MEMS

Marcellino Gemelli, director of global business development at Bosch Sensortec, will present at the upcoming MEMS Sensors Executive Congress on October 29-30, 2018 in Napa, Calif. SEMI’s Maria Vetrano caught up with Gemelli to give MSEC attendees a preview of Gemelli’s feature presentation.Sensor fusion — the integration of different types of sensors through software algorithms to increase overall system performance and/or reduce power consumption— has come a long way since its inception. In those early days, sensor fusion generally involved MEMS inertial sensors only. The advent of new sensor varieties, including environmental sensors, is making new use cases a reality. Gemelli will explore the ways in which the next generation of sensor fusion is improving autonomous mobility devices. SEMI: Why are environmental sensors important to autonomous mobility devices?Gemelli: When most of us think of autonomous systems, we think that they are driven by motion sensors and proximity sensors (e.g., radar, Lidar). When vertical location comes into play, however, in applications such as drones or asset tracking, pressure sensors become an integral part of flight control, navigation and positioning in GPS-challenged areas.While not commonly considered an electronically enabled sense, the ability to “smell” the environment opens new opportunities. The quality of a user’s experience with personal cleaning robots and robo-taxis are good examples of where we might want to enable scent detection.SEMI: I’ve never thought much about using sensors to detect smell. How would a robo-taxi or a cleaning robot benefit from scent detection?Gemelli: Fully autonomous cars will inevitably give rise to robo-taxis. In fact, last month Volvo announced its fully electric robo-taxi, and in March 2018 Waymo announced that Jaguar Land Rover’s SUV would join Fiat Chrysler’s Chrysler Pacifica minivans in its planned fleet of robo-taxis, so we may see robo-taxis in the U.S. within the next five years.With robo-taxis fast-approaching, we need technologies that provide the same level of oversight that a taxi driver once fulfilled. Gas sensors would function like an electronic nose (e-nose) in a robo-taxi to inform the taxi’s owner of prohibited passenger behavior, such as eating, drinking or smoking in the vehicle, which could potentially damage the vehicle’s interior. Camera sensors could record the act as proof of the offense.Cleaning robots would be more sophisticated than they are today. In addition to leveraging image and range-finding sensors to more accurately map the rooms in your house, they could also detect scents from spilled red wine, pet urine or other foreign materials. When the cleaning robot, such as a vacuum, detects the foreign substance, it would navigate around the substance instead of going through it and spreading it all over the carpet.In addition to robo-taxis and cleaning robots, I will also discuss asset tracking and drones.SEMI: What role does sensor fusion play in autonomous mobility devices?Gemelli: Combining sensor fusion with artificial intelligence (AI) will generate new use cases and therefore new markets for sensor suppliers.There is another major benefit as well. With so many connected devices in our lives — including those with cameras, location awareness and always-listening capabilities — we are seeing growing concern about user privacy. Sensor fusion and AI can help to alleviate this concern: By supporting more local processing, they allow for greater control of data, safeguarding personal privacy.SEMI: Who is responsible for the AI part of the sensor-fusion equation?Gemelli: AI is a new frontier for MEMS and sensors suppliers. It benefits us and our customers to embrace AI algorithms through in-house development and/or partnerships.SEMI: What would you like MEMS Sensors Executive Congress attendees to take away from your presentation?Gemelli: I plan to issue a call to action to increase research in hybrid sensor-fusion software architectures, including AI, as suppliers’ collaboration will benefit the industry at large.Marcellino Gemelli is currently based in Palo Alto (CA) responsible for business development of Bosch Sensortec's MEMS product portfolio. He received the ‘Laurea’ degree in Electronic Engineering at the University of Pavia, Italy while in the Italian Army and an MBA from MIP, the Milano (Italy) Polytechnic business school. He previously held various engineering and product management positions at STMicroelectronics from 1995 to 2011 in the fields of MEMS, electronic design automation and data storage. He was contract professor for the Microelectronics course at the Milano (Italy) Polytechnic from 2000 to 2002.Marcellino Gemelli will present Environmental Sensors Systems Enabling Autonomous Mobility on Tuesday, October 30 at MEMS Sensors Executive Congress in Napa Valley, Calif.Register today to learn more about the connection between sensor fusion, AI and next-generation autonomous mobility devices.Maria Vetrano is a public relations consultant at SEMI.

