Innovations in Smart Cities Applications Volume 7

Flooding is a highly dynamic phenomenon, and can occur due to several natural and anthropogenic causes, including flash floods, rising groundwater, gradual sea level rise, and coastal storm surges. With increased flood risk in urban areas, more and more studies suggest an integration of flood management and the concept of Smart City. This paper aims to discuss the connections between Smart Cities and flood management against extreme weather events potentially occurring in the future caused by the growing climate change. Flood prediction and warning are crucial for flood management, and their improvement could rely on the digital technological systems highlighted in many Smart City strategies. Moreover, the installation of technological equipment could benefit from flood maps that indicate high-risk flood zones in the short, medium, and long term.

The integration of predictive maintenance with Industry 4.0 technologies such as big data, the Internet of Things, and artificial intelligence has led to the possibility of the overwhelming high amounts of data together with the production of unstructured and structured data. Although varieties of analytics will be able to be conducted due to additional information obtained with the state-of-the-art technologies, the capability of managing these high amounts of data is concerning. An agile database is required to accommodate this dynamic digital environment that will help in sustaining the data as reliable data sources for future analytics of intelligent asset management. A graph database is known for its flexibility and scalability due to their schema-less and unfixed structures which makes it easier to add new data. Besides that, its unique structures that represent entities in the form of nodes and relationships in the form of edges have made it excels in dealing with complex join-style queries. This paper discussed the possibility of implementing a graph database as an agile database approach by storing asset information to provide reliable data sources for the predictive maintenance process that will help to realise smart asset management.

Sentiment analysis's main goal is to extract the context from the text. The digital world of today offers us a variety of raw data formats, including blogs, Twitter, and Facebook. In order to perform analysis on this raw data, researchers must transform it into useful information. Numerous researchers used both deep learning and traditional machine learning techniques to determine the text's polarity. In order to understand the work done, we reviewed both approaches in this paper. The best methods for classifying the text will be selected by the researchers with the aid of this paper. We select a few of the best articles and evaluate them critically based on various factors. The purpose of this study is to explore the different machine learning and deep learning techniques to identify its importance as well as to raise an interest for this research area.

The advent of the digital revolution has witnessed the proliferation of data generation, from the use of machines in computing to their use in storing data and then to their use in the automatic generation of data, as in the case of the IoT (Internet of Things). Consequently, the volume of data has exponentially increased, necessitating enhanced storage capabilities and processing power for knowledge extraction. This paper highlights the significance of extracting information and knowledge from the early stages of data generation. It introduces key concepts and demonstrates their implementation in the “Knowledge Infrastructure Data Wizard” (KIDW) tool, which utilizes a dynamic tree topology. The tool facilitates human-machine interaction through user-friendly interfaces, enabling effective project management by enhancing cooperative data management. The article showcases the practical application of the developed tool within a European Interreg project, where it facilitated data and knowledge sharing, as well as fostering cooperation and participant management.

Emerging nations, driven by population growth and rapid urbanization, generate significant waste. Inadequate waste management systems prevail in many countries, including Malaysia, due to a lack of understanding and insufficient infrastructure. Despite poor waste management, there needs to be an automated classification system, leading to time-consuming manual recycling processes. The project aims to develop a real-time waste identification and classification system. The project’s objectives are: 1) design a prototype using a web application and a real-time video platform to detect and categorize recyclable waste; 2) develop the prototype utilizing the YOLOv5 model; and 3) test the model’s accuracy. In the real-time video environment, the system can identify the type of waste and the corresponding recycle bin colors for proper disposal. The model achieved an accuracy rate of 86.25% in identifying and detecting the waste.

Living Walls and greenery systems importance is increasing as a sustainable building design elements to enhance environmental building’s impact. Numerous amounts of studies have demonstrated that outdoor greening, such as trees and landscaped areas can reduce a building’s energy consumption indirectly, as well as studies that have been conducted on the impact of indoor vegetation on energy use and air quality. Indoor vegetation and planting decrease the carbon dioxide (CO2) concentration through absorbing carbon dioxide (CO2) and releasing oxygen (O2) where energy expenditures get reduced. Individuals spend around 90% of their time indoors which threatens their health and wellbeing due to poor indoor air quality (IAQ). Therefore, this paper recognizes the impacts of indoor living walls on air quality and energy consumption in various countries. The results of previous studies include pre and post results of analysis and simulation that proves the reduction of concentration, total volatile organic compounds (TVOC), PM10, temperature, and an increase in relative humidity that reduces energy consumption, and boosted air quality using indoor living walls.

This article discusses the use of acoustic emission and machine learning tools for smart monitoring of cable damages in bridges. The need for discovering and measuring the degradation of metallic bridges cables comes out as a must for users’ safety, transportation facility and economic evidence. And the application of acoustic emission for this purpose is emphasized since 1969. However, using this approach to diagnose civil engineering cables is scarce and previous research on friction in the industry and on damaged cables has shown that acoustic emission (AE) signals depend on materials, surface condition, pressure, and relative velocity. Therefore, separating the different sources of acoustic emissions recorded during cable monitoring to identify the signals caused by wire breakages remains a significant challenge. The study focuses on investigating intrafilamentary friction by leveraging the differences in acoustic signatures between cables with broken wires and intact cables. To achieve that, the article suggests an original experimental approach combined to machine learning algorithms to isolate AE sources recorded during data collection. After the experimental setup, parametric analysis, clustering, and classification techniques have been employed to separate different AE sources. The proposed approach could enable tracking the evolution of friction from broken wires over time and recognizing wire break signals even without a reference state for the cable.

