Computer Sciences and Engineering

Advances in wireless sensor network (WSN) technology has provided the availability of small and low-cost sensor nodes with capability of sensing various types of physical and environmental conditions, data processing, and wireless communication. Variety of sensing capabilities results in profusion of application areas. However, the characteristics of wireless sensor networks require more effective methods for data forwarding and processing.

In WSN, the sensor nodes have a limited transmission range, and their processing and storage capabilities as well as their energy resources are also limited. Routing protocols for wireless sensor networks are responsible for maintaining the routes in the network and have to ensure reliable multi-hop communication under these conditions. In this paper, we give a survey of routing protocols for Wireless Sensor Network
and compare their strengths and limitations.

TCP/IP has become an undeniable leader in the areas of Information Technology. It is a well-established fact that data transfer between devices occur by the rules defined by the TCP/IP protocol. Each layer of TCP/IP model generally has more than one protocol for carrying out the functions that the layer complies to. TCP/IP model is used widely and it is essential to understand how different protocols work to provide different functionalities. In this article, through the deep consideration of TCP/IP protocol the understanding of the protocols at five layers of TCP/IP is specified.

Data and computer protection is endured largely by countersigns which are the principle part of the authorization and authentication cognitive process. The most common information processing system authentication process is to apply alphanumerical username and password which has important drawbacks. Graphical passwords are often deliberated prone to shoulder-surfing attacks, where attackers can sneak a user's password by peeking over his or her shoulder in the certification process. Graphical passwords seem to be the solution as it is described more in the design structure of the authentication. A graphical password is an authentication scheme that works by accepting the user select from images, in a particular grade, demonstrated in a graphical user interface (GUI). The proposed research is an approach to enhance the subsisting Graphical Password techniques and resist against attacks like Shoulder Surfing. Based on the principle of zero-knowledge cogent evidence protocol, the additional improvement is the primary figure to overcome the shoulder-surfing attack issue without adding any additional complexity into the authentication process.

Over many centuries, tools of increasing sophistication have been developed to serve the human race Digital computers are, in many respects, just another tool. They can perform the same sort of numerical and symbolic manipulations that an ordinary person can, but faster and more reliably. This paper represents review of artificial intelligence algorithms applying in computer application and software. Include knowledge-based systems; computational intelligence, which leads to Artificial intelligence, is the science of mimicking human mental faculties in a computer. That assists Physician to make dissection in medical diagnosis.

As technology advances, it makes life easy and straightforward by solving many of the real-life problems which are faced by people in their daily life. Various types of technologies are used to improve the life of humans. Hence, this paper has used one of the technologies to ease the life of humans i.e. IoT. This paper represents IoT (Internet of Things) for the smart home automation system. There are many proposed systems which make the home easy to live in. But this paper tells about the newer advanced system. This paper tells the usage of motion detection technique to perform light on/off, MQ2 sensor for gas detection, machine learning for facial expression detection, motor for facade opening/closing, motor for room rotation and last the website “ThingsBoard” to collect the whole data at one place. The main goal of this paper is to provide full security with innovation at home.

The novel human coronavirus is highly contagious and can lead to significant morbidity and mortality. This has triggered major and cascading economic and societal consequences that have contributed considerably to global impact and suffering. It is obvious that there is no immediate solution and one has to learn to live with the virus until either herd immunity has been achieved or a vaccine has been found. As countries exit lockdowns and economies try to revive themselves, it is important to practice social distancing, use masks, avoid fomites and adopt safe practices. Artificial intelligence-based technologies hold the key to success as we emerge back to work and try to revive economies. At the same time, one must also acknowledge its downsides. This article reviews the various artificial intelligence technologies employed as part of exit strategies from lockdowns.

In recent times, several studies focused on the global warming that may affect the hydrological cycle due to intensification of temporal and spatial variations in precipitation. Such climatic change is likely to impact significantly upon freshwater resources availability. In India, demand for water has already increased manifold over the years due to urbanization, agriculture expansion, increasing population, rapid industrialization and economic development. Numerous scientific studies also report increases in the intensity, duration, and spatial extents of floods, higher atmospheric temperatures, warmer sea, changes in precipitation patterns, and changing groundwater levels. This work briefly discusses about the present scenario regarding impact of climate change on water resources in India. Due to the insufficient resolution of climate models and their generally crude representation of sub-grid scale and convective processes, little confidence can be placed in any definite predictions of such effects, although a tendency for more heavy rainfall events seems likely, and a modest increase in frequency in floods. Thus to analyses this effect, this work considers real problems about the changing flood characteristics pattern in two river regions, and the effect of spatial and temporal pattern in rainfall. In addition to these, the work also examines the trend of groundwater level fluctuations in few blocks of Ganga–Yamuna and Sutlej-Yamuna Link interfluves region. As a whole, it examines the potential for sustainable development of surface water and groundwater resources within the constraints imposed by climate change.

