Search

Medical imaging is an important field of research used for the diagnosis and prediction of diseases. Melanoma is considered as one of the hazardous types of cancers and if detected in early stages, it can be cured easily using simple methods. By using clinical examination, it is difficult to predict melanoma at early stages with high accuracy. This paper proposes a novel strategy for the detection of melanoma by skin malignant growth and also proposes a method for early prediction. The proposed system is based on Deep learning algorithm for the prediction of the affected area and type of melanoma using the metrics precision, accuracy, recall and F1 score. The pre-processing methods are utilized for enhancing the image. The Active contour segmentation process differentiates the infected regions from the healthy skin regions. SOM and CNN classifiers are used for the process of classification of melanoma. A randomly chosen sample of 500 images are taken, 350 images are used as the training dataset and 150 images are used as a testing dataset, for which the proposed system showed high efficiency in the detection of melanoma with a greater accuracy of 90%.

Massive MIMO or Very Large Scale MIMO is a key technology in recent 5G and beyond 5G wireless standards to attain high speed, secure, error free communication and accessibility among trillions of users. All the above is possible with increase in complexity of the massive MIMO system. To improve massive MIMO system performance, efficient linear precoding algorithms are used at the downlink. The complexity of linear precoding algorithms lies on the hardware demanding large size matrix inversion module. In this paper, the performance of various approximations such as Neumann series, Conjugate Gradient (CG) and Preconditioned Conjugate Gradient (PCG) algorithms that simplify the matrix inversions of linear precoding algorithms are discussed. The simulations are carried out under various propagation scenarios like rural macro cell and urban micro cell.

With an expanding number of information focused on assaults on cloud-based workers, the hope is to actualize a blockchain backend so as to build security and diminish weaknesses. A customary cloud worker is unified consequently powerless to being a solitary purpose of disappointment. Utilizing certificateless cryptography with blockchain as a stage, the backend becomes decentralized wiping out the previously mentioned issue. Information would be put away in distributed hash tables (DHT) while the pointers to the DHT would be put away in the blockchain. Utilizing this technique can fulfill the three fundamental boundaries of certifiability, transparency, and availability. Edge computing would be actualized to deal with the IoT information at the organization edge rather than a distant cloud. Clients at that point do not have to stress over unapproved endeavors to get to information as vindictive endeavors can undoubtedly be identified. The whole framework is then discernible and responsible.

Advancement in technology has made it possible to reduce the huge workload for humans with the help of robots. The accuracy and reliability of the robots are major reasons for their employment in various fields. They can also be programmed to imitate the functioning of human arms. This will be of great help for disabled people as it will assist them in writing. With the help of advanced techniques like speech recognition, the data collected from the microphone can be detected and then sent to the robot with dual-axis writing control through a microcontroller. The pen that is integrated with the robotic arm will be employed for writing as a disabled person dictates. The proposed system is cost-effective and is easy to use for disabled people.

This paper uses model predictive control that is superior technique to handle sensorless speed control of induction motor driven by a solar system. The proposed system, solar photovoltaic (PV) array connected with voltage source inverter (VSI) and predictive control system, is MRAS. A MPPT algorithm based on perturbation and observation is used for harnessing the full power from a PV series. System predictive control strategy is a predictive control approach to standard optimization. For less dependency on model parameters, MPC can achieve sufficient control efficiency and has been widely used in process control systems. MRAS speed estimation method was implemented to achieve sensorless operation to boost the device reliability and cost reduction of hardware. In MATLAB/Simulink environment, the desired configuration is modeled and simulated.