Among the most destructive natural mechanical events on the planet, seismic waves cause substantial damage and degradation to infrastructure throughout the world, posing a threat to humankind. The development of seismic metamaterials opens up a new frontier for shielding buildings and infrastructure against earthquakes. Furthermore, vibrations from seismic waves propagating at the surface of the earth are mostly due to Rayleigh waves, which have low frequencies, typically below 10 Hz. Within this critical range of frequencies, we report a novel architecture optimized for shielding against seismic waves, which is denoted as a spherical Matryoshka-like seismic metamaterial. We explore the response of this system using numerical analysis based on the finite element method. The band diagram in the irreducible Brillouin zone reveals, most notably, omnidirectional stop bands. Its frequency response analysis was carried out to better explore this metamaterial’s ability to attenuate seismic waves. The findings of this study open up new pathways for designing and optimizing seismic metamaterials. Thus, offering new avenues for improving earthquake shielding.

This research paper examines the efficacy of the Space Syntax theory in analyzing the spatial suitability of the location of urban services within a Palestinian urban community, specifically in Hajjah. The study emphasizes the importance of incorporating specific Space Syntax parameters, such as integration, connectivity, and choice, with spatial configuration analysis to understand the performance of urban services in a given area. The study utilized axial map analysis to generate a comprehensive set of maps and graphs, providing an in-depth understanding of the spatial distribution and performance of different urban services in the study area. The analysis revealed that while some facilities, such as the health clinic and park, are located in favorable locations, others, such as the gas stations and some schools, require better placement. These findings can guide policymakers and urban planners in designing more efficient and accessible urban environments that cater to the community’s diverse needs. The study underscores the potential of the Space Syntax theory to inform more equitable and efficient planning and design in urban areas.

Social media has brought many changes to the way businesses are moving beyond their traditional ways of promoting their products utilizing new strategies like influencer marketing and paid advertising. Influencers are becoming increasingly important, and businesses are racing to hire the most famous people on social media to boost their brand image. However, businesses still use paid advertising as an efficient and effective method to spread information about a product or service and reach consumers. The objective of this study is to provide a comparative analysis of the impact and profitability of paid advertising vs influencer marketing. This study aims to reach a Moroccan national population by putting a cosmetic product from a well-known Moroccan brand to the test. The organization wants to learn more about its consumers’ habits and determine which of the two marketing strategies outlined above is the most successful. According to the findings of this research we confirm that influencer marketing is the most successful marketing method for e-commerce companies, but there’s no doubting that consistent results from sponsored advertisements redirect people to the website who click on the ADs and are thus more likely to make purchases.

Electronic voting (e-voting) is the use of electronic systems and technologies in elections to cast and count votes. There are several types of electronic voting systems, including Direct Recording Electronic (DRE) systems, Optical Scan Systems, Internet Voting, and Remote Electronic Voting, among others. It is a means of improving and strengthening democratic processes in modern information societies.E-voting has the potential to provide several advantages over traditional paper-based voting methods, including increased efficiency, accessibility, and accuracy. It does, however, raise some concerns and challenges that must be addressed in order to ensure the Transparency, privacy, integrity, and security of the voting process. This paper aims to present some requirements of the voting system and give a review of scholarly studies that proposed various schemes and systems to meet the conditions necessary for a highly secure electronic voting system. It offers also an overview of the experiences of various countries that have implemented electronic voting systems, highlighting their successes and challenges.

An environment with reduced pollution from road vehicles and decarbonized transportation is one of the dimensions of smart cities. In this regard, new sales of vehicles intended for urban use should be oriented toward cleaner (greener) vehicles with less harmful environmental impacts. In the current study, two environmental rating variables provided by the American Council for an Energy-Efficient Economy (ACEEE) for model year 2023 vehicles (U.S. market) in 6 broad classes are employed to identify the best 10 models in each class. These classes are: two seaters (sports cars), cars, SUVs (sport utility vehicles), vans, station wagons (estate cars), and pickups (pickup trucks). The method used in these ratings is based on a combination of emissions life cycle assessment (LCA) and environmental economics. The first ACEEE rating variable is the environmental damage index (EDX), representing an estimated environmental damage cost (in U.S. cents per driving mile). The second ACEEE rating variable is the Green Score, which is a non-dimensional number (0–100 scale) derived from EDX. According to version 4 of the green building certification program LEED (Leadership in Energy and Environmental Design) of the U.S. Green Building Council (USGBC), green vehicles are defined as those having a Green Score of 45 or higher. In the current study, 85 selected top models were found to have a Green Score range from 41 to 67. Only 55 models of them (64.7% portion) are LEED compliant (classified as green vehicles), and thus are more recommended for use within smart cities than other models.

Smart transportation nowadays is based on tracking vessels, assets, etc.. Tracking and tracing operation is an important services that can enhance the maritime trade around the world, minimize loss and increase gain in national economies, this is a field that is finding its place among others integrating new technologies such as Internet of things, Big Data, IOT and Blockchain. Blockchain is a pervasive technology that is building trust and transparency in sectors where it is difficult to ignore intermediaries’ intervention. In this article, we will present a model in which we will study the integration of Blockchain technology with IOT in the maritime field, especially container tracking and tracing during their stay in the maritime territory. This model is important to build a system of tracking assets with transparent data using both technologies Blockchain and Internet of things.

In the last decade, mobility prediction has played a crucial role in urban planning, traffic forecasting, advertising, and service recommendation. This paper addresses the prediction of mobility and emphasizes an essential step that is trajectory modeling (better the modelling is, better is the prediction). First, we propose a context-based and prediction-oriented trajectory model. Our model is based on a grid-oriented trajectory description technique that allows overcoming low precision and ambiguity issues. Second, our model is compared to some related trajectory models. Third, an application of the model in intelligent transportation domain is illustrated. Finally, to evaluate our model, we experiment it on a data mining-based prediction algorithm and show the results in terms of prediction accuracy.

