Engineering and Computer Science Research Papers (original) (raw)

This paper addresses the subconscious mind and its fascinating effects on a human’s life without their realization. The subconscious and its phenomenon can be considered a significant source to understand the secrets to the power this mankind beholds. People think they know what they are doing, who they are, not even realizing how they are directed by the greatest power of all “the subconscious mind” whose powers in disguise are yet to be discovered. This paper tells the incompatible nature of human subconscious mind. It has always been a topic of great discussions and arguments. This paper considers all the research papers and patterns of information throughout the history and modern period. Hence, it concludes the importance of the subconscious mind and how one can learn utilizing it at its best.

This is an era of technology; we are surrounded with the technology. Now a dayâ€™s people become smarter they want to operate each and everythingâ€™s with his smart phone/laptop/pc without going anywhere, it happens due to IOT devices. Thatâ€™s why in this paper we have design a smart home with enhance security. In smart home we can operate the household things(fan, light, ac, any applications, door, windows, etc. )with the mobile. We design a IOT based smart and secure home model in latest released cisco packet tracer. Cisco packet is basically a simulator to teach the student about the network. But in newly released cisco packet tracer 7.2.1 it have more sensors, board, Programming languages, IOE devices. In this we can design, test, see the actual working of the network/model in real time. In testing the IoT home network wireless network gateway system, multiple electronic devices can be controlled and monitored via smartphone based on predefined configuration conditions. The smart and secure home is implemented using different types of IOE devices with enhanced security, house environment prospective and safety.

Health care is one of the speedy growing areas. The Health care system contains large amount of medical data which should be mined from data warehouse. The mined data from data warehouse helps in finding the important information. Comprehensive amount of data in health care database need the growth of tools which can be used to access the data, analyze and analysis the data, discovery of knowledge, and versed use of the stored knowledge. The health care system has lot of data about the patient’s details, medications etc. In this paper we have studied different data mining and warehousing techniques used in healthcare areas.

The identity or verification of humans primarily based on their thermal information isn't always an easy mission to perform, but thermal face biometrics can make contributions to that undertaking. Face reputation is an interesting and a successful application of Image analysis and Pattern recognition. Facial pictures are important for intelligent vision based human machine interaction. Face processing is based at the fact that the records approximately a consumer’s identity may be extracted from the image and the computers can act as a consequence. A thermal face image should be represented with biometrics features that highlight thermal face characteristic and are compact and easy to use for classification. Second, image resolution is basically lower for video sequences. If the subject is present in very far from the camera, the actual face image resolution can be as low as 64 by 64 pixels. Finally, face image variations, such as illumination, expression, pose, occlusion, and motion, are more important in video sequences. The approach can address the unbalanced distributions between still images and videos in a robust way by generating multiple “bridges” to connect the still images and video frames. So in this project, implement still to video matching approach to match the images with videos using Grassmann manifold learning approach to know unknown matches. Finally provide voice alert at the time unknown matching in real time environments. And implement neural network classification algorithms to classify the face images in real time captured videos.

Now that many shops, offices and institutions are re-opening again after the Corona lockdown, many businesses are faced with the need to provide the best possible protection for their staff and customers. Face masks and body temperature checks play an important part in the protection effort. While this is already done routinely and at a large scale at airports or railway stations, many businesses and institutions are struggling to meet the challenge. Face mask monitoring often requires additional staff resources. At the same time, body temperature checks by staff come with certain risks in terms of hygiene and data privacy.

Any data that user creates or owns is known as the user's data (For example: Name, USN, Phone number, address, email Id). As the number of users in social networks are increasing day by day the data generated by the user's is also increasing. Network providers will publish the data to others for analysis with hope that mining will provide additional functionality to their users or produce useful results that they can share with others. The analysis of social networks is used in modern sociology, geography, economics and information science as well as in various fields. Publicizing the original data of social networks for analysis raises issues of confidentiality, the adversary can search for documented threats such as identity theft, digital harassment and personalized spam. The published data may contain some sensitive information of individuals which must not be disclosed for this reason social network data must be anonymized before it is published. To do the data in nominate the anonymization technique should be applied, to preserve the privacy of data in the social network in a manner that preserves the privacy of the user whose records are being published while maintaining the published dataset rich enough to allow for the exploration of data. In order to address the issue of privacy protection, we first describe the concept of k-anonymity and illustrate different approaches for its enforcement. We then discuss how the privacy requirements characterized by k-anonymity can be violated in data mining and introduce possible approaches to ensure the satisfaction of k-anonymity in data mining also several attacks on dataset are discussed.