An immense number of the applications are available that necessitate numerous system input data to bring about the wanted or desired results or system outputs. In this case, in case of any data that is lost or absent it announces a huge amount of favoritism or unfairness in the spectrum of the output produced from within the method. Here, we are presenting one algorithm that aids in creating more precise anatomically credible imageries of high dimensions according to acquired medical brain scans having a large gap between the spacing of two corresponding inner image slices. Even in spite of the fact that vast databases containing anatomical images which store a copious amount of data, anatomical procurement parameters produce a result in the form of scattered scans that tend to lose a large part of the anatomical image. The main ambition of this system is to be able to apply previously developed algorithms that were developed for fine resolution scans used for research purposes, to be applied on poorly sampled images. The algorithm alters the problem of anatomical image imputation to an image to image illustration translation task over multiple domains for the purpose that the generator part and the discriminator part of the network is able to recover the lost data from the remaining pure and unsoiled data accumulation. In this envisioned form of the system in place of producing common and general results, the generator part of the network trains itself to learn to generate a counterfeit sample result that is specifically parameterized along with particular conditions. Our goal is to enable application of existing algorithms that were originally developed for high resolution research scans to significantly under-sampled scans. The models we introduce capture fine-scale anatomical similarity across subjects in clinical image collections and use it to fill in the missing data in scans with large slice spacing with good quality as suitable for medical image-based applications.

Wireless sensor networks (WSNs) are used for handling a large amount of data despite their serious limitations such as delay and energy consumption. The constraints become a serious issue when we deploy many nodes for the purpose of data handling. WSNs can be made energy efficient by means of Energy-Efficient Low Duty Cycle (ELDC) protocol which is an artificial neural network-based energy-efficient and robust routing scheme used in wireless sensor networks. ELDC is an extension of energy-efficient unequal clustering and energy-efficient multiple distance-aware clustering protocols. It is a dynamic group-based routing protocol which makes multi-hop strategy for communication. In ELDC there is a large amount of packet loss and load balance is not provided which reduces the lifetime of the network. Therefore, we suggest the use of General Self-Organization Tree-Based Energy Balance (GSTEB) protocol to provide load balance. It is a dynamic tree-based routing protocol which minimizes the energy consumption and has a minimum or no packet loss and data compression is also provided to improve the performance. It also prevents the entry of unauthorized node containing malicious data and the packet delivery ratio is also high. The proposed system greatly improves the lifetime of the network. The applications of our paper include environmental monitoring, air traffic control, surveillance, etc.

Emerging 5G technology is largely supported by the base station signal processing techniques such as precoding. Precoding combines the input signals in a predefined way and deliver them in a right proportion to the multiple antenna elements. Such precoding algorithms are crucial for the design of the emerging 5G technology; massive MIMO system. In this paper, the performance of various linear precoding algorithms such as Zero Forcing (ZF), Minimum Mean Square Error (MMSE) and Conjugate Gradient (CG) based precoding are analyzed in terms of Bit Error Rate (BER) and achievable sum-rate. The results are analyzed under various channel conditions such as rural, sub urban and urban. The above algorithms are tested for MIMO-OFDM system. OFDM system simulated here uses 52 subcarriers and a Base Station equipped with more than 100 antennas serving multiple users simultaneously. The channel models are stochastic channels simulated using WINNER II modeling.

In this paper, ResNet a Convolutional Neural Network for detecting and diagnosing the lung disease Covid-19 pneumonia infection automatically. For identifying, Chest X-rays are widely used for diagnosis of pneumonia disease which affects the lungs. This paper provides an approach to detect and diagnose Covid-19 pneumonia and classify the chest X-ray images into two classes either Covid-19 pneumonia or normal utilizing CNN. This is done by training the CNN to differentiate between the normal and pneumonia chest X-ray images using a deep learning platform Pytorch. Image preprocessing technique has been applied in order to enhance the image accuracy. Python and OpenCV have been used.

Crop production and crop growth monitoring can be improved using agricultural drone i.e., Unmanned Aerial Vehicle (UAV). Nowadays, due to population growth drones helpful for agriculture become most efficiently. In this paper, by using various sensors and Internet of Things applied in drone for crop production improving, UAV using Raspberry Pi 3B module to displayed in the field with advanced solutions.

