Search

With the rapid development of internet in recent years, the networks are growing in size every day. As the networks are growing day by day, the task of managing the networks, effectively and efficiently also become a matter of concern. In case of traditional networks, due to their static nature, it is difficult to monitor the entire network efficiently and so now focus started shifting towards a new architecture that is Software defined networks. Being programmable in nature, SDN overcame a lot of shortcomings of traditional networks, however, the security of the network still remains the point of concern. The controller which is considered as the brain of SDN architecture can be taken as the prime target by attackers in order to attack the entire network. Therefore, in order to provide a robust mechanism for securing the networks, machine learning based intrusion detection systems came into picture. The proposed survey will provide an overview of software defined networks, intrusion detection systems and machine learning algorithms. The performance of machine learning algorithms that have been used recently by the researchers are compared. Also, this paper has highlighted the various challenges.

White blood cells (WBCs) are also called as leukocyte which is a significant component of blood that covers 1% of the total blood, protect us from numerous types of illness and other diseases. The automated classification of different types of leukocytes is very significant since each component have some designated functions in the human body and also the manual classification by skilled medical professionals is a tedious and erroneous task. In this work an automated approach based on transfer learning methodology is used for the detection and classification of leukocytes into four types such as Lymphocyte, Monocyte, Eosinophil and Neutrophil since there are limited numbers of images in the dataset. The methodology adopted in this work is a combination of deep learning and machine learning in which the features are extracted from the segmented nucleus of leukocyte by VGG16 deep learning model which is trained and evaluated using K-Nearest Neighbor (KNN) machine learning algorithm which provided an accuracy of 82.35% which is better when compared to Naive Bayes Classifier.

Data pipelines play an important role throughout the data management process. It automates the steps ranging from data generation to data reception thereby reducing the human intervention. A failure or fault in a single step of a data pipeline has cascading effects that might result in hours of manual intervention and clean-up. Data pipeline failure due to faults at different stages of data pipelines is a common challenge that eventually leads to significant performance degradation of data-intensive systems. To ensure early detection of these faults and to increase the quality of the data products, continuous monitoring and fault detection mechanism should be included in the data pipeline. In this study, we have explored the need for incorporating automated fault detection mechanisms and mitigation strategies at different stages of the data pipeline. Further, we identified faults at different stages of the data pipeline and possible mitigation strategies that can be adopted for reducing the impact of data pipeline faults thereby improving the quality of data products. The idea of incorporating fault detection and mitigation strategies is validated by realizing a small part of the data pipeline using action research in the analytics team at a large software-intensive organization within the telecommunication domain.

In this paper, a broadband substrate integrated waveguide (SIW) cavity-backed irregular shaped slot antenna is proposed. The irregularly shaped slot whose dimensions have been optimized using an evolutionary algorithm called particle swarm optimization (PSO) by fixing its position has been proposed to achieve the broadband response. This antenna maintains the characteristics of low profile, unidirectional radiation while enhancing the bandwidth. The cavity size of the antenna is designed such that it generates two modes (TE 110 and TE 120 ) in the desired frequency range. The shape of the slot aids to couple the two obtained modes in a vicinity region and thus increasing the effective bandwidth.

Hidden or Latent fingerprints are unclear images. These fingerprints are mostly blotted and imbricated. They are low-quality image files with an imprecise rim network. These fingerprints are normally witnessed in the crime arena, therefore improving the quality of these images acts as an essential aspect in finding and disclosing of criminals. After enhancing the fingerprints it becomes easy to identify and match the features of the original image and preprocessed image. So, this plays a vital role by acting as a great witness for the identification of a person. Here, an image is taken as an input and processed. Segmentation is done to compare the detailed features of the fingerprints. After the segmentation process, fingerprints are tried to match. Here, the line-based feature extraction algorithm is used for identifying the detailed features of the fingerprint. Also, we are using minutiae matching algorithm to exactly match the fingerprints. Existing methods could bring only seventy to eight percentage of accuracy. In the proposed system, we are trying to get high accuracy rates than the existing techniques.

SmartCity projects growing with the concept of IoT (Internet of Things) and WSN (Wireless Sensor Network) helps to manage assets and resources efficiently. Nowadays water is getting polluted due to industrialization, use of fertilizers and pesticides, urban development, etc. So we should have a reliable water quality monitoring system. The proposed system based on IoT and WSN gives real-time data of water quality so that the authority can manage and conserve the valuable water resources more effectively. With IoT & WSN, smart monitoring and management is attainable. It helps create more efficient city services and to keep citizens informed. The existing systems of water quality monitoring uses wireless technologies which are short range and much power consuming, which are not suited for sensors nodes in WSN. The proposed system presents a low cost, low power, long range and scalable approach for water quality monitoring using LoRa module based on LoRaWAN protocol which is Low-Power Wide Area Network (LPWAN) technology, which is much more efficient than many existing systems. The design of the proposed system includes integrating sensors to the microcontroller, wireless LoRa module for transmitting and receiving sensor values, and ThingSpeak IoT platform for examining and visualizing water quality sensor values which have been uploaded.