SEMI met with Heinz Martin Esser, managing director at Fabmatics GmbH, to discuss how existing 200mm semiconductor fabs can master the challenges of a 24x7 production under highest cost and quality pressure by implementing intralogistics automation solutions. The two spoke ahead to his presentation at the Fab Management Forum at SEMICON Europa 2018, 13-16, November 2018, in Munich, Germany. To register for the event, click here. SEMI: Looking at the latest production capacity data for 2018 – it is a 200mm fab boom. Growing demand for analog, MEMS and RF chips continues to cause acute shortages for both 200mm fab capacity and equipment. Do you think this trend will continue the next years or is it only a short term run on 200mm fabs?Esser: We at Fabmatics believe in a long-term trend. The emergence of the Internet of Things and growing digitalization in all areas of life will continue to increase demand for integrated circuits (ASICs), analog ICs, high-performance components and micro-mechanical sensors (MEMS) in the coming years. Many of these semiconductor elements should be produced in 200 mm fabs.SEMI: How does Fab automation contribute to increase capacity of existing, mature 200mm fabs?Esser: We are convinced that fab automation is one of the greatest potentials for older 200mm factories to effectively master increased demand, increasing efficiency, quality assurance and flexibility at the same time. In particular, material flow automation, which is often the missing link between existing equipment in different production areas, can help increase productivity in an elementary way.If you analyze how long valuable tools typically wait for loading and unloading, you can see a direct effect of the intralogistics automation system, which leads to a significantly higher utilization of process equipment by making the material flow independent from human performance. Additional side effects such as reduced cycle time, stable fab flow factor or flattened WIP shafts further increase the contribution of material flow automation to get the most out of existing mature factories. Older does not mean obsolete.SEMI: What are the biggest challenges for a successful implementation?Esser: There is no single challenge when you automate an existing mature fab. Instead, you face a whole variety of challenges you have to tackle, ranging from historically grown non-aligned fab layouts over non-linear material flows and older non-standardized equipment to “automation unfriendly” fab environment. Also you should not underestimate the efforts to overcome the practice manual fab operation people in the cleanroom are so familiar with for many years. Before doing automation you have to think automation, i.e. you have to question all processes to make them ready for automation.SEMI: What are the key drivers to automate a mature fab today: costs, process stability, quality or a combination of them?Esser: This question should be better asked to our customers, but we believe it is a mix of many impacts. Most likely everybody sees the cost reduction at first, but we get more aware of process and performance stability as well as quality requirements – and here our customers’ play the most important role – become more and more focused.SEMI: What do you expect from SEMICON Europa 2018 and why do you recommend attending the Fab Management Forum?Esser: This year SEMICON Europa will co-locate with electronica. So it`s going to be the greatest trade fair for electronics manufacturing in Europe. We will meet innovators and decision-makers across the whole electronics supply chain. The Fab Management Forum addresses a highly topical question that concerns all semiconductor manufacturers not only in Europe - how to handle complexity and enable the necessary flexibility to cope with customers' needs. High-ranking speakers will give an insight into the latest technologies and best practices. I am looking forward to the lively exchange with the participants and taking away new impulses for our business. Heinz Martin Esser is managing director at Fabmatics GmbH, responsible for sales and marketing, customer service and administration. He studied supply engineering at the University of Applied Sciences in Cologne and later earned a university degree in business administration. Serena Brischetto is a marketing and communications manager at SEMI Europe.

