Asian Journal of Convergence in Technology
Not a member yet
868 research outputs found
Sort by
Efficient image retrieval using multi neural hash codes and bloom filters
Get PDFThis paper aims to deliver an efficient and modified approach for image retrieval using multiple neural hash codes and limiting the number of queries using bloom filters by identifying false positives beforehand. Traditional approaches involving neural networks for image retrieval tasks tend to use higher layers for feature extraction. But it has been seen that the activations of lower layers have proven to be more effective in a number of scenarios. In our approach, we have leveraged the use of local deep convolutional neural networks which combines the powers of both the features of lower and higher layers for creating feature maps which are then compressed using PCA and fed to a bloom filter after binary sequencing using a modified multi k-means approach. The feature maps obtained are further used in the image retrieval process in a hierarchical coarse-to-fine manner by first comparing the images in the higher layers for semantically similar images and then gradually moving towards the lower layers searching for structural similarities. While searching, the neural hashes for the query image are again calculated and queried in the bloom filter which tells us whether the query image is absent in the set or maybe present. If the bloom filter doesn't necessarily rule out the query, then it goes into the image retrieval process. This approach can be particularly helpful in cases where the image store is distributed since the approach supports parallel querying
Security and Privacy Issues of Medical Systems in Wireless Sensor Networks: A Survey
Get PDFFor decades, the wireless medical sensor network (WMSN) has shown great prospective in refining health care quality. The vast ranges of medical applications that lead to computer-assisted treatment from all over the health monitoring are based on WMSNs technology. These applications introduce emergency medical response systems with its numerous advantages and facilities. However, these technologies have privacy and security challenges that need to be analyzed to make it preferable and socially acceptable. This survey paper depicts the current state-of-the-art wireless sensor network (WSN) technologies being used in medical applications. In this paper, we have focused on system architecture, routing, security, and privacy issues with various medical applications from various research work
Armed and Partially Covered Face Related Robberies Alerting System Using Computer Vision
Get PDFRobbery is the completed or attempted theft, directly from a person, of property or cash by force or threat of force, with or without a weapon, and with or without injury. Armed robbery is a serious crime that can traumatically that emotionally and mentally profoundly traumatize its victims. Armed robbery is usually motivated by a desire to acquire money, which is then commonly used to buy drugs. [1] However, some armed robbers are associated with the crime. [2] In the current decade, armed robbery is one of the major issues in society. According to Statista research department, there were more than 0.25 million armed robberies happened in the USA in 2018. [3] Moreover, these robberies accounted for an estimated $438 million in losses. [2] . Moreover is the USA there were more than 10000 murders, victims, by weapons in 2018. [4]When analyzing most of these armed robberies have happened locations are Banks, Gas or Service stations, and commercial houses in the USA. To monitor and act accordingly to the issue still, there is no proper method. Present in most places there are several security officers to monitor these robberies within 24H using CCTV cameras.
In this research, the authors propose a novel approach to prevent this issue using a computer vision-based armed robberies alerting system. Here this system is able to detect the weapons of the robbers. Since most of the time robbers come with partially covered faces. In this research, the proposed system is able to detect partially covered faces also. When the system identified weapons or a partially covered face in a bank or a commercial house, it will send an alert by notifying the risk of the robbery to the in house security officers and relevant authorities. The proposed solution used an object detection model and a facial landmark identification based approach to detect robbers. Because of this system, no longer the security officers need to monitor CCTV cameras by themselve
Road Accident Analysis and Arduino Based Alert System
Get PDFOver the last two decades, Mumbai, and subsequently India, has seen a huge increase in the number of vehicles on the road. Suddenly, the demand and popularity of the private transport has raced ahead of the public transport by miles. The number of vehicles on the road is always directly proportional to the road accidents and injuries. As a result of the former increasing every year, it is but natural that the latter too, has gone up
Exigency of Vehicular Accidents Detection through Paging using GSM Technology
