Explainable Artificial Intelligence (XAI) for Population Health Management – An Appraisal

This study explores Explainable Artificial Intelligence (XAI) in general and then talked about its potential use for the India Healthcare system. It also demonstrated some XAI techniques on a diabetes dataset with an aim to show practical implementation and implore the readers to think about more application areas. However, there are certain limitations of the technology which are highlighted along with the future scope in the discussion.

Improving BER Performance of Massive MIMO Scheme over Rayleigh Fading Channel

In massive multiple input multiple output (mMIMO) scheme, the system capacity can be improved without additional bandwidth or transmit power by using a huge antenna array at base station with as much separation between antenna elements as possible. Unfortunately, its performance depends on having a perfect channel state estimate between the base state and the users. In this paper, the bit error rate (BER) performance of a mMIMO scheme is improved using genetic algorithm-based optimization with simulation performed in MATLAB software environment. The genetic algorithm used selects the best signal required for effective transmission. Four different antenna configurations in the order of 2x2, 4x4, 8x8 and 16x16 were considered for the simulation. The encoding and decoding were done using an STBC coded. Also, filter bank multicarrier-offset quadrature amplitude modulation (FBMC-OQAM) scheme was used and simulation was carried out for 4-FBMC-OQAM, 16 FBMC-OQAM, and 64 FBMC-OQAM order. The BER is computed for both the optimized and un-optimized mMIMO schemes, and the performance of both schemes is compared. Simulation results show a significant improvement in the BER of the optimized mMIMO compared to the normal (coded) MIMO scheme. The overall results show that the optimized mMIMO experience a reduced BER when compared to the normal mMIMO. In both cases, the BER reduces gradually as the number of antenna increases.

An improved Whale Optimization Approach for Effective Data Transmission for IoT Communication

Internet of Things (IoT) offers interconnection among several wireless communication devices for the provision of device accessibility and in-built capacity. IoT provides device interaction and provision of advantages capability for networking and socialization with consideration of intermediate devices. Through innovation in technology IoT devices convert cyber environments with hyper-connectivity. IoT communication contains several smart devices such as body sensors, smartphones, tags, electronic gadgets, and so on. IoT communication is involved in the provision of heterogeneous connectivity among devices for the provision of interface and connectivity for enhancing service quality. The data sending among IoT devices is affected by several threats that have an impact on the network’s performance. To overcome the limitation related to IoT communication, it is necessary to develop an appropriate technique for enhancing IoT network communication performance. In this research developed a multi-channel routing approach is adopted in IoT communication. The developed approach utilizes a meta-heuristics approach with probability-based characteristics. For the meta-heuristics approach this research utilizes whale optimization technique combined with probability characteristics for improving the IoT communication performance of the network. The proposed approach utilizes initially constructs the IoT communication path for information sharing and gathering. This path information is identified through the objective function of a meta-heuristic approach. Based on the objective function hoping between the devices is minimized through which data are transmitted in the network. Simulation is performed as a unique proposed approach with a coverage area of 100 meters. For identification of the optimal path in the network, WOA identifies the path of communication through probability function. Comparative analysis of research exhibited that WOA provides significant performance with the identification of optimal value at the range of 1.0746e-78. Further, the proposed probability-based WOA approach significantly improves the performance of the IoT network.

Artificial Neural Network Context-Aware Reasoning Engine Model for Predicting User-Ranked Activities

The choice of users’ activity in a context-aware environment depends on users’ preferences and background. Users tend to rank concurrent activities and select their preferred activity. Researchers and developers of context-aware applications have sought various mechanisms to implement context reasoning engines. Recent implementations use Artificial Neural Networks (ANN) and other machine learning techniques to develop a context-aware reasoning engine to predict users’ activities. However, the complexities of these mechanisms overwhelm the processing capabilities and storage capacity of mobile devices. The study models a context-aware reasoning engine using a multi-layered perceptron with a gradient descent back-propagation algorithm to predict activity from user-ranked activities using a stochastic learning mode with a constant learning rate. The work deduced that working with specific rules in training a neural network is not always applicable. Training a network without approximation of neuron’s output to the nearest whole number increases the accuracy level of the network at the end of the training.

Modeling of SCIG-Based Variable Speed Wind Turbine in Power Factor Control Mode for Load Flow Analysis

As they are more efficient in extracting wind energy, variable speed wind power plants (WPPs) are currently replacing the fixed speed WPPs. One possible way to achieve a variable speed WPP is by using a squirrel cage induction generator (SCIG) with full-scale power electronic converter (PEC). In fact, as its cost is relatively lower, the application of SCIG-based variable speed WPP is gaining popularity nowadays. To be able to perform proper analyses (including the load flow analysis) of an electric power system, valid and accurate modeling of the system components is very important. This paper discusses the steady state model of SCIG-based variable speed WPP in power factor control mode for a load flow analysis of an electric power distribution system. The model was developed based on formulas that calculate the turbine mechanical power input and WPP electrical power output. Integration of the proposed model in load flow analysis is also discussed and presented in this paper.