On June 1st, 2018, Toshiba sold Toshiba Memory, Toshiba’s memory business, to an investment group led by Bain Capital. Toshiba Memory was then owned by a consortium of American, Japanese and Korean companies.After the long and tough negotiations, Toshiba Memory moved forward at full throttle, holding a groundbreaking ceremony for its new 3D NAND fab (100,000 WPM) in Kitakami in July and, in September, celebrating the opening of Fab 6 Phase 1 (50,000 WPM). To be sure, NAND memory is a key feature of Japan’s semiconductor industry. But the sector’s reach extends well beyond memory with its rich and versatile product portfolio nourished by active investment.Born in the early 1950s, Japan’s semiconductor industry today boasts more than 30 companies with fabs. Many feature 200mm and smaller wafer lines with legacy technologies, form factors that account for the bulk of the world’s semiconductors and are the oxygen of Japan’s chip industry. Clearly, the world is not built only with the state-of-art 7nm processed chips on the latest generation 300mm lines. Japanese chipmakers are flourishing.Automotive SemiconductorsRenesas Electronics remains a giant in microcontrollers (MCU) and system on chip (SoC) devices for automotive applications. According to IHS Markit, Renesas automotive semiconductor revenue in 2017 reached $3.6 billion while Inineon Technologies and NXP Semiconductors revenues were $3.4 billion and $3.7 billion, respectively. The three companies dominate the global automotive MCU global market. The company recently acquired Integrated Device Technology (IDT), a U.S. fabless company specializing in analog/mixed signal chips, to strengthen its automotive semiconductor portfolio. Renesas operates four volume production fabs, according to the latest World Fab Forecast from SEMI. Renesas’s microcontrollers for automotive applications (Source: Renesas Electronics) Power SemiconductorsWith power semiconductors the chips of choice for boosting the efficiency and performance of motors and batteries used in equipment, demand for the devices is rapidly growing, especially for automotive applications. Power semiconductor companies in Japan are legion and include Denso, Fuji Electric, Fujitsu Semiconductor, Hitachi, Kyocera, Mitsubishi Electric, New Japan Radio, Origin Electric, Phenitec Semiconductor, Renesas, Rohm, Sanken Electric, Sansha Electric Manufacturing, Seiko NPC, Shindengen Electric Manufacturing, Sumitomo Electric Device Innovations, Toshiba and Toyota Industries. The companies account for 26% of global power semiconductor capacity and will spend $317 million for construction and equipping in 2018.CMOS SensorsSony dominates the CMOS image sensors market with 42% share in 2016, according to Yole Développment. To meet growing demand for high-end CMOS image sensors, Sony has acquired several legacy 300mm wafer fabs and retooled them for CMOS sensor manufacturing. What’s more, Sony’s May announcement of its mid-term corporate strategy includes a 1 trillion Japanese yen investment in CMOS image sensors targeted to automotive applications by March 2021.Sony’s 7.42 effective megapixel stacked CMOS image sensor for automotive cameras (Source: Sony Corporation) MEMSMEMS is perhaps the most wide-ranging device market: Every application requires different capabilities and functions. The latest World Fab Forecast report lists 17 MEMS companies in Japan, though three makers of fast-growing RF MEMS, typically known as surface acoustic wave (SAW) or bulk acoustic wave (BAW) filters, are coming to the attention of semiconductor manufacturers. All are familiar passive electronic components suppliers – Murata Manufacturing, Taiyo Yuden and TDK – and all acquired legacy semiconductor fabs to manufacture RF MEMS.Their high-performance radio wave filters make mobile phones usable around the world. Research companies like Yole expect the introduction of 5G cellular mobile communication systems to fuel another wave of growth of the RF MEMS market. Murata Manufacturing’s SAW filters for smart phones (source Murata Manufacturing) Japanese Supply Chain Meets All Different NeedsJapan’s semiconductor supply chain provides one third of the world’s semiconductor manufacturing equipment and more than half of the industry’s materials. But Japanese suppliers also work with small and midsize makers of highly versatile chips critical to enabling the explosion of smart applications.Meet these versatile Japanese suppliers at SEMICON Japan to find solutions to your unique needs and help the world get smarter. Themed “Dreams Start Here,” SEMICON Japan 2018 reflects the promise of AI (artificial intelligence), Internet of Things (IoT) and Smart technologies. Featuring more than 750 exhibitors from around the world, the event is the gathering place to connect the people, technologies and business across the electronics manufacturing supply chain, from semiconductor manufacturing to autonomous cars, robotics and other smart applications. For more information about SEMICON Japan, visit www.semiconjapan.org.Yoichiro Ando is a marketing director at SEMI Japan.