This study investigated the capacity of a deep neural network to distinguish tea sources based on their aromas. The data set of aromas from tea sources, which contained sensor responses measured with a gas–sensing system using a mass– sensitive chemical sensors namelyMQ3, MQ5, MQ7, was used to evaluate the recognition accuracy. To de?ne the input vectors of the deep neural network in aroma recognition experiments, frequency analysis using a continuous wavelet transform, with the Morlet function as the mother wavelet, was used to extract features from the sensor signals of the data set. The deep neural network achieved a recognition accuracy of 100% for the tea sources and the base gas of de humidified indoor air. Comparing the recognition accuracy of the deep neural network to that obtained from other pattern recognition methods, such as naive Bayes and random forests, the experimental results demonstrated the effectiveness of applying a deep neural network to this task.

Developing informal settlements has become an important issue for improving urban structures in developing countries. An Informal Settlements Development Fund (ISDF) was presented to Egypt for supporting urban, economic, social and environmental plans. Development plans do not clearly take into account population priorities or satisfaction criteria. Furthermore, evaluating several alternatives was based on usual statistical methods that cannot deal with multiple criteria or complex problems, leading to imprecise results. Nowadays, adding value to the developed area, restoring cost, and studying social and economic plan impacts on the population, represent high priorities. In this study, a model concerns the optimal decision evaluation for multi-criteria in informal settlements development was proposed. Five clusters (criteria) were identified and included the efficiencies of urban structure, economic, social, and environmental, in addition to population satisfaction. Twenty one internal factors represented in nods were categorized under the five clusters and affecting proposed four alternatives. The model depended on the Analytic Network Process (ANP) technique which is used to support multi-criteria decision making. ANP was selected for its capability to deal with complex problems, create dependencies and feedbacks as well as use the relative weights of all interactions. This technique confirms a logical decision and accurate prediction amongst numerous alternatives. The model was validated and applied to an informal settlements area as a case study in Egypt. The results supported to use first alternative by 38.20%, while the ISDF results selected the third alternative. Moreover, the detailed analysis emphasized that the first alternative was more balanced between the social elements and the direct economic requirements of the population, while the third alternative tended to achieve restoring cost despite its negative social effects. Lastly, the proposed model can be used appropriately in similar cases to improve informal settlements.

Information services are very important to attract tourists to come to a certain country or location which can be provided through e-Tourism application. This application is for people who will find out more about the location they will visit. People need to know the location, the length of the trip or the price details for each item they will buy during the trip. Due to this, many countries have developed their respective e-Tourism application. This paper presented the lesson-learn of e-Tourism development from several countries to understand main components of e-Tourism design. We found four main modules of e-Tourism application including booking services, recommender services, tour plan services and information center services. The human factors of application intention usage are influenced by perceived ease of use, perceived usefulness, experience, information quality, domain specific innovativeness. Moreover, we also obtained the factors influenced tourism tour booking intention, including advice of travel agent, e-commerce feature, access time, possibility of comparison, information obtained from destinations, social media and opinions & perception target.

The average of customer ratings on a product, which we call a reputation, is one of the key factors in online purchasing decisions. There is, however, no guarantee of the trustworthiness of a reputation since it can be manipulated rather easily. In this paper, we define false reputation as the problem of a reputation being manipulated by unfair ratings and design a general framework that provides trustworthy reputations. For this purpose, we propose Trust-reputation, an algorithm that iteratively adjusts a reputation based on the confidence of customer ratings. We also show the effectiveness of Trust-reputation through extensive experiments in comparisons to state-of-the-art approaches.

Stereo vision is a challenging problem and it is a wide research topic in computer vision. It has got a lot of attraction because it is a cost efficient way in place of using costly sensors. Stereo vision has found a great importance in many fields and applications in today’s world. Some of the applications include robotics, 3-D scanning, 3-D reconstruction, driver assistance systems, forensics, 3-D tracking etc. The fundamental test of sound system vision is to create exact difference map. Sound system vision calculations for the most part perform four stages: first, coordinating cost calculation; second, cost collection; third, dissimilarity calculation or enhancement; and fourth, divergence refinement. Sound system coordinating issues are likewise examined. An enormous number of calculations have been produced for sound system vision. But characterization of their performance has achieved less attraction. This paper gives a brief overview of the existing stereo vision algorithms. After evaluating the papers we can say that focus has been on cost aggregation and multi-step refinement process. Segment-based methods have also attracted attention due to their good performance. Also, using improved filter for cost aggregation in stereo matching achieves better results.