This study introduces the service of real-time mapping of mobility restrictions RT-MMR using crowdsourced data to improve people’s mobility in Palestine. The service is part of the Smart and Resilient Mobility Services (SRMS) platform, a mobile web app that provides real-time road information and mobility services in areas with frequent road restrictions. The literature review highlights the adverse effects of mobility restrictions on the Palestinian population's daily life, employment opportunities, and the environment. It also notes the lack of research exploring strategies to mitigate the negative impacts of mobility restrictions, largely due to the difficulty in accessing real-time and historical data on the behavior and functionality of these restrictions. The research argues that common commercial apps such as Waze and Google Map are not effective solutions due to their limited coverage and inaccuracies in accounting for mobility restrictions. To address these challenges, the paper proposes the RT-MMR service, which uses ArcGIS Online and ArcGIS Survey123 to provide real-time and accurate information on mobility restrictions. The service aims to help interurban travelers make informed decisions and optimize their travel to reduce delays, congestion, time losses, and energy consumption. The paper also introduces the Restriction Notification System (RNS), which will notify users in real-time of any updates in specific restrictions, further improving the service's efficiency.

Autonomous vehicles rely on sensors, radars, and lidar entertainment devices to operate. They provide a safer solution for traffic safety, both for the driver and nearby cars. However, they also pose a challenge, as ensuring safety necessitates taking all necessary precautions to guarantee flawless functioning and communication of the autonomous vehicle. Consequently, numerous research investigations have been conducted on the communication protocols employed by self-driving cars. These studies have examined the vulnerabilities of each protocol to propose enhancements and refine existing ones.In our prior research papers, we have conducted comparative analyses among various communication protocols using software such as OMNET++. The critical factor that determines the resilience of a protocol is its response time, which ensures effective communication between the protocols. Some of the protocols examined include C-V2X, DSRC, ITS-G5, and 5G. This article aims to conduct a comparative study between the C-V2X and ITS-G5 protocols based on criteria such as latency, synchronization, resource selection, and response time. This comparison is crucial for improving the performance of both protocols and ensuring efficient, reliable, and smooth communication between vehicles and the environment.

Adaptation to climate change is crucial for Critical Transport Infrastructures (CTIs) due to their proximity to completing their life cycle and the lack of design considerations for weather extremes. Considering the insufficient financial resources during the ageing periods of such infrastructure, investment is necessary to support their resilient and sustainable maintenance. The potential need for investment is examined in this paper by utilizing a novel data-driven methodology and a Life Cycle Cost (LCC) analysis to assess the CTIs’ resources resilience. Further to this, the effectiveness of the mitigation measures on the infrastructures’ adaptative capacity is estimated with the Adaptation Index (AdI), which considers resilience and sustainability levels. Resilience is accounted for three different components related to structural integrity, functionality, and resources. Sustainability is indirectly assessed by weighting the distinct ageing periods of the asset’s life cycle and the calculated resilience levels. To document the proposed methodology, a case study Reinforced Concrete (RC) highway bridge in the Netherlands is considered. The results of this research aim to inform owners and stakeholders about the operation level and the effectiveness of adopted policies for the bridge’s management as well as assist in decision-making for a rapid and reliable data-driven adaptation analysis of the asset.

As the popularity of hydrogen vehicles grows, so does the demand for an efficient and reliable refueling station infrastructure. Hydrogen vehicle (HV) owners face the challenge of finding the best refueling site to meet their specific requirements in terms of comfort, accessibility, and price. Finding the best refueling station for HVs is becoming increasingly important as hydrogen stations expand. This requires analysis of variables such as hydrogen availability, cost, and distance. In this piper, we have two global objectives. In the first one, we drew inspiration from the Pickup and Delivery Problem (PDP) to find the most optimal Hydrogen Refueling Station (HRS) for our HV using a Genetic Algorithm (GA). Secondly, we want to trace the shortest path between the found station and the current location of the vehicle, for which we use the A-Star Algorithm. The approaches proposed in this document have been tested on real data and lead to the conclusion that customers would be exponentially better served by saving time and energy through optimal selection of hydrogen station services rather than the traditional method. The study results indicate the validity of these methods.

Urban transport systems represent a major infrastructure asset in contemporary cities, enabling many millions of people to commute and travel every day. Transport systems are increasingly complex because of rapid urbanization and rising vehicle ownership. Effectively predicting parking availability across a city means more efficient parking management, better urban planning, smoother traffic flow, lower fuel wastage and, ultimately, less environmental pollution. To this end, several research studies have proposed predictive approaches to parking space availability based on supervised machine learning, mainly regression algorithms. But if real-time information on parking space availability is lacking, these approaches become useless, since their driving force is historical data. What’s more, many city zones simply don’t require exact information on parking space occupancy; all that’s needed is a global view of whether there are any spaces available or not. That’s why, in this paper, we outline an approach to predicting parking availability that combines both clustering and classification. Our aim is to model parking availability through a number of typical days. A typical day is defined by a profile characterizing parking space occupancy. We start by determining precisely how many typical days per spatial cluster are required to map parking availability, and then cluster data to form groups typified by each typical day, using six clustering algorithms of ascending difficulty. Obtained results show that this number varies between 3 and 4, depending on which algorithm is applied. Thus, model evaluation reveals that distance between cluster elements is short and separation between clusters is high, in other words, clusters are far apart and not very dispersed.

In urban areas around the world, drivers face the daily challenge of finding a parking space. Unfortunately, these sought-after spaces, located close to their destination, are often either impossible to find, or excessively expensive, resulting in longer search times and increased congestion in city centers. The answer to this persistent problem is an intelligent parking solution. They provide drivers with real-time access to information on parking space availability, gathered through various sensing techniques such as crowdsourcing, parking meters and sensors. Some of these systems also offer opportunistic services, such as forecasts, to adapt to unforeseen dynamic situations. Drivers’ biggest concern is find ing a spot, not knowing the exact number of available spaces or availability rate. Typically, these two parameters are estimated using regression or image processing techniques. While such solutions guarantee high predictive accuracy, their large-scale deployment is hampered by computational and data collection costs. This paper therefore proposes a new approach combining clustering and classification models to predict parking availability. Our aim is to test new methods that are relatively simple and less expensive in terms of both processing costs and amount of training data. Experimental results have proved promising, with accuracy predictions exceeding 0.84.