2017 was a good year for the MEMS and sensors business, and that upward trend should continue. We forecast extended strong growth for the sensors and actuators market, reaching more than $100 billion in 2023 for a total of 185 billion units. Optical sensors, especially CMOS image sensors, will have the lion’s share with almost 40 percent of market value. MEMS will also play an important role in that growth: During 2018–2023, the MEMS market will experience 17.5 percent growth in value and 26.7 percent growth in units, with the consumer market accounting for more than 50 percent(1) share overall. Evolution of SensorsSensors were first developed and used for physical sensing: shock, pressure, then acceleration and rotation. Greater investment in R D spurred MEMS’ expansion from physical sensing to light management (e.g., micromirrors) and then to uncooled infrared sensing (e.g., microbolometers). From sensing light to sensing sound, MEMS microphones formed the next wave of MEMS development. MEMS and sensors are entering a new and exciting phase of evolution as they transcend human perception, progressing toward ultrasonic, infrared and hyperspectral sensing.Sensors can help us to compensate when our physical or emotional sensing is limited in some way. Higher-performance MEMS microphones are already helping the hearing-impaired. Researchers at Arizona State University are among those developing cochlear implants — featuring piezoelectric MEMS sensors — which may one day restore hearing to those with significant hearing loss. The visually impaired may take heart in knowing that researchers at Stanford University are collaborating on silicon retinal implants. Pixium Vision began clinical trials in humans in 2017 with its silicon retinal implants.It’s not science fiction to think that we will use future generations of sensors for emotion/empathy sensing. Augmenting our reality, such sensing could have many uses, perhaps even aiding the ability of people on the autism spectrum to more easily interpret the emotions of others.Through my years in the MEMS industry, I have identified three distinct eras in MEMS’ evolution: The “detection era” in the very first years, when we used simple sensors to detect a shock. The “measuring era” when sensors could not only sense and detect but also measure (e.g., a rotation). The “global-perception awareness era” when we increasingly use sensors to map the environment. We conduct 3D imaging with Lidar for autonomous vehicles. We monitor air quality using environmental sensors. We recognize gestures using accelerometers and/or ultrasonics. We implement biometry with fingerprint and facial recognition sensors. This is possible thanks to sensor fusion of multiple parameters, together with artificial intelligence. Numerous technological breakthroughs are responsible for this steady stream of advancements: new sensor design, new processes and materials, new integration approaches, new packaging, sensor fusion, and new detection principles.Global Awareness SensingThe era of global awareness sensing is upon us. We can either view global awareness as an extension of human sensing capabilities (e.g., adding infrared imaging to visible) or as beyond-human sensing capabilities (e.g., machines with superior environmental perception, such as Lidar in a robotic vehicle). Think about Professor X in Marvel’s universe, and you can imagine how human perception could evolve in the future! Some companies envisioned global awareness from the start. Movea (now part of TDK InvenSense), for example, began their development with inertial MEMS. Others implemented global awareness by combining optical sensors such as Lidar and night-vision sensors for robotic cars. A third contingent grouped environmental sensors (gas, particle, pressure, temperature) to check air quality. The newest entrant in this group, the particle sensor, could play an especially important role in air-quality sensing, particularly in wearable devices.Driven by increasing societal concern over mounting evidence of global air-quality deterioration, air pollution has become a major topic in our society. Studies show that there is no safe level of particulates. Instead, for every increase in concentration of PM10 or PM2.5 inhalable particles in the air, the lung cancer rate is rising proportionately. Combining a particle sensor with a mapping application in a wearable could allow us to identify the locations of the most polluted urban zones.The Need for Artificial Intelligence To realize global awareness, we also need artificial intelligence (AI), but first, we have challenges to solve. Activity tracking, for example, requires accurate live classification of AI data. Relegating all AI processing to a main processor, however, would consume significant CPU resources, reducing available processing power. Likewise, storing all AI data on the device would push up storage costs. To marry AI with MEMS, we must do the following: Decouple