This paper focuses on improving student performance prediction, based on their performance characteristics. Due to various distractions, students may divert from their actual track. This might even lead to a course drop out. Predicting students' performance will help in self-analysis. The dataset used consists of data about students' performance from the academic and other classroom activities during the course time. Educational data mining algorithms are used to predict student performance which is a module in automated intelligent education systems. EDM is a methodology which is used to mine valuable information and patterns or forms from a massive educational database. Subsequently, the student's performance is predicted from the obtained useful information and patterns. The aim of our study is to discover the performance of students using some classification techniques and discovering the best one which yields optimal results. The result of this study is extremely significant and hence provides a greater insight for evaluating the student performance and underlines the significance of data mining in education. It also shows that how students attributes affect the student performance.

The topic of business failure is important because it can be used as a basis for policy making by stakeholders in a company or government. The results of business failure predictions can be used as company managers to take preventive measures for business failure. This study aim is to study the literature regarding the methods and results of predicting business failure from various sectors and regions. We used PRISMA (preferred reporting items for systematic reviews and meta-analyses) for conducting this research. As the result, we found twelve statistical methods for business failure prediction, including Hybrid Failure Prediction (HFP), Altman’s Z-score Model, Data Envelopment Analysis (DEA), Logistic Regression (LR), Neural Networks (NN), Support Vector Machine (SVM), Kernel Fuzzy C-Means (KFCM), IN01, IN05, Ohlson Model, Cart-Based Model and Cash-Flow-Based Measures. The highest result obtained by using cart-based model for dataset of financial indicators of Slovak companies with 92,00% accuracy.

Diabetes is a chronic disease with the potential to cause a worldwide health care crisis. According to International Diabetes Federation 382 million people are living with diabetes across the whole world. By 2035, this will be doubled as 592 million. Diabetes is a disease caused due to the increase level of blood glucose. This high blood glucose produces the symptoms of frequent urination, increased thirst, and increased hunger. Diabetes is a one of the leading cause of blindness, kidney failure, amputations, heart failure and stroke. When we eat, our body turns food into sugars, or glucose. At that point, our pancreas is supposed to release insulin. Insulin serves as a key to open our cells, to allow the glucose to enter and allow us to use the glucose for energy. But with diabetes, this system does not work. Type 1 and type 2 diabetes are the most common forms of the disease, but there are also other kinds, such as gestational diabetes, which occurs during pregnancy, as well as other forms. Machine learning is an emerging scientific field in data science dealing with the ways in which machines learn from experience. The aim of this project is to develop a system which can perform early prediction of diabetes for a patient with a higher accuracy by combining the results of different machine learning techniques. The algorithms like K nearest neighbour, Logistic Regression, Random forest, Support vector machine and Decision tree are used. The accuracy of the model using each of the algorithms is calculated. Then the one with a good accuracy is taken as the model for predicting the diabetes.

IoT is the network which connects and communicates with billions of devices through the internet and due to the massive use of IoT devices, the shared data between the devices or over the network is not confidential because of increasing growth of cyberattacks. The network traffic via loT systems is growing widely and introducing new cybersecurity challenges since these loT devices are connected to sensors that are directly connected to large-scale cloud servers. In order to reduce these cyberattacks, the developers need to raise new techniques for detecting infected loT devices. In this work, to control over this cyberattacks, the fog layer is introduced, to maintain the security of data on a cloud. Also the working of fog layer and different anomaly detection techniques to prevent the cyberattacks has been studied. The proposed AD-IoT can significantly detect malicious behavior using anomalies based on machine learning classification before distributing on a cloud layer. This work discusses the role of machine learning techniques for identifying the type of Cyberattacks. There are two ML techniques i.e. RF and MLP evaluated on the USNW-NB15 dataset. The accuracy and false alarm rate of the techniques are assessed, and the results revealed the superiority of the RF compared with MLP. The Accuracy measures by classifiers are 98 and 53 of RF and MLP respectively, which shows a huge difference and prove the RF as most efficient algorithm with binary classification as well as multi- classification.

Recently it is found that people are becoming more cautious to their diet throughout the universe. Unhealthy diet can cause many problems like sugar, obesity, gain in weight and many other chronic health related issues. Essential part of our diet is contributed by fruits as they are rich source of vitamins,fiber,energy and nutrients. Today's era has been adapted to a system of intake of foods which has several adverse effects on human health. The proposed system is Autonomous Fruit Recognition system based on Deep Convolutional Neural Network (DCNN) method. Using this technology recognition and estimation of fruit calories is necessary to spread awareness about food habits among people suffering from obesity due to bad food culture and consumption of food .This proposed web/app based system simplifies the calorie measuring process of fruit. The machine learning based API used in our system recognize the fruit and provide calorie content of that fruit. System uses convolutional Neural Network called MobileNet. This web/app based application is user friendly.

