Identification of Anomaly Scenes in Videos Using Graph Neural Networks

Generally, conventional methods for anomaly detection rely on clustering, proximity, or classification. With the massive growth in surveillance videos, outliers or anomalies find ingenious ways to obscure themselves in the network and make conventional techniques inefficient. This research explores the structure of Graph neural networks (GNNs) that generalize deep learning frameworks to graph-structured data. Every node in the graph structure is labeled and anomalies, represented by unlabeled nodes, are predicted by performing random walks on the node-based graph structures. Due to their strong learning abilities, GNNs gained popularity in various domains such as natural language processing, social network analytics and healthcare. Anomaly detection is a challenging task in computer vision but the proposed algorithm using GNNs efficiently performs the identification of anomalies. The Graph-based deep learning networks are designed to predict unknown objects and outliers. In our case, they detect unusual objects in the form of malicious nodes. The edges between nodes represent a relationship of nodes among each other. In case of anomaly, such as the bike rider in Pedestrians data, the rider node has a negative value for the edge and it is identified as an anomaly. The encoding and decoding layers are crucial for determining how statistical measurements affect anomaly identification and for correcting the graph path to the best possible outcome. Results show that the proposed framework is a step ahead of the traditional approaches in detecting unusual activities, which shows a huge potential in automatically monitoring surveillance videos. Performing autonomous monitoring of CCTV, crime control and damage or destruction by a group of people or crowd can be identified and alarms may be triggered in unusual activities in streets or public places. The suggested GNN model improves accuracy by 4% for the Pedestrian 2 dataset and 12% for the Pedestrian 1 dataset compared to a few state-of-the-art techniques.     

Effect of temperature and frequency on the dielectric properties of cellulose nanofibers from cotton

The present work has been carried out to evaluate the dielectric properties and ac-electrical conductivity of cellulose nanofibers. The cellulose nanofibers (CNF) described in this work are the ones extracted from cotton via a simple acid hydrolysis method and are characterized with X-ray diffraction analysis (XRD), scanning electron microscopy (SEM), transmission electron microscopy (TEM), Fourier transform infrared spectroscopy (FTIR), and UV–Visible diffuse reflectance spectroscopy. The optical band gap of CNF found out using the Kubelka–Munk plot is 3.30 eV. The dielectric constant, dielectric loss, and ac-electrical conductivity of the prepared CNF have been investigated in the temperature range from 30 °C to 300 °C and in the frequency range from 50 Hz to 5 MHz. The synthesized system exhibits a higher dielectric constant value for all temperatures in the low-frequency (0.1 kHz) region and a frequency-independent behavior above 10 kHz. In the high-frequency region, the dielectric constant is independent of temperature. Also, the study shows that the conductivity increases with increasing frequency and temperature. The maximum values of ac-conductivity at room temperature (30 °C) and high temperature (300 °C) are found to be 4.58?×?10^–5 S/cm and 2.26?×?10^–4 S/cm, respectively. In brief, the studies point to the application potential of CNF for future flexible electronics.

     

Cloud Data Center Selection Using a Modified Differential Evolution

The interest in selecting an appropriate cloud data center is exponentially increasing due to the popularity and continuous growth of the cloud computing sector. Cloud data center selection challenges are compounded by ever-increasing users’ requests and the number of data centers required to execute these requests. Cloud service broker policy defines cloud data center’s selection, which is a case of an NP-hard problem that needs a precise solution for an efficient and superior solution. Differential evolution algorithm is a metaheuristic algorithm characterized by its speed and robustness, and it is well suited for selecting an appropriate cloud data center. This paper presents a modified differential evolution algorithm-based cloud service broker policy for the most appropriate data center selection in the cloud computing environment. The differential evolution algorithm is modified using the proposed new mutation technique ensuring enhanced performance and providing an appropriate selection of data centers. The proposed policy’s superiority in selecting the most suitable data center is evaluated using the CloudAnalyst simulator. The results are compared with the state-of-arts cloud service broker policies.     

A Zeolitic-Imidazole Frameworks-Derived Interconnected Macroporous Carbon Matrix for Efficient Oxygen Electrocatalysis in Rechargeable Zinc–Air Batteries

Nanostructures derived from zeolitic-imidazole frameworks (ZIFs) gain much interest in bifunctional oxygen electrocatalysis. However, they are not satisfied well for long-life rechargeable zinc–air batteries due to the limited single particle morphology. Herein, the preparation of an interconnected macroporous carbon matrix with a well-defined 3D architecture by the pyrolysis of silica templated ZIF-67 assemblies is reported. The matrix catalyst assembled zinc–air battery exhibits a high power density of 221.1 mW cm⁻² as well as excellent stability during 500 discharging/charging cycles, surpassing that of a commercial Pt/C assembled battery. The synergistic effect from the interconnected macroporous structure together with abundant cobalt–nitrogen–carbon active sites justify the excellent electrocatalytic activity and battery performance. Considering the advanced nanostructures and performance, the as-synthesized hybrid would be promising for rechargeable zinc–air batteries and other energy technologies. This work may also provide significant concept in the view of electrocatalysis design for long-life battery.     

A NEW APPROACH FOR THE INCREMENTAL DEVELOPMENT OF RETRIEVAL FUNCTIONS FOR CBR

We present a new approach to the effective development of complex retrieval components for case-based reasoning systems (CBR). Our approach goes beyond the traditional CBR approach by allowing an incremental refinement of an existing retrieval knowledge base during routine use of the system. The refinement takes place through a direct expert-system interaction while the expert is accomplishing their given tasks. We lend ideas from ripple-down rules (RDR), a proven method for the very effective and efficient acquisition of classification knowledge during the routine use of a knowledge-based system (KBS).