feature processing from the execution of the classification engine to a more powerful external processor. Reduce storage and processing demands by deploying only the features required for accurate activity recognition. Install low-power MEMS sensors that can incorporate data from multiple sensors (sensor fusion) and enable pre-processing for always-on execution. Retrain the model with system-supported data that can accurately identify the user’s activities. There are two ways to add AI and software in mobile and automotive applications. The first is a centralized approach, where sensor data is processed in the auxiliary power unit (APU) that contains the software. The second is a decentralized approach, where the sensor chip is localized in the same package, close to the software and the AI (in the DSP for a CMOS image sensor, for example). Whatever the approach, MEMS and sensors manufacturers need to understand AI, although they are unlikely to gain much value at the sensor-chip level.Heading to an Augmented WorldWe have achieved massive progress in sensor development over the years and are now reaching the point when sensors can mimic or augment most of our perception: vision, hearing, touch, smell and even emotion/empathy as well as some aesthetic senses. We should realize that humans are not the only ones to benefit from these developments. Enhanced perception will also allow robots to help us in our daily lives (through smart transportation, better medical care, contextually aware environments and more). We need to couple smart sensors’ development with AI to further enhance our experiences with the people, places and things in our lives.About the authorWith almost 20 years’ experience in MEMS, sensors and photonics applications, markets, and technology analyses, Dr. Eric Mounier provides in-depth industry insight into current and future trends. As a Principal Analyst, Technology Markets, MEMS Photonics, in the Photonics, Sensing Display Division, he contributes daily to the development of MEMS and photonics activities at Yole Développement (Yole). He is involved with a large collection of market and technology reports, as well as multiple custom consulting projects: business strategy, identification of investment or acquisition targets, due diligence (buy/sell side), market and technology analyses, cost modeling, and technology scouting, etc.Previously, Mounier held R D and marketing positions at CEA Leti (France). He has spoken in numerous international conferences and has authored or co-authored more than 100 papers. Mounier has a Semiconductor Engineering Degree and a PhD in Optoelectronics from the National Polytechnic Institute of Grenoble (France).Mounier is a featured speaker at SEMI-MSIG European MEMS Sensors Summit, September 20, 2018 in Grenoble, France. (1) Source: Status of the MEMS Industry report, Yole Développement, 2018

Tracking toward even stronger growth than forecast last year, 200mm fabs worldwide are gearing up to add more than 600,000 wafers per month from 2017 through 2022, an 11 percent growth rate that will lead to a new high of 6 million wafers per month by the end of 2022, according to the SEMI Industry Research and Statistics group in its fourth update of the Global 200mm Fab Outlook report. See chart below. All told, 56 older and newer facilities will add capacity, with the MEMS, power, logic and foundry segments contributing the most. To help meet rising demand, new fabs are under construction. Only six facilities plan to reduce capacity. The global 200mm fab count will increase from the 2017 level of the 194 fabs covered in the report to 203 by 2022. See chart. During the five-year forecast period, China, at 44 percent, is expected to account for the greatest growth, followed by Southeast Asia (19 percent), Taiwan (10 percent) and the Americas (8 percent). However, with strong demand for new 200mm fab equipment, the used 200mm fab equipment market has pretty much dried up. What’s more, the availability of key tools and spare parts has become a primary concern for many device makers. These headwinds notwithstanding, many companies remain bullish with plans to add more capacity. The forecast growth of 600,000 wafers per month may ultimately be a conservative estimate. SEMI’s Global 200mm Fab Outlook report lists more than 300 facilities and lines managed by more than 150 companies, providing details on product type, investment, technology and capacity plans by companies and fabs. The fourth update of the Global 200mm Fab Outlook report covers data and predictions from 2011 through the end of 2022, including milestones, detailed investments by quarter, product types, technology nodes and capacities down to fab and project level. Click here for the Global 200mm Fab Outlook Sample Report. Learn more about other SEMI fab databases at www.semi.org/en/MarketInfo/FabDatabase. Christian G. Dieseldorff is director of Industry Research and Statistics, SEMI, Milpitas, California.