Design of a DC Microgrid System for a Remote Community in Nigeria

This paper presents the design of a DC microgrid for a remote community in Edo State, Nigeria having a solar irradiance of 4.63 kWh/m2/day. The community is isolated and located far away from the city with no access to the electricity grid. There is a need for lighting and running of electronics, as the main source of lighting presently is kerosine, which is not efficient and leads to health issues. The community is made up of 9 residences that are not more than 100 m apart. House 1 was selected as the standard house with a load of 1 kWh/day, while the other 8 houses have a load difference of ±10% with reference to house 1. Using a 48 V DC bus, the designed PV system components comprise of a 100W solar photovoltaic (PV) panel and a 12 V 45 A·hr battery. The system was sized using Homer Pro. Optimization results presented various design for the various houses. The result obtained showed reasonable and feasible cost-effective solution in terms of the Net Present Cost in both installation and running of the hybrid system for the community. Sensitivity analysis was also carried out to test the adaptability of the system using a solar irradiation input of ±10%. Detailed result of the analysis is presented in the paper.

Use Hierarchical Codebook to Improve the Primary User Detection in the Cognitive Radio’s Cooperative Spectrum Sensing

Currently, the cognitive network is receiving much attention due to the advantages it brings to users. An important method in cognitive radio networks is spectrum sensing, as it allows secondary users (SUs) to detect the existence of a primary user (PU). Information of probability of false detection or warning about the PU is sent to a fusion center (FC) by the SUs, from which the FC will decide whether or not to allow the SUs to use the PU spectrum to obtain information. The transmission of information with a high signal to noise ratio (SNR) will increase the FC's ability to detect the existence of the PU. However, researchers are currently focusing on probabilistic formulas assuming that the channel is known ideally or there is nominal channel information at the FC; moreover, one model where the FC only knows the channel correlation matrix. Furthermore, studies are still assuming this is a simple multiple input – multiple output (MIMO) channel model but do not pay much attention to the signal processing at the transmitting and receiving antennas between the SUs and the FCs. A new method introduced in this paper when combining beamforming and hierarchical codebook makes the ability to detect the existence of the PU at the FC significantly increased compared to traditional methods.

3D-Simulation Data-Making Trial to present and analyze Small-sized Farmlands Fields with Car-shaped Robot, ROS2, SLAM and Foxy for Real agricultural workers

In this study, we create various application systems focusing on agricultural (agri-) field data digitalization issues that will benefit traditional agri-researchers, workers, and their respective managers. We obtain three-dimensional (3D) information on agri-environments (e.g., rice fields, farmlands) via roaming robots with sensors. Robot-controlled middleware, such as robot operating systems (ROS), are often used for such robots. Thus, we selected car-shaped robot (NANO-RT1), ROS2, and the SLAM-based system. The car-shaped robot-based system operates sensor units uniformly. With this technology, we can recognize our location at an unknown place, and the robot can run. There are challenges in accurately presenting quantitative accuracy data for this type of study. We address this by providing average and standard deviation (SD) data for certain situations using five algorithms: (1) Hector-SLAM, (2) G-mapping, (3) Karto-SLAM, (4) Core-SLAM, and (5) Lago-SLAM. We believe the proposed holistic system has the potential to improve not only agri-businesses, but also agri-skills and overall security levels.

A Robust Mechanism for Categorizing Context-Aware Applications into Generations

The hunt to categorize context-aware applications has been a prevalent issue to developers of context-aware applications. The previous categorizations were based on the functions of the applications. These mechanisms yielded limited results since many applications could not be categorized. This paper categorizes applications into four generations based on developmental trends through a literature survey. The first generation applications focused on data acquisition and used hardware sensors. The second generation applications focused on knowledge acquisition and used software sensors, semantic language and ontology-based modelling languages. The third generation applications focused on intelligent reasoning and used mechanisms to handle information uncertainty. The fourth generation applications deprecate cumbersome ruleset implementations and focus on artificial intelligence whilst taking into consideration the effect of the dynamics of users’ background and preference on contextual information. The study demonstrated that when applications, methods or technologies can be categorized over some time, it is better to classify them into generations.

Interference Management for the Coexistence of DTTV and LTE Systems within the Proposed Digital Dividend Band in Nigeria

This paper seeks to present the Interference Management for the Coexistence of DTTV and LTE Systems within the proposed digital dividend band in Nigeria. The study focused on LTE Down-link (DL) signal from the nearest cell site interfering with the Digital Terrestrial Television (DTTV) fixed outdoor receiving antenna in Port Harcourt, Nigeria. The qualitative signal analysis of the DTTV systems is essential as DTTV system cannot start to operate in the newly formed frequency band without the evaluation of the possible harmful influence of the coexisting systems. This research work investigated the Compatibility of the two systems and the Probability of interference of Channel 17 (490MHz) and Channel 51 (693MHz) when DTTV and LTE systems coexist within the proposed Digital Dividend band. A test-bed approach method was adopted for the generation of the required simulation data. Star Time transmitting Station in Port Harcourt and Smile LTE 4G Communication LTE Base Station (eNBs) Network also in Port Harcourt were adopted as the Victim Link Transmitter (VLT) and Interfering Link Transmitter (ILT) respectively. Data was obtained, analyzed, and evaluated. It was observed from the simulation result that the probability of interference is a function of the separation distance between ILT and VLR. The Compatibility analysis result shows that the resulting C/I is above the protection criteria (19dB), that is there’s a minimal rate of interference. Hence, the interference issue can be managed when the two systems coexist in700MHz band. It was also established that DTTV channel 51 suffers more interference when compared with DTTV channel 17 for the same separation distance. The study recommended the minimum protection distance approach (Interference Avoidance method) as the interference management techniques when DTTV and LTE systems coexist in the proposed digital dividend (700MHz) band in Nigeria.