Abstract: Nowadays, dialogue systems increasingly become the
way for humans to access many computer systems. So, humans
can interact with computers in natural language. A dialogue
system consists of three parts: understanding what humans say in
natural language, managing dialogue, and generating responses in
natural language. In this paper, we survey deep learning based
methods for dialogue management, response generation and dialogue
evaluation. Specifically, these methods are based on neural network,
long short-term memory network, deep reinforcement learning,
pre-training and generative adversarial network. We compare these
methods and point out the further research directions.
Abstract: With the development of intelligent vehicle systems, a high-precision road map is increasingly needed in many aspects. The automatic lane lines extraction and modeling are the most essential steps for the generation of a precise lane-level road map. In this paper, an automatic lane-level road map generation system is proposed. To extract the road markings on the ground, the multi-region Otsu thresholding method is applied, which calculates the intensity value of laser data that maximizes the variance between background and road markings. The extracted road marking points are then projected to the raster image and clustered using a two-stage clustering algorithm. Lane lines are subsequently recognized from these clusters by the shape features of their minimum bounding rectangle. To ensure the storage efficiency of the map, the lane lines are approximated to cubic polynomial curves using a Bayesian estimation approach. The proposed lane-level road map generation system has been tested on urban and expressway conditions in Hefei, China. The experimental results on the datasets show that our method can achieve excellent extraction and clustering effect, and the fitted lines can reach a high position accuracy with an error of less than 10 cm.
Abstract: This study aims to characterize the physicochemical aspects of the soils of southeastern Chapada Diamantina - Bahia related to the phytophysiognomies of this area, rupestrian field, small savanna (savanna fields), small dense savanna (savanna fields), savanna (Cerrado), dry thorny forest (Caatinga), dry thorny forest/savanna, scrub (Carrasco - ecotone), forest island (seasonal semi-deciduous forest - Capão) and seasonal semi-deciduous forest. To achieve the research objective, soil samples were collected in each plant formation and analyzed in the soil laboratory of ESALQ - USP in order to identify soil fertility through the determination of pH, organic matter, phosphorus, potassium, calcium, magnesium, potential acidity, sum of bases, cation exchange capacity and base saturation. The composition of soil particles was also checked; that is, the texture, step made in the terrestrial ecosystems laboratory of the Department of Ecology of USP and in the soil laboratory of ESALQ. Another important factor also studied was to show the variations in the vegetation cover in the region as a function of soil moisture in the different existing physiographic environments. Another study carried out was a comparison between the average soil moisture data with precipitation data from three locations with very different phytophysiognomies. The soils found in this part of Bahia can be classified into 5 classes, with a predominance of oxisols. All of these classes have a great diversity of physical and chemical properties, as can be seen in photographs and in particle size and fertility analyzes. The deepest soils are located in the Central Pediplano of Chapada Diamantina where the dirty field, the clean field, the executioner and the semideciduous seasonal forest (Capão) are located, and the shallower soils were found in the rupestrian field, dry thorny forest, and savanna fields, the latter located on a hillside. As for the variations in water in the region's soil, the data indicate that there were large spatial variations in humidity in both the rainy and dry periods.
Abstract: Autonomous driving systems require high reliability to provide people with a safe and comfortable driving experience. However, despite the development of a number of vehicle sensors, it is difficult to always provide high perceived performance in driving environments that vary from time to season. The image segmentation method using deep learning, which has recently evolved rapidly, provides high recognition performance in various road environments stably. However, since the system controls a vehicle in real time, a highly complex deep learning network cannot be used due to time and memory constraints. Moreover, efficient networks are optimized for GPU environments, which degrade performance in embedded processor environments equipped simple hardware accelerators. In this paper, a semantic segmentation network, matrix multiplication accelerator network (MMANet), optimized for matrix multiplication accelerator (MMA) on Texas instrument digital signal processors (TI DSP) is proposed to improve the recognition performance of autonomous driving system. The proposed method is designed to maximize the number of layers that can be performed in a limited time to provide reliable driving environment information in real time. First, the number of channels in the activation map is fixed to fit the structure of MMA. By increasing the number of parallel branches, the lack of information caused by fixing the number of channels is resolved. Second, an efficient convolution is selected depending on the size of the activation. Since MMA is a fixed, it may be more efficient for normal convolution than depthwise separable convolution depending on memory access overhead. Thus, a convolution type is decided according to output stride to increase network depth. In addition, memory access time is minimized by processing operations only in L3 cache. Lastly, reliable contexts are extracted using the extended atrous spatial pyramid pooling (ASPP). The suggested method gets stable features from an extended path by increasing the kernel size and accessing consecutive data. In addition, it consists of two ASPPs to obtain high quality contexts using the restored shape without global average pooling paths since the layer uses MMA as a simple adder. To verify the proposed method, an experiment is conducted using perfsim, a timing simulator, and the Cityscapes validation sets. The proposed network can process an image with 640 x 480 resolution for 6.67 ms, so six cameras can be used to identify the surroundings of the vehicle as 20 frame per second (FPS). In addition, it achieves 73.1% mean intersection over union (mIoU) which is the highest recognition rate among embedded networks on the Cityscapes validation set.
