Foundation University Journal of Engineering and Applied Sciences
Not a member yet
56 research outputs found
Sort by
Security in the Internet of Things: A Systematic Mapping Study
Get PDFThe extend of clever gadgets has accelerated touchy statistics trade on the Internet the usage of most of the time unsecured channels. Since a large use of RFID (Radio-frequency Identification) tags in the transportation and development industries from 1980 to 1990, with the multiplied use of the Internet with 2G/3G or 4G when you consider that 2000, we are witnessing a new generation of related objects. A massive wide variety of heterogeneous sensors may also accumulate and dispatch touchy facts from an endpoint to a global community on the Internet. Privacy worries in Iot stay essential problems in the research. This paper aims to understand and additionally grant continuing doe’s research topic, challenge, and Future Direction related to Iot security. A systematic mapping finds out about (SMS) is thus utilized on the way to organize the chosen Articles into the following classification: contribution type, Type of Research, Iot Security, and their approach. We take out an overall of twenty-four Articles in support of this systematic discover out about also they categorize the following described criterion. The findings of this SMS are mentioned and the researcher was once given hints on the possible route for future research
Artificial Intelligence Potential Trends in Military
Get PDFArtificial intelligence (AI) is trending in the military and safety-critical application sectors. Currently, the private sector is helping the government sector to implement new advanced techniques to bring a revolution for different government and public sector management. It also helps to provide sustainable accountability in the accounting field; at present, AI is bringing a revolution in concept building. It is bringing potential revolutions by using novel approaches in such directions. This paper is a novel approach in the same direction; our research aim of this paper is to emphasize the AI in the militaries, what are the latest trend and usages recently worldwide used for AI applications in militaries. In this paper, we not only discuss the usage of AI applications in the military but also in the civil defense and health industry. We review and discuss that AI has potential benefits in military applications, HRMS, decision making, disaster prevention and response, GIS, service personalization, interoperability, extensive data analysis, anomaly and pattern recognition, intrusion detection, and new solution discovery using the highly configurable system and real-time simulation
Kobe Braynt Shot Prediction using Machine Learning
Get PDFKobe Bryant was one of the best players of Basketball. Data regarding his 20 years played games is available on the Kaggle. We transform the categorical features by PCA and normalize the data by minmax normalization technique. Machine learning techniques such as logistic regression, Random Forest, Linear Discriminant Analysis, Naïve bayes, Gradient Boosting, Adaboost and Neural Network are applied on pre-processed data to classify whether he made shot or not. The prediction accuracy of LR, RF, LDA, NB, GB, ABC and ANN is 67.84%, 64.22%, 67.82%, 61%, 67.8%, 68% and 67% respectively on hold an out method. The experimental results shows that Adaboost has highest prediction accuracy as compared to others method with 5 cross validations. Finally, we have got satisfactory results as compared to our benchmark (Kaggle)
A Novel Software Layer to Program Arduino over the Air using Bluetooth
Get PDFProgramming over the air (POTA) is commonly used to update the firmware and configuration of a wireless sensor node without any physical contact with the node. Here we designed a four-wheel student development kit for the remote-controlled car via Bluetooth HC-05 module that was programmed using over the air (OTA). Bluetooth HC-05 module only supports universal asynchronous receive transmits (UART) traffic to communicate with connected slave devices. To implement POTA for robotic cars an additional software layer was written for the HC-05 module and this software layer makes HC-05 able to program Arduino pro mini over serial communication. The written software transfers data over the Bluetooth link to the slave hardware to program Arduino pro mini.This work can be utilized in the swarm of robotics network in which firmware consistently need to update to adapt the surrounding. It can also be utilized in the localization of robots in the indoor environment and similarly can be utilized for student training. Here we designed a four-wheel student development kit for the remote-controlled car via Bluetooth HC-05 module that was programmed using over the air (OTA)
Comparison of Multiple Deep Models on Semantic Segmentation for Breast Tumor Detection
Get PDFThe early diagnosis of breast tumor detection is the most significant research issue in mammography. Computer-aided diagnosis (CAD) is one of the highly essential methods to prevent breast cancer. This research work explored the effectiveness of deep-based pixel-wise segmentation models for low energy X-rays (mammographic imagery) to detect tumors in the breast region. For this purpose, various semantic segmentation models were incorporated into the experimental procedure. All the models were analyzed using the medical images dataset, which was gathered and annotated from one of the largest teaching hospitals in the Khyber Pakhtunkhwa province, known as Lady reading hospital. It is coordinated in cooperation with local health specialists, radiologists, and technologists. The comparative analysis of the incorporated segmentation techniques' performance was observed, selecting the most appropriate model for detecting tumors and normal breast regions. The experimental evaluation of the proposed models performs efficient detection of tumor and non-tumor areas in breast mammograms using traditional evaluation metrics such as mean IoU and Pixel accuracy. The performance of the semantic segmentation techniques was evaluated on two datasets (Cityscapes and mammogram). Dilation 10 (global) performed the best among the four semantic segmentation models by achieving a higher pixel accuracy of 93.69%. It reflects the effectiveness of the pixel-wise segmentation techniques by outperforming other state-of-the-art automatic image segmentation models