In today's world reality has moved toward becoming digitized, on the off chance that we make fuel meter in the vehicle as digital it will help know the accurate measure of fuel present in the fuel tank. In our task, we have made a digital fuel meter. Here, we are showing the measure of fuel present in the tank digitally. Fuel robbery is additionally an issue in everywhere throughout the world. In our undertaking at whatever point there is fuel burglary happens, because of the commotion of thief alert individuals know about fuel robbery and furthermore amid fuel robbery an instant message is conveyed on portable to the proprietor of the bicycle. This is the constant happening process. The past vehicle framework doesn't have such usefulness that there is no presentation gear level whatever might be the condition through the bicycle is running or not. In any case, in our framework, we can defeat the above issue by utilizing the digital meter which demonstrates the rigging level in the enduring state or running condition of the vehicle.

Day by day the number of vehicles is increasing very fast as the demand is increasing. So, the details of the vehicles are very important to maintain for the government of a country. Information like ownership, insurance, emission, road tax etc., need to be maintained and accessed very efficiently and easily. Even for crime purpose the vehicles are used. So, depending on the demand of the requirements we have proposed this model for real time vehicle monitoring and intimating for violation of traffic rules using drone. In our proposed system, the drone is fitted with cameras and Raspberry Pi. The drone will keep on monitoring the non-parking areas from above the level of ground. The drone will capture the image and detect the vehicle and if the vehicle is not moving after two minutes, transmit the vehicle image to the server along with the road signal code.

Now a day, Information Security has primarily more attractive concern and today when most of the sensitive data is stored on Cloud with client organization having lesser control over the outsourced data, the fundamental way to fix this problem is to do encryption of data. So, a secure user can impose with information get to control system must be given before the clients store any information on the cloud storage. Attribute Based Encryption (ABE) is an asymmetric key based crypto system that has received much focus that provides fine-grained data access control to data files deployed on the cloud. Here, we present a more proficient and most important type of ABE technique that not only considers the Outsourced ABE construction but also address the issue of revocation in case of user leaving the group or organization; the keys are updated once a specific user is removed from the group, and these updated new keys are shared between the existing users also our system supports the keywo...

Anonymization techniques are enforced to provide privacy protection for the data published on cloud. These techniques include various algorithms to generalize or suppress the data. Top Down Specification in k anonymity is the best generalization algorithm for data anonymization. As the data increases on cloud, data analysis becomes very tedious. Map reduce framework can be adapted to process on these huge amount of Big Data. We implement generalized method using Map phase and Reduce Phase for data anonymization on cloud in two different phases of Top Down Specification

- by RAMAKRISHNA K
- •
- Face, Authentication, Normalization, Fingerprint

Spam Detection is the process to classify text which contains irrelevant or unsolicited messages sent over the internet, typically to a large number of users, for the purposes of advertising, phishing, spreading malware, etc. Text summarization is the technique of converting long text to short. The intention is to make a coherent and fluent summary having only the most points outlined within the document. A USA based machine learning expert which had 13 years of experience and currently teaches people his skills, states his technique has proved to be critical in quickly and accurately summarizing voluminous texts, something which might be expensive and time-consuming if avoided machines. Machine learning models are usually trained to know documents and distil the useful information before outputting the specified summarized texts.

There is much news that reads smuggling of trees like sandal, sagwan etc. The wood from these trees are very costly and are not widely available everywhere. The scope of the project is to provide alerts about changes happening in the forest due to intrusion. The system not only provides data regarding intruder but also helps to monitor forest fire, fall detection as well as pH content of soil. The system sends various alerts regarding to the type of issue occurred. Multiple sensors are used in this system to monitor data. These sensors reduce the extent of danger that may be caused in a forest. This system can prove very helpful for monitoring areas in forests which have such issues.

