Water Leakage Detection System Using Arduino

Clean water is a scarce resource for the human life and is subject to wastage due to leakage of the distribution pipes in large cities. Water pipe leakage is a big problem around the world of which most of the water distribution authorities faces difficulties to detect the location of the fault. This problem of leakage can be caused by several factors such as breakage of the pipelines due to aging or ongoing constructions in urban cities like Dar es salaam, consequently due to that case, the distribution authorities face hardship to identify the cause and enable them to take action. Therefore, the aim of this project was to develop an IoT-based system for water leakage detection. The prototype was developed comprising two sensors embedded at the source and destination points to measure the flow rate of water. The result indicated that the volume of water generated at the start point can be compared with the other end to determine if there is any leakage. A greater focus on distance calculation could produce interesting findings that account for more research on IoT monitoring systems.

A Multi-Layer Perceptron Model for Classification of E-mail Fraud

This study was developed an e-mail classification model to preempt fraudulent activities. The e-mail has such a predominant nature that makes it suitable for adoption by cyber-fraudsters. This research used a combination of two databases: CLAIR fraudulent and Spambase datasets for creating the training and testing dataset. The CLAIR dataset consists of raw e-mails from users’ inbox which were pre-processed into structured form using Natural Language Processing (NLP) techniques. This dataset was then consolidated with the Spambase dataset as a single dataset. The study deployed the Multi-Layer Perceptron (MLP) architecture which used a back-propagation algorithm for training the fraud detection model. The model was simulated using 70% and 80% for training while 30% and 20% of datasets were used for testing respectively. The results of the performance of the models were compared using a number of evaluation metrics. The study concluded that using the MLP, an effective model for fraud detection among e-mail dataset was proposed.

Smart Irrigation System Using Intelligent Robotics

To optimize water use for agricultural crops while also verifying water scarcity in the field, an automated irrigation system was developed. Weed management and control are critical for high-yielding, high-quality crops, and developments in weed control technologies have had a significant impact on agricultural output. Any weed control method that is effective must be both durable and versatile. Despite the variety in field circumstances, robust weed control technologies will successfully manage weeds. Weed control technology that is adaptable can change its strategy in response to changing weed populations, genetics, and environmental conditions. The system includes a distributed wireless network of soil-moisture and temperature sensors, as well as conductive sensors in the plant's root zone. Agate way unit also manages sensor data, triggers actuators, and sends data to an Android mobile device. To control water quantity, an algorithm with temperature and soil moisture threshold values was developed and programmed into a microcontroller-based gateway. The added future of this research is that we are utilising a robot to monitor the condition of the crop to see if it is affected by insects or not. The robot will move around the field, and we will be able to track the crop's health on our device.

Information System Security Practices and Implementation Issues and Challenges in Public Universities

The use of information and communication technology has been providing the competitive edge for universities globally while Kenyan universities are not an exception. This has in turn made the universities targets of cyber-attacks and hence exposure to unprecedented security risks. The universities need to implement information security best practices and standards in their technological environments to remain secure and operational. The research sought to investigate the information security practices adopted in Kenyan public universities to protect themselves. Descriptive survey method was employed while the study was based on Operationally Critical Threats, Assets and Vulnerability Evaluation (OCTAVE) framework and other industry security best practices. The study targeted the 31 chartered public universities, which were clustered based on their year of establishment. Simple random and purposive sampling methods were utilized to select two target universities per cluster and determine respondents respectively. The study had a response rate of 61%. Analysis of data was done via descriptive statistics while presentation of results was done using tables and Likert scale. The study revealed that universities had implemented information security policies, with 47.6% of respondents somewhat agreeing to that. Funding for security was provided 57.6% somewhat agreeing, though the funding was deemed low by 51% of respondents. Training for security staff was deemed somewhat available (44%) thus below par, while involvement of university management on policies development was at 48% though university management participation in policies review was below average. 38% of respondents somewhat agreed that policies governing use of mobile devices existed. Frequency of user awareness and training was below the average, while 48% of respondents somewhat agreed that universities usually share their intelligence reports on threats and responses with other government agencies. 49% of respondents were somewhat in agreement universities had put in place incidence response plans. Application of updates and improvements was below average, though evaluation of effectiveness of controls was average. To remain protected universities management should cause a review of their employed information security practices and address identified gaps through instigation of essential remedial actions.

The Cyber Crime of Juice Jacking in Developing Economies: Susceptibilities, Consequences and Control Measures

It is convenient and the norm to have both data and power cables (battery charge) integrated as a single Universal Serial Bus (USB) cable for today’s mobile devices. While the data component of the cables serves as the channels for data communication, the power channel charges the mobile devices through an adapter connected to an Alternating Current (A/C) socket or directly to a USB port. This convenient and seemingly harmless design could also serve as a medium through which malicious hacks are carried out on the connected mobile devices as studies and recent experimentations has shown. This hacking variant called Juice Jacking now serve as a potential avenue for mobile device exploitation, especially in developing economies where poor power grid infrastructures has allowed for indiscretions in charging devices from any available. This paper formulates a simple architecture for Juice Jacking cyber-crime, review prove-of-concept experimentation for Juice Jacking from available literatures, identifies significant threats and levels of impact of this cyber-crime on the community. It also highlights strategies that could mitigate juice jacking in developing economies.

