To address the challenge of requiring extensive data and computational resources in intelligent control game systems, this paper proposes a triangular game relationship model on a plane, involving dynamic player A, dynamic player B, and the fixed-point base camp b of player B. The model, which is typically used in real game scenarios where only small-scale effective data can be obtained to support the operation of intelligent game control systems, eliminates the necessary need for complete information in the adversarial deterrence game. In this triangular game relationship model, the coordinate position relationships between player A, player B, and player B's base camp b provide the constraint conditions for optimizing confrontation positions. Subsequently, an objective function for player A's optimal game position is constructed, and the local optimal confrontation position is derived and verified by incorporating the optimization constraints.
Qualitative models help policymakers understand land-use changes by examining the processes involved and predicting future patterns. This study aims to use dynamic synthesis methodology to establish cause-and-effect relationships. The study, conducted in the Mt. Elgon region encompassing Mbale, Manafwa, Bududa, and Namisindwa districts, utilized questionnaires and interviews to gather data. Findings suggest that short-term solutions to reduce wood fuel consumption include raising awareness, promoting mindset change, and providing subsidies for alternative energy sources. Long-term strategies involve advocating for tree planting, strengthening land use policies, and ensuring strict implementation. While stakeholder engagement does not automatically guarantee high-quality decision analysis, it is crucial for promoting natural resource protection and fostering a sense of ownership over the issue.
This paper focuses on using the cooperative neuro-fuzzy system for the effective and customised selection of entities from large and heterogeneous resources by presenting a general architecture. An experiment is carried out with the fast-moving consumer goods to prove the utility of the architecture. It is observed that most consumers go for the frequent purchase of fast-moving consumer items. Further, various brands, costs, discounts, schemes, quantities, and reviews might make it challenging. Hence, such decisions need to be intelligent and practically feasible in terms of time and effort. The paper discusses neural networks to categorise the entities, type-1 & 2 fuzzy membership functions with rules, training sets, and graphical views of the fuzzy rules and the experiment details. Besides the generic approach and experiment, the paper also discusses the work done so far with their limitations and applications in other domains. At the end, the paper presents the limitations and possible future enhancements.
In the recent times transfer learning models have known to exhibited good results in the area of text classification for question-answering, summarization, next word prediction but these learning models have not been extensively used for the problem of hate speech detection yet. We anticipate that these networks may give better results in another task of text classification i.e. hate speech detection. This paper introduces a novel method of hate speech detection based on the concept of attention networks using the BERT attention model. We have conducted exhaustive experiments and evaluation over publicly available datasets using various evaluation metrics (precision, recall and F1 score). We show that our model outperforms all the state-of-the-art methods by almost 4%. We have also discussed in detail the technical challenges faced during the implementation of the proposed model.
Ballots are often hold for fair decisions such as party theme selecting, however, the existing traditional ballot has some problems involving amount of human resources, cost of places, equipment, time and traffic, and repeated procedures. In order to solve the issues aforementioned, a ballot blockchain system is designed and implemented based on the smart contract of Ethereum. It is designed on the core blockchain technologies of the decentralized ledger technology, using a secure hash algorithm, anonymous user, incorruptible data, and adopting a public blockchain. The ballot blockchain system is implemented based on the MetaMask verification and the Remix interface development environment. The smart contract plays the role of the decision-maker for controlling ballot activities instead of numerous human tasks. All ballot transactions are recorded in the ballot blockchain permanently when the ballot completed. The aim of the ballot blockchain system is to achieve a fair, less time-consuming, secured, and transparent environment.
Maximum power point tracking(MPPT) control is an indispensable aspect of photovoltaic(PV) systems. Many MPPT techniques including a few based on soft-computing have been employed earlier. The soft-computing techniques include fuzzy-FSMs (Finite State Machines)which are integration of fuzzy logic (FL) into states or transitions of FSMs which are used for control and modeling of real-time systems. However, FSMs pose certain disadvantages as compared to its advanced variant called ‘statecharts’. In this work, statecharts with abstraction layers are proposed for MPPT control of PV system. An abstract-statechart MPPT(ASM) controller is developed and is verified with PV system using co-simulation. A C++ based FL MPPT program is also developed, which is independent of any predefined and simulation-only functions. A conceptual estimation of execution time of such a FL MPPT program is presented and compared with the execution times delivered by proposed ASM controller. It can be observed that the ASM controller gives accurate, fast tracking speeds, along with the advantage of abstraction.
Nowadays, Reversible Data Hiding (RDH) is used extensively in information sensitive communication domains to protect the integrity of hidden data and the cover medium. However, most of the recently proposed RDH methods lack robustness. Robust RDH methods are required to protect the hidden data from security attacks at the time of communication between the sender and receiver. In this paper, we propose a Robust RDH scheme using IPVO based pairwise embedding. The proposed scheme is designed to prevent unintentional modifications caused to the secret data by JPEG compression. The cover image is decomposed into two planes namely HSB plane and LSB plane. As JPEG compression most likely modifies the LSBs of the cover image during compression, it is best not to hide the secret data into LSB planes. So, the proposed method utilizes a pairwise embedding to embed secret data into HSB plane of the cover image. High fidelity improved pixel value ordering (IPVO) based pairwise embedding ensures that the embedding performance of the proposed method is improved.