Designing an embedded system for practical applications needs objectives such as high accuracy, low power consumption and cost, and secure environment. NVIDIA’s Jetson is the most popular platform for embedded system applications which promises to achieve a balance between all these objectives. This paper focused on autonomous vehicles and embedded system studies evaluating the Jetson card features used in smart cars. The characteristics of autonomous vehicles and presents the data was compared for researchers categorized by author names, vehicle names, platform, camera, purpose and environment. In paper shows that most of studies had different purposes and tested area in different environments. We also developed a cost-effective lane detection model for developing and testing the autonomous vehicle JetRacer AI Kit and detail the overall structure of the system in this work. We tested the lane detection performance for system feasibility. In addition, we presented our ongoing work to further develop the features of this vehicle based on the proposed framework.

The use of simulation software is crucial for determining the expected outcomes of a practical hardware arrangement, which is expensive and time-consuming to change on a regular basis. In the field of communication, there are many different types of network simulators. However, selecting the appropriate simulator for a given task can be challenging due to the wide variations in operating systems, hardware specifications, programming software needs, and scalability. The four mobile ad hoc routing protocols—DSDV, AODV, DSR, and OLSR—are analyzed using packet delivery ratio, throughput, average end-to-end delay, and energy in this study, which compares the results of NS3 and NS2.

The escalating challenges posed by urbanization and rapid population growth are exacerbating the global waste crisis. The World Health Organization underscores the risks of inadequate waste management, as it contributes to the spread of diseases.To address these multifaceted issues, our research is driven by two primary objectives. Firstly, we are dedicated to designing cutting-edge smart garbage bins equipped with nine sensors, including waste level sensors to monitor bin capacity, Humidity sensors to measure moisture content, Temperature sensors for climate insights, Carbon dioxide (CO2) sensors for air quality assessment, Methane (CH4) sensors to detect potential hazards, and ambient temperature sensors to gauge environmental conditions.Secondly, our research establishes a technological backbone for real-time monitoring and informed decision-making through the seamless integration of ThingSpeak and WiFi ESP8266 technologies.In addition, we will explore three usage scenarios for this intelligent waste bin. The initial scenario (Day 1) entails the collection of sensor data throughout the first day, with measurements taken every 15 min. The second scenario (Day 5) involves the collection of sensor data on the fifth day, also at a 15-min interval. Finally, the third scenario involves continuous monitoring of the smart bin over the course of one week.In essence, our research represents a pioneering effort to harness the potential of smart bins and advanced data analysis techniques. It aspires to revolutionize waste management by introducing data-driven approaches that promise not only to improve the efficiency of waste collection and treatment but also to advance the cause of cleaner, more sustainable urban environments.

Thanks to the rapid developments in electronics, computers, and software, state-of-the-art and cost-effective devices are emerging in almost every area. One of these areas is GNSS technologies and related devices. These advances in GNSS devices enable users to provide more advanced and more accurate results at an affordable cost, and thus the use of these devices is increasing rapidly. This study investigated the accuracy performance supplied by the cost-effective ArduSimple CORS system. For this purpose, ArduSimple RTK Calibrated Surveyor Kit and Topcon HiperV GNSS receivers were connected to the Tusaga-Aktif system at 86 points. Real-time position information was collected three different times with 30 epochs of both GNSS receivers. The coordinate data obtained from Topcon and ArduSimple GNSS receivers were compared, and the accuracy performance provided by the ArduSimple system was evaluated. In this study, the coordinate data obtained with the Topcon receiver, whose accuracy is known and tested many times, are accepted as a reference. When the difference values are averaged, it is seen that the position accuracy obtained from the ArduSimple receiver is 1.2 cm in the easting, 1.4 cm in the northing, and 5 cm in height.

Sustainability is a critical issue that affects the education sector in multiple ways. We argue that adopting sustainable practices can reduce the environmental impact of schools, provide valuable educational opportunities for students, promote social responsibility, and deliver economic benefits to educational institutions. Therefore, this paper presents a framework for assessing the sustainability of schools in Palestine, which can help identify areas for improvement and enhance the quality of education. The framework aims to establish a comprehensive set of indicators that cover the environmental, social, and economic dimensions of sustainability for public schools. It is based on the literature review, the Palestinian context, and the opinion of a panel of experts. The paper presents the methodology to identify these indicators and uses the Stepwise Weight Assessment Ratio Analysis method (SWARA) for their ranking and weighting. These indicators include: Social Equity, Indoor Quality, Health and Comfort, Social Cohesion, Accessibility, Energy Use Efficiency, Water Use Efficiency, Site Development, Influence on Local Economy, Annual Operating Costs, and Teaching Quality.

This conference paper investigates the role of low-cost technology and citizen engagement in promoting sustainability in urban public spaces. With the global population increasingly residing in cities, creating inclusive, safe, and sustainable urban environments has become imperative. Focusing on Sustainable Development Goal 11.7, which emphasizes universal access to safe and inclusive public spaces, this study addresses the challenges of data scarcity and limited community involvement. Through a large-scale community-driven spatial survey in Nablus, key findings are presented, including disparities in space distribution and accessibility, gender imbalances in usage, inadequacies in physical features, and safety concerns. Leveraging low-cost technology, such as smartphone applications and open-source data collection tools, the study overcomes data limitations and facilitates citizen participation. The research underscores the importance of citizen engagement in assessing and improving public spaces and highlights the need for collaboration among researchers, policymakers, and community stakeholders. The paper concludes with recommendations for targeted interventions, long-term impact assessment, and evidence-based policies to enhance sustainability and inclusivity in urban public spaces. This work contributes to advancing SDG 11.7 and offers insights for practitioners and policymakers seeking to create vibrant and equitable urban environments.