Emboldened by advances in self-driving and Internet of Vehicles (IoV) technologies, Taiwan’s microelectronics sector is investing heavily in manufacturing processes and equipment as engines of innovation and growth for autonomous driving, the world’s next market goldmine. But breaking into the self-driving vehicle industry can be a steep uphill climb. Semiconductor players hungry to secure their piece of the potentially massive market must know how to navigate the automotive industry’s unique ecosystem of suppliers, not to mention its lofty standards for safety and reliability.To explore opportunities and challenges in the automotive semiconductor market, SEMI recently organized Mobility Tech Talk – a gathering of experts from Strategy Analysis, Yole Développement, Renesas, X-FAB and IHS Markit who examined the evolution of sensors for autonomous cars, advanced driver-assisted system (ADAS) applications, and new energy vehicles (NEVs) in China. Nearly 200 participants exchanged in-depth, forward-looking insights and perspectives as the event helped forge stronger relations among various market segments. Here are four key takeaways from the conference. Lidar: The Hottest Sensing Technology for Smart AutomotiveLidar, mmWave radar, cameras and inertial measurement units (IMUs) are critical sensing devices for autonomous cars. With sensor and high-speed computing technologies maturing at their current pace, some 350,000 self-driving vehicles are expected to hit the road by 2027. But before a single autonomous vehicle takes to the roadways, self-driving technology must become expert at monitoring a vehicle’s environment.That’s where Lidar, the hottest of all sensing technologies and the key to the holy grail of safe self-driving, comes into the picture. Lidar’s versatility supports multiple essential functions such as mapping, object detection and object movement. The problem is that mass production is still impossible due to the technology's high costs. What’s more, technical issues must still be sorted out with solid-state lidar, mechanical lidar and MEMS. Both startups and traditional tier-1 semiconductor manufacturers are aggressively investing in related research and development in hopes of fulfilling lidar's promise and seizing the market opportunity. Smart Automotive Sets New Quality and Safety StandardsAs cars become smarter, so too must silicon. Chips must support vastly more data generated by in-vehicle connectivity, ADAS, electrification, autonomous driving and an array of other functions that rely on advanced automotive electronics components. With demand for smarter silicon surging, Taiwan semiconductor companies are turning to the automotive chip industry for expertise and serving as OEMs for major automakers.Quality and safety for automotive applications is paramount. In-vehicle semiconductors must meet strict requirements for vehicle control, robustness, liability, cost and quality management to meet the automotive specifications necessary to securing certifications. Smart silicon must also pass all AEC-Q liability standards promoted by North America automakers and score “zero defect” for the ISO/TS 16949 Automotive Quality Management System.China’s New Energy Vehicles To Fuel Semiconductor GrowthTo promote NEVs and reduce fuel consumption of cars with internal combustion engines (ICEs), late last year the Chinese government introduced the Measures for the Parallel Administration of the Average Fuel Consumption and New Energy Vehicle Credits of Passenger Vehicle Enterprises. With China the world’s largest market for NEVs, the policy is forcing automakers in Japan, the U.S. and Europe to accelerate moves towards NEVs that, in turn, will fuel growth in the semiconductor and automotive battery industries. NEVs in China are expected to number 2 million by 2020 before more than doubling to 4.9 million by 2025. Today, most cars still run on ICEs as environmentally friendly motor drives are still under development. In unit shipments, motor drives are expected to surpass ICEs by 2025.Cross-field Collaboration is KeyThe rise of smarter, fully autonomous vehicles – a disruptive Car 2.0 – is unlikely to happen overnight. Rapid growth of the global automotive semiconductor market will continue, with safety and powertrain applications driving the strongest chip demand. Meanwhile, automakers are focusing more on innovations from startups and non-traditional suppliers, and some have even started to develop their own IP and solutions. These paradigm industry shifts are diversifying the automotive supply chain into a cross-domain collaborative network of suppliers, pushing the closed, one-way automotive supply chain into lesser relevance. In the near future, rivals and partners may become indistinguishable as traditional turf wars begin to wane. As ADAS and autonomous cars evolve, and the era of electric cars nears, automotive semiconductors are emerging as the engine of growth for the global semiconductor industry. The automotive semiconductor market is expected to grow at a CAGR of 5.8 percent, reaching US$48.78 billion by 2022.For its part, the SEMI Smart Automotive special interest group connects professionals from the microelectronics and automotive industries. The group promotes the semiconductor industry's development of automotive technologies and cross-domain collaboration to help drive autonomous vehicle innovation.