Abstract: Repairable items inventory system is a management tool used to incorporate all information concerning inventory levels and movements for repaired and new items. This paper presents development of an effective simulation model for managing the inventory of repairable items for a production system where production lines send their faulty items to a repair shop considering the stochastic failure behavior and repair times. The developed model imitates the process of handling the on-hand inventory of repaired items and the replenishment of the inventory of new items using Economic Order Quantity and Reorder Point ordering policy in a flexible and risk-free environment. We demonstrate the appropriateness and effectiveness of the proposed simulation model using an illustrative case problem. The developed simulation model can be used as a reliable tool for estimating a healthy on-hand inventory of new and repaired items, backordered items, and downtime due to unavailability of repaired items, and validating and examining Economic Order Quantity and Reorder Point ordering policy, which would further be compared with other ordering strategies as future work.
Abstract: With the increased utilization of technology devices around the world, healthcare and medical diagnosis are critical issues that people worry about these days. Doctors are doing their best to avoid any medical errors while diagnosing diseases and prescribing the wrong medication. Subsequently, artificial intelligence applications that can be installed on mobile devices such as rule-based expert systems facilitate the task of assisting doctors in several ways. Due to their many advantages, the usage of expert systems has increased recently in health sciences. This work presents a backward rule-based expert system that can be used for a headache diagnosis and medication recommendation system. The structure of the system consists of three main modules, namely the input unit, the processing unit, and the output unit.
Abstract: Parkinson's disease (PD) is a heterogeneous disorder with common age of onset, symptoms, and progression levels. In this paper we will solve analytically the PD model as a non-linear delay differential equation using the steps method. The step method transforms a system of delay differential equations (DDEs) into systems of ordinary differential equations (ODEs). On some numerical examples, the analytical solution will be difficult. So we will approximate the analytical solution using Picard method and Taylor method to ODEs.
Abstract: Wireless sensor network was formed by a combination of nodes, systematically it transmitting the data to their base stations, this transmission data can be easily compromised if the limited processing power and the data consistency from these nodes are kept in mind; there is always a discussion to address the secure data transfer or transmission in actual time. This will present a mechanism to securely transmit the data over a chain of sensor nodes without compromising the throughput of the network by utilizing available battery resources available in the sensor node. Our methodology takes many different advantages of Z-MAC protocol for its efficiency, and it provides a unique key by sharing the mechanism using neighbor node MAC address. We present a light weighted data integrity layer which is embedded in the Z-MAC protocol to prove that our protocol performs well than Z-MAC when we introduce the different attack scenarios.
Abstract: Greenhouse cultivation is an energy-intensive process due to the high demands on cooling or heating according to external climatic conditions, which could be extreme in the summer or winter seasons. The thermal radiation rate inside a greenhouse depends mainly on the type of covering material and greenhouse construction. Using additional thermal screens under a greenhouse covering combined with a dehumidification system improves the insulation and could be cost-effective. Greenhouse covering material usually contains protective ultraviolet (UV) radiation additives to prevent the film wear, insect harm, and crop diseases. This paper investigates the overall heat transfer coefficient, or U-value, for greenhouse polyethylene covering contains UV-additives and glass covering with or without a thermal screen supplement. The hot-box method was employed to evaluate overall heat transfer coefficients experimentally as a function of the type and number of the thermal screens. The results show that the overall heat transfer coefficient decreases with increasing the number of thermal screens as a hyperbolic function. The overall heat transfer coefficient highly depends on the ability of the material to reflect thermal radiation. Using a greenhouse covering, i.e., polyethylene films or glass, in combination with high reflective thermal screens, i.e., containing about 98% of aluminum stripes or aluminum foil, the U-value reduces by 61%-89% in the first case, whereas by 70%-92% in the second case, depending on the number of the thermal screen. Using thermal screens made from low reflective materials may reduce the U-value by 30%-57%. The heat transfer coefficient is an indicator of the thermal insulation properties of the materials, which allows farmers to make decisions on the use of appropriate thermal screens depending on the external and internal climate conditions in a greenhouse.