The objective of this article is to study a thermodynamic water heater which uses the energy of the exhaust air from an apartment building to meet the needs for domestic hot water. The investigated energy system, based on an experimental bench of the IUSTI laboratory, is composed of two heat exchangers, a heat pump and a thermal storage to store and draw hot water. Energy and exergy analysis were performed for each component, in order to assess the thermal losses and the irreversibilities of the system, by means of a model developed on Matlab environment. The criteria used to evaluate the performance of the devices are the energy and exergy efficiencies, as well as the coefficient of performance. According the exergetic analysis, the heat pump is mainly responsible for the degradation of the energy quality involved in the system, followed by the recovery heat exchanger, the storage tank and the heat exchanger. The results show that the energy efficiency of the system is $$96 \%$$ 96 % while the exergy efficiency is $$60 \%$$ 60 % , which implies low heat losses but high irreversibilities.

Given the escalating frequency and severity of natural and man-made disasters, post-disaster reconstruction has become a pressing global concern for countries worldwide. Effective decision-making and project management are crucial in achieving the desired outcomes of recovery efforts. However, when coupled with complex geopolitical situations, post-disaster contexts present additional challenges, such as disrupted social cohesion and limited physical, financial, and human resources. To address these complexities, this paper introduces a Priority Index (PI) designed to assess buildings in post-disaster scenarios within complex geopolitical contexts. The PI serves as a valuable tool to aid decision-makers in prioritizing post-disaster reconstruction projects. To demonstrate its applicability, the index is applied to the specific case of Beirut, Lebanon, following a devastating explosion and a subsequent series of crises that unfolded from 2019 onwards. The proposed PI considers both the physical characteristics of the buildings and the socio-economic context surrounding them.

Waste management is one of many crucial challenges across the globe, the fast growth of the population is directly proportional to waste. In other words, more population more waste and garbage. Therefore, using an efficient waste management system can save the planet from assured danger, in addition, an efficient system leads to a clean and proper environment [1]. Since we were able to notice that the waste is on the ground and the dustbins are full in Algeria, we found that the current system was not working adequately [2]. The classic system is not able to cover all the administration needs, such as the administration cannot track the current position of the trucks while collecting, and also without knowing the state of the dustbins, which could cost time, money, and energy. Therefore, we propose a new waste management system based on IoT for real-time tracking of the trucks’ position and the dustbins’ state. We have developed a mobile application specifically designed for truck drivers. This application utilizes GPS technology to retrieve real-time location information of the trucks. Additionally, we have created a smart bin prototype that incorporates ultrasonic sensors for accurately measuring the fill level of the bins. All the collected data is seamlessly displayed on the administration web dashboard. After testing the system, we obtained satisfactory results.

The intersection of artificial intelligence (AI) and behavioral economics represents a paradigm shift since both fields offer innovative approaches to make predictions and optimizing decision-making. In contrast, classical macroeconomics predominantly relies on rational, aggregate models to study macroeconomic conditions. Despite the considerable success in integrating behavioral insights into various economic fields, macroeconomics has seen a slower adaptation. This latency can be attributed to the challenge of scaling individual behavioral biases to a macro level. Moreover, the incorporation of AI into macroeconomics has faced challenges including data requirements and interpretability issues. However, AI and behavioral economics have individually showcased promising results in macroeconomic research. AI’s computational prowess facilitates sophisticated data analysis and predictive accuracy, while behavioral economics provides a more holistic interpretability of macroeconomic patterns by considering cognitive biases and heuristics. This synergy paves the way for a potential rise of AI-driven behavioral macroeconomics. This article aims to review the current progress in the application of AI across behavioral macroeconomic axes. The findings confirm the promise of AI-powered behavioral models in terms of both predictive accuracy and explanatory power. These results imply an emerging trend in the interdisciplinary field of AI and behavioral macroeconomics, thus paving the path for future research and applications in this domain.

The Moroccan dialect is a linguistic area that presents special difficulties because of its complex morphology and wide range of influences. This study offers a novel technique to sentiment analysis in this dialect. Our work focuses on using machine learning methods in conjunction with Natural Language Processing (NLP) techniques, namely Term Frequency-Inverse Document Frequency (TF-IDF) for feature extraction, to effectively classify sentiment.Given the scarcity of resources and standardized forms in Moroccan dialect, conventional sentiment analysis methods are less effective. To address this, our methodology involves rigorous preprocessing steps, including normalization, tokenization, and stemming, ensuring the refinement of input data for the machine learning models. The study utilizes a dataset comprising Moroccan tweets, classified into positive and negative sentiments, to train and test the models.We use algorithms such as Decision Tree, Support Vector Machine, and Logistic Regression, and assess their performance using metrics like accuracy, precision, recall, and F-1 score. Our findings highlight the varying effectiveness of these models in handling sentiment analysis for a morphologically rich and unstructured language like Moroccan dialect.This research not only contributes to the field of sentiment analysis in under-represented languages but also opens avenues for further exploration using more advanced NLP tools and deep learning techniques. It underscores the potential and challenges of applying machine learning to dialect-specific sentiment analysis, providing valuable insights for future research in this domain.

Intestinal parasites are a public health problem. They are at the origin of harmful damage, including malnutrition, which is the main cause of ill health. In order to evaluate this impact, a correlation study between parasitism and nutritional status was carried out at the Moulay Abdellah Center of Sale. This was a prospective 5-month study (May - September 2007) involving children aged 10 months to 15 years and hospitalized in the paediatric department regardless of their reason for hospitalization. The assessment of parasitism was based on three stool examinations plus Ritchie and Willis. The assessment of nutritional status was based on the scale of the National Center for Health Statistics (NCHS). The parasitological results highlighted an overall prevalence of 39.2% and 8 parasites including 5 pathogens: Giardia intestinalis:13.3%, Entamoeba histolytica/dispar: 9.2%, Enterobius vermicularis: 5.8%, Ascaris lumbricoides: 2.5% and Hymenolepis nana: 1.7%. Nutritional results showed prevalences of 17.1%, 22.6% and 27.9% respectively of stunting, wasting and underweight. Statistically, no association is demonstrated, but in proportions, the parasitized seem in the case of stunting and underweight more malnourished than their counterparts: 21.4% against 14.5% and 31% against 26.1% respectively. In conclusion: 39.2% are parasitized, 22.6% are too thin, 27.9% and 17.1% have respectively in relation to their age an insufficient weight and a small height. But in terms of impact on health, this parasitism is proving to have no significant role on this worrying nutritional situation. We hope that this study will further inspire actors to improve strategies to best manage situations.