Artificial intelligence (AI) is making headlines everywhere, offering a range of capabilities, including location and motion awareness — determining whether a user is sitting, walking, running or sleeping. Behind the scenes, AI is capturing volumes of data. Makers of smartphones and fitness and sports trackers, along with application developers, are all clamoring for this data because it helps them analyze real-world user behavior in depth. Manufacturers gain a competitive edge by tapping this intelligence: Using it to improve user engagement, they increase the perceived value of their devices, potentially reducing customer churn. How can consumer-product manufacturers tap the built-in capabilities of MEMS inertial sensors — which are already ubiquitous in end-user devices — to make the most of AI? Machine learningProduct manufacturers can easily build an activity classification engine using commonly available smart sensors and open-source software. Activity trackers, for example, use raw data first collected via the MEMS inertial sensors that are already installed in smartphones, wearables and other consumer products.With the building blocks in place, consumer-product manufacturers can apply machine learning techniques to classify and analyze this data. There are several possible approaches, ranging from logistic regression to deep learning neural networks.One well-documented method used for classifying sequences in AI is Support Vector Machines (SVM). Physical activities, whether walking or playing sports, consist of specific sequential repetitive movements that MEMS sensors gather as data. MEMS sensors make good use of this collected data, which can be easily processed into well-structured models that are classifiable with SVMs.Consumer-product manufacturers have gravitated toward the SVM model since it is easy to use, scale and predict. Using an SVM to set up multiple simultaneous experiments for optimizing classification over diverse, complex real-life datasets is far simpler than with other approaches. An SVM also introduces a wide range of size and performance optimization opportunities for the underlying classifier.Cost impacts of processing, storage and transmissionIn practice, recognizing user activity hinges on accurate live classification of AI data. Therefore, the key to optimizing product cost is to balance transmission, storage and processing costs without compromising classification accuracy.This is not as simple as it sounds. Storing and processing AI data in the cloud would leave users with a substantial data bill. A WiFi, Bluetooth or 4G module would drive up device costs and require uninterrupted internet access, which is not always possible.Relegating all AI processing to the main processor would consume significant CPU resources, reducing available processing power. Likewise, storing all AI data on the device would push up storage costs.Resolving the issuesTo resolve these technology conflicts, we need to do four things to marry the capabilities of AI with MEMS sensors.First, decouple feature processing from the execution of the classification engine to a more powerful external processor. This minimizes the size of the feature processor size while eliminating the need for continuous live data transmission.Next, reduce storage and processing demands by deploying only the features required for accurate activity recognition. In one example created by UC Irvine Machine Learning Repository (UCI), when an AI model was trained using a dataset of activities with 561 features, it identified user activity with an accuracy of 91.84 percent. However, using just the 19 most determinative features, the model still achieved an impressive accuracy of 85.38 percent. Notably, pre-processing alone could not identify these determinative features. Only sensor fusion enabled the data reliability required for accurate classification. Third, install low-power MEMS sensors that can incorporate data from multiple sensors (sensor fusion) and enable pre-processing for always-on execution. A low-power or application-specific MEMS sensor hub can slash the number of CPU cycles that the classification engine needs. The onboard software can then directly generate fused sensor outputs at various sensor data rates to support efficient feature processing.Finally, retrain the model with system-supported data that can accurately identify the user’s activities.Additionally, cutting the data capture rate can reduce the computational and transmission resource requirements to a bare minimum. Typically, a 50 Hz sample rate is adequate for everyday human activities. This may soar, however, to 200 Hz for fast-moving sports. Reducing dynamic data rate selection and processing in this way lowers manufacturing costs while making the product lighter and/or more powerful for the consumer.High efficiency in processing AI data is key to fulfilling its potential, driving down costs and delivering the most value to consumers. MEMS sensors, in combination with sensor fusion and software partitioning, are critical to driving this efficiency. Operating at very low power, MEMS sensors simplify application development while accurately analyzing motion sensor data.Combining AI and MEMS sensors into a symbiotic system promises a new world of undreamt-of opportunities for designers and end users.This blog post is based on an original article that first ran in EDN. It appears here with the permission of the publisher.