Abstract: In Abu Dhabi, there are many different education curriculums where sector of private schools and quality assurance is supervising many private schools in Abu Dhabi for many nationalities. As there are many different education curriculums in Abu Dhabi to meet expats’ needs, there are different requirements for registration and success. In addition, there are different age groups for starting education in each curriculum. In fact, each curriculum has a different number of years, assessment techniques, reassessment rules, and exam boards. Currently, students that transfer curriculums are not being placed in the right year group due to different start and end dates of each academic year and their date of birth for each year group is different for each curriculum and as a result, we find students that are either younger or older for that year group which therefore creates gaps in their learning and performance. In addition, there is not a way of storing student data throughout their academic journey so that schools can track the student learning process. In this paper, we propose to develop a computational framework applicable in multicultural countries such as UAE in which multi-education systems are implemented. The ultimate goal is to use cloud and fog computing technology integrated with Artificial Intelligence techniques of Machine Learning to aid in a smooth transition when assigning students to their year groups, and provide leveling and differentiation information of students who relocate from a particular education curriculum to another, whilst also having the ability to store and access student data from anywhere throughout their academic journey.
Abstract: An essential task in the field of artificial intelligence is
to allow computers to interact with people through natural language.
Therefore, researches such as virtual assistants and dialogue systems
have received widespread attention from industry and academia. The
response generation plays a crucial role in dialogue systems, so to
push forward the research on this topic, this paper surveys various
methods for response generation. We sort out these methods into
three categories. First one includes finite state machine methods,
framework methods, and instance methods. The second contains
full-text indexing methods, ontology methods, vast knowledge base
method, and some other methods. The third covers retrieval methods
and generative methods. We also discuss some hybrid methods based
knowledge and deep learning. We compare their disadvantages and
advantages and point out in which ways these studies can be improved
further. Our discussion covers some studies published in leading
conferences such as IJCAI and AAAI in recent years.
Abstract: Most Gulf Cooperation Council (GCC) countries with oil-based economy like Oman are looking for other potential revenue generation options as the crude oil price is regularly fluctuating due to changing geopolitical environment. Oman has advantage of possessing world-heritage nature tourism hotspots around the country and the government is making investments and strategies to uplift the tourism industry following Oman Vision 2040 strategies. Oman’s agriculture is not significantly contributing to the economy, but possesses specific and diversified arid cropping systems. Oman has modern farms; nevertheless some of the agricultural production activities are done with cultural practices and styles that would be attractive to tourists. The aim of this paper is to investigate the potentials for promoting agritourism industry in Oman; recognize potential sites, commodities and activities, and predict potential revenue generation as a projection from that of the tourism sector. Moreover, the study enables to foresee possible auxiliary advantages of agritourism such as, empowerment of women and youth, enhancement in the value-addition industry for agricultural produce through technology transfer and capacity building, and producing export quality products. Agritourism could increase employability, empowerment of women and youth, improve value-addition industry and export-oriented agribusiness. These efforts including provision of necessary technology-transfer and capacity-building should be rendered by the collaboration of academic institutions, relevant ministries and other public and private sector stakeholders.
Abstract: Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve complex problems and to build AI systems nowadays and especially in those cases where we have tacit knowledge or the knowledge that is not known. We used machine learning algorithms and for identification of fake news; we applied three classifiers; Passive Aggressive, Naïve Bayes, and Support Vector Machine. Simple classification is not completely correct in fake news detection because classification methods are not specialized for fake news. With the integration of machine learning and text-based processing, we can detect fake news and build classifiers that can classify the news data. Text classification mainly focuses on extracting various features of text and after that incorporating those features into classification. The big challenge in this area is the lack of an efficient way to differentiate between fake and non-fake due to the unavailability of corpora. We applied three different machine learning classifiers on two publicly available datasets. Experimental analysis based on the existing dataset indicates a very encouraging and improved performance.