Cloud storage is used generally to store data and realize the data sharing with others. A cloud storage system stores large number of data in its storage server. Data that are stored to the cloud have to be secured in order to avoid the data from exploiting. There are several techniques and methods that are used to secure the data before uploading it to the cloud such as cryptographic encryption techniques. In this paper, we study about different encryption technique to protect the cloud storage environment. This paper covers some of the existing cryptographic approaches that can be used to improve the security in cloud environment.

The production of milkfish in South Sulawesi is considerably high and the processing of milkfish surimi has been done to produce fish jelly products. Generally, surimi must be kept in freezing condition. Therefore we need technology support in order to easy processing of fish product in storage and efficient issue in terms of distribution. One that can be done is that to process it into surimi powder. The surimi powder of milkfish has a great opportunity to develop for diversification of fishery products. The aim of this study was to determine the physicochemical properties of milkfish surimi fish with the addition of different types of dryoprotectant : 2% carragenan (C) ; 4% sucrose + 2% carragenan (Su+C) ;4% sorbitol + 2% carrageenan (So+C) ; 6% trehalose + 2% carragenan (T+C) with vacuum drying. The results showed that the milkfish surimi powder contains 7.22 - 7.91% moisture content; protein 57.06 - 61.9%; fat 9.62 - 10.88%; ash content 1.35 - 1.48% ; surimi powder yield 13.3 - 14.65%; WHC levels 6.42 - 14.64 mL/g ;pH range 6.37 - 6.75; whiteness 61.51 - 72.35. The addition of trehalose 6% + 2% carrageenan (T+C) as dryoprotectant has better physicochemical properties compared with other treatments.

Data privacy and security are incredibly important in the healthcare industry. Federated learning is a new way of training a machine learning algorithm using distributed data which is not hosted in a centralized server. Numerous centralized machine learning models exists in literature but none offers privacy to users’ data. This paper proposes a federated learning approach for early detection of Type-2 Diabetes among patients. A simple federated architecture is exploited for early detection of Type-2 diabetes. We compare the proposed federated learning model against our centralised approach. Experimental results prove that the federated learning model ensures significant privacy over centralised learning model whereas compromising accuracy for a subtle extend.

Almost all technical people know about images and image encryption, but some of them are not aware of the security and performance of the encryption systems. All image encryption systems are capable of encrypting the images, but some are not so secure. However, the question is how to evaluate the encryption systems. This paper gives you what are the analyses that are possible for evaluating the security and performance of the encryption systems. We hope this paper gives you an insight into Images, Image encryption, Security attacks, Noise and information loss, Evaluation Criteria, Analysis, Resistance, Key, Speed, Complexity, and other parameters.

For personal, mobiles and sensor communications wireless sensor networking is an emerging concept in recent years. Normally wireless sensor network (WSN) is combined and integrated data relations for modern communication in infrastructure, energy efficiency; these are the main design parameters to improve network performance with respect to mitigate communication relations. In this paper, we describe different type’s energy optimization techniques/approaches and basic routing scenarios used for efficient communication in wireless sensor networks. To support data communication in wireless sensor networks we also give brief description about different routing protocols. And also define different routing algorithms used in data communication to increase network efficiency with respect to different network parameters. In this survey, we discuss about energy optimization approaches in wireless sensor networks, and also define several techniques which aim energy consumption in wireless nodes in WSNs.

Photographs are taken as valid evidences in various scenarios of our day to day life. Because of the developments in the field of Image Processing, altering images according to ones need is not a difficult task. Techniques of Image Forensics play its crucial role at this juncture. One of the mostly found types of image tampering is Copy-Move forgery. A copy-move forgery is performed by copying a region in an image and pasting it on another region in the same image, mostly after some form of post-processing like rotation, scaling, blurring, noise addition, JPEG compression etc. Two types of copy-move forgery detection techniques exist in literature. They are the Block based methods and Key-point based methods. Both the methods have their own advantages and limitations. This paper presents a survey on the recent developments in block based methods. As forgeries have become popular, the importance of forgery detection is much increased. Copy-move forgery, one of the most commonly used methods, copies a part of the image and pastes it into another part of the image. In this paper, we propose a detection method of copy-move forgery that localizes duplicated regions using Zernike moments. Since the magnitude of Zernike moments is algebraically invariant against rotation, the proposed method can detect a forged region even though it is rotated. Our scheme is also resilient to the intentional distortions such as additive white Gaussian noise, JPEG compression, and blurring. Experimental results demonstrate that the proposed scheme is appropriate to identify the forged region by copy-rotate-move forgery.