There exists a global challenge related to the boosting number of elderly suffering from chronic diseases like Dementia (EWD). Hence, there is a drastic need for cost-effective disruptive technologies that enable and guarantee the quality of life for EWD via implementing telehealth. The purpose of this paper is to propose a telehealth system based on the Internet of Things for the well-being of the elderly suffering from Dementia in a smart home setting. We propose a smart home solution as a whole and a solution based on an NFC-based working prototype of a pill intake in a box for monitoring and recording the proper intake of prescribed medication for the elderly suffering from chronic diseases. A smart home solution was effectively implemented using the Cisco Packet Tracer simulator 7.3. The proposed IoT-based solution ensures the safe wandering of the elderly in a smart home setting using a Cisco packet tracer simulation tool.

Food image recognition and nutritional analysis, in particular glycemic index (GI), play a crucial role in understanding the impact of diet on human health and the management of chronic diseases such as diabetes. Deep learning, a subset of machine learning, has proven to be a powerful tool in this field. It enables precise recognition of foods from images and provides valuable information on their nutritional content. A food dataset is key to achieving accurate food recognition using deep learning. To the best of this paper’s knowledge, no Moroccan food dataset has been created to handle food image recognition and glycemic index estimation of Moroccan foods. This paper presents a new Moroccan food dataset and a method for food image recognition and nutritional analysis, particularly food glycemic index estimation.

Bipolar disorder is a challenging mental health condition characterized by recurrent periods of depression and mania. Successful management of bipolar disorder necessitates ongoing monitoring of symptoms, triggers, and individual behaviors. The emergence of the Internet of Behaviors (IoB) offers a promising prospect to enhance bipolar disorder management through the utilization of connected devices and behavioral data analysis. This paper proposes an IoB-based architecture for managing bipolar disorder. By leveraging connected devices and behavioral data analysis, the architecture aims to provide real-time insights, personalized recommendations, and early warning signs. In order to enhance the security of data, we integrate the blockchain technology to the proposed architecture. The potential advantages of implementing such an architecture are examined as well as some areas for future research are explored.

Falls are one of the causes of severe hilliness among elders, and the COVID-19 pandemic increased the number of unattended cases because of the social distancing measures. This study aims to create a dataset that collects the data from a 3-axis acceleration sensor fixed on a hinged board apparatus that mimics a human fall event. The datalogging system uses off-the-shelf devices to measure, collect and store the data. The resulting dataset includes data from different angle positions and heights, corresponding to joints of the lower limbs of the human body (ankle, knee, and hip). We use the dataset with a threshold-based fall detection algorithm. The result from the Receiver Operating Characteristic curve shows a good behavior with a mean Area Under the Curve of 0.77 and allow to compute a best threshold value with False Positive Rate of 14.8% and True Positive rate of 89.1%. The optimal threshold value may vary depending on the specific population, activity patterns, and environmental conditions, which may require further customization and validation in real-world settings.

This paper presents an innovative method for recognizing fetal electrocardiogram (ECG) signals using a single-channel abdominal lead. The method combines the capabilities of Convolutional Neural Network (CNN) with advanced analytical techniques, including independent component analysis (ICA), Singular Value Decomposition (SVD), and Nonnegative Matrix Factorization (NMF), to reduce the dimensionality of the data. A crucial aspect of the fetal heart rate, which distinguishes it from the mother’s heart rate, is the necessity for a time-scale representation that effectively captures the fetal electrical activity in terms of energy. Additionally, by separating the various components of the fetal ECG, it becomes possible to utilize them as inputs to the CNN model, thereby optimizing the reconstruction of the actual fetal ECG via the proposed method. The experimental findings demonstrate the effectiveness of this innovative technique, indicating the potential for real-time extraction of FECG signals. This method holds promise for enhancing fetal monitoring and healthcare applications.

Estimating patient prognosis has always been a challenge for physicians. One of the first questions asked by a patient entourage during his treatment is related to his vital prognosis. Thus, practitioners, even with several years of experience and the great progress of technology still have difficulties to estimate prognosis. They have tried to build prognostic allowing them to make an estimate as close as possible to the real future of each patient. However, these scores still have many limitations today. In particular, they are confronted with the individual complexity of each patient (history, physiological age, etc.). These imperfections tend to limit their use in the daily practice of medicine. In this work, we propose a machine learning based prognosis-prediction tool for poisoning cases. We use the data of poisoned patients delivered by the Poisoning Centre of Morocco. The Selected features will be fed into five machine learning techniques, including XGBoost, Support Vector Machine (SVM), Naïve Bayes, Decision Tree and Random Forest.

In recent years, the healthcare field has been boosted by the use of new technologies such as the Internet of Medical Things (IoMT), Artificial Intelligence, and Big Data. Furthermore, with the spread of the COVID-19 pandemic, the need for smart and remote healthcare services was greatly amplified leading to the accelerated adoption of digital health solutions. Nevertheless, with the increasing amount of data generated by IoMT devices, the network can undergo the problem of packet latency, packet loss, and congestion leading to delays in the transmission of data that may be urgent. Thus, it becomes essential to develop effective algorithms that can manage notifications’ flow based on their importance levels and delay tolerance. In this paper, we propose an effective algorithm to dynamically allocate the throughput in an IoMT-based smart hospital in response to data emergencies. The algorithm takes into account the criticality of the data and the available bandwidth to allocate the necessary throughput to IoMT devices to ensure that the critical data is transmitted without delay.