Abstract: The prime idea of inclusive education is to mainstream every child in education. However, it will be challenging for implementation when there are policy and practice gaps. It will be even more challenging when children have disabilities. Generally, the focus will be on the policy gap, but the problem may not always be with policy. The proper practice could be a challenge in the countries like Nepal. In determining practice, the teachers’ perceptions toward inclusive will play a vital role. Nepal has categorized disability in 7 types (physical, visual, hearing, vision/hearing, speech, mental, and multiple). Out of these, hearing impairment is the study realm. In the context of a limited number of researches on children with disabilities and rare researches on CWHI and their education in Nepal, this study is a pioneering effort in knowing basically the problems and challenges of CWHI focused on inclusive education in the schools including gaps and barriers in its proper implementation. Philosophically, the paradigm of the study is post-positivism. In the post-positivist worldview, the quantitative approach with the description of the situation and inferential relationship are revealed out in the study. This is related to the natural model of objective reality. The data were collected from an individual survey with the teachers and head teachers of 35 schools in Nepal. The survey questionnaire was prepared and filled by the respondents from the schools where the CWHI study in 7 provincial 20 districts of Nepal. Through these considerations, the perceptions of CWHI focused inclusive education were explored in the study. The data were analyzed using both descriptive and inferential tools on which the Likert scale-based analysis was done for descriptive analysis, and chi-square mathematical tool was used to know the significant relationship between dependent variables and independent variables. The descriptive analysis showed that the majority of teachers have positive perceptions toward implementing CWHI focused inclusive education, and the majority of them have positive perceptions toward CWHI focused inclusive education, though there are some problems and challenges. The study has found out the major challenges and problems categorically. Some of them are: a large number of students in a single class; availability of generic textbooks for CWHI and no availability of textbooks to all students; less opportunity for teachers to acquire knowledge on CWHI; not adequate teachers in the schools; no flexibility in the curriculum; less information system in schools; no availability of educational consular; disaster-prone students; no child abuse control strategy; no disabled-friendly schools; no free health check-up facility; no participation of the students in school activities and in child clubs and so on. By and large, it is found that teachers’ age, gender, years of experience, position, employment status, and disability with him or her show no statistically significant relation to successfully implement CWHI focused inclusive education and perceptions to CWHI focused inclusive education in schools. However, in some of the cases, the set null hypothesis was rejected, and some are completely retained. The study has suggested policy implications, implications for educational authority, and implications for teachers and parents categorically.
Abstract: The article presents results from the AF3 project “Advanced Forest Fire Fighting” focused on Unmanned Aircraft Systems (UAS)-based 3D surveillance and 3D area mapping using high-resolution photogrammetric methods from multispectral imaging, also taking advantage of the 3D scanning techniques from the SCAN4RECO project. We also present a proprietary embedded sensor system used for the detection of fire ignitions in the forest using near-infrared based scanner with weight and form factors allowing it to be easily deployed on standard commercial micro-UAVs, such as DJI Inspire or Mavic. Results from real-life pilot trials in Greece, Spain, and Israel demonstrated added-value in the use of UAS for precise and reliable detection of forest fires, as well as high-resolution 3D aerial modeling for accurate quantification of human resources and equipment required for firefighting.
Abstract: Wildfires are becoming an increasing concern worldwide, causing substantial social, economic, and environmental disruptions. This situation is especially relevant in Mediterranean-climate regions, present in all the five continents of the world, in which fire is not only a natural component of the environment but also perhaps one of the most important evolutionary forces. The rise in wildfire occurrences and their associated impacts suggests the need for identifying knowledge gaps and enhancing the basis of scientific evidence on how managers and policymakers may act effectively to address them. Considering that the main goal of a systematic map is to collate and catalog a body of evidence to describe the state of knowledge for a specific topic, it is a suitable approach to be used for this purpose. In this context, the aim of this study is to systematically map the research trends in wildfire management practices in Mediterranean-climate regions. A total of 201 wildfire management studies were analyzed and systematically mapped in terms of their: Year of publication; Place of study; Scientific outlet; Research area (Web of Science) or Research field (Scopus); Wildfire phase; Central research topic; Main objective of the study; Research methods; and Main conclusions or contributions. The results indicate that there is an increasing number of studies being developed on the topic (most from the last 10 years), but more than half of them are conducted in few Mediterranean countries (60% of the analyzed studies were conducted in Spain, Portugal, Greece, Italy or France), and more than 50% are focused on pre-fire issues, such as prevention and fuel management. In contrast, only 12% of the studies focused on “Economic modeling” or “Human factors and issues,” which suggests that the triple bottom line of the sustainability argument (social, environmental, and economic) is not being fully addressed by fire management research. More than one-fourth of the studies had their objective related to testing new approaches in fire or forest management, suggesting that new knowledge is being produced on the field. Nevertheless, the results indicate that most studies (about 84%) employed quantitative research methods, and only 3% of the studies used research methods that tackled social issues or addressed expert and practitioner’s knowledge. Perhaps this lack of multidisciplinary studies is one of the factors hindering more progress from being made in terms of reducing wildfire occurrences and their impacts.