A Seasonal and Multilevel Association Based Approach for Market Basket Analysis in Retail Supermarket

Market Basket Analysis is an observational data mining methodology to investigate the consumer buying behavior patterns in retail Supermarket. It analyzes customer baskets and explores the relationship among products that helps retailers to design store layouts, make various strategic plans and other merchandising decisions that have a big impact on retail marketing and sales. Frequent itemsets mining is the first step for market basket analysis. The association rules mining uncovers the relationship among products by looking what products the customers frequently purchase together. In retail marketing, the transactional database consists of many itemsets that are frequent only in a particular season however not taken into consideration as frequent in general. In some cases, association rules mining at lower data level with uniform support doesn't reflect any significant pattern however there is valuable information hiding behind it. To overcome those problems, we propose a methodology for mining seasonally frequent patterns and association rules with multilevel data environments. Our main contribution is to discover the hidden seasonal itemsets and extract the seasonal associations among products in additionally with the traditional strong regular rules in transactional database that shows the superiority for making season based merchandising decisions. The dataset has been generated from the transaction slips in large supermarket of Bangladesh that discover 442 more seasonal patterns as well as 1032 seasonal association rules in additionally with the regular rules for 0.1% minimum support and 50% minimum confidence.

Is the Algorithm of Artificial Neural Network a Deduction or Induction? Discussion between Natural Sciences, Mathematics and Philosophy

The algorithm of artificial neural network (ANN) has been defined as a supervised learning and heuristic algorithms. In training an ANN model, big data is necessary to use as training data to obtain perfectly accurate predicted data. However, big data really have no clear definition. Therefore, adding new training data to re-train an ANN model, by which can improve the predicted accuracy. This action of re-training this ANN model with added new training data is repeated to approach the laws of physics that is accessed to the principle of induction e.g., empirical formulas. However, accessing the principle of induction is limited. If the deduction is found using an ANN model, then approach of this ANN model with added new training data is also performed repeatedly to access the principle of deduction e.g., theory formulas. However, accessing the principle of deduction is also limited. It means the law cannot be easily deduced for an ANN model. Therefore, the algorithm of an ANN is not the canonical classical methods. On the other hand, the algorithm of an ANN does not belong to mathematical induction and deduction.

Design and Implementation of Automated Cart for COVID-19 Patients Treatment

With the recent changes in this world due to the pandemic of COVID-19 came the need to change in technology with medical environments. There were few robotic surgeries done in medical field, but the pandemic has put the Doctors and health care workers at risk. So there came a need for rapid change in medical environment to replace man with robots with the help of AI. In this paper a AGV also called as Automatic Guided Vehicle is designed for the benefit of health community. It can also be called as Automated Cart. The chances of health care worker getting affected from the patient in this COVID-19 is more due to the behavior of the novel Corona Virus Spread. Hence this Automated cart is designed in this paper which moves near the patient’s beds delivering medicines whenever needed in time and also collects waste from patients’ bed and returns to the necessary point. It is a line follower automated cart robot it makes use of certain sensors like infrared sensors and ultrasonic sensors. These sensors are used for route mapping and obstacle detection. This robot at the time of giving medicine to the patients’ bed and collecting waste, it also checks the body temperature and pulse rate of the patient and sends information to the doctor via internet. The adaptability of this robot with the patients depends on the preprogram done. A microcontroller is made use for this purpose. This automated cart can be designed and implemented with low cost and the risk of Doctors, health care workers is reduced.

Archaeological Databases and GIS: Working with Databases

Digital databases are considered nowadays, necessary for the organization of a recent archeological project. Typically, one of the main issues at the stage of archaeological surface research preparation is the method of recording all the archaeological information that will emerge, which is directly dependent on two factors, the difference of each area in terms of its geomorphology, including the climate and general environmental conditions, and the different approach to the objectives to be achieved by the leading archaeologists. As a consequence of all of this, there is no such thing as a uniquely generated form that can act as a guideline. This paper provides some basic database knowledge as well as a case study with a database example.

Smart Vehicle Parking System Using Computer Vision and Internet of Things (IoT)

Internet of Things is the interconnectivity between things, individuals and cloud administrations by means of web, which empowers new plans of action. Because of these exchanges, immense volumes of information are smartly created and is shipped off cloud-based server through web; the information is being handled and broken down, bringing about significant and convenient activities for observing the car parking. The serious issue that is arising currently at a worldwide scale and developing dramatically is the gridlock issue brought about by vehicles. A worldwide scale and developing dramatically is the gridlock issue brought about by vehicles. Among that, finding a better parking sparking space in urban areas has become a major problem with an increase of the numbers of vehicles on a daily bases. Therefore making it difficult in having a better and safe parking spot. The system proposes an intelligent smart parking system using computer vision and internet of things. The proposed system starts by acquiring a dataset. The dataset is made up images of various vehicles, which was collected from the faculty of science car park at the Rivers State University, Port Harcourt, Rivers State Nigeria. We proposed two methods for vehicle/parking slot detection. The first method is the use of convolution neural network algorithm which is used with a haar cascade classifier in detection of multiple vehicles in a single picture and video, and put rectangular boxes on identified vehicles. This first method obtained an accuracy of 99.80%. In the second method, we made use of a Mask R-CNN, here we download a pre-trained model weights which was trained on a coco dataset to identify various objects in videos and pictures. The Mask R-CNN model was used to identify various vehicles by putting a bounding box on each of the vehicle detected, but one of the problem of the Mask R-CNN is that it quite slow in training, and it could not really detect all vehicles tested on a high quality high definition video. In summary our, trained model was able to detect vehicles and parking slot on high quality video and it consumes lesser graphic card.