Incorporating Knowledge Graphs (KGs) in healthcare recommender systems offers a powerful means to address the complexities of patient health data. By harnessing the interlinks within a KG, novel paths that connect patients and healthcare items (e.g., treatments or medications) can be discovered. These paths provide invaluable, multi-faceted insights into patient health and preferences. Our work introduces HealthPathFinder, an innovative model that exploits neural attention mechanisms to delve into these connections for personalized healthcare recommendations. HealthPathFinder has the unique capability of modeling the sequential dependencies within a path and capturing holistic path semantics. Moreover, it introduces a weighted pooling operation to evaluate the importance of different paths, thus enhancing the interpretability of healthcare recommendations. Extensive experiments on public healthcare KG datasets show that HealthPathFinder significantly outperforms existing models in terms of both recommendation accuracy and explainability. Our results demonstrate the promise of HealthPathFinder in redefining the effectiveness of healthcare recommender systems and providing more personalized, accurate, and interpretable recommendations related to health.

Since the advent of COVID-19 pandemic, the Cognitive Internet of Medical Things (CIoMT) has been highlighted as a critical need for the healthcare ecosystem, by enhancing operational efficiency and promoting preventive and proactive healthcare approaches through a remote patient monitoring, real-time health data collection and optimized supply chain management. Indeed, the CIoMT is a promising technology that refers to the application of cognitive computing techniques and the Internet of Things (IoT) in the field of e-health to enhance the delivery of healthcare services. However, challenges emerged in data privacy, service integrity, and adaptability to network structure in a such ecosystem since health data are highly private and have great financial values. To deal with these concerns, we propose in this paper a secure and trusted infrastructure based on Federated Learning and Blockchain technologies within a Fog Computing network. The adopted technologies have the potentials to overcome the issue of fragmented data repositories, by providing a distributed model for health data sharing while preserving the privacy of data owners within a trusted collaborative environment based on an Identity Federation paradigm.

COVID-19 is an upper respiratory disease that emerged in the last months of 2019 and affecting people worldwide. According to the World Health Organization data, it is determined that the outbreak spread rapidly. Early diagnosis is very important in preventing the spread of epidemics. Highly accurate identification and isolation of infected persons is essential to prevent the spread of outbreaks. Currently, reverse transcription polymerase chain reaction (RT-PCR) test is the most used method to detect COVID-19. However, the test is expensive, time-consuming, socially distant, difficult to distribute and has a high false negative rate. In this study, we developed a system based on Machine Learning (ML) and Deep Learning (DL) methods using voice signals (cough sounds) for early detection and diagnosis of COVID-19 disease. Since cough sounds are also a symptom of many upper respiratory tract diseases, a three-class system was developed to determine whether the voice recording from a person was COVID-19, upper respiratory tract disease, healthy or not. In this paper, indicative features were extracted Mel Frequency Cepstrum Coefficients (MFCC) from audio signals and features were classified with K-Nearest Neighbor Algorithm (KNN), Random Forest (RF), Decision Tree, Support Vector Machines (SVM), Logistic Regression classifiers. In addition, Convolutional Neural Networks (CNN) methods, one of the DL methods, was used and comparative performance results are given in the experimental section.

This paper explores the application of natural language processing (NLP) and machine learning techniques to sentiment analysis on a dataset of tweets on COVID-19 vaccines. The dataset was obtained from Kaggle and covers the full course of the immunization program. The tweets were cleaned using a variety of preprocessing approaches, such as handling contractions, removing URLs and user handles, and adjusting punctuation. The Text Blob library was used to assign sentiment ratings, while the TF-IDF technique was used to carry out feature extraction. The revised data was used to train a Naive Bayes classifier, which predicted the sentiment labels for every tweet. To evaluate the model’s performance, evaluation criteria such F1 score, accuracy, precision, and recall were used. The study’s findings provide insightful information on how the general public feels about COVID-19 vaccinations.

Fueled by ever-increasing urbanization today, the construction sector is a major contributor to negative environmental impacts, including greenhouse gas emissions, ozone depletion, and carbon footprint. Life Cycle Assessment (LCA) is a systematic method used for the evaluation of the environmental impacts of a building throughout its entire life cycle, from raw material extraction to disposal at end-of-life stage. Early implementation of LCA principles in the design phase of a project aids stakeholders in the decision making process by allowing targeted interventions by seeking sustainable strategies in material selection. The pursuit of sustainability in LCA applications engenders the possibility for smart buildings – the integration of technology in the building design process, yielding increased levels of performance and efficiency. Smart building initiatives further extend the focus of energy optimization in buildings through utilization of and enhanced operational efficiency throughout a building’s lifecycle. The paper presents the beginning steps in a case study concentrating on the principles of life cycle assessment of smart buildings and methods to better optimize energy consumption.

Our research proposes a new antenna array for recovering RF energy, which in-corporates pattern and polarization diversity. We conducted experiments to validate the performance of the optimized model, which provides an impedance bandwidth of 5.5 to 6 GHz according to measurements. By switching the input port, the antenna system can generate four circular polarization diversity beams at ±15 and ±45, with two left-hand circular polarization beams and two right-hand circular polarization beams. Additionally, the antenna array achieves low cross-polarization radiation patterns, an excellent axial ratio around the center frequency, and a low envelope correlation coefficient across the working spectrum. The antenna array has recorded gains of 5.3 and 6.6 dB for energy recovery applications. We designed and simulated all circuits, including the 5.8 GHz antenna array, using ADS and CST software. We calculated and optimized all trans-mission line widths and lengths with a 50 Ω characteristic impedance using the LineCalc tool and Tuning function, respectively.

This research paper proposes the application of Model Predictive Control (MPC) with a reference model for achieving faster convergence in the control of synchronous motors. Synchronous motors are are utilized in a variety of industrial contexts. Nevertheless, due to the complex dynamics and inherent uncertainties of these motors, attaining rapid convergence in the control of these motors can be a difficult task. The MPC technique is known for its ability to handle multivariable systems with constraints and uncertainties. By incorporating a reference model into the MPC framework, the control algorithm can anticipate the system’s behavior and make proactive adjustments, leading to faster convergence. This paper explores the implementation and performance evaluation of the MPC approach with a reference model for controlling synchronous motors.