Abstract: The emergence of digital twin technology, a digital replica of physical world, has improved the real-time access to data from sensors about the performance of buildings. This digital transformation has opened up many opportunities to improve the management of the building by using the data collected to help monitor consumption patterns and energy leakages. One example is the integration of predictive models for anomaly detection. In this paper, we use the GAM (Generalised Additive Model) for the anomaly detection of Air Handling Units (AHU) power consumption pattern. There is ample research work on the use of GAM for the prediction of power consumption at the office building and nation-wide level. However, there is limited illustration of its anomaly detection capabilities, prescriptive analytics case study, and its integration with the latest development of digital twin technology. In this paper, we applied the general GAM modelling framework on the historical data of the AHU power consumption and cooling load of the building between Jan 2018 to Aug 2019 from an education campus in Singapore to train prediction models that, in turn, yield predicted values and ranges. The historical data are seamlessly extracted from the digital twin for modelling purposes. We enhanced the utility of the GAM model by using it to power a real-time anomaly detection system based on the forward predicted ranges. The magnitude of deviation from the upper and lower bounds of the uncertainty intervals is used to inform and identify anomalous data points, all based on historical data, without explicit intervention from domain experts. Notwithstanding, the domain expert fits in through an optional feedback loop through which iterative data cleansing is performed. After an anomalously high or low level of power consumption detected, a set of rule-based conditions are evaluated in real-time to help determine the next course of action for the facilities manager. The performance of GAM is then compared with other approaches to evaluate its effectiveness. Lastly, we discuss the successfully deployment of this approach for the detection of anomalous power consumption pattern and illustrated with real-world use cases.
Abstract: Today’s International Service Learning practices require an update: modern technologies, fresh educational frameworks, and a new operating system to accountably prosper. This paper describes a model of International Service Learning (ISL), which combines current technological hardware, electronic platforms, and asynchronous communications that are grounded in inclusive pedagogy. This model builds on the work around collaborative field trip learning, extending the reach to international partnerships across continents. Mobile technology, 21st century skills and summit-basecamp modeling intersect to support novel forms of learning that tread lightly on fragile natural ecosystems, affirm local reciprocal partnership in projects, and protect traveling participants from common yet avoidable cultural pitfalls.
Abstract: During the process of the industrialization of steel structure housing, a composite structural system with separated gravity and lateral resistant systems has been applied in engineering practices, which consists of composite frame with hinged beam-column joints, steel brace and RC shear wall. As an attempt in steel structural system area, seismic performance evaluation of the separated composite structure is important for further application in steel housing. This paper focuses on the seismic performance comparison of the separated composite structural system and traditional steel frame-shear wall system under the same inter-story drift ratio (IDR) provision limit. The same architectural layout of a high-rise building is designed as two different structural systems at the same IDR level, and finite element analysis using pushover method is carried out. Static pushover analysis implies that the separated structural system exhibits different lateral deformation mode and failure mechanism with traditional steel frame-shear wall system. Different indexes are adopted and discussed in seismic performance evaluation, including IDR, safe factor (SF), shear wall damage, etc. The performance under maximum considered earthquake (MCE) demand spectrum shows that the shear wall damage of two structural systems are similar; the separated composite structural system exhibits less plastic hinges; and the SF index value of the separated composite structural system is higher than the steel frame shear wall structural system.
Abstract: In the actual start-up process of DC motors, the DC drive system often faces a conflict between energy consumption and acceleration performance. To resolve the conflict, this paper proposes a comprehensive performance index that energy consumption index is added on the basis of classical control performance index in the DC motor starting process. Taking the comprehensive performance index as the cost function, particle swarm optimization algorithm is designed to optimize the comprehensive performance. Then it conducts simulations on the optimization of the comprehensive performance of the DC motor on condition that the weight coefficient of the energy consumption index should be properly designed. The simulation results show that as the weight of energy consumption increased, the energy efficiency was significantly improved at the expense of a slight sacrifice of fastness indicators with the comprehensive performance index method. The energy efficiency was increased from 63.18% to 68.48% and the response time reduced from 0.2875s to 0.1736s simultaneously compared with traditional proportion integrals differential controller in energy saving.