Time series is a scientific process of determining an ordered sequence of values of a variable within equally spaced time intervals. Mostly this is applied when looking at technical data and its influences on the neighboring surroundings. This type of scientific analysis that can be applied twofold. Firstly, it can be used to obtain a knowledge of the triggering forces and structure that produced the observed data. Additionally, it can be used to fit a model and to predict, monitor the area of interest. This scientific form of analysis can be applied in various sectors so long as the data can be measured over time. The following are some of the applications: Economic and sales forecasting, Crop Yield prediction, Forest cover changes, urbanization, among many other uses. In this analysis, we will focus on time series change detection using image differencing of a classified image and representing the outcome area in a bar graph. The area of study is Seshachalam Hills, Tirupathi an ecological zone in Andhra Pradesh, India.

The Public Distribution System in India is the largest retail system in the world. Major problem in this system are the inefficiency in the targeting of beneficiaries, improve weighing machines used an illegal selling of goods. Automated public ration distributed system aim to replace the manual work in Public Distribution System there by reducing the corruption an illegal selling of stock. This paper gives the review on the E- Ration card system to distribute the grains automatically. The proposed system is used the conventional ration card which is replaced by smart card by using RIFD card. The RFID card redirect to the web of the shop , the required item are selected and payment is done and then item are collected from the machine. In this system, the government has control overall transaction that occurs in the ration shop and all the stock records are updated to the government databases so as to refill the stock with material thereby reducing the corruption.

In today's world women safety is one of the most important issues to be addressed in our country. When a women needs urgent help at the time of harassment or molestation, proper reachability is not present for them. Apart from being aware about the significance of women's safety, it is essential that they are provided with protection during those crucial times. The earlier existing system are helpful in detecting the women's location after the crime has been committed. In this project we will be using the women's handbag in which we will be fixing camera lenses and which will be carried anywhere they go. Whenever she comes in contact with any person outside, an image of that person is taken and the activities of the person can be monitored continuously. If the person behaves normally the image can be of no use and can be deleted. But if the activities of the person varies resulting in any harmful action then our system will detect it and process the captured image and it will send to the police and family members with GPS location tracked from IP address. Thus our project helps in saving the life of a women and safeguarding her in the present situation.

- by IJCSMC Journal
- •
- Mathematics, Information Technology, Technology, Neural Networks

Augmented Reality is the presentation of objects superimposed on the real world view of the environment. It is an innovative technology that allows multidimensional viewing and understanding of concepts. This paper aims to use this concept of Augmented Reality in the field of Education to create an application that generates 3D models of the images embedded in textual materials using the software Unity and Vuforia. The application uses a smartphone’s camera to scan the embedded image of a textbook, e-book or photocopy and generates a 3D working model with live animations as well as on-click functionalities to view various movements of the model by providing user interaction. This application aims to provide an active learning experience to students.

This paper focuses on proposing a system for centralization of the IT infrastructure by building upon the concept of Diskless Booting. The client stations are configured to boot over an existing network using the Network Boot. The Client Station lacks an actual Hard Drive, which is responsible for storing the boot files and other necessary files. It consists of other hardware excluding the Hard Drive such as, RAM, Processor, etc. The network consists of DHCP (Dynamic Host Configuration Protocol) server which assigns IP addresses to several client stations connected. The NIS (Network Information Service) server stores the login credentials of all the users, enabling the users to login from any client station without any restrictions. The NFS (Network File System) server makes the files available for the user, even on the absence of local secondary storage. Security is ensured by SHA (Security Hash Algorithm), which encrypts the sensitive data by creating the hash values. Individual ports and services can be kept secured by using the Firewall service. The open source Cockpit Tool provides a GUI with which the administrator can conveniently carry out several admin-oriented tasks, such as memory management, user management.