The domain of fashion design evolves continuously and is highly personalised, demanding intelligent and customised recommendation. The traditional artificial intelligence-based systems offer solutions based on stored knowledge; hence they can be quickly obsolete and require high effort. To meet the fashion designers’ needs and provide tailor-made recommendations effectively, a hybrid genetic-fuzzy system is proposed with interactive fitness functions. The system is based on generic hybrid architecture using fuzzy logic and genetic algorithm, which can be used to evolve various products in different domains and tested with interactive fuzzy fitness functions. The design of the generic architecture meets the research gap identified through an in-depth literature survey. To prove the utility of the architecture, an experiment is carried out showing encoding scheme, genetic operators, fuzzy membership functions, and fuzzy rules. The results are also discussed, along with the comparison, advantages, applications, and possible future enhancements.
Biometrics is an interesting study due to the incredible progress in security. Electrocardiogram (ECG) signal analysis is an active research area for diagnoses. Various techniques have been proposed in human identification system based on ECG. This work investigates in ECG as a biometric trait which based on uniqueness represented by physiological and geometrical of ECG signal of person.In this paper, a proposed non-fiducial identification system is presented with comparative study using Radial Basis Functions (RBF) neural network, Back Propagation (BP) neural network and Support Vector Machine (SVM) as classification methods. The Discrete Wavelet Transform method is applied to extract features from the ECG signal. The experimental results show that the proposed scheme achieves high identification rate compared to the existing techniques. Furthermore, the two classifiers RBF and BP are integrated to achieve higher rate of human identification.
One among a lot of public health concerns in rural and tropical areas is the human intestinal parasite. Traditionally, diagnosis of these parasites is by visual analysis of stool specimens, which is usually tedious and time-consuming. In this study, the authors combine techniques in the Laplacian pyramid, Gabor filter, and wavelet to build a feature vector for the discrimination of intestinal worm in a low-resolution image captured with mobile devices. The dimension of the feature vector is reduced using principal component analysis, and the resultant vector is considered as input to the SVM classifier. The proposed framework was applied to the Makerere intestinal dataset. At its preliminary stage, the results demonstrate satisfactory classification with an accuracy rate of 65.22% with possible extension in future work.
This paper focuses on using the cooperative neuro-fuzzy system for the effective and customised selection of entities from large and heterogeneous resources by presenting a general architecture. An experiment is carried out with the fast-moving consumer goods to prove the utility of the architecture. It is observed that most consumers go for the frequent purchase of fast-moving consumer items. Further, various brands, costs, discounts, schemes, quantities, and reviews might make it challenging. Hence, such decisions need to be intelligent and practically feasible in terms of time and effort. The paper discusses neural networks to categorise the entities, type-1 & 2 fuzzy membership functions with rules, training sets, and graphical views of the fuzzy rules and the experiment details. Besides the generic approach and experiment, the paper also discusses the work done so far with their limitations and applications in other domains. At the end, the paper presents the limitations and possible future enhancements.
The statistical growth analysis of field crop has become a great challenge in agriculture. Analyzing the growth of crop through automation provides extensive significance to the farmers for getting information about the problem arising in plants due to irregular growth monitoring. The idea behind this work is the importance of mapping with pixel-based clustering technique for growth analysis in terms of height calculation of rice crop (rice variety is MTU-1010). Height measurement plays a vital role in regular assessment for a healthy crop, and the approach proposed in this work achieves 97.58% accuracy of 14 sampled datasets taken from Indira Gandhi Agriculture University of Raipur, Chhattisgarh; a real-time dataset has been prepared. Proposed work is used for analyzing vertical as well as horizontal scaling technique. Vertical mapping provides the height of a single plant whereas horizontal mapping using k-means clustering provides an average height of the whole field. This work uses machine learning, and image processing techniques are used for this work.
By the second decade of the 21st century, there has been a multi-faceted technological development in the field of networked control system (NCS). This progression in NCS has not only revealed its significant applications in various areas but has also unveiled various difficulties associated with it that hampered the operations of networked control system. Network-induced delays are issues that promote many other issues like packet dropout and brevity in bandwidth utilization. In this research article, network-induced delay has been curtailed by using the harmony between Smith predictor and Markov approach. The error estimation of the Smith predictor controller used for the simulation is carried out through a Markov approach which allows the control of the system to operate smoothly by optimizing the control signal. To implement the proposed method, the authors have simulated a third order system in Matlab/Simulink software.
Inventory optimality is an option of energy utilization proportionality that can lessen carbon emanations and maximize profitability. This study proposes an inventory management model in which the stock volume is optimally decided to diminish energy per resource utilized in-other to reduce carbon emanations. This will likewise help in concluding renewal volume optimally. Consequently, the study utilized economic order quantity (EOQ) to decide inventory volumes in-other to decrease carbon emanations so as to augment profits of the inventory chain. Partial least square(PLS) was additionally utilized to examine the extent of inventory management frameworks on environmental sustainability. The study, therefore, shows its oddity and pertinency by utilizing economic order quantity (EOQ) and partial least square (PLS) to examine and optimize inventory respectively, as it gives a perspective of decreasing carbon emanations during inventory procedures.