In this paper, performance of a high gain quasi Y-source impedance network converter is analysed. This converter has a high voltage gain while using a small duty ratio. Compared to other impedance source converters, Y-source converter operates with lower shoot-through duty cycle for the same boosting gain. To achieve that, a three windings transformer with very low leakage inductance is employed. In turn, the switching losses and heating are low at the same boosting gain. Moreover, in this type of converter, the boosting gain depends on number of variables, and hence more degrees of freedom for meeting design constraints. The voltage and current of the switching elements are analysed during shoot and non-shoot through. The analysis shows that for high boosting gain some components have high voltage stress compared to conventional converters. Moreover, fast switching diodes are required to achieve high boosting gain. The performance of the proposed converter is analysed using numerical simulation and experimental testing.

In an era of globalization, economies over the world have become increasingly international and competitive. According to Alahuhta et al (2005), the last three decade has seen a massive revolution in technology use at both individual and organizations level with several organizations replacing the manual system of operation with modern technologies and computer powered machines. Acheampong, et al (2017) explain that three decades ago it was a dream to conceive that at a point in time all of the world’s knowledge could be put on a single world wide web and browsed by people from different parts of the world for free. These are the realities of the contemporary business place which Casey & Wilson-Evered (2012) explained has been facilitated by the advances in technology and globalization. According to Zaremohzzabieh, et al (2014), e-commerce platform appeared along with the development of internet and the necessities of ventures has given a web-based exchanging spot to customers and suppliers. It is a virtual system for purchasers and merchants, utilizing computer programming technology to coordinate assets on the web and accomplish the objective of community program (Ruzzier, AntonciC, Hisrich, & Konecnik, 2007). E-commerce platform gives all members equivalent and public information location of many services. Merchants can disseminate product information on e-commerce platforms, while purchasers can get a wide range of information without going outside (Strauss, 2016). As a new trend in the economic development and a new pattern of future business advancement, e-commerce platform plays a critical part with many attributes i.e. third party, service nature, neutrality and integration (Ling, et al, 2010).

A Traffic signal control is a challenging problem and to minimize the travel time of vehicles by coordinating their movements at the road intersections. In recent years traffic signal control systems have on over simplified information and rule-based methods and we have large amounts of data, more computing power and advanced methods to drive the development of intelligent transportation. An intelligent transport system to use the machine learning methods likes reinforcement learning and to explain the acknowledged transportation approaches and a list of recent literature in traffic signal control. In this survey can foster interdisciplinary research on this important topic.

Malicious codes have become one of the major threats to computer systems. The malicious software which is also referred to as malware is designed by the attackers and can change their code as they propagate. The existing defense against malware is highly affected by the diversity and volume of malware variants that are being created rapidly. The variants of malware families exhibit typical behavioral patterns exhibiting their origin and purpose. The behavioral patterns can be exploited statically or dynamically to detect and classify malware into their known families. This paper provides a detailed survey of techniques to detect and classify malware into their respective families.

Machine condition checking innovation has around for a long time, designed for advancing machine execution and limiting unplanned personal time. Since the appearance of the IoT, nonetheless, there has been development around machine condition observing. An IoT-based model for machine apparatuses condition examination with AI, IoT computerizes and adds knowledge to machine condition checking. In this paper different techniques are studied about machine tools condition analysis and classification. This examination surveys different techniques which are used to classify machine sound data. The center goal is to order the obtained machine sound sign into the comparing machine conditions effectively for example faulty and normal, which is generally a multi- class order issue.

Now a day’s Security in cloud computing is one of the broad areas for researchers. Cloud computing is a term that involve to deliver the services over the Internet. So, it requires the security upgrade in data transmission approach. One of the ways by which data in the Cloud be secured is cryptography. In fact, the high-quality cloud security can be achieved by efficient encrypting techniques. This paper investigates how the integrity and secure data transfer are improved based on the Elliptic Curve cryptography and DNA computing. Many researchers have tried to exploit the features of ECC field for security applications. In this paper, we attempt to develop a fast hybrid cryptosystem based on Elliptic Curve and DNA computing for providing security service such as confidentiality in the cloud services. The security of the proposed scheme is based on Elliptic Curve Discrete Logarithm Problem (ECDLP). Existing DNA based cryptography technique need more computational power and more processing time with larger key sizes to provide higher level of security. The main goal of our construction is to enhance the security of elliptic curve cryptosystem using DNA Computing. In this approach data stored on the cloud server in the encrypted form and even if data is accessed by the attacker, the attacker can't get the current data.