Get PDF Nowadays, the rate of vehicular accidents is increasing at a tremendous rate. There are many causes of road accidents and fatalities. One of the important causes of the increasing fatality rate is the lack of immediate medical attention. This problem can be solved if immediate medical attention can be provided to the accident victims. There are a lot of existing algorithms that were designed for this purpose. In this paper, an algorithm is proposed, which utilizes cellular communication paging service to notify regarding the accidents. This process is mobile device independent as this setup is fixed to the car and uses the GSM module for requesting medical emergency
An Innovation in Corona Charging of Electrets
Get PDFAn innovation in corona charging of electrets of polymer films has been adopted in locally designed and fabricated corona charging set up by replacing the regular high voltage DC power supply with a light, portable handy 3V-6V DC to DC 400kV boost step-up power module high voltage generator. Polymer film electrets of polyethylene transparency film have been corona charged using this innovative setup. The measurements were done and the results have been analyzed in the light of cited literature to show the effectiveness and advantage of the innovation
Early Detection of Cardiovascular Disease in Patients with Chronic Kidney Disease using Data Mining Techniques
Get PDF A constant obstacle for doctors is the high prevalence of cardiovascular disease (CVD) in patients with chronic kidney disease (CKD). Increasing efforts have been made to jointly treat patients with heart and kidney disease, as shown by an increasing number of basic research and clinical investigations concerning CVD in CKD. Typical risk factors for CVD are common in CKD, such as age, blood pressure (bp), hypertension (htn), and blood sugar (sg). Standard risk factors tend to be the major contributors to CVD in patients with mild to moderate CKD. However, in patients with advanced CKD, non-traditional CKD-specific risk factors (e.g. Potassium level in blood) are more prevalent than in the general population, contributing, in addition to traditional risk factors, to the high burden of CVD in CKD. However, in patients with CKD, CVD often remains underdiagnosed and undertreated. Nevertheless, CVD still remains under control and care in patients with CKD. Researchers in this paper aims to predict the probability of CVD from CKD by using various popular data mining techniques and definitively propose a decision tree and by using Random Forest analysis to test its specificity and sensitivity to achieve concrete results with sufficient precision
Multi-object Detection in Night Time
Get PDFThis paper discusses the work on detecting multi-objects such as person and car in thermal image captured during night time using deep learning architecture. Thermal images are superior to the visible images when it comes to the amount of useful information required to detect the objects during night time. Thermal imager uses radiation emitted by the objects to create an image and improve the visibility of objects in a dark environment. Contrast to that, visible image does not provide useful information in darkness. Hence, it is better to use thermal images to detect objects present in darkness. The state-of-the-art, Yolo-v3, deep learning convolutional neural network model is the latest version of the Yolo model in which the feature extraction layer contains a much deeper network. The results of detecting person and car in the thermal images obtained by the proposed model are compared with the results of Yolo- v3. Experimental results show that there is a significant improvement in detecting person and car in the thermal images in terms of mean average precision (mAP) using the proposed method
Real time Face Detection
Get PDFFace detection puts forth a challenging problem in the field of Computer Vision. Detecting faces in real time have many applications especially in the safety and security domain. The primary aim of Face detection algorithms is to detect faces in an image or in a video stream successfully so that they could be further used for applications such as Face recognition. Object detection systems developed traditionally have had a lot of success in detecting objects such as humans, cars, buildings etc. but real time face detection presents a new challenge. In this paper, we provide efficient and robust face detection algorithms which adapt to real-world situations like the face being in poor light conditions, multiple faces in a window, pose, different orientations, varied expressions, to detect faces with maximum accuracy
Model Predictive Control of Z Source Inverter : Formulation & Simulation
Get PDFThis paper presents Model Predictive Control (MPC) of impedance-source (commonly known as Z-source) inverter in a three phase network. The Z-source converter employs a unique impedance circuitry to couple the converter main circuit to the power source, thus employing unique features that cannot be obtained in the traditional voltage-source and current-source inverters where a capacitor and inductor are used respectively. A typical model for a three phase ZSI using balanced load is developed, where MPC due to its feedback control algorithm, predicted the future output current across the load and solved an optimization problem with a view to selecting the optimal control. The quality of output waveform has been analysed by maintaining the total harmonic distortion (THD) at an optimum level. Moreover, an inverse relationship between THD and Switching frequency is also noted. In addition, inductor current & capacitor voltage has also been tracked and effect on THD is analyzed by changing values in source side inductor & resistor