- by suriya prasath and +1
- •
- Computer Science, Information Technology, Computer Science Education, Computer Engineering

Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we investigate the discriminative power of colour-based invariants in the presence of large illumination changes between training and test data, when appearance changes due to cast shadows and non-Lambertian effects are significant. Specifically, there are three main contributions: (i) we employ a more sophisticated photometric model of the camera and show how its parameters can be estimated, (ii) we derive several novel colour-based face invariants, and (iii) on a large database of video sequences we examine and evaluate the largest number of colour-based representations in the literature. Our results suggest that colour invariants do have a substantial discriminative power which may increase the robustness and accuracy of recognition from low resolution images.

- by Ognjen Arandjelovic
- •
- Engineering, Electrical Engineering, Electronic Engineering, Computer Science

The world is changing rapidly, so is academics. E-learning has altered the area of academics and education. ICT enabled learning has given ideal services to students by providing any type of content on demand which is proportional to the performance of students. The concentration of learner has been found instinctive; thus there is a need of engaging mind towards course progress with its entirety till the objectives of the course will be achieved. There are several e-learning platforms available as EdX, Udacity, Khan Academy, Alison those have a number of learners registered for various courses. Studies suggest that these platforms suffer from the common problem of learners’ dropping out. Investigations also claim early leaving rate is increasing due to lack of quality of content, distraction factors, learners’ mind change, outdated and succinct information, and some more detraction factors. These issues have been observed on the basis of early leaving rates in various MOOCs. Thus t...

- by Shubham Dubey
- •
- Psychology, Computer Science, Information Technology, Computer Science Education

The primary goal of this thesis is to simulate the causes of human face ageing and to detect skin illnesses. This project combines the capabilities of a Deep Learning model, notably EfficientDet, with the capabilities of a machine learning model and Advanced Computer Vision to identify and locate aging and skin disease. In an uploaded photo there are irregularities which can be detected. The appearance of age-related face changes is determined by a variety of factors. Wrinkles, dark patches, and swollen eyes are all variables to consider. The TensorFlow Objection Detection API is used to investigate the factors. TensorFlow Zoo's EfficientDet model is pre-trained. The proposed models are found to be effective based on the outcomes. Very effective in predicting the indications of ageing in people of all ages. Python was used to implement this project.

The machine learning algorithms are capable of managing multi-dimensional data under the dynamic environment. Despite its so many vital features, there are some challenges to overcome. The machine learning algorithms still requires some additional mechanisms or procedures for predicting a large number of new classes with managing privacy. The deficiencies show the reliable use of a machine learning algorithm relies on human experts because raw data may complicate the learning process which may generate inaccurate results. So the interpretation of outcomes with expertise in machine learning mechanisms is a significant challenge in the machine learning algorithm. The machine learning technique suffers from the issue of high dimensionality, adaptability, distributed computing, scalability, the streaming data, and the duplicity. The main issue of the machine learning algorithm is found its vulnerability to manage errors. Furthermore, machine learning techniques are also found to lack va...

Cloud computing associate the computing and storage resources controlled by different operating systems to make available services such as large-scaled data storage and high performance computing to users. The benefits of low-cost, negligible management (from a user’s perspective), and greater flexibility come with increased security concerns is one of the most crucial aspects among those prohibiting the wide-spread adoption of cloud computing. The data outsourced to a public cloud must need to be secured. This work gives Division and Replication of Data (DROPs) inside the Cloud for Optimal Performance and Security that judicially fragments user files into portions and replicates them at strategic places in the cloud. The division of a files into fragments is achieved based on a given consumer standards such that the individual fragments do not comprise any meaningful facts. The node separation is ensured by the means of the Grid Topology algorithm. To further improve the retrieval time, replicate fragments over the nodes that generate the highest read/write requests. The data encrypted using AES encryption algorithm. Duplication checking is implementing to provide efficient storage and time based access control for secure file access system.

Analyze and generation of automated captions for images is one of the most common problems in artificial intelligence. Existing works use LSTM (Long Short-Term Memory) as recurrent neural network cell to solve this task. After training their deep neural models can generate image caption. But there is an issue, the next predicted word of the caption depends mainly on the last predicted word, rather than image content. In this paper, we present model that can automatically generate image description and is based on a recurrent neural network with modified LSTM cell that has an additional gate responsible for image features. This modification results in generation of more accurate captions. We have trained and tested our model on MSCOCO image dataset by using only images and their captions.