This paper presents a low-cost PV emulator for testing PV panels in laboratory conditions. The emulator uses a DC power supply and a DC-DC converter. The converter is controlled through a closed-loop control system. The controller is an Arduino UNO board that regulates the output voltage of the converter. The reference value is given by a PV panel model simulated using a LabVIEW program running on a computer. The Arduino controller communicates with this computer via a USB connection, sending measurement values from the sensors (irradiance, temperature, and voltage) and receiving the reference value for the converter. It also displays the reference value on an electronic display. The software component of the emulator is based on the Model-View-Controller (MVC) paradigm. The LabVIEW program houses the PV panel model but also works as an HMI (the view) for the user, displaying the measured and computed values, plotting the current operating point on the PV characteristic curves, etc. The C program running on the Arduino board is the controller.

A promising new technology, 5G promises a notable improvement in several points, one of these points is the energy part. This study aims to see if this promise is kept in the access network part, and this through the analysis of several radio sites before and after the transition to 5G.

The significance of digital color images in various applications necessitates the development of secure and efficient color image encryption techniques. This study presents a simple yet highly secure method for encrypting color images using dual secret keys, enhancing overall image security and safeguarding against hacking attempts. The first key generates index keys for encrypting and decrypting image segments, while the second key determines the starting point in the image_key and divides the unencrypted image into segments. These index keys are then employed to encrypt and decrypt the segments. Encryption and decryption of segments involve a straightforward process, distributing plain data based on the index key and retrieving decrypted data from encrypted data following the index key’s indices. The proposed method will be assessed and applied to various color images, with the results analyzed to demonstrate improvements in quality, sensitivity, and speed. The method’s speed will be compared with other techniques to highlight the acceleration offered by the proposed approach.

This paper provides a comparative analysis of deep learning algorithms for detecting web attacks and code vulnerability, A review of the literature highlights the methodologies, datasets used, achieved accuracies of these models and their limitations. By understanding web attacks and leveraging advanced technologies, it is possible to enhance the security and protection of digital assets. A notable observation is the underutilization of resources to protect JavaScript, a widely used programming language on the internet. To address this gap, our research prioritizes improving JavaScript’s security. We aim to develop a system that improve web application protection, ensuring a safer online environment for users.

As technological advancements continue to shape smart cities, the complex and interconnected digital networks within these infrastructures are increasingly susceptible to cyber threats. This PhD thesis explores the application of Artificial Intelligence (AI) as a powerful tool for managing and mitigating cyber risks in these advanced infrastructures and network systems. We focus on developing a proactive approach that combine the early detection, comprehensive assessment, and effective mitigation of impending cyber threats. To achieve this goal, we propose an AI-based framework that harnesses the power of Machine Learning (ML), Reinforcement Learning (RL), Natural Language Processing (NLP), and Graph Theory. By employing these techniques, our framework aims to fortify network and system resilience, providing robust cyber risk management by artificial intelligence and for smart cities. This work paves the way for innovative risk management strategies that not only react to cyber threats but also anticipate and neutralize them effectively.

Intrusion detection systems (IDS) monitor and analyze network traffic and system activity to detect and alert security personnel to potential security breaches or attacks. Although deep learning models have shown great promise in improving the accuracy and efficiency of IDSs, several challenges are associated with their use, including data scarcity and model complexity. Furthermore, to overcome these problems, deep transfer learning is considered in this study. Typically, this article presents a novel intrusion detection (ID) approach using transformed 1D signals into 2D representations and applying pre-trained convolutional neural network (CNN) models. The transformed 2D representations of the signals allow the pre-trained CNN models to effectively learn the features of the signals and accurately classify them as normal or malicious. The performance of the proposed method was evaluated on the CIC-IDS-2018 dataset, and the results showed 92% accuracy in differentiating between normal behavior and malicious activities, which is an improvement compared with other detection methods.

The development of information and communication technology has spread throughout the world, including Indonesia. There are many benefits, but the risks are unavoidable. Communication is growing massively in cyberspace and thus poses a security threat to smart city services. In Indonesia, cybersecurity is not yet a priority, so policies that regulate all aspects as a standard reference for implementing cybersecurity are still needed. Therefore, the purpose of this research is to propose a cybersecurity model in smart cities in Indonesia. In this study, unstructured interviews were conducted as a method for collecting data. Seven respondents, namely the Director, Head of Cyber and Code Control Section, Head of Operations, and four staff at Jakarta Smart City were selected as respondents. Initial factors for the implementation of cybersecurity in Indonesia are identified and analyzed qualitatively. Actor-Network Theory (ANT) is used as a theoretical framework to explore and validate factors related to cybersecurity. In the end, a new cybersecurity model was proposed. The proposed model focuses on people, technology, and process and follows the flow of government bureaucracy in Indonesia. The proposed cybersecurity model has three main parts, namely: (1) Cybersecurity Stakeholders, (2) Legal Basis for Cybersecurity Management, and (3) Security Management. The new cybersecurity development model resulting from this research can provide input to government agencies to design and implement cybersecurity in smart city projects in Indonesia in the future.

Today, mobile applications are in widespread use and have become an essential part of their users’ daily lives. However, for users and developers alike, the security of mobile applications has become a significant concern. Security flaws in mobile applications can give cybercriminals access to users’ personal information, steal sensitive data, and compromise their privacy. Through the creation of a survey consisting of eleven questions, each based on a mobile security practice that users should follow, this study examines the different aspects of mobile application security, including security threats, common attacks, security techniques, and the level of security and awareness of good security practices among users in Moroccan society. The results obtained will then be collected, analyzed, and compared with other research work to deduce the gaps to which we must pay attention. Finally, a list of good security practices will be drawn up to be recommended to these users.