A Comprehensive Analysis of Adaptive Image Restoration Techniques in the Presence of Different Noise Models
Get PDFAny deprivation caused in the image signal can be thought as a noise. When any image signal is routed through wireless or wired medium it experiences deterioration because of channel characteristics. By knowing the type of noise interfered in the signal, we can use the pertinent filtering techniques to remove the noise from the image. Restoration of the image signal corrupted by noise is very essential for better communication. This paper provides the digital image handling techniques in MATLAB to restore the corrupted image. In this paper, different filtering methods have been discussed in the presence of two separate noise models that distort images. Four different techniques of filtering, ‘Mean/Average filtering', 'Median filtering', 'Adaptive median filtering' and 'Image Averaging' have been chosen against selected noise models. At the end of the paper we will compare which filtering technique works best for removing a particular noise
Latest Trends in the Cybersecurity after the Solar Wind Hacking Attack
Get PDFThat dominance, in any case, has gotten to be a risk. On Sunday, Solar Winds alarmed thousands of its clients that an “outside country state” had found a back entryway into its most well-known item, an instrument called Orion that makes a difference organizations screen blackouts on their computer systems and servers. The company uncovered that programmers snuck a malevolent code that gave them inaccessible get to customers’ systems into an upgrade of Orion. The hack started as early as Walk, Solar Winds conceded, giving the programmers bounty of time to get to the customers’ inside workings. The breach was not found until the unmistakable cybersecurity company FireEye, which itself employments Solar Winds, decided it had experienced a breach through the program. FireEye has not freely faulted that breach on the Solar Winds hack, but it allegedly affirmed that was the case to the tech location Krebs On Security on Tuesday. FireEye depicted the malware’s bewildering capabilities, from at first lying torpid up to two weeks, to stowed away. That was December 13, 2020. FireEye gauges programmers to begin with picked up get to in Walk 2020. For about eight months, malevolent on-screen characters carted absent untold sums of touchy information from contaminated organizations — and the total scope of the breach is still unfolding. Despite Microsoft seizing the code’s command and control server (a common component in botnet assaults as well), a few security specialists think the assailants may still have get to the Solar Winds Orion program system. Others are conjecturing that these programmers cleared out behind extra, yet-to-be-seen malevolent code
Statistical Analysis of Cricket Leagues Using Principal Component Analysis
Get PDFAny sport has statistics, and cricket is the one, where statistics are extremely important because players are ranked using these data. Individual runs, wickets, and highest scores, among other things, are included in these statistics. Players are chosen for tournaments all over the world based on statistics. By analysing cricket statistics and figures, this study employs Principal Component Analysis. Using the approach called Principal Component Analysis, this study examines the precise co-variation among several measurements linked to the batting and bowling talents of players in the Pakistan Super League PSL T-20 (2016-2019) and the Indian Premier League IPL T-20 (2016-2019). PCA is applied in this study to rank the PSL batsmen and bowlers based on their contributions to their clubs during these competitive seasons. The results of this research revealed the top ten ranked batters and bowlers who excelled during the series. Principal Component Analysis is widely used in applied multivariate data analysis. In the current investigation, PCA was utilized to rank the top ten best-performing batsmen and bowlers of the PSL and IPL. Principal Component Analysis is a dimension reduction technique that is used to reduce dataset dimensions into smaller variables. Here, principal component analysis is successfully used to rank the cricket batsmen and bowlers
Phone Numbers Classification (PNC) with Feed-forward Neural Networks
Get PDFA neural network (NN)-based method for phone number classification or recognition is provided in this paper. The used network is a one-hidden-layer multilayer perceptron (MLP) classifier. Its training is based on backpropagation learning. I present the results of a Feed Forward Neural Network trained to classify phone numbers into four categories: Different training data were pre-processed and then tested to distinguish between four classes/patterns of phone numbers in order to train the FFNN. My goal is to provide a coalescence of the published research in this field and to arouse further research interest in and efforts to research the identified topics