission, improving overall system performance, and alleviating the burden on IoT devices with limited resources. The RPL protocol dealt with the constraints of low-power, lossy networks and objective function influences the behaviour of routing protocols. The RPL objective functions are not based on different criteria and affect the network quality of the services. Furthermore, the framework incorporates Tabu Search Routing (TSR), an adaptive routing algorithm that dynamically adjusts data dissemination paths based on network conditions and device capabilities. The algorithm adapts to network topology and traffic load changes to optimise the routing of data packets. The TSR algorithm aims to find efficient paths for data dissemination by exploring search space and evaluating various routing options. Tabu-RPL objective function is simulated cooja-3.0 simulator for a large-scale IoT network to achieve a 30% reduction of network overhead, 20% less energy consumption, 25% more packet delivery ratio, and 20% reduction of end-to-end delay compared to EPC-RPL, Enhancement of RPL and EEOPS-RPL and finally achieve the quality of services of the network.

Life's routine tempo appears to be rapid and energetic and includes diverse tasks. Bird-watching is a popular hobby which offers relaxation in everyday life. Innumerable people visit bird sanctuaries to observe the elegance of different species of birds. To provide birdwatchers with a convenient tool for identifying the birds in their natural habitat, we developed a Deep Learning model to help birders recognize 60 bird species. We implemented this model to extract information from bird images using the Convolutional Neural Network (CNN) algorithm. We gathered a dataset of our own using Microsoft's Bing Image Search API v7. We created an 80:20 random split of the data. The classification accuracy rate of CNN on the training set was observed to be 93.19%. The accuracy on testing set was observed to be 84.91%. The entire experimental research was carried out on Windows 10 Operating System in Atom Editor with TensorFlow library.

Recent standardization efforts are consolidating the role of RPL as the standard routing protocol for IPv6-based Wireless Sensor and Actuator Networks (WSANs). Investigating possible attacks against RPL is a top priority to improve the security of the future Internet of Things (IoT) systems. In this paper, we present the DIO suppression attack, a novel degradation-of-service attack against RPL. Unlike other attacks in the literature, the DIO suppression attack does not require to steal cryptographic keys from some legitimate node. We show that the attack severely degrades the routing service, and it is far less energy-expensive than a jamming attack.

Marriage of Internet of Everything (IoE) and Cognitive Radio driven technologies seems near under the umbrella of 6G and 6G+ communication standard. The expected new services that will be introduced in 6G communication will require high data rates for transmission. The learning based algorithms will play a key role towards successful implementation of these novel technologies and evolving next generation wireless standards for providing ubiquitous connectivity. This paper investigates performance of two artificial neural network (ANN) based algorithms for Karachi. These include Nonlinear autoregressive exogenous Algorithm (NARX) and cascade feed forward back propagation neural network (CFFBNN) scheme. A dataset for Karachi is also developed for 1805 MHZ. The results of the two algorithms are compared that show Mean Square Error (MSE) for CFFBNN is 6.8877e-5 at epoch 16 and MSE for NARX is 3.1506e-11 at epoch 26. Hence, exploiting computational performance, NARX performs much superior than the classis CFFBNN algorithm.

Indian monsoon is an important climatic phenomenon and a global climatic marker. Both statistical and numerical prediction schemes for Indian monsoon have been widely studied in literature. Statistical schemes are mainly based on regression or neural networks. However, the variability of monsoon is significant over the years and a single model is often inadequate. Meteorologists revise their models on different years based on prevailing global climatic incidents like El-Niño. These indices often have degree of severity associated with them. In this paper, we cluster the monsoon years based on their fuzzy degree of associativity to these climatic event patterns. Next, we develop individual prediction models for the year clusters. A weighted ensemble of these individual models is used to obtain the final forecast. The proposed method performs competitively with existing forecast models.