- by RS Global
- •
- Engineering and Computer Science

Data warehouse is used to provide effective results from multidimensional data analysis. The accuracy and correctness of these results depend on the quality of the data. To improve data quality, data must be properly extracted, transformed and loaded into the data warehouse. This ETL process is the key to the success of a data warehouse. In this paper we propose a conceptual ETL framework for an object oriented data warehouse design, the framework is called UCLEAN. This framework takes into account the concept of requirements of the users .The data is extracted from different UML sources and is converted into a multidimensional model. It is then cleaned and loaded in the data warehouse. We validate the effectiveness of the framework through a case study.

Every individual human might have completely different faces; however, their expressions tell us the same story and it notably plays a significant role in extraction of an individual’s emotions and behavior. Music is the purest form of art and a medium of expression, which is known to have a greater connection with a person’s emotions. It has a novel ability to lift one’s mood. This project system focuses on building an efficient music player which works on emotion of user using facial recognition techniques. The facial features extracted will generate a system thereby reducing the effort and time involved in doing it manually. Facial data is captured by employing a camera. The emotion module makes use of deep learning techniques to spot the exact mood relative to that expression. The accuracy of mood detection module in the system for real time footage is above 80%; while for static pictures it is 95 to one hundred percent. Therefore, it brings out higher accuracy relating to time ...

An introductory course on Software Engineering remains one of the hardest
subjects to teach largely because of the wide range of topics the area encompasses.
I have believed for some time that we often tend to teach too many
concepts and topics in an introductory course resulting in shallow knowledge
and little insight on application of these concepts. And Software Engineering
is finally about application of concepts to efficiently engineer good software
solutions.

- by Camilo Vargas
- •
- Business, Business Administration, Computer Science, Software Engineering

Digitalization of money transfer is a must in the present situation of banking operations. Clients have a variety of ways to carry out transactions, such as credit, wiring money, and so forth. However, depositing cash requires the physical presence of the depositor at the bank, and cashier needs to enroll the transaction into the system, which slows down the rate of money deposit and teller's activity. To accelerate the process, banks around the world have to adapt and construct guidelines for a digital deposit. To accurately digitize and transmit deposit slip information from smartphones to the bank, a scheme called 'Automating Data Entry Forms for Banks Using OCR and CNN'. The deposit slip scanner algorithm is based on input from the Smartphone camera.

GPS is in actuality the main answer for outdoor positioning, no unmistakable arrangement has so far risen for indoor positioning notwithstanding the business hugeness. Along these lines, the principal point is to grow ongoing indoor following framework and utilizing cell phone sensors to give dependable and precise indoor localization. Indoor navigation is a vital empowering innovation for application, for example, finding a gathering room in a place of business, security exit amid a crisis or focused on the retail commercial in a shopping center. Utilizing this thought, an application can be made and by methods for that application, we are handling indoor navigation utilizing continuous navigation. The android application gives mindfulness, straightforwardness to discover your direction, commercial and effortlessness. To give solid indoor navigation to business structures like shopping centers, enterprises, universities, hospitals, inns. In this paper, we give an order and arrangement of the current indoor positioning systems and distinguish some conceivable zones of improvements.

The film industry is not only the center of Entertainment but also a huge source of employment and business. Well, famous actors and directors can ensure the publicity of a movie but can’t promise a good IMDB score. We have collected the data available online about these Hollywood movies and their IMDB ratings to create our dataset. After getting the dataset we have incorporated various exploratory analysis techniques and then applied various machine learning algorithms to predict the IMDB rating. Finally, identified the best-fit algorithm which gives the most accurate prediction.

International Journal of Computer Science and Technology (IJCST) is devoted to fields of Computer Science and Technology. The IJCST is a open access peer-reviewed scientific journal published in electronic form as well as print form. The mission of this journal is to publish original contributions in its field in order to propagate knowledge amongst its readers and to be a reference publication.