IoT devices are having many constraints related to computation power and memory etc. Many existing cryptographic algorithms of security could not work with IoT devices because of these constraints. Since the sensors are used in large amount to collect the relevant data in an IoT environment, and different sensor devices transmit these data as useful information, the first thing needs to be secure is the identity of devices. The second most important thing is the reliable information transmission between a sensor node and a sink node. While designing the cryptographic method in the IoT environment, programmers need to keep in mind the power limitation of the constraint devices. Mutual authentication between devices and encryption-decryption of messages need some sort of secure key. In the proposed cryptographic environment, there will be a hierarchical clustering, and devices will get registered by the authentication center at the time they enter the cluster. The devices will get mutually authenticated before initiating any conversation and will have to follow the public key protocol.
An innovative technology named FinFET (Fin Field Effect Transistor) has been developed to offer better transistor circuit design and to compensate the necessity of superior storage system (SS). As gate loses control over the channel, CMOS devices faces some major issues like increase in manufacturing cost, less reliability and yield, increase of ON current, short channel effects (SCEs), increase in leakage currents etc. However, it is necessary for the memory to have less power dissipation, short access time and low leakage current. The traditional design of SRAM (Static RAM) using CMOS technology represents severe performance degradation due to its higher power dissipation and leakage current. Thus, a Nano-scaled device named FinFET is introduced for designing SRAM since it has three dimensional design of the gate. FinFET has been used to improve the overall performance and has been chosen as a transistor of choice because it is not affected by SCEs. In this work, we have reviewed various FinFET based SRAM cells, performance metrics and the comparison over different technologies.
In this article an effort is made to identify brain tumor disease such as neoplastic, cerebrovascular, Alzheimer's, lethal, sarcoma diseases by successful fusion of images from magnetic resonance imaging (MRI) and computed tomography (CT). Two images are fused in three steps: The two images are independently segmented by hybrid combination of Particle swam optimization (PSO), Genetic algorithm and Symbiotic Organisms Search (SOS) named as hGAPSO-SOS by maximizing 2-dimensional Renyi entropy. Image thresholding with 2-D histogram is stronger in the segmentation than 1-D histogram. Remove the segmented regions with Scale Invariant Feature Transform (SIFT) algorithm. Also after image rotation and scaling, the SIFT algorithm is excellent at removing the features. The fusion laws are eventually rendered on the basis of type-2 blurry interval (IT2FL), where ambiguity effects are reduced unlike type-1. The uniqueness of the proposed study is evaluated on specific data collection of benchmark Image fusion and has proven stronger in all criteria of scale.
Securing vehicles, especially against theft, has become a significant concern. Smart antitheft solutions have emerged to provide better protection. However, most existing smart vehicle antitheft solutions use (GSM) and (GPS) technologies to track stolen vehicles and these technologies are not sufficiently efficient in tracking vehicles in real-time. Hence, there is a need to optimise solutions to incorporate new technologies such as Internet of Things (IoT), Fog Computing (FC), and Face Recognition (FR) technologies. This paper introduces the new concept of Fog Computing to existing tracking systems and presents the design and the development of the Internet of Things (IoT) Cloud-based vehicle anti-theft system to pinpoint the exact location of the stolen vehicle in real-time. The proposed system extends the existing tracking systems to include advanced features influenced by advanced computing technologies such as Fog, Cloud, IoT and FR. Furthermore, it sheds light on the benefits of using FC combined with Cloud Computing (CC) to provide a more accurate and reliable tracking system.
This study is focussed on the design and modelling of a low-cost ventilator design which can be developed using locally sourced materials in Nigeria. This is meant to aid in the Country’s fight against the current COVID-19 pandemic where there is a shortage of ventilators. The ventilator design in this research was based on a mechanical AMBU bag compression principle using the Volume-Control Ventilation(VCV) mode which will eliminate the need for manual compression which can be tedious and uncontrolled. The design is powered by an electric motor with variable speed and tidal volume control. It also features an alarm which alerts medical personnel of unstable conditions in the system parameters. This prototype shows that the mechanical compression systems is a viable and more economical option which provides the essential features required in the standard existing technologies.
Normally web services are classified originate in on the quality of service, wherever the term quality is not absolute and it is a relative term. The quality of web services is measured or derived using various parameters like reliability, scalability, flexibility, availability, etc. However, the limitation of these methods is that they are producing similar web services in recommendation lists some times. To address this research problem, the novel improved the Clustering-based web service recommendation method is proposed in this project. This approach is mainly dealing to produce diversity in the results of web service recommendation. In this method, functional interest, QoS preference, and diversity features are combined to produce the unique recommendation list of web services to end-users. To produce the unique recommendation results, we proposed a vary web service classify order that is clustering-based on web services' functional relevance such as non-useful pertinence, recorded client intrigue importance, potential client intrigue significance, etc.