In this project we are comparing different architectures and adding the features that increases the efficiency of our architecture. Few of them are including multiplexers in the message digester, using different adder architectures in the required places, reducing the critical path by breaking the longest path and making them to operate parallelly. Use of multiplexers reduces the number of registers required in the message expander. It simply transfers the output of expander to compressor block in every clock cycle. Whenever the number of cycle is greater than 16, the multiplexer switches the select line so that the computed message digest to send as output to the compressor. Using of a carry save adder and adder array takes lesser time to perform addition than a pair of adders array. Finally we all know that reducing the critical path reduces the overall operation time and hence increases the efficiency. Considering all these factors in the design we are designing the microarchitecture for SHA-256 algorithm and obtain the RTL code for that architecture. We have also verified the design by designing a test-bench, and finally synthesized the design.

Fake Prescriptions have emerged lately becoming hazardous for people’s lives; bringing their lives at stake. Drugs like Schedule-H cannot be bought without a doctor's consent and thus cases of such drugs being bought with the help of fake prescriptions have become very common today. Sometimes pharmacists find it hard to identify the medicine names from handwritten descriptions and it may eventually lead to misinterpretation of the prescribed medicine name. We provide a solution to this problem. PrEazy is an android application that provides secured and digital prescriptions such that it reduces the use of fake prescriptions. Also, it is a Paperless Technology making it Environment-Friendly. This application is digital prescription software which transmits communication between doctor, patient and pharmacist.

Game theory is a mathematical model which deals with interactions between various entities by analyzing the strategies and choices. In today’s world, Game Theory is being extensively used in fields like computer science, economics, sociology, political science, and so on, due to its versatile nature and applications in numerous conflicts and problems. The application of game theory has been extended to real life problems also due to its versatility and robustness. In this research, various game theory methodologies applied during pandemic was reviewed. Various aspects of these methodologies were highlighted such as methods applied, description, expected result and limitation. This research will act as a reliable and efficient way of understanding the concept of game theory and its application in combating infectious diseases, analyze and eventually understand different strategic scenarios. The main importance of game theory is to formulate the alternative strategy to compete with one another and in the same sense it is an essential tool for decision making process according to fluctuations in relevant contents. These reviewed methodologies would be further categorized into prevent, control or both based on the application they favour most.

In this research, we have been able to simulate some finite difference schemes to predict weather trends of Abuja Station, Nigeria. By analyzing the results from these schemes, it has shown that the best scheme in the finite difference method that gives a close accurate weather forecast is the trapezoidal scheme hence we use it to simulate numerical weather data obtained from Federal Airports Authority of Nigeria (FAAN), Abuja and corresponding numerical weather data obtained by the compatible finite difference schemes, using MATLAB (R2012a) software to obtain future numerical weather trends.

The images have to be described by certain features. The shape is an important visual feature in understanding an image, that remains stable in spite of changes in an object's illumination, color, and texture. So shape features have been applied in object recognition tasks. There are many shape description and recognition techniques in the literature. This survey paper provides an overview of description and recognition techniques and examines implementation procedures for each technique and its advantages and disadvantages. Finally, identify some techniques for image retrieval according to standard principles.

While capturing underwater image there are lot of imposed due to low light, light variation, poor visibility. Photography is about light, but since water has an a lot more prominent density than air — around 800 times more noteworthy not all wavelengths of light travel similarly well inside it. This implies as we go down into deep water, we lose the shades of the range one by one. This is the reason submerged photographs lose all the red and orange hues even at a genuinely shallow profundity and appear to be increasingly more blue as we go deep in water, henceforth captured image need enhancement. It’s a vital research area, in this paper we will review different techniques of underwater image enhancement.

We review existing machine condition monitoring techniques and industrial automation for plant-wide condition monitoring of rotating electrical machines. Cost and complexity of a condition monitoring system increase with the number of measurements, so extensive condition monitoring is currently mainly restricted to the situations where the consequences of poor availability, yield or quality are so severe that they clearly justify the investment in monitoring. There are challenges to obtaining plant-wide monitoring that includes even small machines and non-critical applications. One of the major inhibiting factors is the ratio of condition monitoring cost to equipment cost, which is crucial to the acceptance of using monitoring to guide maintenance for a large fleet of electrical machinery. Ongoing developments in sensing, communication and computation for industrial automation may greatly extend the set of machines for which extensive monitoring is viable.