A large section of World Wide Web is full of Documents, content; Data, Big data, unformatted data, formatted data, unstructured and unorganized data and we need information infrastructure, which is useful and easily accessible as an when required. This research work is combining approach of Natural Language Processing and Machine Learning for content-based classification of documents. Natural Language Processing is used which will divide the problem of understanding entire document at once into smaller chucks and give us only with useful tokens responsible for Feature Extraction, which is machine learning technique to create Feature Set which helps to train classifier to predict label for new document and place it at appropriate location. Machine Learning subset of Artificial Intelligence is enriched with sophisticated algorithms like Support Vector Machine, K – Nearest Neighbor, Naïve Bayes, which works well with many Indian Languages and Foreign Language content’s for classification. This Model is successful in classifying documents with more than 70% of accuracy for major Indian Languages and more than 80% accuracy for English Language.

Dijkstra algorithm, A Search, Greedy Best-first Search, Swarm Search, Breadth-first and Depth-first are some of the popular algorithms today. As a beginner’s step to algorithms and their implementation, this paper demonstrates how the pathfinding algorithm works. Moreover, the user can get a better perception of how different algorithms function and how programming works, in general. By understanding these algorithms, they will also get a basic idea of how to implement various navigation tools. The visualizer comprises a grid page that contains a ‘start node’ and an ‘end node’. The viewer can add various features such as a maze, walls and weights to improve the general outlook and understand how these pathfinding algorithms tackle our day-to-day problems. To build a visualizer, a programmer needs a fair knowledge of front-end programming languages and a good understanding of pathfinding Algorithms.

- by Mohak Mohan and +1
- •
- Computer Science, Information Technology, Computer Science Education, Computer Engineering

Cloud computing is a field which has been fast growing over the last few years. The fact that cloud can provide both computation and storage at low rates makes it popular among corporations and IT industries. This also makes it a very captivating proposition for the future. But in spite of its promise and potential, security in the cloud proves to be a cause for concerns to the business sector. This is due to the out sourcing of data onto third party managed cloud platform. These concerns security also make the use of cloud services not so much flexible. We provide a secure framework to stored data to be securely in the cloud, at the same time allowing operations to be performed on data without compromising of the sensitive parts of the data. A combination of searchable encryption with Partial Homomorphism is proposed.

In recent years, more and more video surveillance devices like drones, CCTV's have been deployed due to an increase in demands related to public security and smart cities. There is a need to overcome the existing drawbacks of post-investigation techniques of video surveillance systems by providing a pre-alert generation system. The video surveillance system has become an important part of the security and protection of modern cities. So we are going to focus on video surveillance by giving video contents containing early fire events detection, suspicious activities and smart parking systems, and crowd estimation. Smart monitoring cameras equipped with intelligent video analytics techniques can monitor and pre-alert systems by capturing suspicious activity and events. Our work is based on deep learning techniques for video analysis with better performance and event detection with the advantages of alert generation.

- by Mukul Borole and +1
- •
- Computer Science, Information Technology, Computer Science Education, Computer Engineering

CampusERP is an implementation of an ERP System, which will be used primarily in educational institutes such as Engineering Colleges. There will be both Web and Flutter Application for Centralized Management of Educational Institutes. Main Goal of the project is to digitize day to day activities of an Educational Institute, further reducing load on teaching as well as non-teaching staff. This project will have primarily two main Users that would be Teacher and Student. The complete system revolves around these two users. Every module that is available in this project is some way or other beneficial to these two types of users. This project has two main modules that is Student Central Platform and Teacher Central Platform which act as base for all the other modules present. Non-primary modules include Library Management System, Student Attendance System, Online Exam & Assignment Portal, Bus Tracking System, Newsletters & Advertisement, Custom APIs, Performance Analysis, etc.