Accurate flow discharge prediction is very important in planning, designing, operating and maintenance of water resources structures. Various models have been developed so far to identify the relation between discharge and stage. In this study, artificial intelligent approach and conventional flow discharge rating curve models are considered for predicting flow discharge (FD) in a natural river. Discharge and stage data obtained from Ahar Chai River in northwest Iran. The accuracy of the ANN models is compared with conventional model. The determination coefficient (DC), coefficient of correlation (R2) and mean normalize error (MNE) statistics are used for evaluating the accuracy of the models. Based on the comparison results, the ANN models are found to be superior alternative to the conventional model.

With the development of deep learning, neural networks are increasingly used in various art fields such as music, literature and pictures, and even comparable to humans. This paper proposes a music generation model based on bidirectional recurrent neural network, which can effectively explore the complex relationship between notes and obtain the conditional probability from time and pitch dimensions. The existing system usually ignored the information in the negative time direction, however which is non-trivial in the music prediction task, so we propose a bidirectional LSTM model to generate the note sequence. Experiments with classical piano datasets have demonstrated that we achieve high performance in music generation tasks compared to the existing unidirectional biaxial LSTM method KEYWORDSmusic generation; bidirectional recurrent neural network; deep learning

Bluetooth Low Energy (BLE) represents the low-power, low-cost extension of the Bluetooth communication technology envisioned for the Internet of Things. Mesh protocols on top of BLE are currently emerging and the standard is currently being released. This paper first proposes a detailed measurement based comparison of two mesh approaches that fit within BLE operation: flooding and connection oriented networking. Using metrics such as packet delivery ratio (PDR), end-to-end delay and power consumption we conclude that the optimal mesh approach depends on the application. It is shown that for a comparable performance in terms of PDR and overhead, flooding can trade a lower end-to-end delay for a higher power consumption when compared to the connected mesh. We then propose an architecture, called Bluetooth Now, that is able to automatically switch the network between the two based on message priority. Our measurement results confirm the reliable delivery of important and urgent data sent using the Bluetooth Now paradigm, while saving battery life when transmitting non-time critical messages.

With the ongoing revolution in the Internet of Things (IoT) and cloud computing has made the potential of every stack holder that is connected through the Internet, to exchange and transfer data. Various users perceive this connection and interaction with devices as very helpful and serviceable in their daily life. However, an improperly configured network system is a soft target to security threats, therefore there is a dire need for a security embedded framework for IoT and cloud communication models is the latest research area. In this paper, different IoT and cloud computing frameworks are discussed in detail and describes the importance of the daily life of people. The main focus is to design the Cloud-IoT integration that is used to implement IoT and Cloud Framework for M2M communication, also building a relationship between different devices to connect through a cloud and also find different security methods to secure those devices. Extensive papers finding and results showed different ways they have been introduced to manipulate M2M in the digital field of health care and the virtual world. While focusing on the methodology used in M2M it is also imperative to concentrate on security levels from different inside and outside attacks on IoT and cloud ecosystem. There is a need to create a strong and secure connection between all of our IoT devices with a cloud so that there should be a fixed and safe connection between cloud environments concerning M2M connection between all wired and wireless devices. Meanwhile in contemplation of security mode also conducive to maintain M2M connection between IoT devices and Cloud and in which areas these methodologies have been implemented.

This project mainly focuses on safety of sewage workers as a large number of sewage workers die every year due to lack of facilities and harmful toxic gases released while cleaning a sewage. This Real-time health monitoring System will be very useful and works as safety equipment. In this Project ,the device will monitor heart beat of the person, hydrogen sulphide concentration and other toxic gases concentration and alerts the worker and exterior unit when the parameters deviate from safe range by sending SMS and provides location of the worker through GPS. Values from sensors were registered and plotted on the ThingSpeak analysis tool in this proposed framework, and a GSM module was used to send a warning to a mobile number that was entered into the code. These parameters in real time alerts the worker to stay safe and detects harmful gases before any harm.

The communication between humans and chatbots have been a topic of interest for a long time in the research community. But the aim of my research is to analyze the emotional intelligence of chatbots when they are engage in communication with humans. Since chatbots are known to give monotonous response for a specific question asked by the users thus, it has a uniform answers to all users irrespective of  difference in the questions. So, by utilizing NLP (Natural Language Processing), we can train these chat bots with dynamic datasets containing emotional words commonly used by humans when they use their emotional appeal in achieving results during conversation. Chat bots will be able to understand emotional conversations with humans.