In Bioinformatics field Protein Structure Classification is the hugest undertaking. The realized proteins have been requested subject to their level, feature, work, amino destructive and family and superfamily. Protein structure segregated into four sorts: all ? protein structure, all ? protein structure, ?+? protein structure, and ?/? protein structure. The use of a standard way to deal with perform plan is a very inconvenient and dreary task. The quantity of cutting edge Machine Intelligence enrolling strategies such Support Vector Machine, Random Forest, Artificial Neural Network, Decision Tree and Naïve Bayes Classifier had been proposed in the composition. Our objective right currently is to develop a system that performs better than anything past markers for protein structure gathering by thinking about the separation among the distinctive Amino Acid buildups. To take a gander at the display of proposed work particular datasets are used.

Vehicular Ad Hoc Networks (VANETs) are gaining much attention from both industry and academia communities as an emerging technology. VANET is composed of self-regulating nodes where the vibrant node mobility changes the network topology frequently. The important aim of VANET is to upgrade road safety conditions to minimize extent of road mishaps. The nodes are very mobile in vehicular ad hoc network so routing becomes complex job. As the VANET nodes move very fast the topology changes accordingly. So node mobility prediction in VANET is a very important issue. Further, prediction of mobility helps to estimate the stable path between the nodes which leads to better routing. Estimating secure paths among the routing of nodes perform in a better way, thereby reducing the overhead and minimizing interruptions in connections. This paper explores VANET's basic architecture and discusses a number of current mobility prediction techniques, and concludes with performance analysis of existing routing protocols and proposed mobility prediction methods.

The network providers are now being challenged with their inability to accurate estimate and characterize traffic in a particular area, due to the increasing number of mobile communication services being rendered by the network providers Hence, this has been greatly undermining their design and planning processes and as such increasingly affected the Quality of Service(QoS).This research work addresses the traffic estimation in mobile communication network using Artificial Neural Network (ANN) approach using measured data collected in Lagos State,Nigeria.The Multilayer Perceptron (MLP) and Radial Basis Function (RBF) ANN techniques were used in the traffic modeling. The results of the ANN modeling showed that the Model 1 of MLP performed better than other models with Coefficient of Determination (R2) of 99%, Root Mean Square Error(RMSE) of 5.456 and Mean Bias Error(MBE) of 0.94.It is recommended that the dataset used in developing the ANN models be increased by collecting and using not more than 12months traffic data for ANN modeling .An appropriate design of the models should also be given a serious concern by choosing appropriate number of neurons at the hidden units of the neural networks .This will provide a good traffic estimation which the mobile network provider can be used in network design and planning.

Data Mining is the process of finding certain patterns and knowledge from big data. In general, the data mining process can be grouped into two categories, namely descriptive data mining and data mining prediction. There are several Math functions that can be used in the data mining process, one of which is the Classification and Regression function. Regression Analysis is also called Prediction analysis, which is a statistical method that is widely used to investigate and model relationships between variables. Regression analysis to estimate the regression curve can be done by analyzing Nonparametric Regression. One well-known method in non-parametric regression is MARS (Multivariate Adaptive Regression Spline). The MARS method is used to overcome the weaknesses of the Linear Regression method. The use of a stepwise backward algorithm with the CQP quadratic programming framework (CQP) from MARS resulted in a new method called CMARS (Conic Multivariate Adaptive Regression Splines). The CMARS method is able to model high dimensional data with nonlinear structures. The flexible nature of the CMARS model can be used in the process of analyzing earthquake predictions, especially in Lombok, West Nusa Tenggara. Test results Obtained a mathematical model of four independent variables gives significant results to the dependent variable, namely Peak Ground Acceleration (PGA). Contributions of independent variables are the distance of the epicenter 100%, magnitude 31.1%, the temperature of the incident location 5.5% and a depth of 3.5%.

Rainfall prediction is useful for all people for decision making in all fields, such as out door gamming, farming, traveling, and factory and for other activities. We studied various methods for rainfall prediction such as machine learning and neural networks. There is various machine learning algorithms are used in previous existing methods such as naïve byes, support vector machines, random forest, decision trees, and ensemble learning methods. We used deep neural network for rainfall prediction, and for optimization of deep neural network Adam optimizer is used for setting modal parameters, as a result our method gives better results as compare to other machine learning methods.

Today Indian economy depends upon agriculture. More than 70% of the people in India have taken it as a main occupation, day by day for a particular crop; the formers are not getting proper yield as well as profit due to environmental conditions like soil quality, weather, heavy rainfall, drought, seed damages, fertilizers, pesticides. The farmers not able to produce high production, so taking the historical agricultural data records we can predict the crop yield using machine learning techniques like Linear regression, comparative analysis are done with decision tree, KNN algorithms, using these to achieve the high accuracy and model performance is computed.