Computational complexity and motion estimation time are the main factors which affect the performance of video codec for real time applications. In block matching motion estimation algorithm, search patterns have more effect on searching speed and distortion performance. The major block matching algorithm search types are full search and fast search. The full search will search all points of the reference frame and the fast search will use only less search points. There are many algorithms in the literature and in which the hybrid algorithms outperforms the other existing fast motion estimation algorithms. In this paper, a new hybrid search algorithm with novel cross diagonal-hexagon search pattern is proposed for fast block motion estimation. It uses a novel search patterns in both global and local search is performed. Compared to the existing algorithms, the proposed algorithm uses an average of 8.791 search points, resulting in reduced computational complexity and faster processing with better video coding quality. The proposed algorithm is implemented in Cyclone IV E (EP4CE115F29C7) and a better performance improvement in terms of area and speed is achieved.

Satellite image enhancement and restoration is scientifically possible by applying image processing and other soft computing techniques. In this study, a comparison of various existing satellite im...

In this letter, a new satellite image contrast enhance- ment technique based on the discrete wavelet transform (DWT) and singular value decomposition has been proposed. The tech- nique decomposes the input image into the four frequency sub- bands by using DWT and estimates the singular value matrix of the low-low subband image, and, then, it reconstructs the en- hanced image by applying inverse DWT. The technique is com- pared with conventional image equalization techniques such as standard general histogram equalization and local histogram equalization, as well as state-of-the-art techniques such as bright- ness preserving dynamic histogram equalization and singular value equalization. The experimental results show the superiority of the proposed method over conventional and state-of-the-art techniques.

Traffic is the most critical problem in metropolitan cities. Traffic control becomes more necessary to provide problem-less, peaceful driving and pollution-less life to people. The work is designed to develop a density based dynamic traffic signal system. The signal timing changes automatically on sensing the traffic density at the junction. The traffic system is structured with a camera. The image captured by the camera is processed in order to calculate the number of vehicles present in the image. The camera also identifies the siren and allows the green light for emergency vehicles like ambulance, fire engine etc. In this paper, masking algorithm is used to process the image and find the vehicle count on the road. This algorithm shows only the required portion of the image and masks the unnecessary details. The visual basic programming is used to control the glowing time of traffic light based on the vehicle count on the road. The Arduino controller is a single board microcontroller used for instructing the LED to glow. This method can be used to detect road accidents and identify violations of the spiral movements of cars. The whole system when installed on road, provides a way for easy traffic clearance for emergency vehicles without a need of sergeant.

This paper proposes about motion estimation in H.264/AVC encoder. Compared with standards such as MPEG-2 and MPEG-4 Visual, H.264 can deliver better image quality at the same compressed bit rate or at a lower bit rate. The increase in compression efficiency comes at the expense of increase in complexity, which is a fact that must be overcome. An efficient Co-design methodology is required, where the encoder software application is highly optimized and structured in a very modular and efficient manner, so as to allow its most complex and time consuming operations to be offloaded to dedicated hardware accelerators. The Motion Estimation algorithm is the most computationally intensive part of the encoder which is simulated using MATLAB. The hardware/software co-simulation is done using system generator tool and implemented using Xilinx FPGA Spartan 3E for different scanning methods.

The progress of science and technology demands multimedia applications to be realized on embedded systems as it involves transfer of large amounts of data. Compared with standards such as MPEG-2, MPEG-4 Visual, H.264 can deliver better image quality at the same compressed bit rate or at a lower bit rate. The increase in compression efficiency and flexibility come at the expense of increase in complexity, which is a fact that must be overcome. Therefore, an efficient Co-design methodology is required, where the encoder software application is highly optimized and structured in a very modular and efficient manner, so as to allow its most complex and time consuming operations to be offloaded to dedicated hardware accelerators. This paper provides an overview of the features of H.264 and surveys the emerging studies related to new coding features of the standard.