Chennai is one of the oldest metropolitan city in India which consists of 15 zones and more than 200 wards. Chennai has the population of more than 8 million people and more than 20 tons of garbage collected and dumped into the two of the dumpyards Kodunkaiyur and Perungudy. These two dumpyards are catering the needs of the garbage and landfills collected from these zones, in which they are used to burn and disposed. The burning of waste is resulted into emission of higher amount of CO2. The decayed waste is one of the source for generating Methane and other greenhouse gases. This is dangerous for human lives and affects the environment. There is no such system has available to detect the CO2 and CH4 level automatically at these dumpyards. If a system automatically detects the level of CO2 and CH4 and make it available in a public domain, it will be helpful to the city administration to take the precautionary steps. Therefore, the need of the hour is to design a cloud enabled IoT based system to monitor the level of CO2 and CH4 and upload these data in the cloud for further processing. The sensor is installed in 20 of different places of these two dumpyard for monitoring the level of CO2 and CH4. The data is collected and uploaded in the cloud. The open source cloud platform Openstack is used to store all the recorded data into the cloud. The webpage www.chennaighgemissions.in is designed and the sensed data is available for public use. The system is successfully implemented and tested, and the test result is promising.

SummaryInternet of Things (IoT) provides the possibility for milliards of devices throughout the world to communicate with each other, and data are collected autonomously. The big data generated by the devices should be managed securely. Due to security challenges, like malicious nodes, many approaches cannot respond to these concerns. In this paper, a robust hybrid method, including encryption, is used as an efficient approach for resolving the Low‐Power and Lossy Networks (RPL) protocol concerns so that the devices are connected securely. Therefore, the proposed Detection of sinkholes in RPL (DSH‐RPL) method for securing the RPL protocol comprises the four following phases: the first phase creates a reliable RPL. The second phase detects the sinkhole attack. The third phase quarantines the detected malicious node, and the fourth phase transmits data through encryption. The simulation results show that the DSH‐RPL reduces the false‐positive rate more than 18.2% and 23.1% and reduce...

The goal of this work is to help the visually impaired by making it possible for them to recognize hidden images on signs, which will hopefully lead to fewer accidents. Although traffic signs are essential for maintaining order, they can also increase the risk of accidents if they are obstructed. Individuals who are visually impaired, such as the blind, can benefit greatly from this technique. Furthermore, the proposed system is conducive to the operation of autonomous cars, as the billboards can be read automatically and the vehicles may be directed by the proposed system. When a potentially dangerous image is received, a warning is displayed to the driver. Throughout this piece, "input image" will refer to the footage recorded by a camera situated at the front of the car. After converting the image to grayscale, a resizing method is applied, and a filter is used to get rid of any noticeable noise that remains. In the end, feature extraction and feature reduction methods are used to priorities certain features over others. Hence, the DNN procedure is an integral aspect of the system, as it is used for both speech recognition and image recognition. This project's main goal is to recognize incoming photos by comparing them to data sets stored in a database, with successful matches sounding an alarm for the driver.

The reliable prediction of dissolved oxygen concentration (DO) is significantly crucial for protecting the health of the aquatic ecosystem. The current research employed four different single AI-based models, namely long short-term memory neural network (LSTM), extreme learning machine (ELM), Hammerstein-Weiner (HW) and general regression neural network (GRNN) for modeling the DO concentration of Kinta River, Malaysia using available water quality (WQ) parameters. Afterwards, the first scenario used four different ensemble techniques (ET). Two linear, i.e. simple averaging ensemble (SAE) and weighted averaging ensemble (WAE) and two nonlinear namely; backpropagation neural network ensemble (BPNN-E) and HW ensemble (HW-E). The second scenario employed a hybrid random forest (RF) ensemble in order to enhance the prediction accuracy of the single models. The WQ parameters were subjected to a different pre-analysis test to ascertain their stability. The four-model combinations are generated using the nonlinear sensitivity input selection approach. The modeling performance was assessed using the statistical measures of Nash-Sutcliffe coefficient efficiency (NSE), Willmott's index of agreement (WI), root mean square error (RMSE), mean absolute error (MAE) and mean square error (MSE) and correlation coefficient (CC). The results of the single AI-based models demonstrated that HW (M3) served as the best model for predicting DO concentration. For ensemble results, BPNN-E (WI = 0.9764) was superior to the other three ET with average decreased of more than 2% with regards to MAE. Investigation on the hybrid RF ensemble demonstrated the reliable accuracy for all the hybrid models with better predictive skill shown by the HW-RF (CC = 0.981) ensemble. The overall results verified the promising impact of HW-M3, ET and hybrid RF ensemble for the prediction of the DO concentration in the Kinta River, Malaysia. INDEX TERMS Dissolved oxygen, artificial intelligence, ensemble techniques, hybrid random forest ensemble, Kinta River.