Artificial Intelligence (AI) helps computers to learn from experience, adjust to new stimuli, and perform tasks of a human nature. It works by combining large amounts of data with fast, iterative processing and smart algorithms, allowing the program to learn from patterns or features in the data automatically. We address AI and various subfields of AI in article. In this paper, we are studying the types, applications, tools. In addition, few examples of existing Internet of Things services with AI working behind them are discussed in this context.

The Internet of things (IoT) refers to a type of network to connect anything with the Internet based on stipulated protocols through information sensing equipment’s to conduct information exchange and communications in order to achieve smart recognitions, positioning, tracing, monitoring, and administration. In this paper we briefly discussed about what IOT is, how IOT enables different technologies, about its architecture, characteristics & applications. The purpose of this paper is to provide the basic information about IoT for young readers.

Earlier, Lung cancer is the primary cause of cancer deaths worldwide among both men and women, with more than 1 million deaths annually. Lung Cancer have been widest difficulty faced by humans over recent couple of decades. When a person has lung cancer, they have abnormal cells that cluster together to form a tumor. A cancerous tumor is a group of cancer cells that can grow into and destroy nearby tissue. It can also spread to other parts of the body. There are two main types of lung cancer:1. Non-small cell lung cancer, 2. Small cell lung cancer. Non- small cell lung cancer has four main stages. In this research we are classifying four stages of lung cancer. Lung cancer detection at early stage has become very important. Currently many techniques are used based on image processing and deep learning techniques for lung cancer classification. For that lung patient Computer Tomography (CT) scan images are used to detect and lung nodules and classify lung cancer stage of that nodules. In this re- search we compare different Machine learning (SVM, KNN, RF etc.) techniques with deep learning (CNN, CDNN) techniques using different parameters accuracy, precision and recall. In this Research paper we com- pare all existing approach and find our better result for future application.

Opinions are personal judgment on entity. This is not only true for individuals but also true for organizations. Opinion mining is a type of natural language processing for tracking the mood of the public about a particular product. The process of sentiment mining involves categorizing an opinionated document into predefined categories such as positive, negative or neutral based on the sentiment terms that appear within the opinionated document. For this study text document corpus is prepared by the researcher encompassing different movies ‘reviews and Various techniques of text pre-processing including tokenization, normalization, stop word removal and stemming are used for this system(sentiment mining model for opinionated afaan Oromo texts). The experiment shows that the performance is on the average 0.849(84.9%) precision and 0.887(88.7%) recall. The challenging tasks in the study are handling synonymy and inability of the stemmer algorithm to all word variants, and ambiguity of words in the language. The performance the system can be increased if stemming algorithm is improved, standard test corpus is used, and thesaurus is used to handle polysemy and synonymy words in the language.

Data mining process extracts useful information from a large amount of data. The most interesting part of data mining is discovering the unseen patterns without unpacking sensitive knowledge. Privacy Preserving Data Mining abbreviated as PPDM deals with the issue of sustaining the privacy of information. This methodology covers the sensitive information from disclosure. PPDM techniques are established for hiding the sensitive information even after performing the data mining. One of the practices to hide the sensitive association rules is termed as association rule hiding. The main objective of association rule hiding algorithm is to slightly adjust the original database so that no sensitive association rule is derived from it. The following article presents a detailed survey of various association rule hiding techniques for preserving privacy in data mining. At first, different techniques developed by previous researchers are studied in detail. Then, a comparative analysis is carried out to know the limitations of each technique and then providing a suggestion for future improvement in association rule hiding for privacy preservation.

In the era where world runs online the storing and publishing of data online has also increased to a great extent. In this era a large amount of information is collected and published to a network which is publically available. With the exposure of data comes the risk of information leakage of an individual while publishing the data online. Hence for the same we need a security system for preserving the privacy of individual and here the concept of preserving privacy in data publishing came into existence. To achieve this privacy different privacy models and techniques have been proposed which gives different levels of resistance against different attacks by adversaries. In this paper we will discuss about these models and techniques and have a comparative study among them.

Globally, skin diseases are among the most common health problems in all humans irrespective of age. Prevention and early detection of these diseases can improve the chance of surviving. This model illustrates the identification of skin diseases providing more objective and reliable solutions using deep learning technology and convolutional neural network approach. In this model, the system design, implementation and identification of common skin diseases such as acne, blister, eczema, warts etc. are explained. The system applies deep learning technology to train itself with various images of skin diseases from the Kaggle platform. The accuracy obtained by using deep learning is 83.23%. The main objective of this system is to achieve maximum accuracy of skin disease prediction. Moreover, if the disease is identified the system provides detailed information about the diseases along with home remedies.