In our approach the expert is only required to provide explanations of why, for a given problem, a certain case should be retrieved. Incrementally a complex retrieval knowledge base as a composition of many simple retrieval functions is developed. This approach is effective with respect to both the development of highly tailored and complex retrieval knowledge bases for CBR as well as providing an intuitive and feasible approach for the expert. The approach has been implemented in our CBR system MIKAS (Menu construction using an Incremental Knowledge Acquisition System) that allows to automatically construct a menu that is strongly tailored to the individual requirements and food preferences of a client.     

Adjustable SAD matching algorithm using frequency domain

Fast Fourier transforms (FFTs) which are O(N logN) algorithms to compute a discrete Fourier transform (DFT) of size N have been called one of the ten most important algorithms of the twentieth century. However, even though many algorithms have been developed to speed up the computation the sum of absolute difference (SAD) matching, they are exclusively designed in the spatial domain. In this paper, we propose a fast frequency algorithm to speed up the process of (SAD) matching. We use a new approach to approximate the SAD metric by cosine series which can be expressed in correlation terms. These latter can be computed using FFT algorithms. Experimental results demonstrate the effectiveness of our method when using only the first correlation terms for block and template matching in terms of accuracy and speed. The proposed algorithm is suitable for software implementations and has a deterministic execution time unlike the existing fast algorithms for SAD matching.

Modeling and simulation of photovoltaic (PV) system during partial shading based on a two-diode model

This paper proposes accurate partial shading modeling of photovoltaic (PV) system. The main contribution of this work is the utilization of the two-diode model to represent the PV cell. This model requires only four parameters and known to have better accuracy at low irradiance level, allowing for more accurate prediction of PV system performance during partial shading condition. The proposed model supports a large array simulation that can be interfaced with MPPT algorithms and power electronic converters. The accurateness of the modeling technique is validated by real time simulator data and compared with the three other types of modeling, namely Neural Network, P&O and single-diode model. It is envisaged that the proposed work is very useful for PV professionals who require simple, fast and accurate PV model to design their systems.     

Analysis and design of a high efficiency bidirectional DC–DC converter for battery and ultracapacitor applications

This paper presents a high efficiency non-isolated bidirectional converter which can be employed as an interface circuit between ultracapacitors or batteries and DC bus voltage. All semiconductor devices in the proposed converter are soft switched while the control circuit remains PWM. So, the energy conversion through the converter is highly efficient. The proposed converter acts as a zero-voltage transition (ZVT) buck to charge an ultracapacitor or battery and acts as a ZVT boost to discharge an ultracapacitor or battery. The performance of the proposed converter with respect to abrupt load and operating mode change is shown through computer simulation results. The results confirm the aforementioned advantages and features of the proposed converter.     

Acute complicating symptoms during hemodialysis sessions have well correlation with deranged blood pressure regulation

Objective: This observational study was undertaken to evaluate the frequency of acute complications occurring during dialysis sessions and their association with other clinical and biochemical parameters. Method: Forty‐six maintenance hemodialysis patients were selected and evaluated. Mean of the weekly evaluations of different parameters over a three‐month period is presented here. Result: Age of study subjects was 39 ± 13 years and body mass index (BMI) 21 ± 4 kg/m². Duration of hemodialysis was 41 ± 29 months. Most of the patients were hypertensive (98%), taking multiple anti‐hypertensive drugs. Mean of the blood pressures before and at the end of dialysis sessions over the three month period were: systolic blood pressure (SBP) 159 ± 18 vs. 163 ± 22 (p < 0.05) and diastolic blood pressure (DBP) 92 ± 13 vs. 87 ± 7 mmHg (p < 0.003). Frequency of acute complicating symptoms during dialysis sessions were: headache (75%), rise in blood pressure (73%), leg cramps (67%), vomiting (60%), palpitation (58%), sweating (52%), and hypotension (35%). Raised blood pressure showed a positive correlation with headache (r = 0.50, p < 0.01) and sweating (r = 0.53, p < 0.05). Vomiting and palpitation were more frequent at low post‐dialysis blood pressure (vomiting vs. post‐SBP‐r = ?0.41, p < 0.05 and palpitation vs. post‐DBP‐r = ?0.48, p < 0.05), and these patients were likely to get inadequate dialysis (hypotension vs. Kt/V‐r = ?0.63, p < 0.01). Pre and post dialysis weight variation was 53 ± 11 vs. 51 ± 11 kg (p < 0.001), average ultrafiltration during dialysis (UF)?2.39 (0.5–4) liter and single session Kt/V was 0.95 ± 0.38. The rising tendency of post‐dialysis blood pressure correlated positively with increasing UF (SBP vs. UF‐r = 0.36, p < 0.01 and DBP vs. UF‐r = 0.25, p < 0.05). Conclusion: From this study it may be concluded that acute complications during dialysis sessions have a significant correlation with deranged blood pressure regulation, and optimum control of blood pressure could provide better dialysis.     

Effects of the Caputo fractional derivatives on convective flow in wavy vented enclosures filled with a porous medium using Al2O3‐Cu hybrid nanofluids

This paper studies the effect of fractional derivatives on the fractional convective flow of hybrid nanofluids in a wavy enclosure that has inlet and outlet parts near the left wall and is filled with a porous medium. The Caputo definition of the fractional derivatives is applied on the partial differential equations governing flow. The complex shape is mapped to a rectangular domain using appropriate transformations. The finite difference method is used to solve the resulting system. The results showed that an increase in order of the fractional derivatives causes a low activity of the fluid flow and a reduction in the rate of heat transfer. Also, an increase in the nanoparticles volume fractions reduces the activity of the fluid flow and, as a result, the rate of heat transfer is diminished. An enhancement in fluid motion and rate of the heat transfer is obtained by increasing the amplitude of the wavy wall.