- by Aakash Mole and +1
- •
- Computer Science, Information Technology, Computer Science Education, Computer Engineering

Internet of Things (IoT) plays a important role in connecting the over all environmental things to the network and it is easy to access those un-internet things from any remote location. It’s unavoidable for the people to update with the increase technology. [1] And generally people are facing problems on parking vehicles in parking slots in a parking area. In this study we plan a Smart Parking System (SPS) which enables the user to find the nearest parking area and gives availability of parking slots in that respective parking area. It mainly concentrates on reducing the time in finding the parking area and also it avoids the unnecessary travelling through filled parking areas in a parking area. Thus it decreases the fuel consumption which in turn reduces carbon footprints in an atmosphere.

— Nowadays, the usage of e-commerce is growing day by day, so online users are also rising. Every user spends their most of the time on e-commerce websites and their behavior is different from one another. E-commerce has become very competitive so, knowing user's behavior has become prior concern. Most of the e-commerce platforms are using either content based or collaborative approach to predict user behavior. Collaborative approach has become obsolete. Many e-commerce websites mainly rely on the content based approach. But for better recommendation, it is important to make use of the user data as well. We propose design and implementation of hybrid system by K-mean algorithm and Hidden Markov Model. Machine learning regression algorithms are used to fetch user's priorities and clustering of data through K-mean algorithm.

Worldwide Interoperability for Microwave Access (WiMAX) networks were expected to be the main Broadband Wireless Access (BWA) technology that provided several services such as data, voice, and video services including different classes of Quality of Services (QoS), which in turn were defined by IEEE 802.16 standard. Scheduling in WiMAX became one of the most challenging issues, since it was responsible for distributing available resources of the network among all users; this leaded to the demand of constructing and designing high efficient scheduling algorithms in order to improve the network utilization, to increase the network throughput, and to minimize the end-to-end delay. In this study, we presenedt a simulation study to measure the performance of several scheduling algorithms in WiMAX, which were Strict Priority algorithm, Round-Robin (RR), Weighted Round Robin (WRR), Weighted Fair Queuing (WFQ), Self-Clocked Fair (SCF), and Diff-Serv Algorithm.

Dynamically changing background ("dynamic background") still presents a great challenge to many motion-based video surveillance systems. In the context of event detection, it is a major source of false alarms. There is a strong need from the security industry either to detect and suppress these false alarms, or dampen the effects of background changes, so as to increase the sensitivity to meaningful events of interest. In this paper, we restrict our focus to one of the most common causes of dynamic background changes: that of swaying tree branches and their shadows under windy conditions. Considering the ultimate goal in a video analytics pipeline, we formulate a new dynamic background detection problem as a signal processing alternative to the previously described but unreliable computer vision-based approaches. Within this new framework, we directly reduce the number of false alarms by testing if the detected events are due to characteristic background motions. In addition, we introduce a new dataset suitable for the evaluation of dynamic background detection. It consists of real-world events detected by a commercial surveillance system from two static surveillance cameras. The research question we address is whether dynamic background can be detected reliably and efficiently using simple motion features and in the presence of similar but meaningful events such as loitering. Inspired by the tree aerodynamics theory, we propose a novel method named local variation persistence (LVP), that captures the key characteristics of swaying motions. The method is posed as a convex optimization problem whose variable is the local variation. We derive a computationally efficient algorithm for solving the optimization problem, the solution of which is then used to form a powerful detection statistic. On our newly collected dataset, we demonstrate that the proposed LVP achieves excellent detection results and outperforms the best alternative adapted from existing art in the dynamic background literature.

- by Ognjen Arandjelovic
- •
- Engineering, Electrical Engineering, Electronic Engineering, Computer Science

A vast fraction of the population of India considers agriculture as its primary occupation. The production of crops plays an important role in our country. Bad quality crop production is often due to either excessive use of fertilizer or using not enough fertilizer. The proposed system of IoT and ML is enabled for soil testing using the sensors, is based on measuring and observing soil parameters. This system lowers the probability of soil degradation and helps maintain crop health. Different sensors such as soil temperature, soil moisture, pH, NPK, are used in this system for monitoring temperature, humidity, soil moisture, and soil pH along with NPK nutrients of the soil respectively. The data sensed by these sensors is stored on the microcontroller and analyzed using machine learning algorithms like random forest based on which suggestions for the growth of the suitable crop are made. This project also has a methodology that focuses on using a convolutional neural network as a pr...