Life's routine tempo appears to be rapid and energetic and includes diverse tasks. Bird-watching is a popular hobby which offers relaxation in everyday life. Innumerable people visit bird sanctuaries to observe the elegance of different species of birds. To provide birdwatchers with a convenient tool for identifying the birds in their natural habitat, we developed a Deep Learning model to help birders recognize 60 bird species. We implemented this model to extract information from bird images using the Convolutional Neural Network (CNN) algorithm. We gathered a dataset of our own using Microsoft's Bing Image Search API v7. We created an 80:20 random split of the data. The classification accuracy rate of CNN on the training set was observed to be 93.19%. The accuracy on testing set was observed to be 84.91%. The entire experimental research was carried out on Windows 10 Operating System in Atom Editor with TensorFlow library.

One of the essential phases in water resource planning and management is streamflow forecast. It is necessary for the functioning of hydropower plants, agricultural planning, and flood control. The present study applied Artificial Neural Network (ANN) model, Adaptive Neuro-Fuzzy Inference System (ANFIS), Bidirectional LSTM (BiLSTM), and hybrid Convolutional Neural Network (CNN) Gated Recurrent Unit (GRU) Long-Short Term Memory (LSTM) model to predict the long-term daily streamflow in the Colorado River, USA. 60% of the data (1921–1981) was used for training, while 40% of the data (1981–2021) was utilized for testing the model's performance. The obtained outcomes of the suggested models were assessed using four assessment indices, including by Normalized Root Mean Square Error (NRMSE), Mean Absolute Error (MAE), Correlation Coefficient (r), and Nash–Sutcliffe Coefficient (ENS). Based on the comparison of outputs, in the testing phase, it was determined that the ANFIS model with N...

This research paper investigates the relationship between the length of the intents.json file and the runtime of NLTK (Natural Language Toolkit) and TensorFlow algorithms for chatbot development in Python. By examining the runtime efficiency based on different intents.json file sizes, the study aims to determine the impact of file length on algorithm performance. Experimental analysis reveals a linear relationship between intents.json length and training runtime, indicating an O(N) runtime complexity. This research provides valuable implications for developers seeking to enhance the runtime performance of chatbot systems by providing them with a baseline of runtime for chatbot dynamic creation - giving organizations the opportunity to properly allocate resources towards chatbot development.

This paper presents the evaluation of performance of Neural Network (NN) model in predicting the behavioral pattern of rainfall depths of some locations in the North Central zones of Nigeria. The input to the model is the consecutive rainfall depths data obtained from the Nigerian Meteorological (NiMET) Agency. The neural networks were trained using neural network toolbox in MATLAB with fifty years (1964–2014) total monthly historical data of five locations while two other locations, Abuja and Lafia with twenty-nine years (1986-2014) and eleven years (2004-2014) total monthly data respectively. Analysis showed the variation in the values of correlation coefficients (R) for each location of the study area in response to change in number of hidden neurons. The average R values of 0.80, 0.62, 0.65, 0.67, 0.79, 0.76 and 0.81 with corresponding mean square errors of 2.12, 0.23, 0.26, 0.36, 2.61, 1.18 and 1.03 were obtained for Abuja, Makurdi, Ilorin, Lokoja, Lafia, Minna and Jos respecti...